maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/lib/AsmParser/LLParser.cpp

3937 lines
136 KiB
C++
Raw Normal View History

Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
//===-- LLParser.cpp - Parser Class ---------------------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file defines the parser class for .ll files.
//
//===----------------------------------------------------------------------===//
#include "LLParser.h"
#include "llvm/AutoUpgrade.h"
#include "llvm/CallingConv.h"
#include "llvm/Constants.h"
#include "llvm/DerivedTypes.h"
#include "llvm/InlineAsm.h"
#include "llvm/Instructions.h"
#include "llvm/Module.h"
Assembly and Bitcode support for unsigned/signed overflow flags and exact sdiv flags. llvm-svn: 76475
2009-07-21 05:19:07 +08:00
#include "llvm/Operator.h"
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
#include "llvm/ValueSymbolTable.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/ADT/StringExtras.h"
assert(0) -> LLVM_UNREACHABLE. Make llvm_unreachable take an optional string, thus moving the cerr<< out of line. LLVM_UNREACHABLE is now a simple wrapper that makes the message go away for NDEBUG builds. llvm-svn: 75379
2009-07-12 04:10:48 +08:00
#include "llvm/Support/ErrorHandling.h"
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
#include "llvm/Support/raw_ostream.h"
using namespace llvm;
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
/// Run: module ::= toplevelentity*
Refactor some parser interfaces to fix PR3278 and a FIXME: ParseAssemblyString with a specified module would not parse into the module, it would create and return a new one. llvm-svn: 61635
2009-01-05 04:44:11 +08:00
bool LLParser::Run() {
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
// Prime the lexer.
Lex.Lex();
Refactor some parser interfaces to fix PR3278 and a FIXME: ParseAssemblyString with a specified module would not parse into the module, it would create and return a new one. llvm-svn: 61635
2009-01-05 04:44:11 +08:00
return ParseTopLevelEntities() ||
ValidateEndOfModule();
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
/// ValidateEndOfModule - Do final validity and sanity checks at the end of the
/// module.
bool LLParser::ValidateEndOfModule() {
Make changes to rev 84292 as requested by Chris Lattner. Most changes are cleanup, but there is 1 correctness fix: I fixed InstCombine so that the icmp is removed only if the malloc call is removed (which requires explicit removal because the Worklist won't DCE any calls since they can have side-effects). llvm-svn: 84772
2009-10-22 03:11:40 +08:00
// Update auto-upgraded malloc calls to "malloc".
add some fixme's llvm-svn: 84408
2009-10-18 13:09:15 +08:00
// FIXME: Remove in LLVM 3.0.
Autoupgrade malloc insts to malloc calls. Update testcases that rely on malloc insts being present. Also prematurely remove MallocInst handling from IndMemRemoval and RaiseAllocations to help pass tests in this incremental step. llvm-svn: 84292
2009-10-17 08:00:19 +08:00
if (MallocF) {
MallocF->setName("malloc");
// If setName() does not set the name to "malloc", then there is already a
// declaration of "malloc". In that case, iterate over all calls to MallocF
// and get them to call the declared "malloc" instead.
if (MallocF->getName() != "malloc") {
full asmparser support for blockaddress. We can now do: $ llvm-as foo.ll -d -disable-output which reads and prints the .ll file. BC encoding is the next project. Testcase will go in once that works. llvm-svn: 85368
2009-10-28 11:39:23 +08:00
Constant *RealMallocF = M->getFunction("malloc");
Make changes to rev 84292 as requested by Chris Lattner. Most changes are cleanup, but there is 1 correctness fix: I fixed InstCombine so that the icmp is removed only if the malloc call is removed (which requires explicit removal because the Worklist won't DCE any calls since they can have side-effects). llvm-svn: 84772
2009-10-22 03:11:40 +08:00
if (RealMallocF->getType() != MallocF->getType())
RealMallocF = ConstantExpr::getBitCast(RealMallocF, MallocF->getType());
MallocF->replaceAllUsesWith(RealMallocF);
Autoupgrade malloc insts to malloc calls. Update testcases that rely on malloc insts being present. Also prematurely remove MallocInst handling from IndMemRemoval and RaiseAllocations to help pass tests in this incremental step. llvm-svn: 84292
2009-10-17 08:00:19 +08:00
MallocF->eraseFromParent();
MallocF = NULL;
}
}
full asmparser support for blockaddress. We can now do: $ llvm-as foo.ll -d -disable-output which reads and prints the .ll file. BC encoding is the next project. Testcase will go in once that works. llvm-svn: 85368
2009-10-28 11:39:23 +08:00
// If there are entries in ForwardRefBlockAddresses at this point, they are
// references after the function was defined. Resolve those now.
while (!ForwardRefBlockAddresses.empty()) {
// Okay, we are referencing an already-parsed function, resolve them now.
Function *TheFn = 0;
const ValID &Fn = ForwardRefBlockAddresses.begin()->first;
if (Fn.Kind == ValID::t_GlobalName)
TheFn = M->getFunction(Fn.StrVal);
else if (Fn.UIntVal < NumberedVals.size())
TheFn = dyn_cast<Function>(NumberedVals[Fn.UIntVal]);
if (TheFn == 0)
return Error(Fn.Loc, "unknown function referenced by blockaddress");
// Resolve all these references.
if (ResolveForwardRefBlockAddresses(TheFn,
ForwardRefBlockAddresses.begin()->second,
0))
return true;
ForwardRefBlockAddresses.erase(ForwardRefBlockAddresses.begin());
}
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (!ForwardRefTypes.empty())
return Error(ForwardRefTypes.begin()->second.second,
"use of undefined type named '" +
ForwardRefTypes.begin()->first + "'");
if (!ForwardRefTypeIDs.empty())
return Error(ForwardRefTypeIDs.begin()->second.second,
"use of undefined type '%" +
utostr(ForwardRefTypeIDs.begin()->first) + "'");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (!ForwardRefVals.empty())
return Error(ForwardRefVals.begin()->second.second,
"use of undefined value '@" + ForwardRefVals.begin()->first +
"'");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (!ForwardRefValIDs.empty())
return Error(ForwardRefValIDs.begin()->second.second,
"use of undefined value '@" +
utostr(ForwardRefValIDs.begin()->first) + "'");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Support MDNode forward reference. llvm-svn: 75031
2009-07-09 03:23:54 +08:00
if (!ForwardRefMDNodes.empty())
return Error(ForwardRefMDNodes.begin()->second.second,
"use of undefined metadata '!" +
utostr(ForwardRefMDNodes.begin()->first) + "'");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Support MDNode forward reference. llvm-svn: 75031
2009-07-09 03:23:54 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Look for intrinsic functions and CallInst that need to be upgraded
for (Module::iterator FI = M->begin(), FE = M->end(); FI != FE; )
UpgradeCallsToIntrinsic(FI++); // must be post-increment, as we remove
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reapply 79977. Use MDNodes to encode debug info in llvm IR. llvm-svn: 80406
2009-08-29 07:24:31 +08:00
// Check debug info intrinsics.
CheckDebugInfoIntrinsics(M);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
}
full asmparser support for blockaddress. We can now do: $ llvm-as foo.ll -d -disable-output which reads and prints the .ll file. BC encoding is the next project. Testcase will go in once that works. llvm-svn: 85368
2009-10-28 11:39:23 +08:00
bool LLParser::ResolveForwardRefBlockAddresses(Function *TheFn,
std::vector<std::pair<ValID, GlobalValue*> > &Refs,
PerFunctionState *PFS) {
// Loop over all the references, resolving them.
for (unsigned i = 0, e = Refs.size(); i != e; ++i) {
BasicBlock *Res;
Revert 85678/85680. The decision is to stay with the current form of indirectbr, thus we don't need "blockaddr(@func, null)". Eliminate it for simplicity. llvm-svn: 85699
2009-11-01 09:27:45 +08:00
if (PFS) {
full asmparser support for blockaddress. We can now do: $ llvm-as foo.ll -d -disable-output which reads and prints the .ll file. BC encoding is the next project. Testcase will go in once that works. llvm-svn: 85368
2009-10-28 11:39:23 +08:00
if (Refs[i].first.Kind == ValID::t_LocalName)
Res = PFS->GetBB(Refs[i].first.StrVal, Refs[i].first.Loc);
Revert 85678/85680. The decision is to stay with the current form of indirectbr, thus we don't need "blockaddr(@func, null)". Eliminate it for simplicity. llvm-svn: 85699
2009-11-01 09:27:45 +08:00
else
full asmparser support for blockaddress. We can now do: $ llvm-as foo.ll -d -disable-output which reads and prints the .ll file. BC encoding is the next project. Testcase will go in once that works. llvm-svn: 85368
2009-10-28 11:39:23 +08:00
Res = PFS->GetBB(Refs[i].first.UIntVal, Refs[i].first.Loc);
} else if (Refs[i].first.Kind == ValID::t_LocalID) {
return Error(Refs[i].first.Loc,
typo llvm-svn: 85812
2009-11-03 02:28:45 +08:00
"cannot take address of numeric label after the function is defined");
full asmparser support for blockaddress. We can now do: $ llvm-as foo.ll -d -disable-output which reads and prints the .ll file. BC encoding is the next project. Testcase will go in once that works. llvm-svn: 85368
2009-10-28 11:39:23 +08:00
} else {
Res = dyn_cast_or_null<BasicBlock>(
TheFn->getValueSymbolTable().lookup(Refs[i].first.StrVal));
}
Revert 85678/85680. The decision is to stay with the current form of indirectbr, thus we don't need "blockaddr(@func, null)". Eliminate it for simplicity. llvm-svn: 85699
2009-11-01 09:27:45 +08:00
if (Res == 0)
full asmparser support for blockaddress. We can now do: $ llvm-as foo.ll -d -disable-output which reads and prints the .ll file. BC encoding is the next project. Testcase will go in once that works. llvm-svn: 85368
2009-10-28 11:39:23 +08:00
return Error(Refs[i].first.Loc,
"referenced value is not a basic block");
// Get the BlockAddress for this and update references to use it.
BlockAddress *BA = BlockAddress::get(TheFn, Res);
Refs[i].second->replaceAllUsesWith(BA);
Refs[i].second->eraseFromParent();
}
return false;
}
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
//===----------------------------------------------------------------------===//
// Top-Level Entities
//===----------------------------------------------------------------------===//
bool LLParser::ParseTopLevelEntities() {
while (1) {
switch (Lex.getKind()) {
default: return TokError("expected top-level entity");
case lltok::Eof: return false;
//case lltok::kw_define:
case lltok::kw_declare: if (ParseDeclare()) return true; break;
case lltok::kw_define: if (ParseDefine()) return true; break;
case lltok::kw_module: if (ParseModuleAsm()) return true; break;
case lltok::kw_target: if (ParseTargetDefinition()) return true; break;
case lltok::kw_deplibs: if (ParseDepLibs()) return true; break;
case lltok::kw_type: if (ParseUnnamedType()) return true; break;
Extend the AsmWriter to print unnamed numbered types as "%0 = type ..." and unnamed numbered global variables as "@0 = global ...". Extend the AsmParser to recognize these forms. llvm-svn: 78859
2009-08-13 07:32:33 +08:00
case lltok::LocalVarID: if (ParseUnnamedType()) return true; break;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case lltok::StringConstant: // FIXME: REMOVE IN LLVM 3.0
case lltok::LocalVar: if (ParseNamedType()) return true; break;
Extend the AsmWriter to print unnamed numbered types as "%0 = type ..." and unnamed numbered global variables as "@0 = global ...". Extend the AsmParser to recognize these forms. llvm-svn: 78859
2009-08-13 07:32:33 +08:00
case lltok::GlobalID: if (ParseUnnamedGlobal()) return true; break;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case lltok::GlobalVar: if (ParseNamedGlobal()) return true; break;
rename lltok::Metadata -> lltok::exclaim. We name tokens after their syntactic form, not their semantic form. llvm-svn: 92294
2009-12-30 12:56:59 +08:00
case lltok::exclaim: if (ParseStandaloneMetadata()) return true; break;
rename NamedOrCustomMD -> MetadataVar to follow conventions of all the rest of the code. llvm-svn: 92295
2009-12-30 13:02:06 +08:00
case lltok::MetadataVar: if (ParseNamedMetadata()) return true; break;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// The Global variable production with no name can have many different
// optional leading prefixes, the production is:
// GlobalVar ::= OptionalLinkage OptionalVisibility OptionalThreadLocal
// OptionalAddrSpace ('constant'|'global') ...
Add plumbing for the `linker_private' linkage type. This type is meant for "private" symbols which the assember shouldn't strip, but which the linker may remove after evaluation. This is mostly useful for Objective-C metadata. This is plumbing, so we don't have a use of it yet. More to come, etc. llvm-svn: 76385
2009-07-20 09:03:30 +08:00
case lltok::kw_private : // OptionalLinkage
case lltok::kw_linker_private: // OptionalLinkage
case lltok::kw_internal: // OptionalLinkage
case lltok::kw_weak: // OptionalLinkage
case lltok::kw_weak_odr: // OptionalLinkage
case lltok::kw_linkonce: // OptionalLinkage
case lltok::kw_linkonce_odr: // OptionalLinkage
case lltok::kw_appending: // OptionalLinkage
case lltok::kw_dllexport: // OptionalLinkage
case lltok::kw_common: // OptionalLinkage
case lltok::kw_dllimport: // OptionalLinkage
case lltok::kw_extern_weak: // OptionalLinkage
case lltok::kw_external: { // OptionalLinkage
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
unsigned Linkage, Visibility;
if (ParseOptionalLinkage(Linkage) ||
ParseOptionalVisibility(Visibility) ||
switch the .ll parser to use SourceMgr. llvm-svn: 74735
2009-07-03 07:08:13 +08:00
ParseGlobal("", SMLoc(), Linkage, true, Visibility))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return true;
break;
}
case lltok::kw_default: // OptionalVisibility
case lltok::kw_hidden: // OptionalVisibility
case lltok::kw_protected: { // OptionalVisibility
unsigned Visibility;
if (ParseOptionalVisibility(Visibility) ||
switch the .ll parser to use SourceMgr. llvm-svn: 74735
2009-07-03 07:08:13 +08:00
ParseGlobal("", SMLoc(), 0, false, Visibility))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return true;
break;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case lltok::kw_thread_local: // OptionalThreadLocal
case lltok::kw_addrspace: // OptionalAddrSpace
case lltok::kw_constant: // GlobalType
case lltok::kw_global: // GlobalType
switch the .ll parser to use SourceMgr. llvm-svn: 74735
2009-07-03 07:08:13 +08:00
if (ParseGlobal("", SMLoc(), 0, false, 0)) return true;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
break;
}
}
}
/// toplevelentity
/// ::= 'module' 'asm' STRINGCONSTANT
bool LLParser::ParseModuleAsm() {
assert(Lex.getKind() == lltok::kw_module);
Lex.Lex();
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
std::string AsmStr;
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
if (ParseToken(lltok::kw_asm, "expected 'module asm'") ||
ParseStringConstant(AsmStr)) return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
const std::string &AsmSoFar = M->getModuleInlineAsm();
if (AsmSoFar.empty())
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
M->setModuleInlineAsm(AsmStr);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
else
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
M->setModuleInlineAsm(AsmSoFar+"\n"+AsmStr);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
}
/// toplevelentity
/// ::= 'target' 'triple' '=' STRINGCONSTANT
/// ::= 'target' 'datalayout' '=' STRINGCONSTANT
bool LLParser::ParseTargetDefinition() {
assert(Lex.getKind() == lltok::kw_target);
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
std::string Str;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
switch (Lex.Lex()) {
default: return TokError("unknown target property");
case lltok::kw_triple:
Lex.Lex();
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
if (ParseToken(lltok::equal, "expected '=' after target triple") ||
ParseStringConstant(Str))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return true;
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
M->setTargetTriple(Str);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
case lltok::kw_datalayout:
Lex.Lex();
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
if (ParseToken(lltok::equal, "expected '=' after target datalayout") ||
ParseStringConstant(Str))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return true;
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
M->setDataLayout(Str);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
}
}
/// toplevelentity
/// ::= 'deplibs' '=' '[' ']'
/// ::= 'deplibs' '=' '[' STRINGCONSTANT (',' STRINGCONSTANT)* ']'
bool LLParser::ParseDepLibs() {
assert(Lex.getKind() == lltok::kw_deplibs);
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
Lex.Lex();
if (ParseToken(lltok::equal, "expected '=' after deplibs") ||
ParseToken(lltok::lsquare, "expected '=' after deplibs"))
return true;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
if (EatIfPresent(lltok::rsquare))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
std::string Str;
if (ParseStringConstant(Str)) return true;
M->addLibrary(Str);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
while (EatIfPresent(lltok::comma)) {
if (ParseStringConstant(Str)) return true;
M->addLibrary(Str);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
return ParseToken(lltok::rsquare, "expected ']' at end of list");
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
Extend the AsmWriter to print unnamed numbered types as "%0 = type ..." and unnamed numbered global variables as "@0 = global ...". Extend the AsmParser to recognize these forms. llvm-svn: 78859
2009-08-13 07:32:33 +08:00
/// ParseUnnamedType:
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
/// ::= 'type' type
Extend the AsmWriter to print unnamed numbered types as "%0 = type ..." and unnamed numbered global variables as "@0 = global ...". Extend the AsmParser to recognize these forms. llvm-svn: 78859
2009-08-13 07:32:33 +08:00
/// ::= LocalVarID '=' 'type' type
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
bool LLParser::ParseUnnamedType() {
Extend the AsmWriter to print unnamed numbered types as "%0 = type ..." and unnamed numbered global variables as "@0 = global ...". Extend the AsmParser to recognize these forms. llvm-svn: 78859
2009-08-13 07:32:33 +08:00
unsigned TypeID = NumberedTypes.size();
// Handle the LocalVarID form.
if (Lex.getKind() == lltok::LocalVarID) {
if (Lex.getUIntVal() != TypeID)
return Error(Lex.getLoc(), "type expected to be numbered '%" +
utostr(TypeID) + "'");
Lex.Lex(); // eat LocalVarID;
if (ParseToken(lltok::equal, "expected '=' after name"))
return true;
}
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
assert(Lex.getKind() == lltok::kw_type);
LocTy TypeLoc = Lex.getLoc();
Lex.Lex(); // eat kw_type
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
PATypeHolder Ty(Type::getVoidTy(Context));
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ParseType(Ty)) return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// See if this type was previously referenced.
std::map<unsigned, std::pair<PATypeHolder, LocTy> >::iterator
FI = ForwardRefTypeIDs.find(TypeID);
if (FI != ForwardRefTypeIDs.end()) {
reject PR3281:crash09.ll with this diagnostic: llvm-as: crash09.ll:3:1: self referential type is invalid type %0 ^ llvm-svn: 61720
2009-01-06 02:19:46 +08:00
if (FI->second.first.get() == Ty)
return Error(TypeLoc, "self referential type is invalid");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
cast<DerivedType>(FI->second.first.get())->refineAbstractTypeTo(Ty);
Ty = FI->second.first.get();
ForwardRefTypeIDs.erase(FI);
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
NumberedTypes.push_back(Ty);
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
}
/// toplevelentity
/// ::= LocalVar '=' 'type' type
bool LLParser::ParseNamedType() {
std::string Name = Lex.getStrVal();
LocTy NameLoc = Lex.getLoc();
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
Lex.Lex(); // eat LocalVar.
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
PATypeHolder Ty(Type::getVoidTy(Context));
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
if (ParseToken(lltok::equal, "expected '=' after name") ||
ParseToken(lltok::kw_type, "expected 'type' after name") ||
ParseType(Ty))
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Set the type name, checking for conflicts as we do so.
bool AlreadyExists = M->addTypeName(Name, Ty);
if (!AlreadyExists) return false;
// See if this type is a forward reference. We need to eagerly resolve
// types to allow recursive type redefinitions below.
std::map<std::string, std::pair<PATypeHolder, LocTy> >::iterator
FI = ForwardRefTypes.find(Name);
if (FI != ForwardRefTypes.end()) {
reject PR3281:crash09.ll with this diagnostic: llvm-as: crash09.ll:3:1: self referential type is invalid type %0 ^ llvm-svn: 61720
2009-01-06 02:19:46 +08:00
if (FI->second.first.get() == Ty)
return Error(NameLoc, "self referential type is invalid");
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
cast<DerivedType>(FI->second.first.get())->refineAbstractTypeTo(Ty);
Ty = FI->second.first.get();
ForwardRefTypes.erase(FI);
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Inserting a name that is already defined, get the existing name.
const Type *Existing = M->getTypeByName(Name);
assert(Existing && "Conflict but no matching type?!");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Otherwise, this is an attempt to redefine a type. That's okay if
// the redefinition is identical to the original.
// FIXME: REMOVE REDEFINITIONS IN LLVM 3.0
if (Existing == Ty) return false;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Any other kind of (non-equivalent) redefinition is an error.
return Error(NameLoc, "redefinition of type named '" + Name + "' of type '" +
Ty->getDescription() + "'");
}
/// toplevelentity
/// ::= 'declare' FunctionHeader
bool LLParser::ParseDeclare() {
assert(Lex.getKind() == lltok::kw_declare);
Lex.Lex();
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Function *F;
return ParseFunctionHeader(F, false);
}
/// toplevelentity
/// ::= 'define' FunctionHeader '{' ...
bool LLParser::ParseDefine() {
assert(Lex.getKind() == lltok::kw_define);
Lex.Lex();
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Function *F;
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
return ParseFunctionHeader(F, true) ||
ParseFunctionBody(*F);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
/// ParseGlobalType
/// ::= 'constant'
/// ::= 'global'
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
bool LLParser::ParseGlobalType(bool &IsConstant) {
if (Lex.getKind() == lltok::kw_constant)
IsConstant = true;
else if (Lex.getKind() == lltok::kw_global)
IsConstant = false;
Pacify gcc-4.3 (thinks IsConstant may be used uninitialized). llvm-svn: 64220
2009-02-11 00:24:55 +08:00
else {
IsConstant = false;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return TokError("expected 'global' or 'constant'");
Pacify gcc-4.3 (thinks IsConstant may be used uninitialized). llvm-svn: 64220
2009-02-11 00:24:55 +08:00
}
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Lex.Lex();
return false;
}
Extend the AsmWriter to print unnamed numbered types as "%0 = type ..." and unnamed numbered global variables as "@0 = global ...". Extend the AsmParser to recognize these forms. llvm-svn: 78859
2009-08-13 07:32:33 +08:00
/// ParseUnnamedGlobal:
/// OptionalVisibility ALIAS ...
/// OptionalLinkage OptionalVisibility ... -> global variable
/// GlobalID '=' OptionalVisibility ALIAS ...
/// GlobalID '=' OptionalLinkage OptionalVisibility ... -> global variable
bool LLParser::ParseUnnamedGlobal() {
unsigned VarID = NumberedVals.size();
std::string Name;
LocTy NameLoc = Lex.getLoc();
// Handle the GlobalID form.
if (Lex.getKind() == lltok::GlobalID) {
if (Lex.getUIntVal() != VarID)
return Error(Lex.getLoc(), "variable expected to be numbered '%" +
utostr(VarID) + "'");
Lex.Lex(); // eat GlobalID;
if (ParseToken(lltok::equal, "expected '=' after name"))
return true;
}
bool HasLinkage;
unsigned Linkage, Visibility;
if (ParseOptionalLinkage(Linkage, HasLinkage) ||
ParseOptionalVisibility(Visibility))
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Extend the AsmWriter to print unnamed numbered types as "%0 = type ..." and unnamed numbered global variables as "@0 = global ...". Extend the AsmParser to recognize these forms. llvm-svn: 78859
2009-08-13 07:32:33 +08:00
if (HasLinkage || Lex.getKind() != lltok::kw_alias)
return ParseGlobal(Name, NameLoc, Linkage, HasLinkage, Visibility);
return ParseAlias(Name, NameLoc, Visibility);
}
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
/// ParseNamedGlobal:
/// GlobalVar '=' OptionalVisibility ALIAS ...
/// GlobalVar '=' OptionalLinkage OptionalVisibility ... -> global variable
bool LLParser::ParseNamedGlobal() {
assert(Lex.getKind() == lltok::GlobalVar);
LocTy NameLoc = Lex.getLoc();
std::string Name = Lex.getStrVal();
Lex.Lex();
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
bool HasLinkage;
unsigned Linkage, Visibility;
if (ParseToken(lltok::equal, "expected '=' in global variable") ||
ParseOptionalLinkage(Linkage, HasLinkage) ||
ParseOptionalVisibility(Visibility))
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (HasLinkage || Lex.getKind() != lltok::kw_alias)
return ParseGlobal(Name, NameLoc, Linkage, HasLinkage, Visibility);
return ParseAlias(Name, NameLoc, Visibility);
}
Refactor metadata parsing routines into separate functions. llvm-svn: 76455
2009-07-21 03:00:08 +08:00
// MDString:
// ::= '!' STRINGCONSTANT
change ParseMDString and ParseMDNode to take arguments of the right type. This exposed a raft of other problems, which I'll deal with in subsequent patches. llvm-svn: 92273
2009-12-30 05:53:55 +08:00
bool LLParser::ParseMDString(MDString *&Result) {
Refactor metadata parsing routines into separate functions. llvm-svn: 76455
2009-07-21 03:00:08 +08:00
std::string Str;
if (ParseStringConstant(Str)) return true;
change ParseMDString and ParseMDNode to take arguments of the right type. This exposed a raft of other problems, which I'll deal with in subsequent patches. llvm-svn: 92273
2009-12-30 05:53:55 +08:00
Result = MDString::get(Context, Str);
Refactor metadata parsing routines into separate functions. llvm-svn: 76455
2009-07-21 03:00:08 +08:00
return false;
}
// MDNode:
// ::= '!' MDNodeNumber
rename ParseMDNode -> ParseMDNodeID, since it parses !42, not !{... } as you'd expect. llvm-svn: 92291
2009-12-30 12:15:23 +08:00
bool LLParser::ParseMDNodeID(MDNode *&Result) {
Refactor metadata parsing routines into separate functions. llvm-svn: 76455
2009-07-21 03:00:08 +08:00
// !{ ..., !42, ... }
unsigned MID = 0;
switch to TrackingVH instead of WeakVH, since these can never be RAUW'd and go to null. This also gets us some sorely lacking type safety. llvm-svn: 92272
2009-12-30 05:43:58 +08:00
if (ParseUInt32(MID)) return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Refactor metadata parsing routines into separate functions. llvm-svn: 76455
2009-07-21 03:00:08 +08:00
// Check existing MDNode.
rename MetadataCache -> NumberedMetadata to follow the convention used by other things. Convert it to a vector since it is a dense numbering. llvm-svn: 92293
2009-12-30 12:51:58 +08:00
if (MID < NumberedMetadata.size() && NumberedMetadata[MID] != 0) {
Result = NumberedMetadata[MID];
Refactor metadata parsing routines into separate functions. llvm-svn: 76455
2009-07-21 03:00:08 +08:00
return false;
}
clean up some really strange code. llvm-svn: 92275
2009-12-30 06:01:50 +08:00
// Create MDNode forward reference.
// FIXME: This is not unique enough!
Refactor metadata parsing routines into separate functions. llvm-svn: 76455
2009-07-21 03:00:08 +08:00
std::string FwdRefName = "llvm.mdnode.fwdref." + utostr(MID);
remove a really wrong parenthesis. llvm-svn: 92277
2009-12-30 06:17:06 +08:00
Value *V = MDString::get(Context, FwdRefName);
clean up some really strange code. llvm-svn: 92275
2009-12-30 06:01:50 +08:00
MDNode *FwdNode = MDNode::get(Context, &V, 1);
Refactor metadata parsing routines into separate functions. llvm-svn: 76455
2009-07-21 03:00:08 +08:00
ForwardRefMDNodes[MID] = std::make_pair(FwdNode, Lex.getLoc());
rename MetadataCache -> NumberedMetadata to follow the convention used by other things. Convert it to a vector since it is a dense numbering. llvm-svn: 92293
2009-12-30 12:51:58 +08:00
if (NumberedMetadata.size() <= MID)
NumberedMetadata.resize(MID+1);
NumberedMetadata[MID] = FwdNode;
change ParseMDString and ParseMDNode to take arguments of the right type. This exposed a raft of other problems, which I'll deal with in subsequent patches. llvm-svn: 92273
2009-12-30 05:53:55 +08:00
Result = FwdNode;
Refactor metadata parsing routines into separate functions. llvm-svn: 76455
2009-07-21 03:00:08 +08:00
return false;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
}
Refactor metadata parsing routines into separate functions. llvm-svn: 76455
2009-07-21 03:00:08 +08:00
simplify some code and unbreak the build by not consuming an extra token. llvm-svn: 92279
2009-12-30 06:35:39 +08:00
/// ParseNamedMetadata:
Parse named metadata. llvm-svn: 77410
2009-07-29 08:34:02 +08:00
/// !foo = !{ !1, !2 }
bool LLParser::ParseNamedMetadata() {
rename NamedOrCustomMD -> MetadataVar to follow conventions of all the rest of the code. llvm-svn: 92295
2009-12-30 13:02:06 +08:00
assert(Lex.getKind() == lltok::MetadataVar);
Parse named metadata. llvm-svn: 77410
2009-07-29 08:34:02 +08:00
std::string Name = Lex.getStrVal();
rename NamedOrCustomMD -> MetadataVar to follow conventions of all the rest of the code. llvm-svn: 92295
2009-12-30 13:02:06 +08:00
Lex.Lex();
Parse named metadata. llvm-svn: 77410
2009-07-29 08:34:02 +08:00
simplify some code and unbreak the build by not consuming an extra token. llvm-svn: 92279
2009-12-30 06:35:39 +08:00
if (ParseToken(lltok::equal, "expected '=' here") ||
rename lltok::Metadata -> lltok::exclaim. We name tokens after their syntactic form, not their semantic form. llvm-svn: 92294
2009-12-30 12:56:59 +08:00
ParseToken(lltok::exclaim, "Expected '!' here") ||
simplify some code and unbreak the build by not consuming an extra token. llvm-svn: 92279
2009-12-30 06:35:39 +08:00
ParseToken(lltok::lbrace, "Expected '{' here"))
Parse named metadata. llvm-svn: 77410
2009-07-29 08:34:02 +08:00
return true;
NamedMDNode is a collection MDNodes. llvm-svn: 92761
2010-01-06 04:41:31 +08:00
SmallVector<MDNode *, 8> Elts;
Parse named metadata. llvm-svn: 77410
2009-07-29 08:34:02 +08:00
do {
Allow null to be an element of NamedMDNode. e.g. !llvm.stuff = !{!0, !1, null} llvm-svn: 92783
2010-01-06 05:47:32 +08:00
// Null is a special case since it is typeless.
if (EatIfPresent(lltok::kw_null)) {
Elts.push_back(0);
continue;
}
rename lltok::Metadata -> lltok::exclaim. We name tokens after their syntactic form, not their semantic form. llvm-svn: 92294
2009-12-30 12:56:59 +08:00
if (ParseToken(lltok::exclaim, "Expected '!' here"))
clean up some really strange code. llvm-svn: 92275
2009-12-30 06:01:50 +08:00
return true;
change ParseMDString and ParseMDNode to take arguments of the right type. This exposed a raft of other problems, which I'll deal with in subsequent patches. llvm-svn: 92273
2009-12-30 05:53:55 +08:00
MDNode *N = 0;
rename ParseMDNode -> ParseMDNodeID, since it parses !42, not !{... } as you'd expect. llvm-svn: 92291
2009-12-30 12:15:23 +08:00
if (ParseMDNodeID(N)) return true;
Parse named metadata. llvm-svn: 77410
2009-07-29 08:34:02 +08:00
Elts.push_back(N);
} while (EatIfPresent(lltok::comma));
if (ParseToken(lltok::rbrace, "expected end of metadata node"))
return true;
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
NamedMDNode::Create(Context, Name, Elts.data(), Elts.size(), M);
Parse named metadata. llvm-svn: 77410
2009-07-29 08:34:02 +08:00
return false;
}
Support stand alone metadata syntax. !0 = constant metadata !{i32 21, i32 22} @llvm.blah = constant metadata !{i32 1000, i16 200, metadata !0} llvm-svn: 74630
2009-07-02 03:21:12 +08:00
/// ParseStandaloneMetadata:
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
/// !42 = !{...}
Support stand alone metadata syntax. !0 = constant metadata !{i32 21, i32 22} @llvm.blah = constant metadata !{i32 1000, i16 200, metadata !0} llvm-svn: 74630
2009-07-02 03:21:12 +08:00
bool LLParser::ParseStandaloneMetadata() {
rename lltok::Metadata -> lltok::exclaim. We name tokens after their syntactic form, not their semantic form. llvm-svn: 92294
2009-12-30 12:56:59 +08:00
assert(Lex.getKind() == lltok::exclaim);
Support stand alone metadata syntax. !0 = constant metadata !{i32 21, i32 22} @llvm.blah = constant metadata !{i32 1000, i16 200, metadata !0} llvm-svn: 74630
2009-07-02 03:21:12 +08:00
Lex.Lex();
unsigned MetadataID = 0;
LocTy TyLoc;
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
PATypeHolder Ty(Type::getVoidTy(Context));
Derive MDNode from MetadataBase instead of Constant. Emit MDNodes into METADATA_BLOCK in bitcode file. llvm-svn: 76834
2009-07-23 09:07:34 +08:00
SmallVector<Value *, 16> Elts;
factor code even more. llvm-svn: 92280
2009-12-30 06:40:21 +08:00
if (ParseUInt32(MetadataID) ||
ParseToken(lltok::equal, "expected '=' here") ||
ParseType(Ty, TyLoc) ||
rename lltok::Metadata -> lltok::exclaim. We name tokens after their syntactic form, not their semantic form. llvm-svn: 92294
2009-12-30 12:56:59 +08:00
ParseToken(lltok::exclaim, "Expected '!' here") ||
factor code even more. llvm-svn: 92280
2009-12-30 06:40:21 +08:00
ParseToken(lltok::lbrace, "Expected '{' here") ||
Compute isFunctionLocal in MDNode ctor or via argument in new function getWhenValsUnresolved(). Document PFS argument to ParseValID() and ConvertGlobalOrMetadataValIDToValue(). llvm-svn: 93108
2010-01-10 15:14:18 +08:00
ParseMDNodeVector(Elts, NULL) ||
factor code even more. llvm-svn: 92280
2009-12-30 06:40:21 +08:00
ParseToken(lltok::rbrace, "expected end of metadata node"))
Derive MDNode from MetadataBase instead of Constant. Emit MDNodes into METADATA_BLOCK in bitcode file. llvm-svn: 76834
2009-07-23 09:07:34 +08:00
return true;
Move the metadata constructors back to 2.5 syntax. llvm-svn: 77733
2009-08-01 05:35:40 +08:00
MDNode *Init = MDNode::get(Context, Elts.data(), Elts.size());
rename MetadataCache -> NumberedMetadata to follow the convention used by other things. Convert it to a vector since it is a dense numbering. llvm-svn: 92293
2009-12-30 12:51:58 +08:00
// See if this was forward referenced, if so, handle it.
switch to TrackingVH instead of WeakVH, since these can never be RAUW'd and go to null. This also gets us some sorely lacking type safety. llvm-svn: 92272
2009-12-30 05:43:58 +08:00
std::map<unsigned, std::pair<TrackingVH<MDNode>, LocTy> >::iterator
Support MDNode forward reference. llvm-svn: 75031
2009-07-09 03:23:54 +08:00
FI = ForwardRefMDNodes.find(MetadataID);
if (FI != ForwardRefMDNodes.end()) {
switch to TrackingVH instead of WeakVH, since these can never be RAUW'd and go to null. This also gets us some sorely lacking type safety. llvm-svn: 92272
2009-12-30 05:43:58 +08:00
FI->second.first->replaceAllUsesWith(Init);
Support MDNode forward reference. llvm-svn: 75031
2009-07-09 03:23:54 +08:00
ForwardRefMDNodes.erase(FI);
rename MetadataCache -> NumberedMetadata to follow the convention used by other things. Convert it to a vector since it is a dense numbering. llvm-svn: 92293
2009-12-30 12:51:58 +08:00
assert(NumberedMetadata[MetadataID] == Init && "Tracking VH didn't work");
} else {
if (MetadataID >= NumberedMetadata.size())
NumberedMetadata.resize(MetadataID+1);
if (NumberedMetadata[MetadataID] != 0)
return TokError("Metadata id is already used");
NumberedMetadata[MetadataID] = Init;
Support MDNode forward reference. llvm-svn: 75031
2009-07-09 03:23:54 +08:00
}
Support stand alone metadata syntax. !0 = constant metadata !{i32 21, i32 22} @llvm.blah = constant metadata !{i32 1000, i16 200, metadata !0} llvm-svn: 74630
2009-07-02 03:21:12 +08:00
return false;
}
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
/// ParseAlias:
/// ::= GlobalVar '=' OptionalVisibility 'alias' OptionalLinkage Aliasee
/// Aliasee
testcase and asmparser fix for PR4066 llvm-svn: 70080
2009-04-26 05:26:00 +08:00
/// ::= TypeAndValue
/// ::= 'bitcast' '(' TypeAndValue 'to' Type ')'
Add a new keyword 'inbounds' for use with getelementptr. See the LangRef.html changes for details. llvm-svn: 77259
2009-07-28 05:53:46 +08:00
/// ::= 'getelementptr' 'inbounds'? '(' ... ')'
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
///
/// Everything through visibility has already been parsed.
///
bool LLParser::ParseAlias(const std::string &Name, LocTy NameLoc,
unsigned Visibility) {
assert(Lex.getKind() == lltok::kw_alias);
Lex.Lex();
unsigned Linkage;
LocTy LinkageLoc = Lex.getLoc();
if (ParseOptionalLinkage(Linkage))
return true;
if (Linkage != GlobalValue::ExternalLinkage &&
Introduce new linkage types linkonce_odr, weak_odr, common_odr and extern_weak_odr. These are the same as the non-odr versions, except that they indicate that the global will only be overridden by an *equivalent* global. In C, a function with weak linkage can be overridden by a function which behaves completely differently. This means that IP passes have to skip weak functions, since any deductions made from the function definition might be wrong, since the definition could be replaced by something completely different at link time. This is not allowed in C++, thanks to the ODR (One-Definition-Rule): if a function is replaced by another at link-time, then the new function must be the same as the original function. If a language knows that a function or other global can only be overridden by an equivalent global, it can give it the weak_odr linkage type, and the optimizers will understand that it is alright to make deductions based on the function body. The code generators on the other hand map weak and weak_odr linkage to the same thing. llvm-svn: 66339
2009-03-07 23:45:40 +08:00
Linkage != GlobalValue::WeakAnyLinkage &&
Linkage != GlobalValue::WeakODRLinkage &&
Add the private linkage. llvm-svn: 62279
2009-01-16 04:18:42 +08:00
Linkage != GlobalValue::InternalLinkage &&
Add plumbing for the `linker_private' linkage type. This type is meant for "private" symbols which the assember shouldn't strip, but which the linker may remove after evaluation. This is mostly useful for Objective-C metadata. This is plumbing, so we don't have a use of it yet. More to come, etc. llvm-svn: 76385
2009-07-20 09:03:30 +08:00
Linkage != GlobalValue::PrivateLinkage &&
Linkage != GlobalValue::LinkerPrivateLinkage)
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(LinkageLoc, "invalid linkage type for alias");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Constant *Aliasee;
LocTy AliaseeLoc = Lex.getLoc();
testcase and asmparser fix for PR4066 llvm-svn: 70080
2009-04-26 05:26:00 +08:00
if (Lex.getKind() != lltok::kw_bitcast &&
Lex.getKind() != lltok::kw_getelementptr) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ParseGlobalTypeAndValue(Aliasee)) return true;
} else {
// The bitcast dest type is not present, it is implied by the dest type.
ValID ID;
if (ParseValID(ID)) return true;
if (ID.Kind != ValID::t_Constant)
return Error(AliaseeLoc, "invalid aliasee");
Aliasee = ID.ConstantVal;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
There are two ways of checking for a given type, for example isa<PointerType>(T) and T->isPointerTy(). Convert most instances of the first form to the second form. Requested by Chris. llvm-svn: 96344
2010-02-16 19:11:14 +08:00
if (!Aliasee->getType()->isPointerTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(AliaseeLoc, "alias must have pointer type");
// Okay, create the alias but do not insert it into the module yet.
GlobalAlias* GA = new GlobalAlias(Aliasee->getType(),
(GlobalValue::LinkageTypes)Linkage, Name,
Aliasee);
GA->setVisibility((GlobalValue::VisibilityTypes)Visibility);
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// See if this value already exists in the symbol table. If so, it is either
// a redefinition or a definition of a forward reference.
fix PR5295 where the .ll parser didn't reject a function after a global or global after a function with conflicting names. Update some testcases that were accidentally depending on this behavior. llvm-svn: 85081
2009-10-26 07:22:50 +08:00
if (GlobalValue *Val = M->getNamedValue(Name)) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// See if this was a redefinition. If so, there is no entry in
// ForwardRefVals.
std::map<std::string, std::pair<GlobalValue*, LocTy> >::iterator
I = ForwardRefVals.find(Name);
if (I == ForwardRefVals.end())
return Error(NameLoc, "redefinition of global named '@" + Name + "'");
// Otherwise, this was a definition of forward ref. Verify that types
// agree.
if (Val->getType() != GA->getType())
return Error(NameLoc,
"forward reference and definition of alias have different types");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// If they agree, just RAUW the old value with the alias and remove the
// forward ref info.
Val->replaceAllUsesWith(GA);
Val->eraseFromParent();
ForwardRefVals.erase(I);
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Insert into the module, we know its name won't collide now.
M->getAliasList().push_back(GA);
assert(GA->getNameStr() == Name && "Should not be a name conflict!");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
}
/// ParseGlobal
/// ::= GlobalVar '=' OptionalLinkage OptionalVisibility OptionalThreadLocal
/// OptionalAddrSpace GlobalType Type Const
/// ::= OptionalLinkage OptionalVisibility OptionalThreadLocal
/// OptionalAddrSpace GlobalType Type Const
///
/// Everything through visibility has been parsed already.
///
bool LLParser::ParseGlobal(const std::string &Name, LocTy NameLoc,
unsigned Linkage, bool HasLinkage,
unsigned Visibility) {
unsigned AddrSpace;
bool ThreadLocal, IsConstant;
LocTy TyLoc;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
PATypeHolder Ty(Type::getVoidTy(Context));
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ParseOptionalToken(lltok::kw_thread_local, ThreadLocal) ||
ParseOptionalAddrSpace(AddrSpace) ||
ParseGlobalType(IsConstant) ||
ParseType(Ty, TyLoc))
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// If the linkage is specified and is external, then no initializer is
// present.
Constant *Init = 0;
if (!HasLinkage || (Linkage != GlobalValue::DLLImportLinkage &&
Remove the one-definition-rule version of extern_weak linkage: this linkage type only applies to declarations, but ODR is only relevant to globals with definitions. llvm-svn: 66650
2009-03-11 16:08:06 +08:00
Linkage != GlobalValue::ExternalWeakLinkage &&
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Linkage != GlobalValue::ExternalLinkage)) {
if (ParseGlobalValue(Ty, Init))
return true;
}
There are two ways of checking for a given type, for example isa<PointerType>(T) and T->isPointerTy(). Convert most instances of the first form to the second form. Requested by Chris. llvm-svn: 96344
2010-02-16 19:11:14 +08:00
if (Ty->isFunctionTy() || Ty->isLabelTy())
fix typo llvm-svn: 64091
2009-02-09 04:00:15 +08:00
return Error(TyLoc, "invalid type for global variable");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
GlobalVariable *GV = 0;
// See if the global was forward referenced, if so, use the global.
Fix PR3372 llvm-svn: 63501
2009-02-02 15:24:28 +08:00
if (!Name.empty()) {
fix PR5295 where the .ll parser didn't reject a function after a global or global after a function with conflicting names. Update some testcases that were accidentally depending on this behavior. llvm-svn: 85081
2009-10-26 07:22:50 +08:00
if (GlobalValue *GVal = M->getNamedValue(Name)) {
if (!ForwardRefVals.erase(Name) || !isa<GlobalValue>(GVal))
return Error(NameLoc, "redefinition of global '@" + Name + "'");
GV = cast<GlobalVariable>(GVal);
}
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
} else {
std::map<unsigned, std::pair<GlobalValue*, LocTy> >::iterator
I = ForwardRefValIDs.find(NumberedVals.size());
if (I != ForwardRefValIDs.end()) {
GV = cast<GlobalVariable>(I->second.first);
ForwardRefValIDs.erase(I);
}
}
if (GV == 0) {
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
GV = new GlobalVariable(*M, Ty, false, GlobalValue::ExternalLinkage, 0,
Switch GlobalVariable ctors to a sane API, where *either* a context or a module is required. llvm-svn: 75025
2009-07-09 03:03:57 +08:00
Name, 0, false, AddrSpace);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
} else {
if (GV->getType()->getElementType() != Ty)
return Error(TyLoc,
"forward reference and definition of global have different types");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Move the forward-reference to the correct spot in the module.
M->getGlobalList().splice(M->global_end(), M->getGlobalList(), GV);
}
if (Name.empty())
NumberedVals.push_back(GV);
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Set the parsed properties on the global.
if (Init)
GV->setInitializer(Init);
GV->setConstant(IsConstant);
GV->setLinkage((GlobalValue::LinkageTypes)Linkage);
GV->setVisibility((GlobalValue::VisibilityTypes)Visibility);
GV->setThreadLocal(ThreadLocal);
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Parse attributes on the global.
while (Lex.getKind() == lltok::comma) {
Lex.Lex();
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (Lex.getKind() == lltok::kw_section) {
Lex.Lex();
GV->setSection(Lex.getStrVal());
if (ParseToken(lltok::StringConstant, "expected global section string"))
return true;
} else if (Lex.getKind() == lltok::kw_align) {
unsigned Alignment;
if (ParseOptionalAlignment(Alignment)) return true;
GV->setAlignment(Alignment);
} else {
TokError("unknown global variable property!");
}
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
}
//===----------------------------------------------------------------------===//
// GlobalValue Reference/Resolution Routines.
//===----------------------------------------------------------------------===//
/// GetGlobalVal - Get a value with the specified name or ID, creating a
/// forward reference record if needed. This can return null if the value
/// exists but does not have the right type.
GlobalValue *LLParser::GetGlobalVal(const std::string &Name, const Type *Ty,
LocTy Loc) {
const PointerType *PTy = dyn_cast<PointerType>(Ty);
if (PTy == 0) {
Error(Loc, "global variable reference must have pointer type");
return 0;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Look this name up in the normal function symbol table.
GlobalValue *Val =
cast_or_null<GlobalValue>(M->getValueSymbolTable().lookup(Name));
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// If this is a forward reference for the value, see if we already created a
// forward ref record.
if (Val == 0) {
std::map<std::string, std::pair<GlobalValue*, LocTy> >::iterator
I = ForwardRefVals.find(Name);
if (I != ForwardRefVals.end())
Val = I->second.first;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// If we have the value in the symbol table or fwd-ref table, return it.
if (Val) {
if (Val->getType() == Ty) return Val;
Error(Loc, "'@" + Name + "' defined with type '" +
Val->getType()->getDescription() + "'");
return 0;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Otherwise, create a new forward reference for this value and remember it.
GlobalValue *FwdVal;
one more crash from PR3281, we now diagnose: llvm-as: t.ll:2:39: function may not return opaque type %"bwmoyl" = tail call coldcc opaque @g() ^ llvm-svn: 61933
2009-01-09 03:05:36 +08:00
if (const FunctionType *FT = dyn_cast<FunctionType>(PTy->getElementType())) {
// Function types can return opaque but functions can't.
Introduce isOpaqueTy and use it rather than isa<OpaqueType>. Also, move some methods to try to have the type predicates be more logically positioned. llvm-svn: 96349
2010-02-16 22:50:09 +08:00
if (FT->getReturnType()->isOpaqueTy()) {
one more crash from PR3281, we now diagnose: llvm-as: t.ll:2:39: function may not return opaque type %"bwmoyl" = tail call coldcc opaque @g() ^ llvm-svn: 61933
2009-01-09 03:05:36 +08:00
Error(Loc, "function may not return opaque type");
return 0;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Remove the one-definition-rule version of extern_weak linkage: this linkage type only applies to declarations, but ODR is only relevant to globals with definitions. llvm-svn: 66650
2009-03-11 16:08:06 +08:00
FwdVal = Function::Create(FT, GlobalValue::ExternalWeakLinkage, Name, M);
one more crash from PR3281, we now diagnose: llvm-as: t.ll:2:39: function may not return opaque type %"bwmoyl" = tail call coldcc opaque @g() ^ llvm-svn: 61933
2009-01-09 03:05:36 +08:00
} else {
Switch GlobalVariable ctors to a sane API, where *either* a context or a module is required. llvm-svn: 75025
2009-07-09 03:03:57 +08:00
FwdVal = new GlobalVariable(*M, PTy->getElementType(), false,
GlobalValue::ExternalWeakLinkage, 0, Name);
one more crash from PR3281, we now diagnose: llvm-as: t.ll:2:39: function may not return opaque type %"bwmoyl" = tail call coldcc opaque @g() ^ llvm-svn: 61933
2009-01-09 03:05:36 +08:00
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ForwardRefVals[Name] = std::make_pair(FwdVal, Loc);
return FwdVal;
}
GlobalValue *LLParser::GetGlobalVal(unsigned ID, const Type *Ty, LocTy Loc) {
const PointerType *PTy = dyn_cast<PointerType>(Ty);
if (PTy == 0) {
Error(Loc, "global variable reference must have pointer type");
return 0;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
GlobalValue *Val = ID < NumberedVals.size() ? NumberedVals[ID] : 0;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// If this is a forward reference for the value, see if we already created a
// forward ref record.
if (Val == 0) {
std::map<unsigned, std::pair<GlobalValue*, LocTy> >::iterator
I = ForwardRefValIDs.find(ID);
if (I != ForwardRefValIDs.end())
Val = I->second.first;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// If we have the value in the symbol table or fwd-ref table, return it.
if (Val) {
if (Val->getType() == Ty) return Val;
Error(Loc, "'@" + utostr(ID) + "' defined with type '" +
Val->getType()->getDescription() + "'");
return 0;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Otherwise, create a new forward reference for this value and remember it.
GlobalValue *FwdVal;
reject PR3281:crash11.ll with: llvm-as: crash11.ll:2:27: function may not return return opaque type "xw" = tail call opaque @608(label %31) ^ llvm-svn: 61722
2009-01-06 02:27:50 +08:00
if (const FunctionType *FT = dyn_cast<FunctionType>(PTy->getElementType())) {
// Function types can return opaque but functions can't.
Introduce isOpaqueTy and use it rather than isa<OpaqueType>. Also, move some methods to try to have the type predicates be more logically positioned. llvm-svn: 96349
2010-02-16 22:50:09 +08:00
if (FT->getReturnType()->isOpaqueTy()) {
fix wordo llvm-svn: 61728
2009-01-06 02:56:52 +08:00
Error(Loc, "function may not return opaque type");
reject PR3281:crash11.ll with: llvm-as: crash11.ll:2:27: function may not return return opaque type "xw" = tail call opaque @608(label %31) ^ llvm-svn: 61722
2009-01-06 02:27:50 +08:00
return 0;
}
Remove the one-definition-rule version of extern_weak linkage: this linkage type only applies to declarations, but ODR is only relevant to globals with definitions. llvm-svn: 66650
2009-03-11 16:08:06 +08:00
FwdVal = Function::Create(FT, GlobalValue::ExternalWeakLinkage, "", M);
reject PR3281:crash11.ll with: llvm-as: crash11.ll:2:27: function may not return return opaque type "xw" = tail call opaque @608(label %31) ^ llvm-svn: 61722
2009-01-06 02:27:50 +08:00
} else {
Switch GlobalVariable ctors to a sane API, where *either* a context or a module is required. llvm-svn: 75025
2009-07-09 03:03:57 +08:00
FwdVal = new GlobalVariable(*M, PTy->getElementType(), false,
GlobalValue::ExternalWeakLinkage, 0, "");
reject PR3281:crash11.ll with: llvm-as: crash11.ll:2:27: function may not return return opaque type "xw" = tail call opaque @608(label %31) ^ llvm-svn: 61722
2009-01-06 02:27:50 +08:00
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ForwardRefValIDs[ID] = std::make_pair(FwdVal, Loc);
return FwdVal;
}
//===----------------------------------------------------------------------===//
// Helper Routines.
//===----------------------------------------------------------------------===//
/// ParseToken - If the current token has the specified kind, eat it and return
/// success. Otherwise, emit the specified error and return failure.
bool LLParser::ParseToken(lltok::Kind T, const char *ErrMsg) {
if (Lex.getKind() != T)
return TokError(ErrMsg);
Lex.Lex();
return false;
}
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
/// ParseStringConstant
/// ::= StringConstant
bool LLParser::ParseStringConstant(std::string &Result) {
if (Lex.getKind() != lltok::StringConstant)
return TokError("expected string constant");
Result = Lex.getStrVal();
Lex.Lex();
return false;
}
/// ParseUInt32
/// ::= uint32
bool LLParser::ParseUInt32(unsigned &Val) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (Lex.getKind() != lltok::APSInt || Lex.getAPSIntVal().isSigned())
return TokError("expected integer");
uint64_t Val64 = Lex.getAPSIntVal().getLimitedValue(0xFFFFFFFFULL+1);
if (Val64 != unsigned(Val64))
return TokError("expected 32-bit integer (too large)");
Val = Val64;
Lex.Lex();
return false;
}
/// ParseOptionalAddrSpace
/// := /*empty*/
/// := 'addrspace' '(' uint32 ')'
bool LLParser::ParseOptionalAddrSpace(unsigned &AddrSpace) {
AddrSpace = 0;
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
if (!EatIfPresent(lltok::kw_addrspace))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
return ParseToken(lltok::lparen, "expected '(' in address space") ||
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
ParseUInt32(AddrSpace) ||
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ParseToken(lltok::rparen, "expected ')' in address space");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
}
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
/// ParseOptionalAttrs - Parse a potentially empty attribute list. AttrKind
/// indicates what kind of attribute list this is: 0: function arg, 1: result,
/// 2: function attr.
Fix a bug in our autoupgrade support: in an argument list to a function call, we should treat "i64 zext" as the start of a constant expr, but "i64 0 zext" as an argument with an obsolete attribute on it (this form is already tested by test/Assembler/2007-07-30-AutoUpgradeZextSext.ll). Make the autoupgrade logic more discerning to avoid treating "i64 zext" as an old-style attribute, causing us to reject a valid constant expr. This fixes PR3876. llvm-svn: 67682
2009-03-25 14:36:36 +08:00
/// 3: function arg after value: FIXME: REMOVE IN LLVM 3.0
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
bool LLParser::ParseOptionalAttrs(unsigned &Attrs, unsigned AttrKind) {
Attrs = Attribute::None;
LocTy AttrLoc = Lex.getLoc();
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
while (1) {
switch (Lex.getKind()) {
case lltok::kw_sext:
case lltok::kw_zext:
Fix a bug in our autoupgrade support: in an argument list to a function call, we should treat "i64 zext" as the start of a constant expr, but "i64 0 zext" as an argument with an obsolete attribute on it (this form is already tested by test/Assembler/2007-07-30-AutoUpgradeZextSext.ll). Make the autoupgrade logic more discerning to avoid treating "i64 zext" as an old-style attribute, causing us to reject a valid constant expr. This fixes PR3876. llvm-svn: 67682
2009-03-25 14:36:36 +08:00
// Treat these as signext/zeroext if they occur in the argument list after
// the value, as in "call i8 @foo(i8 10 sext)". If they occur before the
// value, as in "call i8 @foo(i8 sext (" then it is part of a constant
// expr.
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// FIXME: REMOVE THIS IN LLVM 3.0
Fix a bug in our autoupgrade support: in an argument list to a function call, we should treat "i64 zext" as the start of a constant expr, but "i64 0 zext" as an argument with an obsolete attribute on it (this form is already tested by test/Assembler/2007-07-30-AutoUpgradeZextSext.ll). Make the autoupgrade logic more discerning to avoid treating "i64 zext" as an old-style attribute, causing us to reject a valid constant expr. This fixes PR3876. llvm-svn: 67682
2009-03-25 14:36:36 +08:00
if (AttrKind == 3) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (Lex.getKind() == lltok::kw_sext)
Attrs |= Attribute::SExt;
else
Attrs |= Attribute::ZExt;
break;
}
// FALL THROUGH.
default: // End of attributes.
if (AttrKind != 2 && (Attrs & Attribute::FunctionOnly))
return Error(AttrLoc, "invalid use of function-only attribute");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Fix a bug in our autoupgrade support: in an argument list to a function call, we should treat "i64 zext" as the start of a constant expr, but "i64 0 zext" as an argument with an obsolete attribute on it (this form is already tested by test/Assembler/2007-07-30-AutoUpgradeZextSext.ll). Make the autoupgrade logic more discerning to avoid treating "i64 zext" as an old-style attribute, causing us to reject a valid constant expr. This fixes PR3876. llvm-svn: 67682
2009-03-25 14:36:36 +08:00
if (AttrKind != 0 && AttrKind != 3 && (Attrs & Attribute::ParameterOnly))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(AttrLoc, "invalid use of parameter-only attribute");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
Add new function attribute - noimplicitfloat Update code generator to use this attribute and remove NoImplicitFloat target option. Update llc to set this attribute when -no-implicit-float command line option is used. llvm-svn: 72959
2009-06-06 05:57:13 +08:00
case lltok::kw_zeroext: Attrs |= Attribute::ZExt; break;
case lltok::kw_signext: Attrs |= Attribute::SExt; break;
case lltok::kw_inreg: Attrs |= Attribute::InReg; break;
case lltok::kw_sret: Attrs |= Attribute::StructRet; break;
case lltok::kw_noalias: Attrs |= Attribute::NoAlias; break;
case lltok::kw_nocapture: Attrs |= Attribute::NoCapture; break;
case lltok::kw_byval: Attrs |= Attribute::ByVal; break;
case lltok::kw_nest: Attrs |= Attribute::Nest; break;
case lltok::kw_noreturn: Attrs |= Attribute::NoReturn; break;
case lltok::kw_nounwind: Attrs |= Attribute::NoUnwind; break;
case lltok::kw_noinline: Attrs |= Attribute::NoInline; break;
case lltok::kw_readnone: Attrs |= Attribute::ReadNone; break;
case lltok::kw_readonly: Attrs |= Attribute::ReadOnly; break;
Reintroduce the InlineHint function attribute. This time it's for real! I am going to hook this up in the frontends as well. The inliner has some experimental heuristics for dealing with the inline hint. When given a -respect-inlinehint option, functions marked with the inline keyword are given a threshold just above the default for -O3. We need some experiments to determine if that is the right thing to do. llvm-svn: 95466
2010-02-06 09:16:28 +08:00
case lltok::kw_inlinehint: Attrs |= Attribute::InlineHint; break;
Add new function attribute - noimplicitfloat Update code generator to use this attribute and remove NoImplicitFloat target option. Update llc to set this attribute when -no-implicit-float command line option is used. llvm-svn: 72959
2009-06-06 05:57:13 +08:00
case lltok::kw_alwaysinline: Attrs |= Attribute::AlwaysInline; break;
case lltok::kw_optsize: Attrs |= Attribute::OptimizeForSize; break;
case lltok::kw_ssp: Attrs |= Attribute::StackProtect; break;
case lltok::kw_sspreq: Attrs |= Attribute::StackProtectReq; break;
case lltok::kw_noredzone: Attrs |= Attribute::NoRedZone; break;
case lltok::kw_noimplicitfloat: Attrs |= Attribute::NoImplicitFloat; break;
Add support for naked functions llvm-svn: 76198
2009-07-18 02:07:26 +08:00
case lltok::kw_naked: Attrs |= Attribute::Naked; break;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Add a new function attribute, 'alignstack'. It will indicate (when the backends implement support for it) that the stack should be forcibly realigned in the prologue (and the process reversed in the epilogue). llvm-svn: 95945
2010-02-12 08:31:15 +08:00
case lltok::kw_alignstack: {
unsigned Alignment;
if (ParseOptionalStackAlignment(Alignment))
return true;
Attrs |= Attribute::constructStackAlignmentFromInt(Alignment);
continue;
}
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case lltok::kw_align: {
unsigned Alignment;
if (ParseOptionalAlignment(Alignment))
return true;
Attrs |= Attribute::constructAlignmentFromInt(Alignment);
continue;
}
Add a new function attribute, 'alignstack'. It will indicate (when the backends implement support for it) that the stack should be forcibly realigned in the prologue (and the process reversed in the epilogue). llvm-svn: 95945
2010-02-12 08:31:15 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
Lex.Lex();
}
}
/// ParseOptionalLinkage
/// ::= /*empty*/
Add the private linkage. llvm-svn: 62279
2009-01-16 04:18:42 +08:00
/// ::= 'private'
Add plumbing for the `linker_private' linkage type. This type is meant for "private" symbols which the assember shouldn't strip, but which the linker may remove after evaluation. This is mostly useful for Objective-C metadata. This is plumbing, so we don't have a use of it yet. More to come, etc. llvm-svn: 76385
2009-07-20 09:03:30 +08:00
/// ::= 'linker_private'
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
/// ::= 'internal'
/// ::= 'weak'
Introduce new linkage types linkonce_odr, weak_odr, common_odr and extern_weak_odr. These are the same as the non-odr versions, except that they indicate that the global will only be overridden by an *equivalent* global. In C, a function with weak linkage can be overridden by a function which behaves completely differently. This means that IP passes have to skip weak functions, since any deductions made from the function definition might be wrong, since the definition could be replaced by something completely different at link time. This is not allowed in C++, thanks to the ODR (One-Definition-Rule): if a function is replaced by another at link-time, then the new function must be the same as the original function. If a language knows that a function or other global can only be overridden by an equivalent global, it can give it the weak_odr linkage type, and the optimizers will understand that it is alright to make deductions based on the function body. The code generators on the other hand map weak and weak_odr linkage to the same thing. llvm-svn: 66339
2009-03-07 23:45:40 +08:00
/// ::= 'weak_odr'
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
/// ::= 'linkonce'
Introduce new linkage types linkonce_odr, weak_odr, common_odr and extern_weak_odr. These are the same as the non-odr versions, except that they indicate that the global will only be overridden by an *equivalent* global. In C, a function with weak linkage can be overridden by a function which behaves completely differently. This means that IP passes have to skip weak functions, since any deductions made from the function definition might be wrong, since the definition could be replaced by something completely different at link time. This is not allowed in C++, thanks to the ODR (One-Definition-Rule): if a function is replaced by another at link-time, then the new function must be the same as the original function. If a language knows that a function or other global can only be overridden by an equivalent global, it can give it the weak_odr linkage type, and the optimizers will understand that it is alright to make deductions based on the function body. The code generators on the other hand map weak and weak_odr linkage to the same thing. llvm-svn: 66339
2009-03-07 23:45:40 +08:00
/// ::= 'linkonce_odr'
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
/// ::= 'appending'
/// ::= 'dllexport'
/// ::= 'common'
/// ::= 'dllimport'
/// ::= 'extern_weak'
/// ::= 'external'
bool LLParser::ParseOptionalLinkage(unsigned &Res, bool &HasLinkage) {
HasLinkage = false;
switch (Lex.getKind()) {
Add plumbing for the `linker_private' linkage type. This type is meant for "private" symbols which the assember shouldn't strip, but which the linker may remove after evaluation. This is mostly useful for Objective-C metadata. This is plumbing, so we don't have a use of it yet. More to come, etc. llvm-svn: 76385
2009-07-20 09:03:30 +08:00
default: Res=GlobalValue::ExternalLinkage; return false;
case lltok::kw_private: Res = GlobalValue::PrivateLinkage; break;
case lltok::kw_linker_private: Res = GlobalValue::LinkerPrivateLinkage; break;
case lltok::kw_internal: Res = GlobalValue::InternalLinkage; break;
case lltok::kw_weak: Res = GlobalValue::WeakAnyLinkage; break;
case lltok::kw_weak_odr: Res = GlobalValue::WeakODRLinkage; break;
case lltok::kw_linkonce: Res = GlobalValue::LinkOnceAnyLinkage; break;
case lltok::kw_linkonce_odr: Res = GlobalValue::LinkOnceODRLinkage; break;
Add a new "available_externally" linkage type. This is intended to support C99 inline, GNU extern inline, etc. Related bugzilla's include PR3517, PR3100, & PR2933. Nothing uses this yet, but it appears to work. llvm-svn: 68940
2009-04-13 13:44:34 +08:00
case lltok::kw_available_externally:
Res = GlobalValue::AvailableExternallyLinkage;
break;
Add plumbing for the `linker_private' linkage type. This type is meant for "private" symbols which the assember shouldn't strip, but which the linker may remove after evaluation. This is mostly useful for Objective-C metadata. This is plumbing, so we don't have a use of it yet. More to come, etc. llvm-svn: 76385
2009-07-20 09:03:30 +08:00
case lltok::kw_appending: Res = GlobalValue::AppendingLinkage; break;
case lltok::kw_dllexport: Res = GlobalValue::DLLExportLinkage; break;
case lltok::kw_common: Res = GlobalValue::CommonLinkage; break;
case lltok::kw_dllimport: Res = GlobalValue::DLLImportLinkage; break;
case lltok::kw_extern_weak: Res = GlobalValue::ExternalWeakLinkage; break;
case lltok::kw_external: Res = GlobalValue::ExternalLinkage; break;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
Lex.Lex();
HasLinkage = true;
return false;
}
/// ParseOptionalVisibility
/// ::= /*empty*/
/// ::= 'default'
/// ::= 'hidden'
/// ::= 'protected'
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
///
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
bool LLParser::ParseOptionalVisibility(unsigned &Res) {
switch (Lex.getKind()) {
default: Res = GlobalValue::DefaultVisibility; return false;
case lltok::kw_default: Res = GlobalValue::DefaultVisibility; break;
case lltok::kw_hidden: Res = GlobalValue::HiddenVisibility; break;
case lltok::kw_protected: Res = GlobalValue::ProtectedVisibility; break;
}
Lex.Lex();
return false;
}
/// ParseOptionalCallingConv
/// ::= /*empty*/
/// ::= 'ccc'
/// ::= 'fastcc'
/// ::= 'coldcc'
/// ::= 'x86_stdcallcc'
/// ::= 'x86_fastcallcc'
Address review comments: add 3 ARM calling conventions. Dispatch C calling conv. to one of these conventions based on target triple and subtarget features. llvm-svn: 73530
2009-06-17 02:50:49 +08:00
/// ::= 'arm_apcscc'
/// ::= 'arm_aapcscc'
/// ::= 'arm_aapcs_vfpcc'
Add MSP430 interrupt calling conv. No functionality change yet. llvm-svn: 90738
2009-12-07 10:27:35 +08:00
/// ::= 'msp430_intrcc'
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
/// ::= 'cc' UINT
Address review comments: add 3 ARM calling conventions. Dispatch C calling conv. to one of these conventions based on target triple and subtarget features. llvm-svn: 73530
2009-06-17 02:50:49 +08:00
///
Retype from unsigned to CallingConv::ID accordingly. Approved by Bob Wilson. llvm-svn: 80773
2009-09-02 16:44:58 +08:00
bool LLParser::ParseOptionalCallingConv(CallingConv::ID &CC) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
switch (Lex.getKind()) {
default: CC = CallingConv::C; return false;
case lltok::kw_ccc: CC = CallingConv::C; break;
case lltok::kw_fastcc: CC = CallingConv::Fast; break;
case lltok::kw_coldcc: CC = CallingConv::Cold; break;
case lltok::kw_x86_stdcallcc: CC = CallingConv::X86_StdCall; break;
case lltok::kw_x86_fastcallcc: CC = CallingConv::X86_FastCall; break;
Address review comments: add 3 ARM calling conventions. Dispatch C calling conv. to one of these conventions based on target triple and subtarget features. llvm-svn: 73530
2009-06-17 02:50:49 +08:00
case lltok::kw_arm_apcscc: CC = CallingConv::ARM_APCS; break;
case lltok::kw_arm_aapcscc: CC = CallingConv::ARM_AAPCS; break;
case lltok::kw_arm_aapcs_vfpcc:CC = CallingConv::ARM_AAPCS_VFP; break;
Add MSP430 interrupt calling conv. No functionality change yet. llvm-svn: 90738
2009-12-07 10:27:35 +08:00
case lltok::kw_msp430_intrcc: CC = CallingConv::MSP430_INTR; break;
Retype from unsigned to CallingConv::ID accordingly. Approved by Bob Wilson. llvm-svn: 80773
2009-09-02 16:44:58 +08:00
case lltok::kw_cc: {
unsigned ArbitraryCC;
Lex.Lex();
if (ParseUInt32(ArbitraryCC)) {
return true;
} else
CC = static_cast<CallingConv::ID>(ArbitraryCC);
return false;
}
break;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Lex.Lex();
return false;
}
rename ParseOptionalCustomMetadata -> ParseInstructionMetadata, and make it non-optional. This fixes the bug where we'd accept and ignore a spurious comma after some instructions. llvm-svn: 92300
2009-12-30 13:31:19 +08:00
/// ParseInstructionMetadata
Each instruction is allowed to have *multiple* different metadata objects on them. Though the entire compiler supports this, the asmparser didn't. llvm-svn: 92270
2009-12-30 05:25:40 +08:00
/// ::= !dbg !42 (',' !dbg !57)*
now that instruction metadata is only parsed in one place, eliminate the parser-global MDsOnInst vector and make ParseInstructionMetadata return its result by-ref through an argument like the entire rest of the parser. llvm-svn: 92302
2009-12-30 13:48:36 +08:00
bool LLParser::
ParseInstructionMetadata(SmallVectorImpl<std::pair<unsigned,
MDNode *> > &Result){
rename ParseOptionalCustomMetadata -> ParseInstructionMetadata, and make it non-optional. This fixes the bug where we'd accept and ignore a spurious comma after some instructions. llvm-svn: 92300
2009-12-30 13:31:19 +08:00
do {
if (Lex.getKind() != lltok::MetadataVar)
return TokError("expected metadata after comma");
Parse custom metadata attached with an instruction. llvm-svn: 83033
2009-09-29 08:01:14 +08:00
Each instruction is allowed to have *multiple* different metadata objects on them. Though the entire compiler supports this, the asmparser didn't. llvm-svn: 92270
2009-12-30 05:25:40 +08:00
std::string Name = Lex.getStrVal();
Lex.Lex();
clean up after metadata changes. llvm-svn: 84463
2009-10-19 13:31:10 +08:00
change ParseMDString and ParseMDNode to take arguments of the right type. This exposed a raft of other problems, which I'll deal with in subsequent patches. llvm-svn: 92273
2009-12-30 05:53:55 +08:00
MDNode *Node;
rename lltok::Metadata -> lltok::exclaim. We name tokens after their syntactic form, not their semantic form. llvm-svn: 92294
2009-12-30 12:56:59 +08:00
if (ParseToken(lltok::exclaim, "expected '!' here") ||
ParseMDNodeID(Node))
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Each instruction is allowed to have *multiple* different metadata objects on them. Though the entire compiler supports this, the asmparser didn't. llvm-svn: 92270
2009-12-30 05:25:40 +08:00
unsigned MDK = M->getMDKindID(Name.c_str());
now that instruction metadata is only parsed in one place, eliminate the parser-global MDsOnInst vector and make ParseInstructionMetadata return its result by-ref through an argument like the entire rest of the parser. llvm-svn: 92302
2009-12-30 13:48:36 +08:00
Result.push_back(std::make_pair(MDK, Node));
Each instruction is allowed to have *multiple* different metadata objects on them. Though the entire compiler supports this, the asmparser didn't. llvm-svn: 92270
2009-12-30 05:25:40 +08:00
// If this is the end of the list, we're done.
rename ParseOptionalCustomMetadata -> ParseInstructionMetadata, and make it non-optional. This fixes the bug where we'd accept and ignore a spurious comma after some instructions. llvm-svn: 92300
2009-12-30 13:31:19 +08:00
} while (EatIfPresent(lltok::comma));
return false;
Fix parsing of optional metadata for 'load', 'store' and 'alloc' instructions. llvm-svn: 82175
2009-09-18 07:04:48 +08:00
}
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
/// ParseOptionalAlignment
/// ::= /* empty */
/// ::= 'align' 4
bool LLParser::ParseOptionalAlignment(unsigned &Alignment) {
Alignment = 0;
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
if (!EatIfPresent(lltok::kw_align))
return false;
PR3281:crash00.ll: produce this diagnostic instead of crashing: @t = global i8 0, align 3 ^ llvm-svn: 61675
2009-01-05 15:46:05 +08:00
LocTy AlignLoc = Lex.getLoc();
if (ParseUInt32(Alignment)) return true;
if (!isPowerOf2_32(Alignment))
return Error(AlignLoc, "alignment is not a power of two");
return false;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
reimplement ParseOptionalInfo as ParseOptionalCommaAlign, correctly handle the comma case for metadata. llvm-svn: 92301
2009-12-30 13:44:30 +08:00
/// ParseOptionalCommaAlign
/// ::=
/// ::= ',' align 4
///
/// This returns with AteExtraComma set to true if it ate an excess comma at the
/// end.
bool LLParser::ParseOptionalCommaAlign(unsigned &Alignment,
bool &AteExtraComma) {
AteExtraComma = false;
while (EatIfPresent(lltok::comma)) {
// Metadata at the end is an early exit.
rename NamedOrCustomMD -> MetadataVar to follow conventions of all the rest of the code. llvm-svn: 92295
2009-12-30 13:02:06 +08:00
if (Lex.getKind() == lltok::MetadataVar) {
reimplement ParseOptionalInfo as ParseOptionalCommaAlign, correctly handle the comma case for metadata. llvm-svn: 92301
2009-12-30 13:44:30 +08:00
AteExtraComma = true;
return false;
}
if (Lex.getKind() == lltok::kw_align) {
Fix parsing of optional metadata for 'load', 'store' and 'alloc' instructions. llvm-svn: 82175
2009-09-18 07:04:48 +08:00
if (ParseOptionalAlignment(Alignment)) return true;
} else
return true;
reimplement ParseOptionalInfo as ParseOptionalCommaAlign, correctly handle the comma case for metadata. llvm-svn: 92301
2009-12-30 13:44:30 +08:00
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Fix parsing of optional metadata for 'load', 'store' and 'alloc' instructions. llvm-svn: 82175
2009-09-18 07:04:48 +08:00
return false;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
Add a new function attribute, 'alignstack'. It will indicate (when the backends implement support for it) that the stack should be forcibly realigned in the prologue (and the process reversed in the epilogue). llvm-svn: 95945
2010-02-12 08:31:15 +08:00
/// ParseOptionalStackAlignment
/// ::= /* empty */
/// ::= 'alignstack' '(' 4 ')'
bool LLParser::ParseOptionalStackAlignment(unsigned &Alignment) {
Alignment = 0;
if (!EatIfPresent(lltok::kw_alignstack))
return false;
LocTy ParenLoc = Lex.getLoc();
if (!EatIfPresent(lltok::lparen))
return Error(ParenLoc, "expected '('");
LocTy AlignLoc = Lex.getLoc();
if (ParseUInt32(Alignment)) return true;
ParenLoc = Lex.getLoc();
if (!EatIfPresent(lltok::rparen))
return Error(ParenLoc, "expected ')'");
if (!isPowerOf2_32(Alignment))
return Error(AlignLoc, "stack alignment is not a power of two");
return false;
}
Fix parsing of optional metadata for 'load', 'store' and 'alloc' instructions. llvm-svn: 82175
2009-09-18 07:04:48 +08:00
reimplement insertvalue/extractvalue metadata handling to not blindly accept invalid input. Actually add a testcase. llvm-svn: 92297
2009-12-30 13:14:00 +08:00
/// ParseIndexList - This parses the index list for an insert/extractvalue
/// instruction. This sets AteExtraComma in the case where we eat an extra
/// comma at the end of the line and find that it is followed by metadata.
/// Clients that don't allow metadata can call the version of this function that
/// only takes one argument.
///
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
/// ParseIndexList
/// ::= (',' uint32)+
reimplement insertvalue/extractvalue metadata handling to not blindly accept invalid input. Actually add a testcase. llvm-svn: 92297
2009-12-30 13:14:00 +08:00
///
bool LLParser::ParseIndexList(SmallVectorImpl<unsigned> &Indices,
bool &AteExtraComma) {
AteExtraComma = false;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (Lex.getKind() != lltok::comma)
return TokError("expected ',' as start of index list");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
while (EatIfPresent(lltok::comma)) {
reimplement insertvalue/extractvalue metadata handling to not blindly accept invalid input. Actually add a testcase. llvm-svn: 92297
2009-12-30 13:14:00 +08:00
if (Lex.getKind() == lltok::MetadataVar) {
AteExtraComma = true;
return false;
}
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
unsigned Idx;
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
if (ParseUInt32(Idx)) return true;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Indices.push_back(Idx);
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
}
//===----------------------------------------------------------------------===//
// Type Parsing.
//===----------------------------------------------------------------------===//
/// ParseType - Parse and resolve a full type.
Fix two classes of bugs. First: validate an invariant so that the asmparser rejects a bad construct instead of the verifier. Before: llvm-as: assembly parsed, but does not verify as correct! Invalid struct return type! i64 (%struct.Type*, %struct.Type*)* @foo after: llvm-as: t.ll:5:8: functions with 'sret' argument must return void define i64 @foo(%struct.Type* noalias nocapture sret %agg.result, %struct.Type* nocapture byval %t) nounwind { ^ Second, check that void is only used where allowed (in function return types) not in arbitrary places, fixing PR3747 - Crash in llvm-as with void field in struct. We now reject that example with: $ llvm-as t.ll llvm-as: t.ll:1:12: struct element can not have void type %x = type {void} ^ llvm-svn: 66394
2009-03-09 12:49:14 +08:00
bool LLParser::ParseType(PATypeHolder &Result, bool AllowVoid) {
LocTy TypeLoc = Lex.getLoc();
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ParseTypeRec(Result)) return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Verify no unresolved uprefs.
if (!UpRefs.empty())
return Error(UpRefs.back().Loc, "invalid unresolved type up reference");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
strength reduce a ton of type equality tests to check the typeid (Through the new predicates I added) instead of going through a context and doing a pointer comparison. Besides being cheaper, this allows a smart compiler to turn the if sequence into a switch. llvm-svn: 83297
2009-10-05 13:54:46 +08:00
if (!AllowVoid && Result.get()->isVoidTy())
Fix two classes of bugs. First: validate an invariant so that the asmparser rejects a bad construct instead of the verifier. Before: llvm-as: assembly parsed, but does not verify as correct! Invalid struct return type! i64 (%struct.Type*, %struct.Type*)* @foo after: llvm-as: t.ll:5:8: functions with 'sret' argument must return void define i64 @foo(%struct.Type* noalias nocapture sret %agg.result, %struct.Type* nocapture byval %t) nounwind { ^ Second, check that void is only used where allowed (in function return types) not in arbitrary places, fixing PR3747 - Crash in llvm-as with void field in struct. We now reject that example with: $ llvm-as t.ll llvm-as: t.ll:1:12: struct element can not have void type %x = type {void} ^ llvm-svn: 66394
2009-03-09 12:49:14 +08:00
return Error(TypeLoc, "void type only allowed for function results");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
}
/// HandleUpRefs - Every time we finish a new layer of types, this function is
/// called. It loops through the UpRefs vector, which is a list of the
/// currently active types. For each type, if the up-reference is contained in
/// the newly completed type, we decrement the level count. When the level
/// count reaches zero, the up-referenced type is the type that is passed in:
/// thus we can complete the cycle.
///
PATypeHolder LLParser::HandleUpRefs(const Type *ty) {
// If Ty isn't abstract, or if there are no up-references in it, then there is
// nothing to resolve here.
if (!ty->isAbstract() || UpRefs.empty()) return ty;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
PATypeHolder Ty(ty);
#if 0
Change errs() to dbgs(). llvm-svn: 92088
2009-12-24 07:38:28 +08:00
dbgs() << "Type '" << Ty->getDescription()
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
<< "' newly formed. Resolving upreferences.\n"
<< UpRefs.size() << " upreferences active!\n";
#endif
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// If we find any resolvable upreferences (i.e., those whose NestingLevel goes
// to zero), we resolve them all together before we resolve them to Ty. At
// the end of the loop, if there is anything to resolve to Ty, it will be in
// this variable.
OpaqueType *TypeToResolve = 0;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
for (unsigned i = 0; i != UpRefs.size(); ++i) {
// Determine if 'Ty' directly contains this up-references 'LastContainedTy'.
bool ContainsType =
std::find(Ty->subtype_begin(), Ty->subtype_end(),
UpRefs[i].LastContainedTy) != Ty->subtype_end();
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
#if 0
Change errs() to dbgs(). llvm-svn: 92088
2009-12-24 07:38:28 +08:00
dbgs() << " UR#" << i << " - TypeContains(" << Ty->getDescription() << ", "
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
<< UpRefs[i].LastContainedTy->getDescription() << ") = "
<< (ContainsType ? "true" : "false")
<< " level=" << UpRefs[i].NestingLevel << "\n";
#endif
if (!ContainsType)
continue;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Decrement level of upreference
unsigned Level = --UpRefs[i].NestingLevel;
UpRefs[i].LastContainedTy = Ty;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// If the Up-reference has a non-zero level, it shouldn't be resolved yet.
if (Level != 0)
continue;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
#if 0
Change errs() to dbgs(). llvm-svn: 92088
2009-12-24 07:38:28 +08:00
dbgs() << " * Resolving upreference for " << UpRefs[i].UpRefTy << "\n";
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
#endif
if (!TypeToResolve)
TypeToResolve = UpRefs[i].UpRefTy;
else
UpRefs[i].UpRefTy->refineAbstractTypeTo(TypeToResolve);
UpRefs.erase(UpRefs.begin()+i); // Remove from upreference list.
--i; // Do not skip the next element.
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (TypeToResolve)
TypeToResolve->refineAbstractTypeTo(Ty);
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Ty;
}
/// ParseTypeRec - The recursive function used to process the internal
/// implementation details of types.
bool LLParser::ParseTypeRec(PATypeHolder &Result) {
switch (Lex.getKind()) {
default:
return TokError("expected type");
case lltok::Type:
// TypeRec ::= 'float' | 'void' (etc)
Result = Lex.getTyVal();
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Lex.Lex();
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
break;
case lltok::kw_opaque:
// TypeRec ::= 'opaque'
Actually privatize a IntegerTypes, and fix a few bugs exposed by this. llvm-svn: 78955
2009-08-14 07:27:32 +08:00
Result = OpaqueType::get(Context);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Lex.Lex();
break;
case lltok::lbrace:
// TypeRec ::= '{' ... '}'
if (ParseStructType(Result, false))
return true;
break;
Add support for a union type in LLVM IR. Patch by Talin! llvm-svn: 96011
2010-02-13 04:49:41 +08:00
case lltok::kw_union:
// TypeRec ::= 'union' '{' ... '}'
if (ParseUnionType(Result))
return true;
break;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case lltok::lsquare:
// TypeRec ::= '[' ... ']'
Lex.Lex(); // eat the lsquare.
if (ParseArrayVectorType(Result, false))
return true;
break;
case lltok::less: // Either vector or packed struct.
// TypeRec ::= '<' ... '>'
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
Lex.Lex();
if (Lex.getKind() == lltok::lbrace) {
if (ParseStructType(Result, true) ||
ParseToken(lltok::greater, "expected '>' at end of packed struct"))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return true;
} else if (ParseArrayVectorType(Result, true))
return true;
break;
case lltok::LocalVar:
case lltok::StringConstant: // FIXME: REMOVE IN LLVM 3.0
// TypeRec ::= %foo
if (const Type *T = M->getTypeByName(Lex.getStrVal())) {
Result = T;
} else {
Actually privatize a IntegerTypes, and fix a few bugs exposed by this. llvm-svn: 78955
2009-08-14 07:27:32 +08:00
Result = OpaqueType::get(Context);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ForwardRefTypes.insert(std::make_pair(Lex.getStrVal(),
std::make_pair(Result,
Lex.getLoc())));
M->addTypeName(Lex.getStrVal(), Result.get());
}
Lex.Lex();
break;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case lltok::LocalVarID:
// TypeRec ::= %4
if (Lex.getUIntVal() < NumberedTypes.size())
Result = NumberedTypes[Lex.getUIntVal()];
else {
std::map<unsigned, std::pair<PATypeHolder, LocTy> >::iterator
I = ForwardRefTypeIDs.find(Lex.getUIntVal());
if (I != ForwardRefTypeIDs.end())
Result = I->second.first;
else {
Actually privatize a IntegerTypes, and fix a few bugs exposed by this. llvm-svn: 78955
2009-08-14 07:27:32 +08:00
Result = OpaqueType::get(Context);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ForwardRefTypeIDs.insert(std::make_pair(Lex.getUIntVal(),
std::make_pair(Result,
Lex.getLoc())));
}
}
Lex.Lex();
break;
case lltok::backslash: {
// TypeRec ::= '\' 4
Lex.Lex();
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
unsigned Val;
if (ParseUInt32(Val)) return true;
Actually privatize a IntegerTypes, and fix a few bugs exposed by this. llvm-svn: 78955
2009-08-14 07:27:32 +08:00
OpaqueType *OT = OpaqueType::get(Context); //Use temporary placeholder.
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
UpRefs.push_back(UpRefRecord(Lex.getLoc(), Val, OT));
Result = OT;
break;
}
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
// Parse the type suffixes.
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
while (1) {
switch (Lex.getKind()) {
// End of type.
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
default: return false;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// TypeRec ::= TypeRec '*'
case lltok::star:
strength reduce a ton of type equality tests to check the typeid (Through the new predicates I added) instead of going through a context and doing a pointer comparison. Besides being cheaper, this allows a smart compiler to turn the if sequence into a switch. llvm-svn: 83297
2009-10-05 13:54:46 +08:00
if (Result.get()->isLabelTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return TokError("basic block pointers are invalid");
strength reduce a ton of type equality tests to check the typeid (Through the new predicates I added) instead of going through a context and doing a pointer comparison. Besides being cheaper, this allows a smart compiler to turn the if sequence into a switch. llvm-svn: 83297
2009-10-05 13:54:46 +08:00
if (Result.get()->isVoidTy())
Use slightly more correct grammar in error messages. llvm-svn: 64148
2009-02-10 01:41:21 +08:00
return TokError("pointers to void are invalid; use i8* instead");
Create FunctionType::isValidArgumentType to go along with isValidReturnType. Also create isValidElementType for ArrayType, PointerType, StructType and VectorType. Make LLParser use them. This closes up some holes like an assertion failure on: %x = type {label} but largely doesn't change any semantics. The only thing we accept now which we didn't before is vectors of opaque type such as "<4 x opaque>". The opaque can be resolved to an int or float when linking. llvm-svn: 73016
2009-06-07 15:26:46 +08:00
if (!PointerType::isValidElementType(Result.get()))
return TokError("pointer to this type is invalid");
Move types back to the 2.5 API. llvm-svn: 77516
2009-07-30 06:17:13 +08:00
Result = HandleUpRefs(PointerType::getUnqual(Result.get()));
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Lex.Lex();
break;
// TypeRec ::= TypeRec 'addrspace' '(' uint32 ')' '*'
case lltok::kw_addrspace: {
strength reduce a ton of type equality tests to check the typeid (Through the new predicates I added) instead of going through a context and doing a pointer comparison. Besides being cheaper, this allows a smart compiler to turn the if sequence into a switch. llvm-svn: 83297
2009-10-05 13:54:46 +08:00
if (Result.get()->isLabelTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return TokError("basic block pointers are invalid");
strength reduce a ton of type equality tests to check the typeid (Through the new predicates I added) instead of going through a context and doing a pointer comparison. Besides being cheaper, this allows a smart compiler to turn the if sequence into a switch. llvm-svn: 83297
2009-10-05 13:54:46 +08:00
if (Result.get()->isVoidTy())
Use slightly more correct grammar in error messages. llvm-svn: 64148
2009-02-10 01:41:21 +08:00
return TokError("pointers to void are invalid; use i8* instead");
Create FunctionType::isValidArgumentType to go along with isValidReturnType. Also create isValidElementType for ArrayType, PointerType, StructType and VectorType. Make LLParser use them. This closes up some holes like an assertion failure on: %x = type {label} but largely doesn't change any semantics. The only thing we accept now which we didn't before is vectors of opaque type such as "<4 x opaque>". The opaque can be resolved to an int or float when linking. llvm-svn: 73016
2009-06-07 15:26:46 +08:00
if (!PointerType::isValidElementType(Result.get()))
return TokError("pointer to this type is invalid");
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
unsigned AddrSpace;
if (ParseOptionalAddrSpace(AddrSpace) ||
ParseToken(lltok::star, "expected '*' in address space"))
return true;
Move types back to the 2.5 API. llvm-svn: 77516
2009-07-30 06:17:13 +08:00
Result = HandleUpRefs(PointerType::get(Result.get(), AddrSpace));
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
break;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
/// Types '(' ArgTypeListI ')' OptFuncAttrs
case lltok::lparen:
if (ParseFunctionType(Result))
return true;
break;
}
}
}
/// ParseParameterList
/// ::= '(' ')'
/// ::= '(' Arg (',' Arg)* ')'
/// Arg
/// ::= Type OptionalAttributes Value OptionalAttributes
bool LLParser::ParseParameterList(SmallVectorImpl<ParamInfo> &ArgList,
PerFunctionState &PFS) {
if (ParseToken(lltok::lparen, "expected '(' in call"))
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
while (Lex.getKind() != lltok::rparen) {
// If this isn't the first argument, we need a comma.
if (!ArgList.empty() &&
ParseToken(lltok::comma, "expected ',' in argument list"))
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Parse the argument.
LocTy ArgLoc;
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
PATypeHolder ArgTy(Type::getVoidTy(Context));
Add ParseInlineMetadata() which can parses metadata that refers to an instruction. Extend ParseParameterList() to use this new function so that calls to llvm.dbg.declare can pass inline metadata llvm-svn: 90497
2009-12-04 07:40:58 +08:00
unsigned ArgAttrs1 = Attribute::None;
unsigned ArgAttrs2 = Attribute::None;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Value *V;
Add ParseInlineMetadata() which can parses metadata that refers to an instruction. Extend ParseParameterList() to use this new function so that calls to llvm.dbg.declare can pass inline metadata llvm-svn: 90497
2009-12-04 07:40:58 +08:00
if (ParseType(ArgTy, ArgLoc))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return true;
Add ParseInlineMetadata() which can parses metadata that refers to an instruction. Extend ParseParameterList() to use this new function so that calls to llvm.dbg.declare can pass inline metadata llvm-svn: 90497
2009-12-04 07:40:58 +08:00
split t_Metadata into t_MDNode and t_MDString, eliminating some unsafe casting. llvm-svn: 92287
2009-12-30 10:11:14 +08:00
// Otherwise, handle normal operands.
if (ParseOptionalAttrs(ArgAttrs1, 0) ||
ParseValue(ArgTy, V, PFS) ||
// FIXME: Should not allow attributes after the argument, remove this
// in LLVM 3.0.
ParseOptionalAttrs(ArgAttrs2, 3))
return true;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ArgList.push_back(ParamInfo(ArgLoc, V, ArgAttrs1|ArgAttrs2));
}
Lex.Lex(); // Lex the ')'.
return false;
}
Reject PR3281:accepted03.ll with: llvm-as: accepted03.ll:1:35: invalid unresolved type up reference declare void @r({ \7, opaque, \10 } %su) ^ llvm-svn: 61725
2009-01-06 02:34:07 +08:00
/// ParseArgumentList - Parse the argument list for a function type or function
/// prototype. If 'inType' is true then we are parsing a FunctionType.
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
/// ::= '(' ArgTypeListI ')'
/// ArgTypeListI
/// ::= /*empty*/
/// ::= '...'
/// ::= ArgTypeList ',' '...'
/// ::= ArgType (',' ArgType)*
Reject PR3281:accepted03.ll with: llvm-as: accepted03.ll:1:35: invalid unresolved type up reference declare void @r({ \7, opaque, \10 } %su) ^ llvm-svn: 61725
2009-01-06 02:34:07 +08:00
///
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
bool LLParser::ParseArgumentList(std::vector<ArgInfo> &ArgList,
Reject PR3281:accepted03.ll with: llvm-as: accepted03.ll:1:35: invalid unresolved type up reference declare void @r({ \7, opaque, \10 } %su) ^ llvm-svn: 61725
2009-01-06 02:34:07 +08:00
bool &isVarArg, bool inType) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
isVarArg = false;
assert(Lex.getKind() == lltok::lparen);
Lex.Lex(); // eat the (.
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (Lex.getKind() == lltok::rparen) {
// empty
} else if (Lex.getKind() == lltok::dotdotdot) {
isVarArg = true;
Lex.Lex();
} else {
LocTy TypeLoc = Lex.getLoc();
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
PATypeHolder ArgTy(Type::getVoidTy(Context));
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
unsigned Attrs;
std::string Name;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reject PR3281:accepted03.ll with: llvm-as: accepted03.ll:1:35: invalid unresolved type up reference declare void @r({ \7, opaque, \10 } %su) ^ llvm-svn: 61725
2009-01-06 02:34:07 +08:00
// If we're parsing a type, use ParseTypeRec, because we allow recursive
// types (such as a function returning a pointer to itself). If parsing a
// function prototype, we require fully resolved types.
if ((inType ? ParseTypeRec(ArgTy) : ParseType(ArgTy)) ||
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
ParseOptionalAttrs(Attrs, 0)) return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
strength reduce a ton of type equality tests to check the typeid (Through the new predicates I added) instead of going through a context and doing a pointer comparison. Besides being cheaper, this allows a smart compiler to turn the if sequence into a switch. llvm-svn: 83297
2009-10-05 13:54:46 +08:00
if (ArgTy->isVoidTy())
Fix two classes of bugs. First: validate an invariant so that the asmparser rejects a bad construct instead of the verifier. Before: llvm-as: assembly parsed, but does not verify as correct! Invalid struct return type! i64 (%struct.Type*, %struct.Type*)* @foo after: llvm-as: t.ll:5:8: functions with 'sret' argument must return void define i64 @foo(%struct.Type* noalias nocapture sret %agg.result, %struct.Type* nocapture byval %t) nounwind { ^ Second, check that void is only used where allowed (in function return types) not in arbitrary places, fixing PR3747 - Crash in llvm-as with void field in struct. We now reject that example with: $ llvm-as t.ll llvm-as: t.ll:1:12: struct element can not have void type %x = type {void} ^ llvm-svn: 66394
2009-03-09 12:49:14 +08:00
return Error(TypeLoc, "argument can not have void type");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (Lex.getKind() == lltok::LocalVar ||
Lex.getKind() == lltok::StringConstant) { // FIXME: REMOVE IN LLVM 3.0
Name = Lex.getStrVal();
Lex.Lex();
}
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
Create FunctionType::isValidArgumentType to go along with isValidReturnType. Also create isValidElementType for ArrayType, PointerType, StructType and VectorType. Make LLParser use them. This closes up some holes like an assertion failure on: %x = type {label} but largely doesn't change any semantics. The only thing we accept now which we didn't before is vectors of opaque type such as "<4 x opaque>". The opaque can be resolved to an int or float when linking. llvm-svn: 73016
2009-06-07 15:26:46 +08:00
if (!FunctionType::isValidArgumentType(ArgTy))
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
return Error(TypeLoc, "invalid type for function argument");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ArgList.push_back(ArgInfo(TypeLoc, ArgTy, Attrs, Name));
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
while (EatIfPresent(lltok::comma)) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Handle ... at end of arg list.
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
if (EatIfPresent(lltok::dotdotdot)) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
isVarArg = true;
break;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Otherwise must be an argument type.
TypeLoc = Lex.getLoc();
Fix two classes of bugs. First: validate an invariant so that the asmparser rejects a bad construct instead of the verifier. Before: llvm-as: assembly parsed, but does not verify as correct! Invalid struct return type! i64 (%struct.Type*, %struct.Type*)* @foo after: llvm-as: t.ll:5:8: functions with 'sret' argument must return void define i64 @foo(%struct.Type* noalias nocapture sret %agg.result, %struct.Type* nocapture byval %t) nounwind { ^ Second, check that void is only used where allowed (in function return types) not in arbitrary places, fixing PR3747 - Crash in llvm-as with void field in struct. We now reject that example with: $ llvm-as t.ll llvm-as: t.ll:1:12: struct element can not have void type %x = type {void} ^ llvm-svn: 66394
2009-03-09 12:49:14 +08:00
if ((inType ? ParseTypeRec(ArgTy) : ParseType(ArgTy)) ||
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
ParseOptionalAttrs(Attrs, 0)) return true;
strength reduce a ton of type equality tests to check the typeid (Through the new predicates I added) instead of going through a context and doing a pointer comparison. Besides being cheaper, this allows a smart compiler to turn the if sequence into a switch. llvm-svn: 83297
2009-10-05 13:54:46 +08:00
if (ArgTy->isVoidTy())
Fix two classes of bugs. First: validate an invariant so that the asmparser rejects a bad construct instead of the verifier. Before: llvm-as: assembly parsed, but does not verify as correct! Invalid struct return type! i64 (%struct.Type*, %struct.Type*)* @foo after: llvm-as: t.ll:5:8: functions with 'sret' argument must return void define i64 @foo(%struct.Type* noalias nocapture sret %agg.result, %struct.Type* nocapture byval %t) nounwind { ^ Second, check that void is only used where allowed (in function return types) not in arbitrary places, fixing PR3747 - Crash in llvm-as with void field in struct. We now reject that example with: $ llvm-as t.ll llvm-as: t.ll:1:12: struct element can not have void type %x = type {void} ^ llvm-svn: 66394
2009-03-09 12:49:14 +08:00
return Error(TypeLoc, "argument can not have void type");
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (Lex.getKind() == lltok::LocalVar ||
Lex.getKind() == lltok::StringConstant) { // FIXME: REMOVE IN LLVM 3.0
Name = Lex.getStrVal();
Lex.Lex();
} else {
Name = "";
}
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
Introduce isOpaqueTy and use it rather than isa<OpaqueType>. Also, move some methods to try to have the type predicates be more logically positioned. llvm-svn: 96349
2010-02-16 22:50:09 +08:00
if (!ArgTy->isFirstClassType() && !ArgTy->isOpaqueTy())
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
return Error(TypeLoc, "invalid type for function argument");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ArgList.push_back(ArgInfo(TypeLoc, ArgTy, Attrs, Name));
}
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
return ParseToken(lltok::rparen, "expected ')' at end of argument list");
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
/// ParseFunctionType
/// ::= Type ArgumentList OptionalAttrs
bool LLParser::ParseFunctionType(PATypeHolder &Result) {
assert(Lex.getKind() == lltok::lparen);
diagnose PR3281:crash02.ll with: llvm-as: crash02.ll:1:62: invalid function return type declare { <{ <{}>, void ([1898 x { void ()* }], opaque, ...) (), fp128 * }>, opaque } @t () ^ llvm-svn: 61679
2009-01-05 16:04:33 +08:00
if (!FunctionType::isValidReturnType(Result))
return TokError("invalid function return type");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
std::vector<ArgInfo> ArgList;
bool isVarArg;
unsigned Attrs;
Reject PR3281:accepted03.ll with: llvm-as: accepted03.ll:1:35: invalid unresolved type up reference declare void @r({ \7, opaque, \10 } %su) ^ llvm-svn: 61725
2009-01-06 02:34:07 +08:00
if (ParseArgumentList(ArgList, isVarArg, true) ||
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// FIXME: Allow, but ignore attributes on function types!
// FIXME: Remove in LLVM 3.0
ParseOptionalAttrs(Attrs, 2))
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Reject names on the arguments lists.
for (unsigned i = 0, e = ArgList.size(); i != e; ++i) {
if (!ArgList[i].Name.empty())
return Error(ArgList[i].Loc, "argument name invalid in function type");
if (!ArgList[i].Attrs != 0) {
// Allow but ignore attributes on function types; this permits
// auto-upgrade.
// FIXME: REJECT ATTRIBUTES ON FUNCTION TYPES in LLVM 3.0
}
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
std::vector<const Type*> ArgListTy;
for (unsigned i = 0, e = ArgList.size(); i != e; ++i)
ArgListTy.push_back(ArgList[i].Type);
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Move types back to the 2.5 API. llvm-svn: 77516
2009-07-30 06:17:13 +08:00
Result = HandleUpRefs(FunctionType::get(Result.get(),
Try again at converting the LLParser to use LLVMContext, without massive breakage this time. llvm-svn: 74671
2009-07-02 07:57:11 +08:00
ArgListTy, isVarArg));
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
}
/// ParseStructType: Handles packed and unpacked types. </> parsed elsewhere.
/// TypeRec
/// ::= '{' '}'
/// ::= '{' TypeRec (',' TypeRec)* '}'
/// ::= '<' '{' '}' '>'
/// ::= '<' '{' TypeRec (',' TypeRec)* '}' '>'
bool LLParser::ParseStructType(PATypeHolder &Result, bool Packed) {
assert(Lex.getKind() == lltok::lbrace);
Lex.Lex(); // Consume the '{'
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
if (EatIfPresent(lltok::rbrace)) {
Privatize the StructType table, which unfortunately involves routing contexts through a number of APIs. llvm-svn: 78258
2009-08-06 07:16:16 +08:00
Result = StructType::get(Context, Packed);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
}
std::vector<PATypeHolder> ParamsList;
Fix two classes of bugs. First: validate an invariant so that the asmparser rejects a bad construct instead of the verifier. Before: llvm-as: assembly parsed, but does not verify as correct! Invalid struct return type! i64 (%struct.Type*, %struct.Type*)* @foo after: llvm-as: t.ll:5:8: functions with 'sret' argument must return void define i64 @foo(%struct.Type* noalias nocapture sret %agg.result, %struct.Type* nocapture byval %t) nounwind { ^ Second, check that void is only used where allowed (in function return types) not in arbitrary places, fixing PR3747 - Crash in llvm-as with void field in struct. We now reject that example with: $ llvm-as t.ll llvm-as: t.ll:1:12: struct element can not have void type %x = type {void} ^ llvm-svn: 66394
2009-03-09 12:49:14 +08:00
LocTy EltTyLoc = Lex.getLoc();
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ParseTypeRec(Result)) return true;
ParamsList.push_back(Result);
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
strength reduce a ton of type equality tests to check the typeid (Through the new predicates I added) instead of going through a context and doing a pointer comparison. Besides being cheaper, this allows a smart compiler to turn the if sequence into a switch. llvm-svn: 83297
2009-10-05 13:54:46 +08:00
if (Result->isVoidTy())
Fix two classes of bugs. First: validate an invariant so that the asmparser rejects a bad construct instead of the verifier. Before: llvm-as: assembly parsed, but does not verify as correct! Invalid struct return type! i64 (%struct.Type*, %struct.Type*)* @foo after: llvm-as: t.ll:5:8: functions with 'sret' argument must return void define i64 @foo(%struct.Type* noalias nocapture sret %agg.result, %struct.Type* nocapture byval %t) nounwind { ^ Second, check that void is only used where allowed (in function return types) not in arbitrary places, fixing PR3747 - Crash in llvm-as with void field in struct. We now reject that example with: $ llvm-as t.ll llvm-as: t.ll:1:12: struct element can not have void type %x = type {void} ^ llvm-svn: 66394
2009-03-09 12:49:14 +08:00
return Error(EltTyLoc, "struct element can not have void type");
Create FunctionType::isValidArgumentType to go along with isValidReturnType. Also create isValidElementType for ArrayType, PointerType, StructType and VectorType. Make LLParser use them. This closes up some holes like an assertion failure on: %x = type {label} but largely doesn't change any semantics. The only thing we accept now which we didn't before is vectors of opaque type such as "<4 x opaque>". The opaque can be resolved to an int or float when linking. llvm-svn: 73016
2009-06-07 15:26:46 +08:00
if (!StructType::isValidElementType(Result))
return Error(EltTyLoc, "invalid element type for struct");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
while (EatIfPresent(lltok::comma)) {
Fix two classes of bugs. First: validate an invariant so that the asmparser rejects a bad construct instead of the verifier. Before: llvm-as: assembly parsed, but does not verify as correct! Invalid struct return type! i64 (%struct.Type*, %struct.Type*)* @foo after: llvm-as: t.ll:5:8: functions with 'sret' argument must return void define i64 @foo(%struct.Type* noalias nocapture sret %agg.result, %struct.Type* nocapture byval %t) nounwind { ^ Second, check that void is only used where allowed (in function return types) not in arbitrary places, fixing PR3747 - Crash in llvm-as with void field in struct. We now reject that example with: $ llvm-as t.ll llvm-as: t.ll:1:12: struct element can not have void type %x = type {void} ^ llvm-svn: 66394
2009-03-09 12:49:14 +08:00
EltTyLoc = Lex.getLoc();
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ParseTypeRec(Result)) return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
strength reduce a ton of type equality tests to check the typeid (Through the new predicates I added) instead of going through a context and doing a pointer comparison. Besides being cheaper, this allows a smart compiler to turn the if sequence into a switch. llvm-svn: 83297
2009-10-05 13:54:46 +08:00
if (Result->isVoidTy())
Fix two classes of bugs. First: validate an invariant so that the asmparser rejects a bad construct instead of the verifier. Before: llvm-as: assembly parsed, but does not verify as correct! Invalid struct return type! i64 (%struct.Type*, %struct.Type*)* @foo after: llvm-as: t.ll:5:8: functions with 'sret' argument must return void define i64 @foo(%struct.Type* noalias nocapture sret %agg.result, %struct.Type* nocapture byval %t) nounwind { ^ Second, check that void is only used where allowed (in function return types) not in arbitrary places, fixing PR3747 - Crash in llvm-as with void field in struct. We now reject that example with: $ llvm-as t.ll llvm-as: t.ll:1:12: struct element can not have void type %x = type {void} ^ llvm-svn: 66394
2009-03-09 12:49:14 +08:00
return Error(EltTyLoc, "struct element can not have void type");
Create FunctionType::isValidArgumentType to go along with isValidReturnType. Also create isValidElementType for ArrayType, PointerType, StructType and VectorType. Make LLParser use them. This closes up some holes like an assertion failure on: %x = type {label} but largely doesn't change any semantics. The only thing we accept now which we didn't before is vectors of opaque type such as "<4 x opaque>". The opaque can be resolved to an int or float when linking. llvm-svn: 73016
2009-06-07 15:26:46 +08:00
if (!StructType::isValidElementType(Result))
return Error(EltTyLoc, "invalid element type for struct");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ParamsList.push_back(Result);
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
if (ParseToken(lltok::rbrace, "expected '}' at end of struct"))
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
std::vector<const Type*> ParamsListTy;
for (unsigned i = 0, e = ParamsList.size(); i != e; ++i)
ParamsListTy.push_back(ParamsList[i].get());
Privatize the StructType table, which unfortunately involves routing contexts through a number of APIs. llvm-svn: 78258
2009-08-06 07:16:16 +08:00
Result = HandleUpRefs(StructType::get(Context, ParamsListTy, Packed));
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
}
Add support for a union type in LLVM IR. Patch by Talin! llvm-svn: 96011
2010-02-13 04:49:41 +08:00
/// ParseUnionType
/// TypeRec
/// ::= 'union' '{' TypeRec (',' TypeRec)* '}'
bool LLParser::ParseUnionType(PATypeHolder &Result) {
assert(Lex.getKind() == lltok::kw_union);
Lex.Lex(); // Consume the 'union'
if (ParseToken(lltok::lbrace, "'{' expected after 'union'")) return true;
SmallVector<PATypeHolder, 8> ParamsList;
do {
LocTy EltTyLoc = Lex.getLoc();
if (ParseTypeRec(Result)) return true;
ParamsList.push_back(Result);
if (Result->isVoidTy())
return Error(EltTyLoc, "union element can not have void type");
if (!UnionType::isValidElementType(Result))
return Error(EltTyLoc, "invalid element type for union");
} while (EatIfPresent(lltok::comma)) ;
if (ParseToken(lltok::rbrace, "expected '}' at end of union"))
return true;
SmallVector<const Type*, 8> ParamsListTy;
for (unsigned i = 0, e = ParamsList.size(); i != e; ++i)
ParamsListTy.push_back(ParamsList[i].get());
Result = HandleUpRefs(UnionType::get(&ParamsListTy[0], ParamsListTy.size()));
return false;
}
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
/// ParseArrayVectorType - Parse an array or vector type, assuming the first
/// token has already been consumed.
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
/// TypeRec
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
/// ::= '[' APSINTVAL 'x' Types ']'
/// ::= '<' APSINTVAL 'x' Types '>'
bool LLParser::ParseArrayVectorType(PATypeHolder &Result, bool isVector) {
if (Lex.getKind() != lltok::APSInt || Lex.getAPSIntVal().isSigned() ||
Lex.getAPSIntVal().getBitWidth() > 64)
return TokError("expected number in address space");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
LocTy SizeLoc = Lex.getLoc();
uint64_t Size = Lex.getAPSIntVal().getZExtValue();
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
Lex.Lex();
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
if (ParseToken(lltok::kw_x, "expected 'x' after element count"))
return true;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
LocTy TypeLoc = Lex.getLoc();
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
PATypeHolder EltTy(Type::getVoidTy(Context));
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ParseTypeRec(EltTy)) return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
strength reduce a ton of type equality tests to check the typeid (Through the new predicates I added) instead of going through a context and doing a pointer comparison. Besides being cheaper, this allows a smart compiler to turn the if sequence into a switch. llvm-svn: 83297
2009-10-05 13:54:46 +08:00
if (EltTy->isVoidTy())
Fix two classes of bugs. First: validate an invariant so that the asmparser rejects a bad construct instead of the verifier. Before: llvm-as: assembly parsed, but does not verify as correct! Invalid struct return type! i64 (%struct.Type*, %struct.Type*)* @foo after: llvm-as: t.ll:5:8: functions with 'sret' argument must return void define i64 @foo(%struct.Type* noalias nocapture sret %agg.result, %struct.Type* nocapture byval %t) nounwind { ^ Second, check that void is only used where allowed (in function return types) not in arbitrary places, fixing PR3747 - Crash in llvm-as with void field in struct. We now reject that example with: $ llvm-as t.ll llvm-as: t.ll:1:12: struct element can not have void type %x = type {void} ^ llvm-svn: 66394
2009-03-09 12:49:14 +08:00
return Error(TypeLoc, "array and vector element type cannot be void");
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
if (ParseToken(isVector ? lltok::greater : lltok::rsquare,
"expected end of sequential type"))
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (isVector) {
reject 0 element vectors with: @a = internal constant void bitcast(<0 x i8> <> to void) ^ Fixes PR3685 llvm-svn: 65698
2009-03-01 02:12:41 +08:00
if (Size == 0)
return Error(SizeLoc, "zero element vector is illegal");
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if ((unsigned)Size != Size)
return Error(SizeLoc, "size too large for vector");
Create FunctionType::isValidArgumentType to go along with isValidReturnType. Also create isValidElementType for ArrayType, PointerType, StructType and VectorType. Make LLParser use them. This closes up some holes like an assertion failure on: %x = type {label} but largely doesn't change any semantics. The only thing we accept now which we didn't before is vectors of opaque type such as "<4 x opaque>". The opaque can be resolved to an int or float when linking. llvm-svn: 73016
2009-06-07 15:26:46 +08:00
if (!VectorType::isValidElementType(EltTy))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(TypeLoc, "vector element type must be fp or integer");
Move types back to the 2.5 API. llvm-svn: 77516
2009-07-30 06:17:13 +08:00
Result = VectorType::get(EltTy, unsigned(Size));
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
} else {
Create FunctionType::isValidArgumentType to go along with isValidReturnType. Also create isValidElementType for ArrayType, PointerType, StructType and VectorType. Make LLParser use them. This closes up some holes like an assertion failure on: %x = type {label} but largely doesn't change any semantics. The only thing we accept now which we didn't before is vectors of opaque type such as "<4 x opaque>". The opaque can be resolved to an int or float when linking. llvm-svn: 73016
2009-06-07 15:26:46 +08:00
if (!ArrayType::isValidElementType(EltTy))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(TypeLoc, "invalid array element type");
Move types back to the 2.5 API. llvm-svn: 77516
2009-07-30 06:17:13 +08:00
Result = HandleUpRefs(ArrayType::get(EltTy, Size));
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
return false;
}
//===----------------------------------------------------------------------===//
// Function Semantic Analysis.
//===----------------------------------------------------------------------===//
full asmparser support for blockaddress. We can now do: $ llvm-as foo.ll -d -disable-output which reads and prints the .ll file. BC encoding is the next project. Testcase will go in once that works. llvm-svn: 85368
2009-10-28 11:39:23 +08:00
LLParser::PerFunctionState::PerFunctionState(LLParser &p, Function &f,
int functionNumber)
: P(p), F(f), FunctionNumber(functionNumber) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Insert unnamed arguments into the NumberedVals list.
for (Function::arg_iterator AI = F.arg_begin(), E = F.arg_end();
AI != E; ++AI)
if (!AI->hasName())
NumberedVals.push_back(AI);
}
LLParser::PerFunctionState::~PerFunctionState() {
// If there were any forward referenced non-basicblock values, delete them.
for (std::map<std::string, std::pair<Value*, LocTy> >::iterator
I = ForwardRefVals.begin(), E = ForwardRefVals.end(); I != E; ++I)
if (!isa<BasicBlock>(I->second.first)) {
Use LLVMContext for generating UndefValue constants too! llvm-svn: 74703
2009-07-03 01:04:01 +08:00
I->second.first->replaceAllUsesWith(
Move more code back to 2.5 APIs. llvm-svn: 77635
2009-07-31 07:03:37 +08:00
UndefValue::get(I->second.first->getType()));
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
delete I->second.first;
I->second.first = 0;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
for (std::map<unsigned, std::pair<Value*, LocTy> >::iterator
I = ForwardRefValIDs.begin(), E = ForwardRefValIDs.end(); I != E; ++I)
if (!isa<BasicBlock>(I->second.first)) {
Use LLVMContext for generating UndefValue constants too! llvm-svn: 74703
2009-07-03 01:04:01 +08:00
I->second.first->replaceAllUsesWith(
Move more code back to 2.5 APIs. llvm-svn: 77635
2009-07-31 07:03:37 +08:00
UndefValue::get(I->second.first->getType()));
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
delete I->second.first;
I->second.first = 0;
}
}
full asmparser support for blockaddress. We can now do: $ llvm-as foo.ll -d -disable-output which reads and prints the .ll file. BC encoding is the next project. Testcase will go in once that works. llvm-svn: 85368
2009-10-28 11:39:23 +08:00
bool LLParser::PerFunctionState::FinishFunction() {
// Check to see if someone took the address of labels in this block.
if (!P.ForwardRefBlockAddresses.empty()) {
ValID FunctionID;
if (!F.getName().empty()) {
FunctionID.Kind = ValID::t_GlobalName;
FunctionID.StrVal = F.getName();
} else {
FunctionID.Kind = ValID::t_GlobalID;
FunctionID.UIntVal = FunctionNumber;
}
std::map<ValID, std::vector<std::pair<ValID, GlobalValue*> > >::iterator
FRBAI = P.ForwardRefBlockAddresses.find(FunctionID);
if (FRBAI != P.ForwardRefBlockAddresses.end()) {
// Resolve all these references.
if (P.ResolveForwardRefBlockAddresses(&F, FRBAI->second, this))
return true;
P.ForwardRefBlockAddresses.erase(FRBAI);
}
}
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (!ForwardRefVals.empty())
return P.Error(ForwardRefVals.begin()->second.second,
"use of undefined value '%" + ForwardRefVals.begin()->first +
"'");
if (!ForwardRefValIDs.empty())
return P.Error(ForwardRefValIDs.begin()->second.second,
"use of undefined value '%" +
utostr(ForwardRefValIDs.begin()->first) + "'");
return false;
}
/// GetVal - Get a value with the specified name or ID, creating a
/// forward reference record if needed. This can return null if the value
/// exists but does not have the right type.
Value *LLParser::PerFunctionState::GetVal(const std::string &Name,
const Type *Ty, LocTy Loc) {
// Look this name up in the normal function symbol table.
Value *Val = F.getValueSymbolTable().lookup(Name);
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// If this is a forward reference for the value, see if we already created a
// forward ref record.
if (Val == 0) {
std::map<std::string, std::pair<Value*, LocTy> >::iterator
I = ForwardRefVals.find(Name);
if (I != ForwardRefVals.end())
Val = I->second.first;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// If we have the value in the symbol table or fwd-ref table, return it.
if (Val) {
if (Val->getType() == Ty) return Val;
strength reduce a ton of type equality tests to check the typeid (Through the new predicates I added) instead of going through a context and doing a pointer comparison. Besides being cheaper, this allows a smart compiler to turn the if sequence into a switch. llvm-svn: 83297
2009-10-05 13:54:46 +08:00
if (Ty->isLabelTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
P.Error(Loc, "'%" + Name + "' is not a basic block");
else
P.Error(Loc, "'%" + Name + "' defined with type '" +
Val->getType()->getDescription() + "'");
return 0;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Don't make placeholders with invalid type.
Introduce isOpaqueTy and use it rather than isa<OpaqueType>. Also, move some methods to try to have the type predicates be more logically positioned. llvm-svn: 96349
2010-02-16 22:50:09 +08:00
if (!Ty->isFirstClassType() && !Ty->isOpaqueTy() && !Ty->isLabelTy()) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
P.Error(Loc, "invalid use of a non-first-class type");
return 0;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Otherwise, create a new forward reference for this value and remember it.
Value *FwdVal;
strength reduce a ton of type equality tests to check the typeid (Through the new predicates I added) instead of going through a context and doing a pointer comparison. Besides being cheaper, this allows a smart compiler to turn the if sequence into a switch. llvm-svn: 83297
2009-10-05 13:54:46 +08:00
if (Ty->isLabelTy())
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
FwdVal = BasicBlock::Create(F.getContext(), Name, &F);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
else
FwdVal = new Argument(Ty, Name);
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ForwardRefVals[Name] = std::make_pair(FwdVal, Loc);
return FwdVal;
}
Value *LLParser::PerFunctionState::GetVal(unsigned ID, const Type *Ty,
LocTy Loc) {
// Look this name up in the normal function symbol table.
Value *Val = ID < NumberedVals.size() ? NumberedVals[ID] : 0;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// If this is a forward reference for the value, see if we already created a
// forward ref record.
if (Val == 0) {
std::map<unsigned, std::pair<Value*, LocTy> >::iterator
I = ForwardRefValIDs.find(ID);
if (I != ForwardRefValIDs.end())
Val = I->second.first;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// If we have the value in the symbol table or fwd-ref table, return it.
if (Val) {
if (Val->getType() == Ty) return Val;
strength reduce a ton of type equality tests to check the typeid (Through the new predicates I added) instead of going through a context and doing a pointer comparison. Besides being cheaper, this allows a smart compiler to turn the if sequence into a switch. llvm-svn: 83297
2009-10-05 13:54:46 +08:00
if (Ty->isLabelTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
P.Error(Loc, "'%" + utostr(ID) + "' is not a basic block");
else
P.Error(Loc, "'%" + utostr(ID) + "' defined with type '" +
Val->getType()->getDescription() + "'");
return 0;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Introduce isOpaqueTy and use it rather than isa<OpaqueType>. Also, move some methods to try to have the type predicates be more logically positioned. llvm-svn: 96349
2010-02-16 22:50:09 +08:00
if (!Ty->isFirstClassType() && !Ty->isOpaqueTy() && !Ty->isLabelTy()) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
P.Error(Loc, "invalid use of a non-first-class type");
return 0;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Otherwise, create a new forward reference for this value and remember it.
Value *FwdVal;
strength reduce a ton of type equality tests to check the typeid (Through the new predicates I added) instead of going through a context and doing a pointer comparison. Besides being cheaper, this allows a smart compiler to turn the if sequence into a switch. llvm-svn: 83297
2009-10-05 13:54:46 +08:00
if (Ty->isLabelTy())
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
FwdVal = BasicBlock::Create(F.getContext(), "", &F);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
else
FwdVal = new Argument(Ty);
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ForwardRefValIDs[ID] = std::make_pair(FwdVal, Loc);
return FwdVal;
}
/// SetInstName - After an instruction is parsed and inserted into its
/// basic block, this installs its name.
bool LLParser::PerFunctionState::SetInstName(int NameID,
const std::string &NameStr,
LocTy NameLoc, Instruction *Inst) {
// If this instruction has void type, it cannot have a name or ID specified.
strength reduce a ton of type equality tests to check the typeid (Through the new predicates I added) instead of going through a context and doing a pointer comparison. Besides being cheaper, this allows a smart compiler to turn the if sequence into a switch. llvm-svn: 83297
2009-10-05 13:54:46 +08:00
if (Inst->getType()->isVoidTy()) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (NameID != -1 || !NameStr.empty())
return P.Error(NameLoc, "instructions returning void cannot have a name");
return false;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// If this was a numbered instruction, verify that the instruction is the
// expected value and resolve any forward references.
if (NameStr.empty()) {
// If neither a name nor an ID was specified, just use the next ID.
if (NameID == -1)
NameID = NumberedVals.size();
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (unsigned(NameID) != NumberedVals.size())
return P.Error(NameLoc, "instruction expected to be numbered '%" +
utostr(NumberedVals.size()) + "'");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
std::map<unsigned, std::pair<Value*, LocTy> >::iterator FI =
ForwardRefValIDs.find(NameID);
if (FI != ForwardRefValIDs.end()) {
if (FI->second.first->getType() != Inst->getType())
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
return P.Error(NameLoc, "instruction forward referenced with type '" +
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
FI->second.first->getType()->getDescription() + "'");
FI->second.first->replaceAllUsesWith(Inst);
plug another leak in LLParser::PerFunctionState::SetInstName() llvm-svn: 80792
2009-09-02 23:02:57 +08:00
delete FI->second.first;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ForwardRefValIDs.erase(FI);
}
NumberedVals.push_back(Inst);
return false;
}
// Otherwise, the instruction had a name. Resolve forward refs and set it.
std::map<std::string, std::pair<Value*, LocTy> >::iterator
FI = ForwardRefVals.find(NameStr);
if (FI != ForwardRefVals.end()) {
if (FI->second.first->getType() != Inst->getType())
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
return P.Error(NameLoc, "instruction forward referenced with type '" +
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
FI->second.first->getType()->getDescription() + "'");
FI->second.first->replaceAllUsesWith(Inst);
plug memory leak in LLParser::PerFunctionState::SetInstName() by deleting a value after replacing it llvm-svn: 80790
2009-09-02 22:22:03 +08:00
delete FI->second.first;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ForwardRefVals.erase(FI);
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Set the name on the instruction.
Inst->setName(NameStr);
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (Inst->getNameStr() != NameStr)
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
return P.Error(NameLoc, "multiple definition of local value named '" +
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
NameStr + "'");
return false;
}
/// GetBB - Get a basic block with the specified name or ID, creating a
/// forward reference record if needed.
BasicBlock *LLParser::PerFunctionState::GetBB(const std::string &Name,
LocTy Loc) {
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
return cast_or_null<BasicBlock>(GetVal(Name,
Type::getLabelTy(F.getContext()), Loc));
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
BasicBlock *LLParser::PerFunctionState::GetBB(unsigned ID, LocTy Loc) {
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
return cast_or_null<BasicBlock>(GetVal(ID,
Type::getLabelTy(F.getContext()), Loc));
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
/// DefineBB - Define the specified basic block, which is either named or
/// unnamed. If there is an error, this returns null otherwise it returns
/// the block being defined.
BasicBlock *LLParser::PerFunctionState::DefineBB(const std::string &Name,
LocTy Loc) {
BasicBlock *BB;
if (Name.empty())
BB = GetBB(NumberedVals.size(), Loc);
else
BB = GetBB(Name, Loc);
if (BB == 0) return 0; // Already diagnosed error.
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Move the block to the end of the function. Forward ref'd blocks are
// inserted wherever they happen to be referenced.
F.getBasicBlockList().splice(F.end(), F.getBasicBlockList(), BB);
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Remove the block from forward ref sets.
if (Name.empty()) {
ForwardRefValIDs.erase(NumberedVals.size());
NumberedVals.push_back(BB);
} else {
// BB forward references are already in the function symbol table.
ForwardRefVals.erase(Name);
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return BB;
}
//===----------------------------------------------------------------------===//
// Constants.
//===----------------------------------------------------------------------===//
/// ParseValID - Parse an abstract value that doesn't necessarily have a
/// type implied. For example, if we parse "4" we don't know what integer type
/// it has. The value will later be combined with its type and checked for
Compute isFunctionLocal in MDNode ctor or via argument in new function getWhenValsUnresolved(). Document PFS argument to ParseValID() and ConvertGlobalOrMetadataValIDToValue(). llvm-svn: 93108
2010-01-10 15:14:18 +08:00
/// sanity. PFS is used to convert function-local operands of metadata (since
/// metadata operands are not just parsed here but also converted to values).
/// PFS can be null when we are not parsing metadata values inside a function.
Re-add parsing of function-local metadata; this time with testcase. llvm-svn: 92793
2010-01-06 06:22:14 +08:00
bool LLParser::ParseValID(ValID &ID, PerFunctionState *PFS) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ID.Loc = Lex.getLoc();
switch (Lex.getKind()) {
default: return TokError("expected value token");
case lltok::GlobalID: // @42
ID.UIntVal = Lex.getUIntVal();
ID.Kind = ValID::t_GlobalID;
break;
case lltok::GlobalVar: // @foo
ID.StrVal = Lex.getStrVal();
ID.Kind = ValID::t_GlobalName;
break;
case lltok::LocalVarID: // %42
ID.UIntVal = Lex.getUIntVal();
ID.Kind = ValID::t_LocalID;
break;
case lltok::LocalVar: // %foo
case lltok::StringConstant: // "foo" - FIXME: REMOVE IN LLVM 3.0
ID.StrVal = Lex.getStrVal();
ID.Kind = ValID::t_LocalName;
break;
rename lltok::Metadata -> lltok::exclaim. We name tokens after their syntactic form, not their semantic form. llvm-svn: 92294
2009-12-30 12:56:59 +08:00
case lltok::exclaim: // !{...} MDNode, !"foo" MDString
Add support for embedded metadata to LLVM. This introduces two new types of Constant, MDString and MDNode which can only be used by globals with a name that starts with "llvm." or as arguments to a function with the same naming restriction. llvm-svn: 68420
2009-04-04 15:22:01 +08:00
Lex.Lex();
change ParseMDString and ParseMDNode to take arguments of the right type. This exposed a raft of other problems, which I'll deal with in subsequent patches. llvm-svn: 92273
2009-12-30 05:53:55 +08:00
factor code even more. llvm-svn: 92280
2009-12-30 06:40:21 +08:00
if (EatIfPresent(lltok::lbrace)) {
Make MDNode use CallbackVH. Also change MDNode to store Value* instead of Constant* in preperation of a future change to support holding non-Constants in an MDNode. llvm-svn: 71407
2009-05-11 04:57:05 +08:00
SmallVector<Value*, 16> Elts;
Compute isFunctionLocal in MDNode ctor or via argument in new function getWhenValsUnresolved(). Document PFS argument to ParseValID() and ConvertGlobalOrMetadataValIDToValue(). llvm-svn: 93108
2010-01-10 15:14:18 +08:00
if (ParseMDNodeVector(Elts, PFS) ||
Add support for embedded metadata to LLVM. This introduces two new types of Constant, MDString and MDNode which can only be used by globals with a name that starts with "llvm." or as arguments to a function with the same naming restriction. llvm-svn: 68420
2009-04-04 15:22:01 +08:00
ParseToken(lltok::rbrace, "expected end of metadata node"))
return true;
Make MDNode use CallbackVH. Also change MDNode to store Value* instead of Constant* in preperation of a future change to support holding non-Constants in an MDNode. llvm-svn: 71407
2009-05-11 04:57:05 +08:00
Compute isFunctionLocal in MDNode ctor or via argument in new function getWhenValsUnresolved(). Document PFS argument to ParseValID() and ConvertGlobalOrMetadataValIDToValue(). llvm-svn: 93108
2010-01-10 15:14:18 +08:00
ID.MDNodeVal = MDNode::get(Context, Elts.data(), Elts.size());
split t_Metadata into t_MDNode and t_MDString, eliminating some unsafe casting. llvm-svn: 92287
2009-12-30 10:11:14 +08:00
ID.Kind = ValID::t_MDNode;
Add support for embedded metadata to LLVM. This introduces two new types of Constant, MDString and MDNode which can only be used by globals with a name that starts with "llvm." or as arguments to a function with the same naming restriction. llvm-svn: 68420
2009-04-04 15:22:01 +08:00
return false;
}
Support stand alone metadata syntax. !0 = constant metadata !{i32 21, i32 22} @llvm.blah = constant metadata !{i32 1000, i16 200, metadata !0} llvm-svn: 74630
2009-07-02 03:21:12 +08:00
// Standalone metadata reference
// !{ ..., !42, ... }
fix parsing of mdstring values. llvm-svn: 92290
2009-12-30 12:13:37 +08:00
if (Lex.getKind() == lltok::APSInt) {
rename ParseMDNode -> ParseMDNodeID, since it parses !42, not !{... } as you'd expect. llvm-svn: 92291
2009-12-30 12:15:23 +08:00
if (ParseMDNodeID(ID.MDNodeVal)) return true;
split t_Metadata into t_MDNode and t_MDString, eliminating some unsafe casting. llvm-svn: 92287
2009-12-30 10:11:14 +08:00
ID.Kind = ValID::t_MDNode;
Support stand alone metadata syntax. !0 = constant metadata !{i32 21, i32 22} @llvm.blah = constant metadata !{i32 1000, i16 200, metadata !0} llvm-svn: 74630
2009-07-02 03:21:12 +08:00
return false;
split t_Metadata into t_MDNode and t_MDString, eliminating some unsafe casting. llvm-svn: 92287
2009-12-30 10:11:14 +08:00
}
Add support for embedded metadata to LLVM. This introduces two new types of Constant, MDString and MDNode which can only be used by globals with a name that starts with "llvm." or as arguments to a function with the same naming restriction. llvm-svn: 68420
2009-04-04 15:22:01 +08:00
// MDString:
// ::= '!' STRINGCONSTANT
split t_Metadata into t_MDNode and t_MDString, eliminating some unsafe casting. llvm-svn: 92287
2009-12-30 10:11:14 +08:00
if (ParseMDString(ID.MDStringVal)) return true;
ID.Kind = ValID::t_MDString;
Add support for embedded metadata to LLVM. This introduces two new types of Constant, MDString and MDNode which can only be used by globals with a name that starts with "llvm." or as arguments to a function with the same naming restriction. llvm-svn: 68420
2009-04-04 15:22:01 +08:00
return false;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case lltok::APSInt:
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
ID.APSIntVal = Lex.getAPSIntVal();
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ID.Kind = ValID::t_APSInt;
break;
case lltok::APFloat:
ID.APFloatVal = Lex.getAPFloatVal();
ID.Kind = ValID::t_APFloat;
break;
case lltok::kw_true:
Move getTrue() and getFalse() to 2.5-like APIs. llvm-svn: 77685
2009-08-01 01:39:07 +08:00
ID.ConstantVal = ConstantInt::getTrue(Context);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ID.Kind = ValID::t_Constant;
break;
case lltok::kw_false:
Move getTrue() and getFalse() to 2.5-like APIs. llvm-svn: 77685
2009-08-01 01:39:07 +08:00
ID.ConstantVal = ConstantInt::getFalse(Context);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ID.Kind = ValID::t_Constant;
break;
case lltok::kw_null: ID.Kind = ValID::t_Null; break;
case lltok::kw_undef: ID.Kind = ValID::t_Undef; break;
case lltok::kw_zeroinitializer: ID.Kind = ValID::t_Zero; break;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case lltok::lbrace: {
// ValID ::= '{' ConstVector '}'
Lex.Lex();
SmallVector<Constant*, 16> Elts;
if (ParseGlobalValueVector(Elts) ||
ParseToken(lltok::rbrace, "expected end of struct constant"))
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Privatize the StructType table, which unfortunately involves routing contexts through a number of APIs. llvm-svn: 78258
2009-08-06 07:16:16 +08:00
ID.ConstantVal = ConstantStruct::get(Context, Elts.data(),
Elts.size(), false);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ID.Kind = ValID::t_Constant;
return false;
}
case lltok::less: {
// ValID ::= '<' ConstVector '>' --> Vector.
// ValID ::= '<' '{' ConstVector '}' '>' --> Packed Struct.
Lex.Lex();
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
bool isPackedStruct = EatIfPresent(lltok::lbrace);
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
SmallVector<Constant*, 16> Elts;
LocTy FirstEltLoc = Lex.getLoc();
if (ParseGlobalValueVector(Elts) ||
(isPackedStruct &&
ParseToken(lltok::rbrace, "expected end of packed struct")) ||
ParseToken(lltok::greater, "expected end of constant"))
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (isPackedStruct) {
Try again at converting the LLParser to use LLVMContext, without massive breakage this time. llvm-svn: 74671
2009-07-02 07:57:11 +08:00
ID.ConstantVal =
Privatize the StructType table, which unfortunately involves routing contexts through a number of APIs. llvm-svn: 78258
2009-08-06 07:16:16 +08:00
ConstantStruct::get(Context, Elts.data(), Elts.size(), true);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ID.Kind = ValID::t_Constant;
return false;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (Elts.empty())
return Error(ID.Loc, "constant vector must not be empty");
Uniformize the names of type predicates: rather than having isFloatTy and isInteger, we now have isFloatTy and isIntegerTy. Requested by Chris! llvm-svn: 96223
2010-02-16 00:12:20 +08:00
if (!Elts[0]->getType()->isIntegerTy() &&
!Elts[0]->getType()->isFloatingPointTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(FirstEltLoc,
"vector elements must have integer or floating point type");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Verify that all the vector elements have the same type.
for (unsigned i = 1, e = Elts.size(); i != e; ++i)
if (Elts[i]->getType() != Elts[0]->getType())
return Error(FirstEltLoc,
"vector element #" + utostr(i) +
" is not of type '" + Elts[0]->getType()->getDescription());
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Return ConstantVector to 2.5 API. llvm-svn: 77366
2009-07-29 05:19:26 +08:00
ID.ConstantVal = ConstantVector::get(Elts.data(), Elts.size());
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ID.Kind = ValID::t_Constant;
return false;
}
case lltok::lsquare: { // Array Constant
Lex.Lex();
SmallVector<Constant*, 16> Elts;
LocTy FirstEltLoc = Lex.getLoc();
if (ParseGlobalValueVector(Elts) ||
ParseToken(lltok::rsquare, "expected end of array constant"))
return true;
// Handle empty element.
if (Elts.empty()) {
// Use undef instead of an array because it's inconvenient to determine
// the element type at this point, there being no elements to examine.
fix PR3281:accepted0[02].ll: represent empty arrays distinctly, and diagnose attempts to initialize non-empty arrays with them. This produces: llvm-as: accepted02.ll:1:28: invalid empty array initializer @"o" = global [5 x double] [] ^ llvm-as: accepted00.ll:1:32: invalid empty array initializer @"za" = thread_local global {} [] ^ [ llvm-svn: 61676
2009-01-05 15:52:51 +08:00
ID.Kind = ValID::t_EmptyArray;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (!Elts[0]->getType()->isFirstClassType())
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
return Error(FirstEltLoc, "invalid array element type: " +
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Elts[0]->getType()->getDescription());
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Move types back to the 2.5 API. llvm-svn: 77516
2009-07-30 06:17:13 +08:00
ArrayType *ATy = ArrayType::get(Elts[0]->getType(), Elts.size());
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Verify all elements are correct type!
Fix a really horrible typo, which caused undefined behavior. llvm-svn: 61566
2009-01-02 16:49:06 +08:00
for (unsigned i = 0, e = Elts.size(); i != e; ++i) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (Elts[i]->getType() != Elts[0]->getType())
return Error(FirstEltLoc,
"array element #" + utostr(i) +
" is not of type '" +Elts[0]->getType()->getDescription());
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Change ConstantArray to 2.5 API. llvm-svn: 77347
2009-07-29 02:32:17 +08:00
ID.ConstantVal = ConstantArray::get(ATy, Elts.data(), Elts.size());
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ID.Kind = ValID::t_Constant;
return false;
}
case lltok::kw_c: // c "foo"
Lex.Lex();
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
ID.ConstantVal = ConstantArray::get(Context, Lex.getStrVal(), false);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ParseToken(lltok::StringConstant, "expected string")) return true;
ID.Kind = ValID::t_Constant;
return false;
case lltok::kw_asm: {
Rename msasm to alignstack per review. llvm-svn: 84795
2009-10-22 07:28:00 +08:00
// ValID ::= 'asm' SideEffect? AlignStack? STRINGCONSTANT ',' STRINGCONSTANT
bool HasSideEffect, AlignStack;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Lex.Lex();
if (ParseOptionalToken(lltok::kw_sideeffect, HasSideEffect) ||
Rename msasm to alignstack per review. llvm-svn: 84795
2009-10-22 07:28:00 +08:00
ParseOptionalToken(lltok::kw_alignstack, AlignStack) ||
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
ParseStringConstant(ID.StrVal) ||
ParseToken(lltok::comma, "expected comma in inline asm expression") ||
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ParseToken(lltok::StringConstant, "expected constraint string"))
return true;
ID.StrVal2 = Lex.getStrVal();
Fix MSVC warning ( | with bool and unsigned int). llvm-svn: 86417
2009-11-08 07:51:55 +08:00
ID.UIntVal = unsigned(HasSideEffect) | (unsigned(AlignStack)<<1);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ID.Kind = ValID::t_InlineAsm;
return false;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
full asmparser support for blockaddress. We can now do: $ llvm-as foo.ll -d -disable-output which reads and prints the .ll file. BC encoding is the next project. Testcase will go in once that works. llvm-svn: 85368
2009-10-28 11:39:23 +08:00
case lltok::kw_blockaddress: {
// ValID ::= 'blockaddress' '(' @foo ',' %bar ')'
Lex.Lex();
ValID Fn, Label;
LocTy FnLoc, LabelLoc;
if (ParseToken(lltok::lparen, "expected '(' in block address expression") ||
ParseValID(Fn) ||
ParseToken(lltok::comma, "expected comma in block address expression")||
ParseValID(Label) ||
ParseToken(lltok::rparen, "expected ')' in block address expression"))
return true;
Revert 85678/85680. The decision is to stay with the current form of indirectbr, thus we don't need "blockaddr(@func, null)". Eliminate it for simplicity. llvm-svn: 85699
2009-11-01 09:27:45 +08:00
full asmparser support for blockaddress. We can now do: $ llvm-as foo.ll -d -disable-output which reads and prints the .ll file. BC encoding is the next project. Testcase will go in once that works. llvm-svn: 85368
2009-10-28 11:39:23 +08:00
if (Fn.Kind != ValID::t_GlobalID && Fn.Kind != ValID::t_GlobalName)
return Error(Fn.Loc, "expected function name in blockaddress");
Revert 85678/85680. The decision is to stay with the current form of indirectbr, thus we don't need "blockaddr(@func, null)". Eliminate it for simplicity. llvm-svn: 85699
2009-11-01 09:27:45 +08:00
if (Label.Kind != ValID::t_LocalID && Label.Kind != ValID::t_LocalName)
full asmparser support for blockaddress. We can now do: $ llvm-as foo.ll -d -disable-output which reads and prints the .ll file. BC encoding is the next project. Testcase will go in once that works. llvm-svn: 85368
2009-10-28 11:39:23 +08:00
return Error(Label.Loc, "expected basic block name in blockaddress");
// Make a global variable as a placeholder for this reference.
GlobalVariable *FwdRef = new GlobalVariable(*M, Type::getInt8Ty(Context),
false, GlobalValue::InternalLinkage,
0, "");
ForwardRefBlockAddresses[Fn].push_back(std::make_pair(Label, FwdRef));
ID.ConstantVal = FwdRef;
ID.Kind = ValID::t_Constant;
return false;
}
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case lltok::kw_trunc:
case lltok::kw_zext:
case lltok::kw_sext:
case lltok::kw_fptrunc:
case lltok::kw_fpext:
case lltok::kw_bitcast:
case lltok::kw_uitofp:
case lltok::kw_sitofp:
case lltok::kw_fptoui:
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
case lltok::kw_fptosi:
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case lltok::kw_inttoptr:
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
case lltok::kw_ptrtoint: {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
unsigned Opc = Lex.getUIntVal();
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
PATypeHolder DestTy(Type::getVoidTy(Context));
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Constant *SrcVal;
Lex.Lex();
if (ParseToken(lltok::lparen, "expected '(' after constantexpr cast") ||
ParseGlobalTypeAndValue(SrcVal) ||
Fix a typo in a diagnostic. llvm-svn: 73429
2009-06-16 05:52:11 +08:00
ParseToken(lltok::kw_to, "expected 'to' in constantexpr cast") ||
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ParseType(DestTy) ||
ParseToken(lltok::rparen, "expected ')' at end of constantexpr cast"))
return true;
if (!CastInst::castIsValid((Instruction::CastOps)Opc, SrcVal, DestTy))
return Error(ID.Loc, "invalid cast opcode for cast from '" +
SrcVal->getType()->getDescription() + "' to '" +
DestTy->getDescription() + "'");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
ID.ConstantVal = ConstantExpr::getCast((Instruction::CastOps)Opc,
Try again at converting the LLParser to use LLVMContext, without massive breakage this time. llvm-svn: 74671
2009-07-02 07:57:11 +08:00
SrcVal, DestTy);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ID.Kind = ValID::t_Constant;
return false;
}
case lltok::kw_extractvalue: {
Lex.Lex();
Constant *Val;
SmallVector<unsigned, 4> Indices;
if (ParseToken(lltok::lparen, "expected '(' in extractvalue constantexpr")||
ParseGlobalTypeAndValue(Val) ||
ParseIndexList(Indices) ||
ParseToken(lltok::rparen, "expected ')' in extractvalue constantexpr"))
return true;
Parse debug info attached with insertvalue and extractvalue instructions. llvm-svn: 85921
2009-11-04 03:06:07 +08:00
Add support for a union type in LLVM IR. Patch by Talin! llvm-svn: 96011
2010-02-13 04:49:41 +08:00
if (!Val->getType()->isAggregateType())
return Error(ID.Loc, "extractvalue operand must be aggregate type");
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (!ExtractValueInst::getIndexedType(Val->getType(), Indices.begin(),
Indices.end()))
return Error(ID.Loc, "invalid indices for extractvalue");
Use v.data() instead of &v[0] when SmallVector v might be empty. llvm-svn: 72210
2009-05-21 17:52:38 +08:00
ID.ConstantVal =
Move ConstantExpr to 2.5 API. llvm-svn: 77494
2009-07-30 02:55:55 +08:00
ConstantExpr::getExtractValue(Val, Indices.data(), Indices.size());
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ID.Kind = ValID::t_Constant;
return false;
}
case lltok::kw_insertvalue: {
Lex.Lex();
Constant *Val0, *Val1;
SmallVector<unsigned, 4> Indices;
if (ParseToken(lltok::lparen, "expected '(' in insertvalue constantexpr")||
ParseGlobalTypeAndValue(Val0) ||
ParseToken(lltok::comma, "expected comma in insertvalue constantexpr")||
ParseGlobalTypeAndValue(Val1) ||
ParseIndexList(Indices) ||
ParseToken(lltok::rparen, "expected ')' in insertvalue constantexpr"))
return true;
Add support for a union type in LLVM IR. Patch by Talin! llvm-svn: 96011
2010-02-13 04:49:41 +08:00
if (!Val0->getType()->isAggregateType())
return Error(ID.Loc, "insertvalue operand must be aggregate type");
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (!ExtractValueInst::getIndexedType(Val0->getType(), Indices.begin(),
Indices.end()))
return Error(ID.Loc, "invalid indices for insertvalue");
Move ConstantExpr to 2.5 API. llvm-svn: 77494
2009-07-30 02:55:55 +08:00
ID.ConstantVal = ConstantExpr::getInsertValue(Val0, Val1,
Try again at converting the LLParser to use LLVMContext, without massive breakage this time. llvm-svn: 74671
2009-07-02 07:57:11 +08:00
Indices.data(), Indices.size());
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ID.Kind = ValID::t_Constant;
return false;
}
case lltok::kw_icmp:
Remove the vicmp and vfcmp instructions. Because we never had a release with these instructions, no autoupgrade or backwards compatibility support is provided. llvm-svn: 74991
2009-07-08 11:04:38 +08:00
case lltok::kw_fcmp: {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
unsigned PredVal, Opc = Lex.getUIntVal();
Constant *Val0, *Val1;
Lex.Lex();
if (ParseCmpPredicate(PredVal, Opc) ||
ParseToken(lltok::lparen, "expected '(' in compare constantexpr") ||
ParseGlobalTypeAndValue(Val0) ||
ParseToken(lltok::comma, "expected comma in compare constantexpr") ||
ParseGlobalTypeAndValue(Val1) ||
ParseToken(lltok::rparen, "expected ')' in compare constantexpr"))
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (Val0->getType() != Val1->getType())
return Error(ID.Loc, "compare operands must have the same type");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
CmpInst::Predicate Pred = (CmpInst::Predicate)PredVal;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (Opc == Instruction::FCmp) {
Uniformize the names of type predicates: rather than having isFloatTy and isInteger, we now have isFloatTy and isIntegerTy. Requested by Chris! llvm-svn: 96223
2010-02-16 00:12:20 +08:00
if (!Val0->getType()->isFPOrFPVectorTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(ID.Loc, "fcmp requires floating point operands");
Move ConstantExpr to 2.5 API. llvm-svn: 77494
2009-07-30 02:55:55 +08:00
ID.ConstantVal = ConstantExpr::getFCmp(Pred, Val0, Val1);
Remove the vicmp and vfcmp instructions. Because we never had a release with these instructions, no autoupgrade or backwards compatibility support is provided. llvm-svn: 74991
2009-07-08 11:04:38 +08:00
} else {
assert(Opc == Instruction::ICmp && "Unexpected opcode for CmpInst!");
Uniformize the names of type predicates: rather than having isFloatTy and isInteger, we now have isFloatTy and isIntegerTy. Requested by Chris! llvm-svn: 96223
2010-02-16 00:12:20 +08:00
if (!Val0->getType()->isIntOrIntVectorTy() &&
There are two ways of checking for a given type, for example isa<PointerType>(T) and T->isPointerTy(). Convert most instances of the first form to the second form. Requested by Chris. llvm-svn: 96344
2010-02-16 19:11:14 +08:00
!Val0->getType()->isPointerTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(ID.Loc, "icmp requires pointer or integer operands");
Move ConstantExpr to 2.5 API. llvm-svn: 77494
2009-07-30 02:55:55 +08:00
ID.ConstantVal = ConstantExpr::getICmp(Pred, Val0, Val1);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
ID.Kind = ValID::t_Constant;
return false;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Binary Operators.
case lltok::kw_add:
Split the Add, Sub, and Mul instruction opcodes into separate integer and floating-point opcodes, introducing FAdd, FSub, and FMul. For now, the AsmParser, BitcodeReader, and IRBuilder all preserve backwards compatability, and the Core LLVM APIs preserve backwards compatibility for IR producers. Most front-ends won't need to change immediately. This implements the first step of the plan outlined here: http://nondot.org/sabre/LLVMNotes/IntegerOverflow.txt llvm-svn: 72897
2009-06-05 06:49:04 +08:00
case lltok::kw_fadd:
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case lltok::kw_sub:
Split the Add, Sub, and Mul instruction opcodes into separate integer and floating-point opcodes, introducing FAdd, FSub, and FMul. For now, the AsmParser, BitcodeReader, and IRBuilder all preserve backwards compatability, and the Core LLVM APIs preserve backwards compatibility for IR producers. Most front-ends won't need to change immediately. This implements the first step of the plan outlined here: http://nondot.org/sabre/LLVMNotes/IntegerOverflow.txt llvm-svn: 72897
2009-06-05 06:49:04 +08:00
case lltok::kw_fsub:
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case lltok::kw_mul:
Split the Add, Sub, and Mul instruction opcodes into separate integer and floating-point opcodes, introducing FAdd, FSub, and FMul. For now, the AsmParser, BitcodeReader, and IRBuilder all preserve backwards compatability, and the Core LLVM APIs preserve backwards compatibility for IR producers. Most front-ends won't need to change immediately. This implements the first step of the plan outlined here: http://nondot.org/sabre/LLVMNotes/IntegerOverflow.txt llvm-svn: 72897
2009-06-05 06:49:04 +08:00
case lltok::kw_fmul:
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case lltok::kw_udiv:
case lltok::kw_sdiv:
case lltok::kw_fdiv:
case lltok::kw_urem:
case lltok::kw_srem:
case lltok::kw_frem: {
Change the assembly syntax for nsw, nuw, and exact, putting them after their associated opcodes rather than before. This makes them a little easier to read. llvm-svn: 77194
2009-07-28 00:11:46 +08:00
bool NUW = false;
bool NSW = false;
bool Exact = false;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
unsigned Opc = Lex.getUIntVal();
Constant *Val0, *Val1;
Lex.Lex();
Change the assembly syntax for nsw, nuw, and exact, putting them after their associated opcodes rather than before. This makes them a little easier to read. llvm-svn: 77194
2009-07-28 00:11:46 +08:00
LocTy ModifierLoc = Lex.getLoc();
if (Opc == Instruction::Add ||
Opc == Instruction::Sub ||
Opc == Instruction::Mul) {
if (EatIfPresent(lltok::kw_nuw))
NUW = true;
if (EatIfPresent(lltok::kw_nsw)) {
NSW = true;
if (EatIfPresent(lltok::kw_nuw))
NUW = true;
}
} else if (Opc == Instruction::SDiv) {
if (EatIfPresent(lltok::kw_exact))
Exact = true;
}
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ParseToken(lltok::lparen, "expected '(' in binary constantexpr") ||
ParseGlobalTypeAndValue(Val0) ||
ParseToken(lltok::comma, "expected comma in binary constantexpr") ||
ParseGlobalTypeAndValue(Val1) ||
ParseToken(lltok::rparen, "expected ')' in binary constantexpr"))
return true;
if (Val0->getType() != Val1->getType())
return Error(ID.Loc, "operands of constexpr must have same type");
Uniformize the names of type predicates: rather than having isFloatTy and isInteger, we now have isFloatTy and isIntegerTy. Requested by Chris! llvm-svn: 96223
2010-02-16 00:12:20 +08:00
if (!Val0->getType()->isIntOrIntVectorTy()) {
Change the assembly syntax for nsw, nuw, and exact, putting them after their associated opcodes rather than before. This makes them a little easier to read. llvm-svn: 77194
2009-07-28 00:11:46 +08:00
if (NUW)
return Error(ModifierLoc, "nuw only applies to integer operations");
if (NSW)
return Error(ModifierLoc, "nsw only applies to integer operations");
}
// API compatibility: Accept either integer or floating-point types with
// add, sub, and mul.
Uniformize the names of type predicates: rather than having isFloatTy and isInteger, we now have isFloatTy and isIntegerTy. Requested by Chris! llvm-svn: 96223
2010-02-16 00:12:20 +08:00
if (!Val0->getType()->isIntOrIntVectorTy() &&
!Val0->getType()->isFPOrFPVectorTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(ID.Loc,"constexpr requires integer, fp, or vector operands");
Reappy r80998, now that the GlobalOpt bug that it exposed on MiniSAT is fixed. llvm-svn: 81172
2009-09-08 07:54:19 +08:00
unsigned Flags = 0;
if (NUW) Flags |= OverflowingBinaryOperator::NoUnsignedWrap;
if (NSW) Flags |= OverflowingBinaryOperator::NoSignedWrap;
if (Exact) Flags |= SDivOperator::IsExact;
Constant *C = ConstantExpr::get(Opc, Val0, Val1, Flags);
Change the assembly syntax for nsw, nuw, and exact, putting them after their associated opcodes rather than before. This makes them a little easier to read. llvm-svn: 77194
2009-07-28 00:11:46 +08:00
ID.ConstantVal = C;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ID.Kind = ValID::t_Constant;
return false;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Logical Operations
case lltok::kw_shl:
case lltok::kw_lshr:
case lltok::kw_ashr:
case lltok::kw_and:
case lltok::kw_or:
case lltok::kw_xor: {
unsigned Opc = Lex.getUIntVal();
Constant *Val0, *Val1;
Lex.Lex();
if (ParseToken(lltok::lparen, "expected '(' in logical constantexpr") ||
ParseGlobalTypeAndValue(Val0) ||
ParseToken(lltok::comma, "expected comma in logical constantexpr") ||
ParseGlobalTypeAndValue(Val1) ||
ParseToken(lltok::rparen, "expected ')' in logical constantexpr"))
return true;
if (Val0->getType() != Val1->getType())
return Error(ID.Loc, "operands of constexpr must have same type");
Uniformize the names of type predicates: rather than having isFloatTy and isInteger, we now have isFloatTy and isIntegerTy. Requested by Chris! llvm-svn: 96223
2010-02-16 00:12:20 +08:00
if (!Val0->getType()->isIntOrIntVectorTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(ID.Loc,
"constexpr requires integer or integer vector operands");
Move ConstantExpr to 2.5 API. llvm-svn: 77494
2009-07-30 02:55:55 +08:00
ID.ConstantVal = ConstantExpr::get(Opc, Val0, Val1);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ID.Kind = ValID::t_Constant;
return false;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
}
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case lltok::kw_getelementptr:
case lltok::kw_shufflevector:
case lltok::kw_insertelement:
case lltok::kw_extractelement:
case lltok::kw_select: {
unsigned Opc = Lex.getUIntVal();
SmallVector<Constant*, 16> Elts;
Add a new keyword 'inbounds' for use with getelementptr. See the LangRef.html changes for details. llvm-svn: 77259
2009-07-28 05:53:46 +08:00
bool InBounds = false;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Lex.Lex();
Add a new keyword 'inbounds' for use with getelementptr. See the LangRef.html changes for details. llvm-svn: 77259
2009-07-28 05:53:46 +08:00
if (Opc == Instruction::GetElementPtr)
Minor code simplification. llvm-svn: 77459
2009-07-29 23:58:36 +08:00
InBounds = EatIfPresent(lltok::kw_inbounds);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ParseToken(lltok::lparen, "expected '(' in constantexpr") ||
ParseGlobalValueVector(Elts) ||
ParseToken(lltok::rparen, "expected ')' in constantexpr"))
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (Opc == Instruction::GetElementPtr) {
There are two ways of checking for a given type, for example isa<PointerType>(T) and T->isPointerTy(). Convert most instances of the first form to the second form. Requested by Chris. llvm-svn: 96344
2010-02-16 19:11:14 +08:00
if (Elts.size() == 0 || !Elts[0]->getType()->isPointerTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(ID.Loc, "getelementptr requires pointer operand");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (!GetElementPtrInst::getIndexedType(Elts[0]->getType(),
Fix assert assembling zero-argument constant GEP. There's still a strict-aliasing violation here, but I don't feel like dealing with that right now... llvm-svn: 77005
2009-07-25 05:56:17 +08:00
(Value**)(Elts.data() + 1),
Elts.size() - 1))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(ID.Loc, "invalid indices for getelementptr");
Reappy r80998, now that the GlobalOpt bug that it exposed on MiniSAT is fixed. llvm-svn: 81172
2009-09-08 07:54:19 +08:00
ID.ConstantVal = InBounds ?
ConstantExpr::getInBoundsGetElementPtr(Elts[0],
Elts.data() + 1,
Elts.size() - 1) :
ConstantExpr::getGetElementPtr(Elts[0],
Elts.data() + 1, Elts.size() - 1);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
} else if (Opc == Instruction::Select) {
if (Elts.size() != 3)
return Error(ID.Loc, "expected three operands to select");
if (const char *Reason = SelectInst::areInvalidOperands(Elts[0], Elts[1],
Elts[2]))
return Error(ID.Loc, Reason);
Move ConstantExpr to 2.5 API. llvm-svn: 77494
2009-07-30 02:55:55 +08:00
ID.ConstantVal = ConstantExpr::getSelect(Elts[0], Elts[1], Elts[2]);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
} else if (Opc == Instruction::ShuffleVector) {
if (Elts.size() != 3)
return Error(ID.Loc, "expected three operands to shufflevector");
if (!ShuffleVectorInst::isValidOperands(Elts[0], Elts[1], Elts[2]))
return Error(ID.Loc, "invalid operands to shufflevector");
Try again at converting the LLParser to use LLVMContext, without massive breakage this time. llvm-svn: 74671
2009-07-02 07:57:11 +08:00
ID.ConstantVal =
Move ConstantExpr to 2.5 API. llvm-svn: 77494
2009-07-30 02:55:55 +08:00
ConstantExpr::getShuffleVector(Elts[0], Elts[1],Elts[2]);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
} else if (Opc == Instruction::ExtractElement) {
if (Elts.size() != 2)
return Error(ID.Loc, "expected two operands to extractelement");
if (!ExtractElementInst::isValidOperands(Elts[0], Elts[1]))
return Error(ID.Loc, "invalid extractelement operands");
Move ConstantExpr to 2.5 API. llvm-svn: 77494
2009-07-30 02:55:55 +08:00
ID.ConstantVal = ConstantExpr::getExtractElement(Elts[0], Elts[1]);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
} else {
assert(Opc == Instruction::InsertElement && "Unknown opcode");
if (Elts.size() != 3)
return Error(ID.Loc, "expected three operands to insertelement");
if (!InsertElementInst::isValidOperands(Elts[0], Elts[1], Elts[2]))
return Error(ID.Loc, "invalid insertelement operands");
Try again at converting the LLParser to use LLVMContext, without massive breakage this time. llvm-svn: 74671
2009-07-02 07:57:11 +08:00
ID.ConstantVal =
Move ConstantExpr to 2.5 API. llvm-svn: 77494
2009-07-30 02:55:55 +08:00
ConstantExpr::getInsertElement(Elts[0], Elts[1],Elts[2]);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ID.Kind = ValID::t_Constant;
return false;
}
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Lex.Lex();
return false;
}
/// ParseGlobalValue - Parse a global value with the specified type.
Consolidate ConvertGlobalValIDToValue, ConvertGlobalOrMetadataValIDToValue, and ConvertValIDToValue into a more powerful ConvertValIDToValue() that does all three's work llvm-svn: 93197
2010-01-12 06:31:58 +08:00
bool LLParser::ParseGlobalValue(const Type *Ty, Constant *&C) {
C = 0;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ValID ID;
Consolidate ConvertGlobalValIDToValue, ConvertGlobalOrMetadataValIDToValue, and ConvertValIDToValue into a more powerful ConvertValIDToValue() that does all three's work llvm-svn: 93197
2010-01-12 06:31:58 +08:00
Value *V = NULL;
bool Parsed = ParseValID(ID) ||
ConvertValIDToValue(Ty, ID, V, NULL);
if (V && !(C = dyn_cast<Constant>(V)))
return Error(ID.Loc, "global values must be constants");
return Parsed;
}
bool LLParser::ParseGlobalTypeAndValue(Constant *&V) {
PATypeHolder Type(Type::getVoidTy(Context));
return ParseType(Type) ||
ParseGlobalValue(Type, V);
}
/// ParseGlobalValueVector
/// ::= /*empty*/
/// ::= TypeAndValue (',' TypeAndValue)*
bool LLParser::ParseGlobalValueVector(SmallVectorImpl<Constant*> &Elts) {
// Empty list.
if (Lex.getKind() == lltok::rbrace ||
Lex.getKind() == lltok::rsquare ||
Lex.getKind() == lltok::greater ||
Lex.getKind() == lltok::rparen)
return false;
Constant *C;
if (ParseGlobalTypeAndValue(C)) return true;
Elts.push_back(C);
while (EatIfPresent(lltok::comma)) {
if (ParseGlobalTypeAndValue(C)) return true;
Elts.push_back(C);
}
return false;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
Consolidate ConvertGlobalValIDToValue, ConvertGlobalOrMetadataValIDToValue, and ConvertValIDToValue into a more powerful ConvertValIDToValue() that does all three's work llvm-svn: 93197
2010-01-12 06:31:58 +08:00
//===----------------------------------------------------------------------===//
// Function Parsing.
//===----------------------------------------------------------------------===//
bool LLParser::ConvertValIDToValue(const Type *Ty, ValID &ID, Value *&V,
PerFunctionState *PFS) {
There are two ways of checking for a given type, for example isa<PointerType>(T) and T->isPointerTy(). Convert most instances of the first form to the second form. Requested by Chris. llvm-svn: 96344
2010-02-16 19:11:14 +08:00
if (Ty->isFunctionTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(ID.Loc, "functions are not values, refer to them as pointers");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
switch (ID.Kind) {
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
default: llvm_unreachable("Unknown ValID!");
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case ValID::t_LocalID:
Consolidate ConvertGlobalValIDToValue, ConvertGlobalOrMetadataValIDToValue, and ConvertValIDToValue into a more powerful ConvertValIDToValue() that does all three's work llvm-svn: 93197
2010-01-12 06:31:58 +08:00
if (!PFS) return Error(ID.Loc, "invalid use of function-local name");
V = PFS->GetVal(ID.UIntVal, Ty, ID.Loc);
return (V == 0);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case ValID::t_LocalName:
Consolidate ConvertGlobalValIDToValue, ConvertGlobalOrMetadataValIDToValue, and ConvertValIDToValue into a more powerful ConvertValIDToValue() that does all three's work llvm-svn: 93197
2010-01-12 06:31:58 +08:00
if (!PFS) return Error(ID.Loc, "invalid use of function-local name");
V = PFS->GetVal(ID.StrVal, Ty, ID.Loc);
return (V == 0);
case ValID::t_InlineAsm: {
const PointerType *PTy = dyn_cast<PointerType>(Ty);
const FunctionType *FTy =
PTy ? dyn_cast<FunctionType>(PTy->getElementType()) : 0;
if (!FTy || !InlineAsm::Verify(FTy, ID.StrVal2))
return Error(ID.Loc, "invalid type for inline asm constraint string");
V = InlineAsm::get(FTy, ID.StrVal, ID.StrVal2, ID.UIntVal&1, ID.UIntVal>>1);
return false;
}
case ValID::t_MDNode:
if (!Ty->isMetadataTy())
return Error(ID.Loc, "metadata value must have metadata type");
V = ID.MDNodeVal;
return false;
case ValID::t_MDString:
if (!Ty->isMetadataTy())
return Error(ID.Loc, "metadata value must have metadata type");
V = ID.MDStringVal;
return false;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case ValID::t_GlobalName:
V = GetGlobalVal(ID.StrVal, Ty, ID.Loc);
return V == 0;
case ValID::t_GlobalID:
V = GetGlobalVal(ID.UIntVal, Ty, ID.Loc);
return V == 0;
case ValID::t_APSInt:
There are two ways of checking for a given type, for example isa<PointerType>(T) and T->isPointerTy(). Convert most instances of the first form to the second form. Requested by Chris. llvm-svn: 96344
2010-02-16 19:11:14 +08:00
if (!Ty->isIntegerTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(ID.Loc, "integer constant must have integer type");
ID.APSIntVal.extOrTrunc(Ty->getPrimitiveSizeInBits());
Revert the ConstantInt constructors back to their 2.5 forms where possible, thanks to contexts-on-types. More to come. llvm-svn: 77011
2009-07-25 07:12:02 +08:00
V = ConstantInt::get(Context, ID.APSIntVal);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
case ValID::t_APFloat:
Uniformize the names of type predicates: rather than having isFloatTy and isInteger, we now have isFloatTy and isIntegerTy. Requested by Chris! llvm-svn: 96223
2010-02-16 00:12:20 +08:00
if (!Ty->isFloatingPointTy() ||
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
!ConstantFP::isValueValidForType(Ty, ID.APFloatVal))
return Error(ID.Loc, "floating point constant invalid for type");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// The lexer has no type info, so builds all float and double FP constants
// as double. Fix this here. Long double does not need this.
if (&ID.APFloatVal.getSemantics() == &APFloat::IEEEdouble &&
strength reduce a ton of type equality tests to check the typeid (Through the new predicates I added) instead of going through a context and doing a pointer comparison. Besides being cheaper, this allows a smart compiler to turn the if sequence into a switch. llvm-svn: 83297
2009-10-05 13:54:46 +08:00
Ty->isFloatTy()) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
bool Ignored;
ID.APFloatVal.convert(APFloat::IEEEsingle, APFloat::rmNearestTiesToEven,
&Ignored);
}
Move ConstantFP construction back to the 2.5-ish API. llvm-svn: 77247
2009-07-28 04:59:43 +08:00
V = ConstantFP::get(Context, ID.APFloatVal);
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
reject PR3281:crash10.ll with: llvm-as: crash10.ll:3:35: floating point constant does not have type 'ppc_fp128' "dumy" = fcmp ult ppc_fp128 "j",9209.4 ^ llvm-svn: 61721
2009-01-06 02:24:23 +08:00
if (V->getType() != Ty)
return Error(ID.Loc, "floating point constant does not have type '" +
Ty->getDescription() + "'");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
case ValID::t_Null:
There are two ways of checking for a given type, for example isa<PointerType>(T) and T->isPointerTy(). Convert most instances of the first form to the second form. Requested by Chris. llvm-svn: 96344
2010-02-16 19:11:14 +08:00
if (!Ty->isPointerTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(ID.Loc, "null must be a pointer type");
Move more code back to 2.5 APIs. llvm-svn: 77635
2009-07-31 07:03:37 +08:00
V = ConstantPointerNull::get(cast<PointerType>(Ty));
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
case ValID::t_Undef:
reject undef/zero labels. This fixes PR3281:crash0[56].ll with these diagnostics: llvm-as: crash05.ll:1:14: invalid type for null constant global label zeroinitializer addrspace (75), section "c" ^ llvm-as: crash06.ll:2:14: invalid type for null constant udiv label zeroinitializer, @0 ^ llvm-svn: 61681
2009-01-05 16:13:38 +08:00
// FIXME: LabelTy should not be a first-class type.
strength reduce a ton of type equality tests to check the typeid (Through the new predicates I added) instead of going through a context and doing a pointer comparison. Besides being cheaper, this allows a smart compiler to turn the if sequence into a switch. llvm-svn: 83297
2009-10-05 13:54:46 +08:00
if ((!Ty->isFirstClassType() || Ty->isLabelTy()) &&
Introduce isOpaqueTy and use it rather than isa<OpaqueType>. Also, move some methods to try to have the type predicates be more logically positioned. llvm-svn: 96349
2010-02-16 22:50:09 +08:00
!Ty->isOpaqueTy())
reject undef/zero labels. This fixes PR3281:crash0[56].ll with these diagnostics: llvm-as: crash05.ll:1:14: invalid type for null constant global label zeroinitializer addrspace (75), section "c" ^ llvm-as: crash06.ll:2:14: invalid type for null constant udiv label zeroinitializer, @0 ^ llvm-svn: 61681
2009-01-05 16:13:38 +08:00
return Error(ID.Loc, "invalid type for undef constant");
Move more code back to 2.5 APIs. llvm-svn: 77635
2009-07-31 07:03:37 +08:00
V = UndefValue::get(Ty);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
fix PR3281:accepted0[02].ll: represent empty arrays distinctly, and diagnose attempts to initialize non-empty arrays with them. This produces: llvm-as: accepted02.ll:1:28: invalid empty array initializer @"o" = global [5 x double] [] ^ llvm-as: accepted00.ll:1:32: invalid empty array initializer @"za" = thread_local global {} [] ^ [ llvm-svn: 61676
2009-01-05 15:52:51 +08:00
case ValID::t_EmptyArray:
There are two ways of checking for a given type, for example isa<PointerType>(T) and T->isPointerTy(). Convert most instances of the first form to the second form. Requested by Chris. llvm-svn: 96344
2010-02-16 19:11:14 +08:00
if (!Ty->isArrayTy() || cast<ArrayType>(Ty)->getNumElements() != 0)
fix PR3281:accepted0[02].ll: represent empty arrays distinctly, and diagnose attempts to initialize non-empty arrays with them. This produces: llvm-as: accepted02.ll:1:28: invalid empty array initializer @"o" = global [5 x double] [] ^ llvm-as: accepted00.ll:1:32: invalid empty array initializer @"za" = thread_local global {} [] ^ [ llvm-svn: 61676
2009-01-05 15:52:51 +08:00
return Error(ID.Loc, "invalid empty array initializer");
Move more code back to 2.5 APIs. llvm-svn: 77635
2009-07-31 07:03:37 +08:00
V = UndefValue::get(Ty);
fix PR3281:accepted0[02].ll: represent empty arrays distinctly, and diagnose attempts to initialize non-empty arrays with them. This produces: llvm-as: accepted02.ll:1:28: invalid empty array initializer @"o" = global [5 x double] [] ^ llvm-as: accepted00.ll:1:32: invalid empty array initializer @"za" = thread_local global {} [] ^ [ llvm-svn: 61676
2009-01-05 15:52:51 +08:00
return false;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case ValID::t_Zero:
reject undef/zero labels. This fixes PR3281:crash0[56].ll with these diagnostics: llvm-as: crash05.ll:1:14: invalid type for null constant global label zeroinitializer addrspace (75), section "c" ^ llvm-as: crash06.ll:2:14: invalid type for null constant udiv label zeroinitializer, @0 ^ llvm-svn: 61681
2009-01-05 16:13:38 +08:00
// FIXME: LabelTy should not be a first-class type.
strength reduce a ton of type equality tests to check the typeid (Through the new predicates I added) instead of going through a context and doing a pointer comparison. Besides being cheaper, this allows a smart compiler to turn the if sequence into a switch. llvm-svn: 83297
2009-10-05 13:54:46 +08:00
if (!Ty->isFirstClassType() || Ty->isLabelTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(ID.Loc, "invalid type for null constant");
Move a few more APIs back to 2.5 forms. The only remaining ones left to change back are metadata related, which I'm waiting on to avoid conflicting with Devang. llvm-svn: 77721
2009-08-01 04:28:14 +08:00
V = Constant::getNullValue(Ty);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
case ValID::t_Constant:
Add support for a union type in LLVM IR. Patch by Talin! llvm-svn: 96011
2010-02-13 04:49:41 +08:00
if (ID.ConstantVal->getType() != Ty) {
// Allow a constant struct with a single member to be converted
// to a union, if the union has a member which is the same type
// as the struct member.
if (const UnionType* utype = dyn_cast<UnionType>(Ty)) {
return ParseUnionValue(utype, ID, V);
}
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(ID.Loc, "constant expression type mismatch");
Add support for a union type in LLVM IR. Patch by Talin! llvm-svn: 96011
2010-02-13 04:49:41 +08:00
}
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
V = ID.ConstantVal;
return false;
}
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
bool LLParser::ParseValue(const Type *Ty, Value *&V, PerFunctionState &PFS) {
V = 0;
ValID ID;
Re-add parsing of function-local metadata; this time with testcase. llvm-svn: 92793
2010-01-06 06:22:14 +08:00
return ParseValID(ID, &PFS) ||
Consolidate ConvertGlobalValIDToValue, ConvertGlobalOrMetadataValIDToValue, and ConvertValIDToValue into a more powerful ConvertValIDToValue() that does all three's work llvm-svn: 93197
2010-01-12 06:31:58 +08:00
ConvertValIDToValue(Ty, ID, V, &PFS);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
bool LLParser::ParseTypeAndValue(Value *&V, PerFunctionState &PFS) {
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
PATypeHolder T(Type::getVoidTy(Context));
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
return ParseType(T) ||
ParseValue(T, V, PFS);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
add enough support for indirect branch for the feature test to pass (assembler,asmprinter, bc reader+writer) and document it. Codegen currently aborts on it. llvm-svn: 85274
2009-10-28 03:13:16 +08:00
bool LLParser::ParseTypeAndBasicBlock(BasicBlock *&BB, LocTy &Loc,
PerFunctionState &PFS) {
Value *V;
Loc = Lex.getLoc();
if (ParseTypeAndValue(V, PFS)) return true;
if (!isa<BasicBlock>(V))
return Error(Loc, "expected a basic block");
BB = cast<BasicBlock>(V);
return false;
}
Add support for a union type in LLVM IR. Patch by Talin! llvm-svn: 96011
2010-02-13 04:49:41 +08:00
bool LLParser::ParseUnionValue(const UnionType* utype, ValID &ID, Value *&V) {
if (const StructType* stype = dyn_cast<StructType>(ID.ConstantVal->getType())) {
if (stype->getNumContainedTypes() != 1)
return Error(ID.Loc, "constant expression type mismatch");
int index = utype->getElementTypeIndex(stype->getContainedType(0));
if (index < 0)
return Error(ID.Loc, "initializer type is not a member of the union");
V = ConstantUnion::get(
utype, cast<Constant>(ID.ConstantVal->getOperand(0)));
return false;
}
return Error(ID.Loc, "constant expression type mismatch");
}
add enough support for indirect branch for the feature test to pass (assembler,asmprinter, bc reader+writer) and document it. Codegen currently aborts on it. llvm-svn: 85274
2009-10-28 03:13:16 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
/// FunctionHeader
/// ::= OptionalLinkage OptionalVisibility OptionalCallingConv OptRetAttrs
/// Type GlobalName '(' ArgList ')' OptFuncAttrs OptSection
/// OptionalAlign OptGC
bool LLParser::ParseFunctionHeader(Function *&Fn, bool isDefine) {
// Parse the linkage.
LocTy LinkageLoc = Lex.getLoc();
unsigned Linkage;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Retype from unsigned to CallingConv::ID accordingly. Approved by Bob Wilson. llvm-svn: 80773
2009-09-02 16:44:58 +08:00
unsigned Visibility, RetAttrs;
CallingConv::ID CC;
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
PATypeHolder RetType(Type::getVoidTy(Context));
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
LocTy RetTypeLoc = Lex.getLoc();
if (ParseOptionalLinkage(Linkage) ||
ParseOptionalVisibility(Visibility) ||
ParseOptionalCallingConv(CC) ||
ParseOptionalAttrs(RetAttrs, 1) ||
Fix two classes of bugs. First: validate an invariant so that the asmparser rejects a bad construct instead of the verifier. Before: llvm-as: assembly parsed, but does not verify as correct! Invalid struct return type! i64 (%struct.Type*, %struct.Type*)* @foo after: llvm-as: t.ll:5:8: functions with 'sret' argument must return void define i64 @foo(%struct.Type* noalias nocapture sret %agg.result, %struct.Type* nocapture byval %t) nounwind { ^ Second, check that void is only used where allowed (in function return types) not in arbitrary places, fixing PR3747 - Crash in llvm-as with void field in struct. We now reject that example with: $ llvm-as t.ll llvm-as: t.ll:1:12: struct element can not have void type %x = type {void} ^ llvm-svn: 66394
2009-03-09 12:49:14 +08:00
ParseType(RetType, RetTypeLoc, true /*void allowed*/))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return true;
// Verify that the linkage is ok.
switch ((GlobalValue::LinkageTypes)Linkage) {
case GlobalValue::ExternalLinkage:
break; // always ok.
case GlobalValue::DLLImportLinkage:
Remove the one-definition-rule version of extern_weak linkage: this linkage type only applies to declarations, but ODR is only relevant to globals with definitions. llvm-svn: 66650
2009-03-11 16:08:06 +08:00
case GlobalValue::ExternalWeakLinkage:
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (isDefine)
return Error(LinkageLoc, "invalid linkage for function definition");
break;
Add the private linkage. llvm-svn: 62279
2009-01-16 04:18:42 +08:00
case GlobalValue::PrivateLinkage:
Add plumbing for the `linker_private' linkage type. This type is meant for "private" symbols which the assember shouldn't strip, but which the linker may remove after evaluation. This is mostly useful for Objective-C metadata. This is plumbing, so we don't have a use of it yet. More to come, etc. llvm-svn: 76385
2009-07-20 09:03:30 +08:00
case GlobalValue::LinkerPrivateLinkage:
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case GlobalValue::InternalLinkage:
Fix warning in .ll parser, detect and reject available_externally on function declarations. llvm-svn: 68944
2009-04-13 15:02:02 +08:00
case GlobalValue::AvailableExternallyLinkage:
Introduce new linkage types linkonce_odr, weak_odr, common_odr and extern_weak_odr. These are the same as the non-odr versions, except that they indicate that the global will only be overridden by an *equivalent* global. In C, a function with weak linkage can be overridden by a function which behaves completely differently. This means that IP passes have to skip weak functions, since any deductions made from the function definition might be wrong, since the definition could be replaced by something completely different at link time. This is not allowed in C++, thanks to the ODR (One-Definition-Rule): if a function is replaced by another at link-time, then the new function must be the same as the original function. If a language knows that a function or other global can only be overridden by an equivalent global, it can give it the weak_odr linkage type, and the optimizers will understand that it is alright to make deductions based on the function body. The code generators on the other hand map weak and weak_odr linkage to the same thing. llvm-svn: 66339
2009-03-07 23:45:40 +08:00
case GlobalValue::LinkOnceAnyLinkage:
case GlobalValue::LinkOnceODRLinkage:
case GlobalValue::WeakAnyLinkage:
case GlobalValue::WeakODRLinkage:
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case GlobalValue::DLLExportLinkage:
if (!isDefine)
return Error(LinkageLoc, "invalid linkage for function declaration");
break;
case GlobalValue::AppendingLinkage:
It makes no sense to have a ODR version of common linkage, so remove it. llvm-svn: 66690
2009-03-12 04:14:15 +08:00
case GlobalValue::CommonLinkage:
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(LinkageLoc, "invalid function linkage type");
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
reject PR3281:crash01.ll with: llvm-as: crash01.ll:1:9: invalid function return type declare opaque @t() ^ llvm-svn: 61678
2009-01-05 16:00:30 +08:00
if (!FunctionType::isValidReturnType(RetType) ||
Introduce isOpaqueTy and use it rather than isa<OpaqueType>. Also, move some methods to try to have the type predicates be more logically positioned. llvm-svn: 96349
2010-02-16 22:50:09 +08:00
RetType->isOpaqueTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(RetTypeLoc, "invalid function return type");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
add proper asmwriter and asmparser support for anonymous functions. llvm-svn: 64953
2009-02-19 05:48:13 +08:00
LocTy NameLoc = Lex.getLoc();
std::string FunctionName;
if (Lex.getKind() == lltok::GlobalVar) {
FunctionName = Lex.getStrVal();
} else if (Lex.getKind() == lltok::GlobalID) { // @42 is ok.
unsigned NameID = Lex.getUIntVal();
if (NameID != NumberedVals.size())
return TokError("function expected to be numbered '%" +
utostr(NumberedVals.size()) + "'");
} else {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return TokError("expected function name");
add proper asmwriter and asmparser support for anonymous functions. llvm-svn: 64953
2009-02-19 05:48:13 +08:00
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
Lex.Lex();
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
if (Lex.getKind() != lltok::lparen)
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return TokError("expected '(' in function argument list");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
std::vector<ArgInfo> ArgList;
bool isVarArg;
unsigned FuncAttrs;
std::string Section;
unsigned Alignment;
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
std::string GC;
Reject PR3281:accepted03.ll with: llvm-as: accepted03.ll:1:35: invalid unresolved type up reference declare void @r({ \7, opaque, \10 } %su) ^ llvm-svn: 61725
2009-01-06 02:34:07 +08:00
if (ParseArgumentList(ArgList, isVarArg, false) ||
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
ParseOptionalAttrs(FuncAttrs, 2) ||
(EatIfPresent(lltok::kw_section) &&
ParseStringConstant(Section)) ||
ParseOptionalAlignment(Alignment) ||
(EatIfPresent(lltok::kw_gc) &&
ParseStringConstant(GC)))
return true;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// If the alignment was parsed as an attribute, move to the alignment field.
if (FuncAttrs & Attribute::Alignment) {
Alignment = Attribute::getAlignmentFromAttrs(FuncAttrs);
FuncAttrs &= ~Attribute::Alignment;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Okay, if we got here, the function is syntactically valid. Convert types
// and do semantic checks.
std::vector<const Type*> ParamTypeList;
SmallVector<AttributeWithIndex, 8> Attrs;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
// FIXME : In 3.0, stop accepting zext, sext and inreg as optional function
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// attributes.
unsigned ObsoleteFuncAttrs = Attribute::ZExt|Attribute::SExt|Attribute::InReg;
if (FuncAttrs & ObsoleteFuncAttrs) {
RetAttrs |= FuncAttrs & ObsoleteFuncAttrs;
FuncAttrs &= ~ObsoleteFuncAttrs;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (RetAttrs != Attribute::None)
Attrs.push_back(AttributeWithIndex::get(0, RetAttrs));
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
for (unsigned i = 0, e = ArgList.size(); i != e; ++i) {
ParamTypeList.push_back(ArgList[i].Type);
if (ArgList[i].Attrs != Attribute::None)
Attrs.push_back(AttributeWithIndex::get(i+1, ArgList[i].Attrs));
}
if (FuncAttrs != Attribute::None)
Attrs.push_back(AttributeWithIndex::get(~0, FuncAttrs));
AttrListPtr PAL = AttrListPtr::get(Attrs.begin(), Attrs.end());
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Avoid going through the LLVMContext for type equality where it's safe to dereference the type pointer. llvm-svn: 92726
2010-01-05 21:12:22 +08:00
if (PAL.paramHasAttr(1, Attribute::StructRet) && !RetType->isVoidTy())
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
return Error(RetTypeLoc, "functions with 'sret' argument must return void");
Try again at converting the LLParser to use LLVMContext, without massive breakage this time. llvm-svn: 74671
2009-07-02 07:57:11 +08:00
const FunctionType *FT =
Move types back to the 2.5 API. llvm-svn: 77516
2009-07-30 06:17:13 +08:00
FunctionType::get(RetType, ParamTypeList, isVarArg);
const PointerType *PFT = PointerType::getUnqual(FT);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Fn = 0;
if (!FunctionName.empty()) {
// If this was a definition of a forward reference, remove the definition
// from the forward reference table and fill in the forward ref.
std::map<std::string, std::pair<GlobalValue*, LocTy> >::iterator FRVI =
ForwardRefVals.find(FunctionName);
if (FRVI != ForwardRefVals.end()) {
Fn = M->getFunction(FunctionName);
ForwardRefVals.erase(FRVI);
} else if ((Fn = M->getFunction(FunctionName))) {
// If this function already exists in the symbol table, then it is
// multiply defined. We accept a few cases for old backwards compat.
// FIXME: Remove this stuff for LLVM 3.0.
if (Fn->getType() != PFT || Fn->getAttributes() != PAL ||
(!Fn->isDeclaration() && isDefine)) {
// If the redefinition has different type or different attributes,
// reject it. If both have bodies, reject it.
return Error(NameLoc, "invalid redefinition of function '" +
FunctionName + "'");
} else if (Fn->isDeclaration()) {
// Make sure to strip off any argument names so we can't get conflicts.
for (Function::arg_iterator AI = Fn->arg_begin(), AE = Fn->arg_end();
AI != AE; ++AI)
AI->setName("");
}
fix PR5295 where the .ll parser didn't reject a function after a global or global after a function with conflicting names. Update some testcases that were accidentally depending on this behavior. llvm-svn: 85081
2009-10-26 07:22:50 +08:00
} else if (M->getNamedValue(FunctionName)) {
return Error(NameLoc, "redefinition of function '@" + FunctionName + "'");
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Minor logic simplification. llvm-svn: 80453
2009-08-30 07:37:49 +08:00
} else {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// If this is a definition of a forward referenced function, make sure the
// types agree.
std::map<unsigned, std::pair<GlobalValue*, LocTy> >::iterator I
= ForwardRefValIDs.find(NumberedVals.size());
if (I != ForwardRefValIDs.end()) {
Fn = cast<Function>(I->second.first);
if (Fn->getType() != PFT)
return Error(NameLoc, "type of definition and forward reference of '@" +
utostr(NumberedVals.size()) +"' disagree");
ForwardRefValIDs.erase(I);
}
}
if (Fn == 0)
Fn = Function::Create(FT, GlobalValue::ExternalLinkage, FunctionName, M);
else // Move the forward-reference to the correct spot in the module.
M->getFunctionList().splice(M->end(), M->getFunctionList(), Fn);
if (FunctionName.empty())
NumberedVals.push_back(Fn);
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Fn->setLinkage((GlobalValue::LinkageTypes)Linkage);
Fn->setVisibility((GlobalValue::VisibilityTypes)Visibility);
Fn->setCallingConv(CC);
Fn->setAttributes(PAL);
Fn->setAlignment(Alignment);
Fn->setSection(Section);
if (!GC.empty()) Fn->setGC(GC.c_str());
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Add all of the arguments we parsed to the function.
Function::arg_iterator ArgIt = Fn->arg_begin();
for (unsigned i = 0, e = ArgList.size(); i != e; ++i, ++ArgIt) {
Add a hack for PR5601, a crash on obsolete syntax that we plan to remove in LLVM 3.0 llvm-svn: 89973
2009-11-27 06:48:23 +08:00
// If we run out of arguments in the Function prototype, exit early.
// FIXME: REMOVE THIS IN LLVM 3.0, this is just for the mismatch case above.
if (ArgIt == Fn->arg_end()) break;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// If the argument has a name, insert it into the argument symbol table.
if (ArgList[i].Name.empty()) continue;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Set the name, if it conflicted, it will be auto-renamed.
ArgIt->setName(ArgList[i].Name);
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ArgIt->getNameStr() != ArgList[i].Name)
return Error(ArgList[i].Loc, "redefinition of argument '%" +
ArgList[i].Name + "'");
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
}
/// ParseFunctionBody
/// ::= '{' BasicBlock+ '}'
/// ::= 'begin' BasicBlock+ 'end' // FIXME: remove in LLVM 3.0
///
bool LLParser::ParseFunctionBody(Function &Fn) {
if (Lex.getKind() != lltok::lbrace && Lex.getKind() != lltok::kw_begin)
return TokError("expected '{' in function body");
Lex.Lex(); // eat the {.
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
full asmparser support for blockaddress. We can now do: $ llvm-as foo.ll -d -disable-output which reads and prints the .ll file. BC encoding is the next project. Testcase will go in once that works. llvm-svn: 85368
2009-10-28 11:39:23 +08:00
int FunctionNumber = -1;
if (!Fn.hasName()) FunctionNumber = NumberedVals.size()-1;
PerFunctionState PFS(*this, Fn, FunctionNumber);
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
fix PR5983, reject function bodies with no blocks per the grammar. llvm-svn: 93067
2010-01-10 03:20:07 +08:00
// We need at least one basic block.
if (Lex.getKind() == lltok::rbrace || Lex.getKind() == lltok::kw_end)
return TokError("function body requires at least one basic block");
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
while (Lex.getKind() != lltok::rbrace && Lex.getKind() != lltok::kw_end)
if (ParseBasicBlock(PFS)) return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Eat the }.
Lex.Lex();
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Verify function is ok.
full asmparser support for blockaddress. We can now do: $ llvm-as foo.ll -d -disable-output which reads and prints the .ll file. BC encoding is the next project. Testcase will go in once that works. llvm-svn: 85368
2009-10-28 11:39:23 +08:00
return PFS.FinishFunction();
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
/// ParseBasicBlock
/// ::= LabelStr? Instruction*
bool LLParser::ParseBasicBlock(PerFunctionState &PFS) {
// If this basic block starts out with a name, remember it.
std::string Name;
LocTy NameLoc = Lex.getLoc();
if (Lex.getKind() == lltok::LabelStr) {
Name = Lex.getStrVal();
Lex.Lex();
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
BasicBlock *BB = PFS.DefineBB(Name, NameLoc);
if (BB == 0) return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
std::string NameStr;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Parse the instructions in this block until we get a terminator.
Instruction *Inst;
now that instruction metadata is only parsed in one place, eliminate the parser-global MDsOnInst vector and make ParseInstructionMetadata return its result by-ref through an argument like the entire rest of the parser. llvm-svn: 92302
2009-12-30 13:48:36 +08:00
SmallVector<std::pair<unsigned, MDNode *>, 4> MetadataOnInst;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
do {
// This instruction may have three possibilities for a name: a) none
// specified, b) name specified "%foo =", c) number specified: "%4 =".
LocTy NameLoc = Lex.getLoc();
int NameID = -1;
NameStr = "";
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (Lex.getKind() == lltok::LocalVarID) {
NameID = Lex.getUIntVal();
Lex.Lex();
if (ParseToken(lltok::equal, "expected '=' after instruction id"))
return true;
} else if (Lex.getKind() == lltok::LocalVar ||
// FIXME: REMOVE IN LLVM 3.0
Lex.getKind() == lltok::StringConstant) {
NameStr = Lex.getStrVal();
Lex.Lex();
if (ParseToken(lltok::equal, "expected '=' after instruction name"))
return true;
}
Fix parsing of optional metadata for 'load', 'store' and 'alloc' instructions. llvm-svn: 82175
2009-09-18 07:04:48 +08:00
add facilities to start factoring instruction metadata parsing out of each opcode's handler. Change ret over so far. llvm-svn: 92298
2009-12-30 13:23:43 +08:00
switch (ParseInstruction(Inst, BB, PFS)) {
default: assert(0 && "Unknown ParseInstruction result!");
case InstError: return true;
case InstNormal:
// With a normal result, we check to see if the instruction is followed by
// a comma and metadata.
if (EatIfPresent(lltok::comma))
now that instruction metadata is only parsed in one place, eliminate the parser-global MDsOnInst vector and make ParseInstructionMetadata return its result by-ref through an argument like the entire rest of the parser. llvm-svn: 92302
2009-12-30 13:48:36 +08:00
if (ParseInstructionMetadata(MetadataOnInst))
add facilities to start factoring instruction metadata parsing out of each opcode's handler. Change ret over so far. llvm-svn: 92298
2009-12-30 13:23:43 +08:00
return true;
break;
case InstExtraComma:
// If the instruction parser ate an extra comma at the end of it, it
// *must* be followed by metadata.
now that instruction metadata is only parsed in one place, eliminate the parser-global MDsOnInst vector and make ParseInstructionMetadata return its result by-ref through an argument like the entire rest of the parser. llvm-svn: 92302
2009-12-30 13:48:36 +08:00
if (ParseInstructionMetadata(MetadataOnInst))
add facilities to start factoring instruction metadata parsing out of each opcode's handler. Change ret over so far. llvm-svn: 92298
2009-12-30 13:23:43 +08:00
return true;
break;
}
Fix parsing of optional metadata for 'load', 'store' and 'alloc' instructions. llvm-svn: 82175
2009-09-18 07:04:48 +08:00
// Set metadata attached with this instruction.
now that instruction metadata is only parsed in one place, eliminate the parser-global MDsOnInst vector and make ParseInstructionMetadata return its result by-ref through an argument like the entire rest of the parser. llvm-svn: 92302
2009-12-30 13:48:36 +08:00
for (unsigned i = 0, e = MetadataOnInst.size(); i != e; ++i)
Inst->setMetadata(MetadataOnInst[i].first, MetadataOnInst[i].second);
MetadataOnInst.clear();
Fix parsing of optional metadata for 'load', 'store' and 'alloc' instructions. llvm-svn: 82175
2009-09-18 07:04:48 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
BB->getInstList().push_back(Inst);
// Set the name on the instruction.
if (PFS.SetInstName(NameID, NameStr, NameLoc, Inst)) return true;
} while (!isa<TerminatorInst>(Inst));
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
}
//===----------------------------------------------------------------------===//
// Instruction Parsing.
//===----------------------------------------------------------------------===//
/// ParseInstruction - Parse one of the many different instructions.
///
add facilities to start factoring instruction metadata parsing out of each opcode's handler. Change ret over so far. llvm-svn: 92298
2009-12-30 13:23:43 +08:00
int LLParser::ParseInstruction(Instruction *&Inst, BasicBlock *BB,
PerFunctionState &PFS) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
lltok::Kind Token = Lex.getKind();
if (Token == lltok::Eof)
return TokError("found end of file when expecting more instructions");
LocTy Loc = Lex.getLoc();
Fix a pretty awesome bug that only happened in a strange case with anonymous types. This was reading the uint for the keyword after the token was advanced. llvm-svn: 65743
2009-03-01 08:53:13 +08:00
unsigned KeywordVal = Lex.getUIntVal();
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Lex.Lex(); // Eat the keyword.
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
switch (Token) {
default: return Error(Loc, "expected instruction opcode");
// Terminator Instructions.
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
case lltok::kw_unwind: Inst = new UnwindInst(Context); return false;
case lltok::kw_unreachable: Inst = new UnreachableInst(Context); return false;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case lltok::kw_ret: return ParseRet(Inst, BB, PFS);
case lltok::kw_br: return ParseBr(Inst, PFS);
case lltok::kw_switch: return ParseSwitch(Inst, PFS);
rename indbr -> indirectbr to appease the residents of #llvm. llvm-svn: 85351
2009-10-28 08:19:10 +08:00
case lltok::kw_indirectbr: return ParseIndirectBr(Inst, PFS);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case lltok::kw_invoke: return ParseInvoke(Inst, PFS);
// Binary Operators.
case lltok::kw_add:
case lltok::kw_sub:
Change the assembly syntax for nsw, nuw, and exact, putting them after their associated opcodes rather than before. This makes them a little easier to read. llvm-svn: 77194
2009-07-28 00:11:46 +08:00
case lltok::kw_mul: {
bool NUW = false;
bool NSW = false;
LocTy ModifierLoc = Lex.getLoc();
if (EatIfPresent(lltok::kw_nuw))
NUW = true;
if (EatIfPresent(lltok::kw_nsw)) {
NSW = true;
if (EatIfPresent(lltok::kw_nuw))
NUW = true;
}
Split the Add, Sub, and Mul instruction opcodes into separate integer and floating-point opcodes, introducing FAdd, FSub, and FMul. For now, the AsmParser, BitcodeReader, and IRBuilder all preserve backwards compatability, and the Core LLVM APIs preserve backwards compatibility for IR producers. Most front-ends won't need to change immediately. This implements the first step of the plan outlined here: http://nondot.org/sabre/LLVMNotes/IntegerOverflow.txt llvm-svn: 72897
2009-06-05 06:49:04 +08:00
// API compatibility: Accept either integer or floating-point types.
Change the assembly syntax for nsw, nuw, and exact, putting them after their associated opcodes rather than before. This makes them a little easier to read. llvm-svn: 77194
2009-07-28 00:11:46 +08:00
bool Result = ParseArithmetic(Inst, PFS, KeywordVal, 0);
if (!Result) {
Uniformize the names of type predicates: rather than having isFloatTy and isInteger, we now have isFloatTy and isIntegerTy. Requested by Chris! llvm-svn: 96223
2010-02-16 00:12:20 +08:00
if (!Inst->getType()->isIntOrIntVectorTy()) {
Change the assembly syntax for nsw, nuw, and exact, putting them after their associated opcodes rather than before. This makes them a little easier to read. llvm-svn: 77194
2009-07-28 00:11:46 +08:00
if (NUW)
return Error(ModifierLoc, "nuw only applies to integer operations");
if (NSW)
return Error(ModifierLoc, "nsw only applies to integer operations");
}
if (NUW)
Reappy r80998, now that the GlobalOpt bug that it exposed on MiniSAT is fixed. llvm-svn: 81172
2009-09-08 07:54:19 +08:00
cast<BinaryOperator>(Inst)->setHasNoUnsignedWrap(true);
Change the assembly syntax for nsw, nuw, and exact, putting them after their associated opcodes rather than before. This makes them a little easier to read. llvm-svn: 77194
2009-07-28 00:11:46 +08:00
if (NSW)
Reappy r80998, now that the GlobalOpt bug that it exposed on MiniSAT is fixed. llvm-svn: 81172
2009-09-08 07:54:19 +08:00
cast<BinaryOperator>(Inst)->setHasNoSignedWrap(true);
Change the assembly syntax for nsw, nuw, and exact, putting them after their associated opcodes rather than before. This makes them a little easier to read. llvm-svn: 77194
2009-07-28 00:11:46 +08:00
}
return Result;
}
Split the Add, Sub, and Mul instruction opcodes into separate integer and floating-point opcodes, introducing FAdd, FSub, and FMul. For now, the AsmParser, BitcodeReader, and IRBuilder all preserve backwards compatability, and the Core LLVM APIs preserve backwards compatibility for IR producers. Most front-ends won't need to change immediately. This implements the first step of the plan outlined here: http://nondot.org/sabre/LLVMNotes/IntegerOverflow.txt llvm-svn: 72897
2009-06-05 06:49:04 +08:00
case lltok::kw_fadd:
case lltok::kw_fsub:
case lltok::kw_fmul: return ParseArithmetic(Inst, PFS, KeywordVal, 2);
Change the assembly syntax for nsw, nuw, and exact, putting them after their associated opcodes rather than before. This makes them a little easier to read. llvm-svn: 77194
2009-07-28 00:11:46 +08:00
case lltok::kw_sdiv: {
bool Exact = false;
if (EatIfPresent(lltok::kw_exact))
Exact = true;
bool Result = ParseArithmetic(Inst, PFS, KeywordVal, 1);
if (!Result)
if (Exact)
Reappy r80998, now that the GlobalOpt bug that it exposed on MiniSAT is fixed. llvm-svn: 81172
2009-09-08 07:54:19 +08:00
cast<BinaryOperator>(Inst)->setIsExact(true);
Change the assembly syntax for nsw, nuw, and exact, putting them after their associated opcodes rather than before. This makes them a little easier to read. llvm-svn: 77194
2009-07-28 00:11:46 +08:00
return Result;
}
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case lltok::kw_udiv:
case lltok::kw_urem:
Fix a pretty awesome bug that only happened in a strange case with anonymous types. This was reading the uint for the keyword after the token was advanced. llvm-svn: 65743
2009-03-01 08:53:13 +08:00
case lltok::kw_srem: return ParseArithmetic(Inst, PFS, KeywordVal, 1);
Fix PR3281:crash08.ll with this diagnostic: llvm-as: crash08.ll:3:15: invalid operand type for instruction "qp" = sdiv fp128 0x1, %30 ^ llvm-svn: 61684
2009-01-05 16:24:46 +08:00
case lltok::kw_fdiv:
Fix a pretty awesome bug that only happened in a strange case with anonymous types. This was reading the uint for the keyword after the token was advanced. llvm-svn: 65743
2009-03-01 08:53:13 +08:00
case lltok::kw_frem: return ParseArithmetic(Inst, PFS, KeywordVal, 2);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case lltok::kw_shl:
case lltok::kw_lshr:
case lltok::kw_ashr:
case lltok::kw_and:
case lltok::kw_or:
Fix a pretty awesome bug that only happened in a strange case with anonymous types. This was reading the uint for the keyword after the token was advanced. llvm-svn: 65743
2009-03-01 08:53:13 +08:00
case lltok::kw_xor: return ParseLogical(Inst, PFS, KeywordVal);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case lltok::kw_icmp:
Remove the vicmp and vfcmp instructions. Because we never had a release with these instructions, no autoupgrade or backwards compatibility support is provided. llvm-svn: 74991
2009-07-08 11:04:38 +08:00
case lltok::kw_fcmp: return ParseCompare(Inst, PFS, KeywordVal);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Casts.
case lltok::kw_trunc:
case lltok::kw_zext:
case lltok::kw_sext:
case lltok::kw_fptrunc:
case lltok::kw_fpext:
case lltok::kw_bitcast:
case lltok::kw_uitofp:
case lltok::kw_sitofp:
case lltok::kw_fptoui:
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
case lltok::kw_fptosi:
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case lltok::kw_inttoptr:
Fix a pretty awesome bug that only happened in a strange case with anonymous types. This was reading the uint for the keyword after the token was advanced. llvm-svn: 65743
2009-03-01 08:53:13 +08:00
case lltok::kw_ptrtoint: return ParseCast(Inst, PFS, KeywordVal);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Other.
case lltok::kw_select: return ParseSelect(Inst, PFS);
reject PR3281:crash07.ll with: llvm-as: crash07.ll:2:32: va_arg requires operand with first class type %y = va_arg [52 x <{}>] %43, double (...) sspreq ^ llvm-svn: 61683
2009-01-05 16:18:44 +08:00
case lltok::kw_va_arg: return ParseVA_Arg(Inst, PFS);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case lltok::kw_extractelement: return ParseExtractElement(Inst, PFS);
case lltok::kw_insertelement: return ParseInsertElement(Inst, PFS);
case lltok::kw_shufflevector: return ParseShuffleVector(Inst, PFS);
case lltok::kw_phi: return ParsePHI(Inst, PFS);
case lltok::kw_call: return ParseCall(Inst, PFS, false);
case lltok::kw_tail: return ParseCall(Inst, PFS, true);
// Memory.
Autoupgrade malloc insts to malloc calls. Update testcases that rely on malloc insts being present. Also prematurely remove MallocInst handling from IndMemRemoval and RaiseAllocations to help pass tests in this incremental step. llvm-svn: 84292
2009-10-17 08:00:19 +08:00
case lltok::kw_alloca: return ParseAlloc(Inst, PFS);
case lltok::kw_malloc: return ParseAlloc(Inst, PFS, BB, false);
Auto-upgrade free instructions to calls to the builtin free function. Update all analysis passes and transforms to treat free calls just like FreeInst. Remove RaiseAllocations and all its tests since FreeInst no longer needs to be raised. llvm-svn: 84987
2009-10-24 12:23:03 +08:00
case lltok::kw_free: return ParseFree(Inst, PFS, BB);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
case lltok::kw_load: return ParseLoad(Inst, PFS, false);
case lltok::kw_store: return ParseStore(Inst, PFS, false);
case lltok::kw_volatile:
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
if (EatIfPresent(lltok::kw_load))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return ParseLoad(Inst, PFS, true);
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
else if (EatIfPresent(lltok::kw_store))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return ParseStore(Inst, PFS, true);
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
else
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return TokError("expected 'load' or 'store'");
case lltok::kw_getresult: return ParseGetResult(Inst, PFS);
case lltok::kw_getelementptr: return ParseGetElementPtr(Inst, PFS);
case lltok::kw_extractvalue: return ParseExtractValue(Inst, PFS);
case lltok::kw_insertvalue: return ParseInsertValue(Inst, PFS);
}
}
/// ParseCmpPredicate - Parse an integer or fp predicate, based on Kind.
bool LLParser::ParseCmpPredicate(unsigned &P, unsigned Opc) {
Remove the vicmp and vfcmp instructions. Because we never had a release with these instructions, no autoupgrade or backwards compatibility support is provided. llvm-svn: 74991
2009-07-08 11:04:38 +08:00
if (Opc == Instruction::FCmp) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
switch (Lex.getKind()) {
default: TokError("expected fcmp predicate (e.g. 'oeq')");
case lltok::kw_oeq: P = CmpInst::FCMP_OEQ; break;
case lltok::kw_one: P = CmpInst::FCMP_ONE; break;
case lltok::kw_olt: P = CmpInst::FCMP_OLT; break;
case lltok::kw_ogt: P = CmpInst::FCMP_OGT; break;
case lltok::kw_ole: P = CmpInst::FCMP_OLE; break;
case lltok::kw_oge: P = CmpInst::FCMP_OGE; break;
case lltok::kw_ord: P = CmpInst::FCMP_ORD; break;
case lltok::kw_uno: P = CmpInst::FCMP_UNO; break;
case lltok::kw_ueq: P = CmpInst::FCMP_UEQ; break;
case lltok::kw_une: P = CmpInst::FCMP_UNE; break;
case lltok::kw_ult: P = CmpInst::FCMP_ULT; break;
case lltok::kw_ugt: P = CmpInst::FCMP_UGT; break;
case lltok::kw_ule: P = CmpInst::FCMP_ULE; break;
case lltok::kw_uge: P = CmpInst::FCMP_UGE; break;
case lltok::kw_true: P = CmpInst::FCMP_TRUE; break;
case lltok::kw_false: P = CmpInst::FCMP_FALSE; break;
}
} else {
switch (Lex.getKind()) {
default: TokError("expected icmp predicate (e.g. 'eq')");
case lltok::kw_eq: P = CmpInst::ICMP_EQ; break;
case lltok::kw_ne: P = CmpInst::ICMP_NE; break;
case lltok::kw_slt: P = CmpInst::ICMP_SLT; break;
case lltok::kw_sgt: P = CmpInst::ICMP_SGT; break;
case lltok::kw_sle: P = CmpInst::ICMP_SLE; break;
case lltok::kw_sge: P = CmpInst::ICMP_SGE; break;
case lltok::kw_ult: P = CmpInst::ICMP_ULT; break;
case lltok::kw_ugt: P = CmpInst::ICMP_UGT; break;
case lltok::kw_ule: P = CmpInst::ICMP_ULE; break;
case lltok::kw_uge: P = CmpInst::ICMP_UGE; break;
}
}
Lex.Lex();
return false;
}
//===----------------------------------------------------------------------===//
// Terminator Instructions.
//===----------------------------------------------------------------------===//
/// ParseRet - Parse a return instruction.
Each instruction is allowed to have *multiple* different metadata objects on them. Though the entire compiler supports this, the asmparser didn't. llvm-svn: 92270
2009-12-30 05:25:40 +08:00
/// ::= 'ret' void (',' !dbg, !1)*
/// ::= 'ret' TypeAndValue (',' !dbg, !1)*
/// ::= 'ret' TypeAndValue (',' TypeAndValue)+ (',' !dbg, !1)*
Fix parsing of optional metadata for 'load', 'store' and 'alloc' instructions. llvm-svn: 82175
2009-09-18 07:04:48 +08:00
/// [[obsolete: LLVM 3.0]]
add facilities to start factoring instruction metadata parsing out of each opcode's handler. Change ret over so far. llvm-svn: 92298
2009-12-30 13:23:43 +08:00
int LLParser::ParseRet(Instruction *&Inst, BasicBlock *BB,
PerFunctionState &PFS) {
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
PATypeHolder Ty(Type::getVoidTy(Context));
Fix two classes of bugs. First: validate an invariant so that the asmparser rejects a bad construct instead of the verifier. Before: llvm-as: assembly parsed, but does not verify as correct! Invalid struct return type! i64 (%struct.Type*, %struct.Type*)* @foo after: llvm-as: t.ll:5:8: functions with 'sret' argument must return void define i64 @foo(%struct.Type* noalias nocapture sret %agg.result, %struct.Type* nocapture byval %t) nounwind { ^ Second, check that void is only used where allowed (in function return types) not in arbitrary places, fixing PR3747 - Crash in llvm-as with void field in struct. We now reject that example with: $ llvm-as t.ll llvm-as: t.ll:1:12: struct element can not have void type %x = type {void} ^ llvm-svn: 66394
2009-03-09 12:49:14 +08:00
if (ParseType(Ty, true /*void allowed*/)) return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
strength reduce a ton of type equality tests to check the typeid (Through the new predicates I added) instead of going through a context and doing a pointer comparison. Besides being cheaper, this allows a smart compiler to turn the if sequence into a switch. llvm-svn: 83297
2009-10-05 13:54:46 +08:00
if (Ty->isVoidTy()) {
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
Inst = ReturnInst::Create(Context);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Value *RV;
if (ParseValue(Ty, RV, PFS)) return true;
add facilities to start factoring instruction metadata parsing out of each opcode's handler. Change ret over so far. llvm-svn: 92298
2009-12-30 13:23:43 +08:00
bool ExtraComma = false;
Fix parsing of optional metadata for 'load', 'store' and 'alloc' instructions. llvm-svn: 82175
2009-09-18 07:04:48 +08:00
if (EatIfPresent(lltok::comma)) {
Parse custom metadata attached with an instruction. llvm-svn: 83033
2009-09-29 08:01:14 +08:00
// Parse optional custom metadata, e.g. !dbg
rename NamedOrCustomMD -> MetadataVar to follow conventions of all the rest of the code. llvm-svn: 92295
2009-12-30 13:02:06 +08:00
if (Lex.getKind() == lltok::MetadataVar) {
add facilities to start factoring instruction metadata parsing out of each opcode's handler. Change ret over so far. llvm-svn: 92298
2009-12-30 13:23:43 +08:00
ExtraComma = true;
Fix parsing of optional metadata for 'load', 'store' and 'alloc' instructions. llvm-svn: 82175
2009-09-18 07:04:48 +08:00
} else {
// The normal case is one return value.
Each instruction is allowed to have *multiple* different metadata objects on them. Though the entire compiler supports this, the asmparser didn't. llvm-svn: 92270
2009-12-30 05:25:40 +08:00
// FIXME: LLVM 3.0 remove MRV support for 'ret i32 1, i32 2', requiring
// use of 'ret {i32,i32} {i32 1, i32 2}'
Fix parsing of optional metadata for 'load', 'store' and 'alloc' instructions. llvm-svn: 82175
2009-09-18 07:04:48 +08:00
SmallVector<Value*, 8> RVs;
RVs.push_back(RV);
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Fix parsing of optional metadata for 'load', 'store' and 'alloc' instructions. llvm-svn: 82175
2009-09-18 07:04:48 +08:00
do {
Parse custom metadata attached with an instruction. llvm-svn: 83033
2009-09-29 08:01:14 +08:00
// If optional custom metadata, e.g. !dbg is seen then this is the
// end of MRV.
rename NamedOrCustomMD -> MetadataVar to follow conventions of all the rest of the code. llvm-svn: 92295
2009-12-30 13:02:06 +08:00
if (Lex.getKind() == lltok::MetadataVar)
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
break;
if (ParseTypeAndValue(RV, PFS)) return true;
RVs.push_back(RV);
Fix parsing of optional metadata for 'load', 'store' and 'alloc' instructions. llvm-svn: 82175
2009-09-18 07:04:48 +08:00
} while (EatIfPresent(lltok::comma));
RV = UndefValue::get(PFS.getFunction().getReturnType());
for (unsigned i = 0, e = RVs.size(); i != e; ++i) {
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Instruction *I = InsertValueInst::Create(RV, RVs[i], i, "mrv");
BB->getInstList().push_back(I);
RV = I;
Fix parsing of optional metadata for 'load', 'store' and 'alloc' instructions. llvm-svn: 82175
2009-09-18 07:04:48 +08:00
}
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
}
Fix parsing of optional metadata for 'load', 'store' and 'alloc' instructions. llvm-svn: 82175
2009-09-18 07:04:48 +08:00
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
Inst = ReturnInst::Create(Context, RV);
add facilities to start factoring instruction metadata parsing out of each opcode's handler. Change ret over so far. llvm-svn: 92298
2009-12-30 13:23:43 +08:00
return ExtraComma ? InstExtraComma : InstNormal;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
/// ParseBr
/// ::= 'br' TypeAndValue
/// ::= 'br' TypeAndValue ',' TypeAndValue ',' TypeAndValue
bool LLParser::ParseBr(Instruction *&Inst, PerFunctionState &PFS) {
LocTy Loc, Loc2;
add enough support for indirect branch for the feature test to pass (assembler,asmprinter, bc reader+writer) and document it. Codegen currently aborts on it. llvm-svn: 85274
2009-10-28 03:13:16 +08:00
Value *Op0;
BasicBlock *Op1, *Op2;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ParseTypeAndValue(Op0, Loc, PFS)) return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (BasicBlock *BB = dyn_cast<BasicBlock>(Op0)) {
Inst = BranchInst::Create(BB);
return false;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
if (Op0->getType() != Type::getInt1Ty(Context))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(Loc, "branch condition must have 'i1' type");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ParseToken(lltok::comma, "expected ',' after branch condition") ||
add enough support for indirect branch for the feature test to pass (assembler,asmprinter, bc reader+writer) and document it. Codegen currently aborts on it. llvm-svn: 85274
2009-10-28 03:13:16 +08:00
ParseTypeAndBasicBlock(Op1, Loc, PFS) ||
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ParseToken(lltok::comma, "expected ',' after true destination") ||
add enough support for indirect branch for the feature test to pass (assembler,asmprinter, bc reader+writer) and document it. Codegen currently aborts on it. llvm-svn: 85274
2009-10-28 03:13:16 +08:00
ParseTypeAndBasicBlock(Op2, Loc2, PFS))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
add enough support for indirect branch for the feature test to pass (assembler,asmprinter, bc reader+writer) and document it. Codegen currently aborts on it. llvm-svn: 85274
2009-10-28 03:13:16 +08:00
Inst = BranchInst::Create(Op1, Op2, Op0);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
}
/// ParseSwitch
/// Instruction
/// ::= 'switch' TypeAndValue ',' TypeAndValue '[' JumpTable ']'
/// JumpTable
/// ::= (TypeAndValue ',' TypeAndValue)*
bool LLParser::ParseSwitch(Instruction *&Inst, PerFunctionState &PFS) {
LocTy CondLoc, BBLoc;
add enough support for indirect branch for the feature test to pass (assembler,asmprinter, bc reader+writer) and document it. Codegen currently aborts on it. llvm-svn: 85274
2009-10-28 03:13:16 +08:00
Value *Cond;
BasicBlock *DefaultBB;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ParseTypeAndValue(Cond, CondLoc, PFS) ||
ParseToken(lltok::comma, "expected ',' after switch condition") ||
add enough support for indirect branch for the feature test to pass (assembler,asmprinter, bc reader+writer) and document it. Codegen currently aborts on it. llvm-svn: 85274
2009-10-28 03:13:16 +08:00
ParseTypeAndBasicBlock(DefaultBB, BBLoc, PFS) ||
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ParseToken(lltok::lsquare, "expected '[' with switch table"))
return true;
There are two ways of checking for a given type, for example isa<PointerType>(T) and T->isPointerTy(). Convert most instances of the first form to the second form. Requested by Chris. llvm-svn: 96344
2010-02-16 19:11:14 +08:00
if (!Cond->getType()->isIntegerTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(CondLoc, "switch condition must have integer type");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Parse the jump table pairs.
SmallPtrSet<Value*, 32> SeenCases;
SmallVector<std::pair<ConstantInt*, BasicBlock*>, 32> Table;
while (Lex.getKind() != lltok::rsquare) {
add enough support for indirect branch for the feature test to pass (assembler,asmprinter, bc reader+writer) and document it. Codegen currently aborts on it. llvm-svn: 85274
2009-10-28 03:13:16 +08:00
Value *Constant;
BasicBlock *DestBB;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ParseTypeAndValue(Constant, CondLoc, PFS) ||
ParseToken(lltok::comma, "expected ',' after case value") ||
add enough support for indirect branch for the feature test to pass (assembler,asmprinter, bc reader+writer) and document it. Codegen currently aborts on it. llvm-svn: 85274
2009-10-28 03:13:16 +08:00
ParseTypeAndBasicBlock(DestBB, PFS))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return true;
add enough support for indirect branch for the feature test to pass (assembler,asmprinter, bc reader+writer) and document it. Codegen currently aborts on it. llvm-svn: 85274
2009-10-28 03:13:16 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (!SeenCases.insert(Constant))
return Error(CondLoc, "duplicate case value in switch");
if (!isa<ConstantInt>(Constant))
return Error(CondLoc, "case value is not a constant integer");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
add enough support for indirect branch for the feature test to pass (assembler,asmprinter, bc reader+writer) and document it. Codegen currently aborts on it. llvm-svn: 85274
2009-10-28 03:13:16 +08:00
Table.push_back(std::make_pair(cast<ConstantInt>(Constant), DestBB));
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Lex.Lex(); // Eat the ']'.
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
add enough support for indirect branch for the feature test to pass (assembler,asmprinter, bc reader+writer) and document it. Codegen currently aborts on it. llvm-svn: 85274
2009-10-28 03:13:16 +08:00
SwitchInst *SI = SwitchInst::Create(Cond, DefaultBB, Table.size());
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
for (unsigned i = 0, e = Table.size(); i != e; ++i)
SI->addCase(Table[i].first, Table[i].second);
Inst = SI;
return false;
}
rename indbr -> indirectbr to appease the residents of #llvm. llvm-svn: 85351
2009-10-28 08:19:10 +08:00
/// ParseIndirectBr
add enough support for indirect branch for the feature test to pass (assembler,asmprinter, bc reader+writer) and document it. Codegen currently aborts on it. llvm-svn: 85274
2009-10-28 03:13:16 +08:00
/// Instruction
rename indbr -> indirectbr to appease the residents of #llvm. llvm-svn: 85351
2009-10-28 08:19:10 +08:00
/// ::= 'indirectbr' TypeAndValue ',' '[' LabelList ']'
bool LLParser::ParseIndirectBr(Instruction *&Inst, PerFunctionState &PFS) {
add enough support for indirect branch for the feature test to pass (assembler,asmprinter, bc reader+writer) and document it. Codegen currently aborts on it. llvm-svn: 85274
2009-10-28 03:13:16 +08:00
LocTy AddrLoc;
Value *Address;
if (ParseTypeAndValue(Address, AddrLoc, PFS) ||
rename indbr -> indirectbr to appease the residents of #llvm. llvm-svn: 85351
2009-10-28 08:19:10 +08:00
ParseToken(lltok::comma, "expected ',' after indirectbr address") ||
ParseToken(lltok::lsquare, "expected '[' with indirectbr"))
add enough support for indirect branch for the feature test to pass (assembler,asmprinter, bc reader+writer) and document it. Codegen currently aborts on it. llvm-svn: 85274
2009-10-28 03:13:16 +08:00
return true;
There are two ways of checking for a given type, for example isa<PointerType>(T) and T->isPointerTy(). Convert most instances of the first form to the second form. Requested by Chris. llvm-svn: 96344
2010-02-16 19:11:14 +08:00
if (!Address->getType()->isPointerTy())
rename indbr -> indirectbr to appease the residents of #llvm. llvm-svn: 85351
2009-10-28 08:19:10 +08:00
return Error(AddrLoc, "indirectbr address must have pointer type");
add enough support for indirect branch for the feature test to pass (assembler,asmprinter, bc reader+writer) and document it. Codegen currently aborts on it. llvm-svn: 85274
2009-10-28 03:13:16 +08:00
// Parse the destination list.
SmallVector<BasicBlock*, 16> DestList;
if (Lex.getKind() != lltok::rsquare) {
BasicBlock *DestBB;
if (ParseTypeAndBasicBlock(DestBB, PFS))
return true;
DestList.push_back(DestBB);
while (EatIfPresent(lltok::comma)) {
if (ParseTypeAndBasicBlock(DestBB, PFS))
return true;
DestList.push_back(DestBB);
}
}
if (ParseToken(lltok::rsquare, "expected ']' at end of block list"))
return true;
rename indbr -> indirectbr to appease the residents of #llvm. llvm-svn: 85351
2009-10-28 08:19:10 +08:00
IndirectBrInst *IBI = IndirectBrInst::Create(Address, DestList.size());
add enough support for indirect branch for the feature test to pass (assembler,asmprinter, bc reader+writer) and document it. Codegen currently aborts on it. llvm-svn: 85274
2009-10-28 03:13:16 +08:00
for (unsigned i = 0, e = DestList.size(); i != e; ++i)
IBI->addDestination(DestList[i]);
Inst = IBI;
return false;
}
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
/// ParseInvoke
/// ::= 'invoke' OptionalCallingConv OptionalAttrs Type Value ParamList
/// OptionalAttrs 'to' TypeAndValue 'unwind' TypeAndValue
bool LLParser::ParseInvoke(Instruction *&Inst, PerFunctionState &PFS) {
LocTy CallLoc = Lex.getLoc();
Retype from unsigned to CallingConv::ID accordingly. Approved by Bob Wilson. llvm-svn: 80773
2009-09-02 16:44:58 +08:00
unsigned RetAttrs, FnAttrs;
CallingConv::ID CC;
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
PATypeHolder RetType(Type::getVoidTy(Context));
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
LocTy RetTypeLoc;
ValID CalleeID;
SmallVector<ParamInfo, 16> ArgList;
add enough support for indirect branch for the feature test to pass (assembler,asmprinter, bc reader+writer) and document it. Codegen currently aborts on it. llvm-svn: 85274
2009-10-28 03:13:16 +08:00
BasicBlock *NormalBB, *UnwindBB;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ParseOptionalCallingConv(CC) ||
ParseOptionalAttrs(RetAttrs, 1) ||
Fix two classes of bugs. First: validate an invariant so that the asmparser rejects a bad construct instead of the verifier. Before: llvm-as: assembly parsed, but does not verify as correct! Invalid struct return type! i64 (%struct.Type*, %struct.Type*)* @foo after: llvm-as: t.ll:5:8: functions with 'sret' argument must return void define i64 @foo(%struct.Type* noalias nocapture sret %agg.result, %struct.Type* nocapture byval %t) nounwind { ^ Second, check that void is only used where allowed (in function return types) not in arbitrary places, fixing PR3747 - Crash in llvm-as with void field in struct. We now reject that example with: $ llvm-as t.ll llvm-as: t.ll:1:12: struct element can not have void type %x = type {void} ^ llvm-svn: 66394
2009-03-09 12:49:14 +08:00
ParseType(RetType, RetTypeLoc, true /*void allowed*/) ||
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ParseValID(CalleeID) ||
ParseParameterList(ArgList, PFS) ||
ParseOptionalAttrs(FnAttrs, 2) ||
ParseToken(lltok::kw_to, "expected 'to' in invoke") ||
add enough support for indirect branch for the feature test to pass (assembler,asmprinter, bc reader+writer) and document it. Codegen currently aborts on it. llvm-svn: 85274
2009-10-28 03:13:16 +08:00
ParseTypeAndBasicBlock(NormalBB, PFS) ||
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ParseToken(lltok::kw_unwind, "expected 'unwind' in invoke") ||
add enough support for indirect branch for the feature test to pass (assembler,asmprinter, bc reader+writer) and document it. Codegen currently aborts on it. llvm-svn: 85274
2009-10-28 03:13:16 +08:00
ParseTypeAndBasicBlock(UnwindBB, PFS))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// If RetType is a non-function pointer type, then this is the short syntax
// for the call, which means that RetType is just the return type. Infer the
// rest of the function argument types from the arguments that are present.
const PointerType *PFTy = 0;
const FunctionType *Ty = 0;
if (!(PFTy = dyn_cast<PointerType>(RetType)) ||
!(Ty = dyn_cast<FunctionType>(PFTy->getElementType()))) {
// Pull out the types of all of the arguments...
std::vector<const Type*> ParamTypes;
for (unsigned i = 0, e = ArgList.size(); i != e; ++i)
ParamTypes.push_back(ArgList[i].V->getType());
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (!FunctionType::isValidReturnType(RetType))
return Error(RetTypeLoc, "Invalid result type for LLVM function");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Move types back to the 2.5 API. llvm-svn: 77516
2009-07-30 06:17:13 +08:00
Ty = FunctionType::get(RetType, ParamTypes, false);
PFTy = PointerType::getUnqual(Ty);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Look up the callee.
Value *Callee;
Consolidate ConvertGlobalValIDToValue, ConvertGlobalOrMetadataValIDToValue, and ConvertValIDToValue into a more powerful ConvertValIDToValue() that does all three's work llvm-svn: 93197
2010-01-12 06:31:58 +08:00
if (ConvertValIDToValue(PFTy, CalleeID, Callee, &PFS)) return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// FIXME: In LLVM 3.0, stop accepting zext, sext and inreg as optional
// function attributes.
unsigned ObsoleteFuncAttrs = Attribute::ZExt|Attribute::SExt|Attribute::InReg;
if (FnAttrs & ObsoleteFuncAttrs) {
RetAttrs |= FnAttrs & ObsoleteFuncAttrs;
FnAttrs &= ~ObsoleteFuncAttrs;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Set up the Attributes for the function.
SmallVector<AttributeWithIndex, 8> Attrs;
if (RetAttrs != Attribute::None)
Attrs.push_back(AttributeWithIndex::get(0, RetAttrs));
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
SmallVector<Value*, 8> Args;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Loop through FunctionType's arguments and ensure they are specified
// correctly. Also, gather any parameter attributes.
FunctionType::param_iterator I = Ty->param_begin();
FunctionType::param_iterator E = Ty->param_end();
for (unsigned i = 0, e = ArgList.size(); i != e; ++i) {
const Type *ExpectedTy = 0;
if (I != E) {
ExpectedTy = *I++;
} else if (!Ty->isVarArg()) {
return Error(ArgList[i].Loc, "too many arguments specified");
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ExpectedTy && ExpectedTy != ArgList[i].V->getType())
return Error(ArgList[i].Loc, "argument is not of expected type '" +
ExpectedTy->getDescription() + "'");
Args.push_back(ArgList[i].V);
if (ArgList[i].Attrs != Attribute::None)
Attrs.push_back(AttributeWithIndex::get(i+1, ArgList[i].Attrs));
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (I != E)
return Error(CallLoc, "not enough parameters specified for call");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (FnAttrs != Attribute::None)
Attrs.push_back(AttributeWithIndex::get(~0, FnAttrs));
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Finish off the Attributes and check them
AttrListPtr PAL = AttrListPtr::get(Attrs.begin(), Attrs.end());
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
add enough support for indirect branch for the feature test to pass (assembler,asmprinter, bc reader+writer) and document it. Codegen currently aborts on it. llvm-svn: 85274
2009-10-28 03:13:16 +08:00
InvokeInst *II = InvokeInst::Create(Callee, NormalBB, UnwindBB,
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Args.begin(), Args.end());
II->setCallingConv(CC);
II->setAttributes(PAL);
Inst = II;
return false;
}
//===----------------------------------------------------------------------===//
// Binary Operators.
//===----------------------------------------------------------------------===//
/// ParseArithmetic
Fix PR3281:crash08.ll with this diagnostic: llvm-as: crash08.ll:3:15: invalid operand type for instruction "qp" = sdiv fp128 0x1, %30 ^ llvm-svn: 61684
2009-01-05 16:24:46 +08:00
/// ::= ArithmeticOps TypeAndValue ',' Value
///
/// If OperandType is 0, then any FP or integer operand is allowed. If it is 1,
/// then any integer operand is allowed, if it is 2, any fp operand is allowed.
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
bool LLParser::ParseArithmetic(Instruction *&Inst, PerFunctionState &PFS,
Fix PR3281:crash08.ll with this diagnostic: llvm-as: crash08.ll:3:15: invalid operand type for instruction "qp" = sdiv fp128 0x1, %30 ^ llvm-svn: 61684
2009-01-05 16:24:46 +08:00
unsigned Opc, unsigned OperandType) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
LocTy Loc; Value *LHS, *RHS;
if (ParseTypeAndValue(LHS, Loc, PFS) ||
ParseToken(lltok::comma, "expected ',' in arithmetic operation") ||
ParseValue(LHS->getType(), RHS, PFS))
return true;
Fix PR3281:crash08.ll with this diagnostic: llvm-as: crash08.ll:3:15: invalid operand type for instruction "qp" = sdiv fp128 0x1, %30 ^ llvm-svn: 61684
2009-01-05 16:24:46 +08:00
bool Valid;
switch (OperandType) {
llvm_unreachable->llvm_unreachable(0), LLVM_UNREACHABLE->llvm_unreachable. This adds location info for all llvm_unreachable calls (which is a macro now) in !NDEBUG builds. In NDEBUG builds location info and the message is off (it only prints "UREACHABLE executed"). llvm-svn: 75640
2009-07-15 00:55:14 +08:00
default: llvm_unreachable("Unknown operand type!");
Fix PR3281:crash08.ll with this diagnostic: llvm-as: crash08.ll:3:15: invalid operand type for instruction "qp" = sdiv fp128 0x1, %30 ^ llvm-svn: 61684
2009-01-05 16:24:46 +08:00
case 0: // int or FP.
Uniformize the names of type predicates: rather than having isFloatTy and isInteger, we now have isFloatTy and isIntegerTy. Requested by Chris! llvm-svn: 96223
2010-02-16 00:12:20 +08:00
Valid = LHS->getType()->isIntOrIntVectorTy() ||
LHS->getType()->isFPOrFPVectorTy();
Fix PR3281:crash08.ll with this diagnostic: llvm-as: crash08.ll:3:15: invalid operand type for instruction "qp" = sdiv fp128 0x1, %30 ^ llvm-svn: 61684
2009-01-05 16:24:46 +08:00
break;
Uniformize the names of type predicates: rather than having isFloatTy and isInteger, we now have isFloatTy and isIntegerTy. Requested by Chris! llvm-svn: 96223
2010-02-16 00:12:20 +08:00
case 1: Valid = LHS->getType()->isIntOrIntVectorTy(); break;
case 2: Valid = LHS->getType()->isFPOrFPVectorTy(); break;
Fix PR3281:crash08.ll with this diagnostic: llvm-as: crash08.ll:3:15: invalid operand type for instruction "qp" = sdiv fp128 0x1, %30 ^ llvm-svn: 61684
2009-01-05 16:24:46 +08:00
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Fix PR3281:crash08.ll with this diagnostic: llvm-as: crash08.ll:3:15: invalid operand type for instruction "qp" = sdiv fp128 0x1, %30 ^ llvm-svn: 61684
2009-01-05 16:24:46 +08:00
if (!Valid)
return Error(Loc, "invalid operand type for instruction");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Inst = BinaryOperator::Create((Instruction::BinaryOps)Opc, LHS, RHS);
return false;
}
/// ParseLogical
/// ::= ArithmeticOps TypeAndValue ',' Value {
bool LLParser::ParseLogical(Instruction *&Inst, PerFunctionState &PFS,
unsigned Opc) {
LocTy Loc; Value *LHS, *RHS;
if (ParseTypeAndValue(LHS, Loc, PFS) ||
ParseToken(lltok::comma, "expected ',' in logical operation") ||
ParseValue(LHS->getType(), RHS, PFS))
return true;
Uniformize the names of type predicates: rather than having isFloatTy and isInteger, we now have isFloatTy and isIntegerTy. Requested by Chris! llvm-svn: 96223
2010-02-16 00:12:20 +08:00
if (!LHS->getType()->isIntOrIntVectorTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(Loc,"instruction requires integer or integer vector operands");
Inst = BinaryOperator::Create((Instruction::BinaryOps)Opc, LHS, RHS);
return false;
}
/// ParseCompare
/// ::= 'icmp' IPredicates TypeAndValue ',' Value
/// ::= 'fcmp' FPredicates TypeAndValue ',' Value
bool LLParser::ParseCompare(Instruction *&Inst, PerFunctionState &PFS,
unsigned Opc) {
// Parse the integer/fp comparison predicate.
LocTy Loc;
unsigned Pred;
Value *LHS, *RHS;
if (ParseCmpPredicate(Pred, Opc) ||
ParseTypeAndValue(LHS, Loc, PFS) ||
ParseToken(lltok::comma, "expected ',' after compare value") ||
ParseValue(LHS->getType(), RHS, PFS))
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (Opc == Instruction::FCmp) {
Uniformize the names of type predicates: rather than having isFloatTy and isInteger, we now have isFloatTy and isIntegerTy. Requested by Chris! llvm-svn: 96223
2010-02-16 00:12:20 +08:00
if (!LHS->getType()->isFPOrFPVectorTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(Loc, "fcmp requires floating point operands");
Eliminate the unused Context argument on one of the ICmpInst and FCmpInst constructors. llvm-svn: 80049
2009-08-26 07:17:54 +08:00
Inst = new FCmpInst(CmpInst::Predicate(Pred), LHS, RHS);
Remove the vicmp and vfcmp instructions. Because we never had a release with these instructions, no autoupgrade or backwards compatibility support is provided. llvm-svn: 74991
2009-07-08 11:04:38 +08:00
} else {
assert(Opc == Instruction::ICmp && "Unknown opcode for CmpInst!");
Uniformize the names of type predicates: rather than having isFloatTy and isInteger, we now have isFloatTy and isIntegerTy. Requested by Chris! llvm-svn: 96223
2010-02-16 00:12:20 +08:00
if (!LHS->getType()->isIntOrIntVectorTy() &&
There are two ways of checking for a given type, for example isa<PointerType>(T) and T->isPointerTy(). Convert most instances of the first form to the second form. Requested by Chris. llvm-svn: 96344
2010-02-16 19:11:14 +08:00
!LHS->getType()->isPointerTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(Loc, "icmp requires integer operands");
Eliminate the unused Context argument on one of the ICmpInst and FCmpInst constructors. llvm-svn: 80049
2009-08-26 07:17:54 +08:00
Inst = new ICmpInst(CmpInst::Predicate(Pred), LHS, RHS);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
return false;
}
//===----------------------------------------------------------------------===//
// Other Instructions.
//===----------------------------------------------------------------------===//
/// ParseCast
/// ::= CastOpc TypeAndValue 'to' Type
bool LLParser::ParseCast(Instruction *&Inst, PerFunctionState &PFS,
unsigned Opc) {
LocTy Loc; Value *Op;
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
PATypeHolder DestTy(Type::getVoidTy(Context));
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ParseTypeAndValue(Op, Loc, PFS) ||
ParseToken(lltok::kw_to, "expected 'to' after cast value") ||
ParseType(DestTy))
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Fix a pretty awesome bug that only happened in a strange case with anonymous types. This was reading the uint for the keyword after the token was advanced. llvm-svn: 65743
2009-03-01 08:53:13 +08:00
if (!CastInst::castIsValid((Instruction::CastOps)Opc, Op, DestTy)) {
CastInst::castIsValid((Instruction::CastOps)Opc, Op, DestTy);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(Loc, "invalid cast opcode for cast from '" +
Op->getType()->getDescription() + "' to '" +
DestTy->getDescription() + "'");
Fix a pretty awesome bug that only happened in a strange case with anonymous types. This was reading the uint for the keyword after the token was advanced. llvm-svn: 65743
2009-03-01 08:53:13 +08:00
}
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Inst = CastInst::Create((Instruction::CastOps)Opc, Op, DestTy);
return false;
}
/// ParseSelect
/// ::= 'select' TypeAndValue ',' TypeAndValue ',' TypeAndValue
bool LLParser::ParseSelect(Instruction *&Inst, PerFunctionState &PFS) {
LocTy Loc;
Value *Op0, *Op1, *Op2;
if (ParseTypeAndValue(Op0, Loc, PFS) ||
ParseToken(lltok::comma, "expected ',' after select condition") ||
ParseTypeAndValue(Op1, PFS) ||
ParseToken(lltok::comma, "expected ',' after select value") ||
ParseTypeAndValue(Op2, PFS))
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (const char *Reason = SelectInst::areInvalidOperands(Op0, Op1, Op2))
return Error(Loc, Reason);
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Inst = SelectInst::Create(Op0, Op1, Op2);
return false;
}
reject PR3281:crash07.ll with: llvm-as: crash07.ll:2:32: va_arg requires operand with first class type %y = va_arg [52 x <{}>] %43, double (...) sspreq ^ llvm-svn: 61683
2009-01-05 16:18:44 +08:00
/// ParseVA_Arg
/// ::= 'va_arg' TypeAndValue ',' Type
bool LLParser::ParseVA_Arg(Instruction *&Inst, PerFunctionState &PFS) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Value *Op;
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
PATypeHolder EltTy(Type::getVoidTy(Context));
reject PR3281:crash07.ll with: llvm-as: crash07.ll:2:32: va_arg requires operand with first class type %y = va_arg [52 x <{}>] %43, double (...) sspreq ^ llvm-svn: 61683
2009-01-05 16:18:44 +08:00
LocTy TypeLoc;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ParseTypeAndValue(Op, PFS) ||
ParseToken(lltok::comma, "expected ',' after vaarg operand") ||
reject PR3281:crash07.ll with: llvm-as: crash07.ll:2:32: va_arg requires operand with first class type %y = va_arg [52 x <{}>] %43, double (...) sspreq ^ llvm-svn: 61683
2009-01-05 16:18:44 +08:00
ParseType(EltTy, TypeLoc))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
reject PR3281:crash07.ll with: llvm-as: crash07.ll:2:32: va_arg requires operand with first class type %y = va_arg [52 x <{}>] %43, double (...) sspreq ^ llvm-svn: 61683
2009-01-05 16:18:44 +08:00
if (!EltTy->isFirstClassType())
return Error(TypeLoc, "va_arg requires operand with first class type");
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Inst = new VAArgInst(Op, EltTy);
return false;
}
/// ParseExtractElement
/// ::= 'extractelement' TypeAndValue ',' TypeAndValue
bool LLParser::ParseExtractElement(Instruction *&Inst, PerFunctionState &PFS) {
LocTy Loc;
Value *Op0, *Op1;
if (ParseTypeAndValue(Op0, Loc, PFS) ||
ParseToken(lltok::comma, "expected ',' after extract value") ||
ParseTypeAndValue(Op1, PFS))
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (!ExtractElementInst::isValidOperands(Op0, Op1))
return Error(Loc, "invalid extractelement operands");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Move ExtractElementInst to ::Create instead of new. Update all uses. llvm-svn: 77044
2009-07-25 10:28:41 +08:00
Inst = ExtractElementInst::Create(Op0, Op1);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
}
/// ParseInsertElement
/// ::= 'insertelement' TypeAndValue ',' TypeAndValue ',' TypeAndValue
bool LLParser::ParseInsertElement(Instruction *&Inst, PerFunctionState &PFS) {
LocTy Loc;
Value *Op0, *Op1, *Op2;
if (ParseTypeAndValue(Op0, Loc, PFS) ||
ParseToken(lltok::comma, "expected ',' after insertelement value") ||
ParseTypeAndValue(Op1, PFS) ||
ParseToken(lltok::comma, "expected ',' after insertelement value") ||
ParseTypeAndValue(Op2, PFS))
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (!InsertElementInst::isValidOperands(Op0, Op1, Op2))
Fix error message for correct opcode. llvm-svn: 76829
2009-07-23 09:01:32 +08:00
return Error(Loc, "invalid insertelement operands");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Inst = InsertElementInst::Create(Op0, Op1, Op2);
return false;
}
/// ParseShuffleVector
/// ::= 'shufflevector' TypeAndValue ',' TypeAndValue ',' TypeAndValue
bool LLParser::ParseShuffleVector(Instruction *&Inst, PerFunctionState &PFS) {
LocTy Loc;
Value *Op0, *Op1, *Op2;
if (ParseTypeAndValue(Op0, Loc, PFS) ||
ParseToken(lltok::comma, "expected ',' after shuffle mask") ||
ParseTypeAndValue(Op1, PFS) ||
ParseToken(lltok::comma, "expected ',' after shuffle value") ||
ParseTypeAndValue(Op2, PFS))
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (!ShuffleVectorInst::isValidOperands(Op0, Op1, Op2))
return Error(Loc, "invalid extractelement operands");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Inst = new ShuffleVectorInst(Op0, Op1, Op2);
return false;
}
/// ParsePHI
remove some nonascii weird stuff llvm-svn: 84410
2009-10-18 13:27:44 +08:00
/// ::= 'phi' Type '[' Value ',' Value ']' (',' '[' Value ',' Value ']')*
convert 4 more instructions over. llvm-svn: 92299
2009-12-30 13:27:33 +08:00
int LLParser::ParsePHI(Instruction *&Inst, PerFunctionState &PFS) {
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
PATypeHolder Ty(Type::getVoidTy(Context));
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Value *Op0, *Op1;
LocTy TypeLoc = Lex.getLoc();
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ParseType(Ty) ||
ParseToken(lltok::lsquare, "expected '[' in phi value list") ||
ParseValue(Ty, Op0, PFS) ||
ParseToken(lltok::comma, "expected ',' after insertelement value") ||
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
ParseValue(Type::getLabelTy(Context), Op1, PFS) ||
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ParseToken(lltok::rsquare, "expected ']' in phi value list"))
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
convert 4 more instructions over. llvm-svn: 92299
2009-12-30 13:27:33 +08:00
bool AteExtraComma = false;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
SmallVector<std::pair<Value*, BasicBlock*>, 16> PHIVals;
while (1) {
PHIVals.push_back(std::make_pair(Op0, cast<BasicBlock>(Op1)));
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
if (!EatIfPresent(lltok::comma))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
break;
convert 4 more instructions over. llvm-svn: 92299
2009-12-30 13:27:33 +08:00
if (Lex.getKind() == lltok::MetadataVar) {
AteExtraComma = true;
Parse PHI instruction with attached metadata. llvm-svn: 84264
2009-10-17 02:45:49 +08:00
break;
convert 4 more instructions over. llvm-svn: 92299
2009-12-30 13:27:33 +08:00
}
Parse PHI instruction with attached metadata. llvm-svn: 84264
2009-10-17 02:45:49 +08:00
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
if (ParseToken(lltok::lsquare, "expected '[' in phi value list") ||
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ParseValue(Ty, Op0, PFS) ||
ParseToken(lltok::comma, "expected ',' after insertelement value") ||
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
ParseValue(Type::getLabelTy(Context), Op1, PFS) ||
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ParseToken(lltok::rsquare, "expected ']' in phi value list"))
return true;
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (!Ty->isFirstClassType())
return Error(TypeLoc, "phi node must have first class type");
PHINode *PN = PHINode::Create(Ty);
PN->reserveOperandSpace(PHIVals.size());
for (unsigned i = 0, e = PHIVals.size(); i != e; ++i)
PN->addIncoming(PHIVals[i].first, PHIVals[i].second);
Inst = PN;
convert 4 more instructions over. llvm-svn: 92299
2009-12-30 13:27:33 +08:00
return AteExtraComma ? InstExtraComma : InstNormal;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
/// ParseCall
/// ::= 'tail'? 'call' OptionalCallingConv OptionalAttrs Type Value
/// ParameterList OptionalAttrs
bool LLParser::ParseCall(Instruction *&Inst, PerFunctionState &PFS,
bool isTail) {
Retype from unsigned to CallingConv::ID accordingly. Approved by Bob Wilson. llvm-svn: 80773
2009-09-02 16:44:58 +08:00
unsigned RetAttrs, FnAttrs;
CallingConv::ID CC;
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
PATypeHolder RetType(Type::getVoidTy(Context));
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
LocTy RetTypeLoc;
ValID CalleeID;
SmallVector<ParamInfo, 16> ArgList;
LocTy CallLoc = Lex.getLoc();
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if ((isTail && ParseToken(lltok::kw_call, "expected 'tail call'")) ||
ParseOptionalCallingConv(CC) ||
ParseOptionalAttrs(RetAttrs, 1) ||
Fix two classes of bugs. First: validate an invariant so that the asmparser rejects a bad construct instead of the verifier. Before: llvm-as: assembly parsed, but does not verify as correct! Invalid struct return type! i64 (%struct.Type*, %struct.Type*)* @foo after: llvm-as: t.ll:5:8: functions with 'sret' argument must return void define i64 @foo(%struct.Type* noalias nocapture sret %agg.result, %struct.Type* nocapture byval %t) nounwind { ^ Second, check that void is only used where allowed (in function return types) not in arbitrary places, fixing PR3747 - Crash in llvm-as with void field in struct. We now reject that example with: $ llvm-as t.ll llvm-as: t.ll:1:12: struct element can not have void type %x = type {void} ^ llvm-svn: 66394
2009-03-09 12:49:14 +08:00
ParseType(RetType, RetTypeLoc, true /*void allowed*/) ||
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
ParseValID(CalleeID) ||
ParseParameterList(ArgList, PFS) ||
ParseOptionalAttrs(FnAttrs, 2))
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// If RetType is a non-function pointer type, then this is the short syntax
// for the call, which means that RetType is just the return type. Infer the
// rest of the function argument types from the arguments that are present.
const PointerType *PFTy = 0;
const FunctionType *Ty = 0;
if (!(PFTy = dyn_cast<PointerType>(RetType)) ||
!(Ty = dyn_cast<FunctionType>(PFTy->getElementType()))) {
// Pull out the types of all of the arguments...
std::vector<const Type*> ParamTypes;
for (unsigned i = 0, e = ArgList.size(); i != e; ++i)
ParamTypes.push_back(ArgList[i].V->getType());
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (!FunctionType::isValidReturnType(RetType))
return Error(RetTypeLoc, "Invalid result type for LLVM function");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Move types back to the 2.5 API. llvm-svn: 77516
2009-07-30 06:17:13 +08:00
Ty = FunctionType::get(RetType, ParamTypes, false);
PFTy = PointerType::getUnqual(Ty);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Look up the callee.
Value *Callee;
Consolidate ConvertGlobalValIDToValue, ConvertGlobalOrMetadataValIDToValue, and ConvertValIDToValue into a more powerful ConvertValIDToValue() that does all three's work llvm-svn: 93197
2010-01-12 06:31:58 +08:00
if (ConvertValIDToValue(PFTy, CalleeID, Callee, &PFS)) return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// FIXME: In LLVM 3.0, stop accepting zext, sext and inreg as optional
// function attributes.
unsigned ObsoleteFuncAttrs = Attribute::ZExt|Attribute::SExt|Attribute::InReg;
if (FnAttrs & ObsoleteFuncAttrs) {
RetAttrs |= FnAttrs & ObsoleteFuncAttrs;
FnAttrs &= ~ObsoleteFuncAttrs;
}
// Set up the Attributes for the function.
SmallVector<AttributeWithIndex, 8> Attrs;
if (RetAttrs != Attribute::None)
Attrs.push_back(AttributeWithIndex::get(0, RetAttrs));
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
SmallVector<Value*, 8> Args;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Loop through FunctionType's arguments and ensure they are specified
// correctly. Also, gather any parameter attributes.
FunctionType::param_iterator I = Ty->param_begin();
FunctionType::param_iterator E = Ty->param_end();
for (unsigned i = 0, e = ArgList.size(); i != e; ++i) {
const Type *ExpectedTy = 0;
if (I != E) {
ExpectedTy = *I++;
} else if (!Ty->isVarArg()) {
return Error(ArgList[i].Loc, "too many arguments specified");
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ExpectedTy && ExpectedTy != ArgList[i].V->getType())
return Error(ArgList[i].Loc, "argument is not of expected type '" +
ExpectedTy->getDescription() + "'");
Args.push_back(ArgList[i].V);
if (ArgList[i].Attrs != Attribute::None)
Attrs.push_back(AttributeWithIndex::get(i+1, ArgList[i].Attrs));
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (I != E)
return Error(CallLoc, "not enough parameters specified for call");
if (FnAttrs != Attribute::None)
Attrs.push_back(AttributeWithIndex::get(~0, FnAttrs));
// Finish off the Attributes and check them
AttrListPtr PAL = AttrListPtr::get(Attrs.begin(), Attrs.end());
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
CallInst *CI = CallInst::Create(Callee, Args.begin(), Args.end());
CI->setTailCall(isTail);
CI->setCallingConv(CC);
CI->setAttributes(PAL);
Inst = CI;
return false;
}
//===----------------------------------------------------------------------===//
// Memory Instructions.
//===----------------------------------------------------------------------===//
/// ParseAlloc
Fix parsing of optional metadata for 'load', 'store' and 'alloc' instructions. llvm-svn: 82175
2009-09-18 07:04:48 +08:00
/// ::= 'malloc' Type (',' TypeAndValue)? (',' OptionalInfo)?
/// ::= 'alloca' Type (',' TypeAndValue)? (',' OptionalInfo)?
reimplement ParseOptionalInfo as ParseOptionalCommaAlign, correctly handle the comma case for metadata. llvm-svn: 92301
2009-12-30 13:44:30 +08:00
int LLParser::ParseAlloc(Instruction *&Inst, PerFunctionState &PFS,
BasicBlock* BB, bool isAlloca) {
Push LLVMContexts through the IntegerType APIs. llvm-svn: 78948
2009-08-14 05:58:54 +08:00
PATypeHolder Ty(Type::getVoidTy(Context));
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Value *Size = 0;
switch the .ll parser to use SourceMgr. llvm-svn: 74735
2009-07-03 07:08:13 +08:00
LocTy SizeLoc;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
unsigned Alignment = 0;
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
if (ParseType(Ty)) return true;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
reimplement ParseOptionalInfo as ParseOptionalCommaAlign, correctly handle the comma case for metadata. llvm-svn: 92301
2009-12-30 13:44:30 +08:00
bool AteExtraComma = false;
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
if (EatIfPresent(lltok::comma)) {
reimplement ParseOptionalInfo as ParseOptionalCommaAlign, correctly handle the comma case for metadata. llvm-svn: 92301
2009-12-30 13:44:30 +08:00
if (Lex.getKind() == lltok::kw_align) {
if (ParseOptionalAlignment(Alignment)) return true;
} else if (Lex.getKind() == lltok::MetadataVar) {
AteExtraComma = true;
Fix parsing of optional metadata for 'load', 'store' and 'alloc' instructions. llvm-svn: 82175
2009-09-18 07:04:48 +08:00
} else {
reimplement ParseOptionalInfo as ParseOptionalCommaAlign, correctly handle the comma case for metadata. llvm-svn: 92301
2009-12-30 13:44:30 +08:00
if (ParseTypeAndValue(Size, SizeLoc, PFS) ||
ParseOptionalCommaAlign(Alignment, AteExtraComma))
return true;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
}
Uniformize the names of type predicates: rather than having isFloatTy and isInteger, we now have isFloatTy and isIntegerTy. Requested by Chris! llvm-svn: 96223
2010-02-16 00:12:20 +08:00
if (Size && !Size->getType()->isIntegerTy(32))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(SizeLoc, "element count must be i32");
Make changes to rev 84292 as requested by Chris Lattner. Most changes are cleanup, but there is 1 correctness fix: I fixed InstCombine so that the icmp is removed only if the malloc call is removed (which requires explicit removal because the Worklist won't DCE any calls since they can have side-effects). llvm-svn: 84772
2009-10-22 03:11:40 +08:00
if (isAlloca) {
Revert yesterday's change by removing the LLVMContext parameter to AllocaInst and MallocInst. llvm-svn: 75863
2009-07-16 07:53:25 +08:00
Inst = new AllocaInst(Ty, Size, Alignment);
reimplement ParseOptionalInfo as ParseOptionalCommaAlign, correctly handle the comma case for metadata. llvm-svn: 92301
2009-12-30 13:44:30 +08:00
return AteExtraComma ? InstExtraComma : InstNormal;
Autoupgrade malloc insts to malloc calls. Update testcases that rely on malloc insts being present. Also prematurely remove MallocInst handling from IndMemRemoval and RaiseAllocations to help pass tests in this incremental step. llvm-svn: 84292
2009-10-17 08:00:19 +08:00
}
Make changes to rev 84292 as requested by Chris Lattner. Most changes are cleanup, but there is 1 correctness fix: I fixed InstCombine so that the icmp is removed only if the malloc call is removed (which requires explicit removal because the Worklist won't DCE any calls since they can have side-effects). llvm-svn: 84772
2009-10-22 03:11:40 +08:00
// Autoupgrade old malloc instruction to malloc call.
// FIXME: Remove in LLVM 3.0.
const Type *IntPtrTy = Type::getInt32Ty(Context);
Re-commit r86077 now that r86290 fixes the 179.art and 175.vpr ARM regressions. Here is the original commit message: This commit updates malloc optimizations to operate on malloc calls that have constant int size arguments. Update CreateMalloc so that its callers specify the size to allocate: MallocInst-autoupgrade users use non-TargetData-computed allocation sizes. Optimization uses use TargetData to compute the allocation size. Now that malloc calls can have constant sizes, update isArrayMallocHelper() to use TargetData to determine the size of the malloced type and the size of malloced arrays. Extend getMallocType() to support malloc calls that have non-bitcast uses. Update OptimizeGlobalAddressOfMalloc() to optimize malloc calls that have non-bitcast uses. The bitcast use of a malloc call has to be treated specially here because the uses of the bitcast need to be replaced and the bitcast needs to be erased (just like the malloc call) for OptimizeGlobalAddressOfMalloc() to work correctly. Update PerformHeapAllocSRoA() to optimize malloc calls that have non-bitcast uses. The bitcast use of the malloc is not handled specially here because ReplaceUsesOfMallocWithGlobal replaces through the bitcast use. Update OptimizeOnceStoredGlobal() to not care about the malloc calls' bitcast use. Update all globalopt malloc tests to not rely on autoupgraded-MallocInsts, but instead use explicit malloc calls with correct allocation sizes. llvm-svn: 86311
2009-11-07 08:16:28 +08:00
Constant *AllocSize = ConstantExpr::getSizeOf(Ty);
AllocSize = ConstantExpr::getTruncOrBitCast(AllocSize, IntPtrTy);
Make changes to rev 84292 as requested by Chris Lattner. Most changes are cleanup, but there is 1 correctness fix: I fixed InstCombine so that the icmp is removed only if the malloc call is removed (which requires explicit removal because the Worklist won't DCE any calls since they can have side-effects). llvm-svn: 84772
2009-10-22 03:11:40 +08:00
if (!MallocF)
// Prototype malloc as "void *(int32)".
// This function is renamed as "malloc" in ValidateEndOfModule().
Minor code cleanup. llvm-svn: 84919
2009-10-23 08:59:10 +08:00
MallocF = cast<Function>(
M->getOrInsertFunction("", Type::getInt8PtrTy(Context), IntPtrTy, NULL));
Re-commit r86077 now that r86290 fixes the 179.art and 175.vpr ARM regressions. Here is the original commit message: This commit updates malloc optimizations to operate on malloc calls that have constant int size arguments. Update CreateMalloc so that its callers specify the size to allocate: MallocInst-autoupgrade users use non-TargetData-computed allocation sizes. Optimization uses use TargetData to compute the allocation size. Now that malloc calls can have constant sizes, update isArrayMallocHelper() to use TargetData to determine the size of the malloced type and the size of malloced arrays. Extend getMallocType() to support malloc calls that have non-bitcast uses. Update OptimizeGlobalAddressOfMalloc() to optimize malloc calls that have non-bitcast uses. The bitcast use of a malloc call has to be treated specially here because the uses of the bitcast need to be replaced and the bitcast needs to be erased (just like the malloc call) for OptimizeGlobalAddressOfMalloc() to work correctly. Update PerformHeapAllocSRoA() to optimize malloc calls that have non-bitcast uses. The bitcast use of the malloc is not handled specially here because ReplaceUsesOfMallocWithGlobal replaces through the bitcast use. Update OptimizeOnceStoredGlobal() to not care about the malloc calls' bitcast use. Update all globalopt malloc tests to not rely on autoupgraded-MallocInsts, but instead use explicit malloc calls with correct allocation sizes. llvm-svn: 86311
2009-11-07 08:16:28 +08:00
Inst = CallInst::CreateMalloc(BB, IntPtrTy, Ty, AllocSize, Size, MallocF);
reimplement ParseOptionalInfo as ParseOptionalCommaAlign, correctly handle the comma case for metadata. llvm-svn: 92301
2009-12-30 13:44:30 +08:00
return AteExtraComma ? InstExtraComma : InstNormal;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
/// ParseFree
/// ::= 'free' TypeAndValue
Auto-upgrade free instructions to calls to the builtin free function. Update all analysis passes and transforms to treat free calls just like FreeInst. Remove RaiseAllocations and all its tests since FreeInst no longer needs to be raised. llvm-svn: 84987
2009-10-24 12:23:03 +08:00
bool LLParser::ParseFree(Instruction *&Inst, PerFunctionState &PFS,
BasicBlock* BB) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Value *Val; LocTy Loc;
if (ParseTypeAndValue(Val, Loc, PFS)) return true;
There are two ways of checking for a given type, for example isa<PointerType>(T) and T->isPointerTy(). Convert most instances of the first form to the second form. Requested by Chris. llvm-svn: 96344
2010-02-16 19:11:14 +08:00
if (!Val->getType()->isPointerTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(Loc, "operand to free must be a pointer");
Auto-upgrade free instructions to calls to the builtin free function. Update all analysis passes and transforms to treat free calls just like FreeInst. Remove RaiseAllocations and all its tests since FreeInst no longer needs to be raised. llvm-svn: 84987
2009-10-24 12:23:03 +08:00
Inst = CallInst::CreateFree(Val, BB);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return false;
}
/// ParseLoad
Fix parsing of optional metadata for 'load', 'store' and 'alloc' instructions. llvm-svn: 82175
2009-09-18 07:04:48 +08:00
/// ::= 'volatile'? 'load' TypeAndValue (',' OptionalInfo)?
reimplement ParseOptionalInfo as ParseOptionalCommaAlign, correctly handle the comma case for metadata. llvm-svn: 92301
2009-12-30 13:44:30 +08:00
int LLParser::ParseLoad(Instruction *&Inst, PerFunctionState &PFS,
bool isVolatile) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Value *Val; LocTy Loc;
Fix parsing of optional metadata for 'load', 'store' and 'alloc' instructions. llvm-svn: 82175
2009-09-18 07:04:48 +08:00
unsigned Alignment = 0;
reimplement ParseOptionalInfo as ParseOptionalCommaAlign, correctly handle the comma case for metadata. llvm-svn: 92301
2009-12-30 13:44:30 +08:00
bool AteExtraComma = false;
if (ParseTypeAndValue(Val, Loc, PFS) ||
ParseOptionalCommaAlign(Alignment, AteExtraComma))
return true;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
There are two ways of checking for a given type, for example isa<PointerType>(T) and T->isPointerTy(). Convert most instances of the first form to the second form. Requested by Chris. llvm-svn: 96344
2010-02-16 19:11:14 +08:00
if (!Val->getType()->isPointerTy() ||
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
!cast<PointerType>(Val->getType())->getElementType()->isFirstClassType())
return Error(Loc, "load operand must be a pointer to a first class type");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Inst = new LoadInst(Val, "", isVolatile, Alignment);
reimplement ParseOptionalInfo as ParseOptionalCommaAlign, correctly handle the comma case for metadata. llvm-svn: 92301
2009-12-30 13:44:30 +08:00
return AteExtraComma ? InstExtraComma : InstNormal;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
/// ParseStore
Fix old-style type names in comments. llvm-svn: 73362
2009-06-15 07:30:43 +08:00
/// ::= 'volatile'? 'store' TypeAndValue ',' TypeAndValue (',' 'align' i32)?
reimplement ParseOptionalInfo as ParseOptionalCommaAlign, correctly handle the comma case for metadata. llvm-svn: 92301
2009-12-30 13:44:30 +08:00
int LLParser::ParseStore(Instruction *&Inst, PerFunctionState &PFS,
bool isVolatile) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Value *Val, *Ptr; LocTy Loc, PtrLoc;
Fix parsing of optional metadata for 'load', 'store' and 'alloc' instructions. llvm-svn: 82175
2009-09-18 07:04:48 +08:00
unsigned Alignment = 0;
reimplement ParseOptionalInfo as ParseOptionalCommaAlign, correctly handle the comma case for metadata. llvm-svn: 92301
2009-12-30 13:44:30 +08:00
bool AteExtraComma = false;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ParseTypeAndValue(Val, Loc, PFS) ||
ParseToken(lltok::comma, "expected ',' after store operand") ||
reimplement ParseOptionalInfo as ParseOptionalCommaAlign, correctly handle the comma case for metadata. llvm-svn: 92301
2009-12-30 13:44:30 +08:00
ParseTypeAndValue(Ptr, PtrLoc, PFS) ||
ParseOptionalCommaAlign(Alignment, AteExtraComma))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return true;
Fix parsing of optional metadata for 'load', 'store' and 'alloc' instructions. llvm-svn: 82175
2009-09-18 07:04:48 +08:00
There are two ways of checking for a given type, for example isa<PointerType>(T) and T->isPointerTy(). Convert most instances of the first form to the second form. Requested by Chris. llvm-svn: 96344
2010-02-16 19:11:14 +08:00
if (!Ptr->getType()->isPointerTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(PtrLoc, "store operand must be a pointer");
if (!Val->getType()->isFirstClassType())
return Error(Loc, "store operand must be a first class value");
if (cast<PointerType>(Ptr->getType())->getElementType() != Val->getType())
return Error(Loc, "stored value and pointer type do not match");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Inst = new StoreInst(Val, Ptr, isVolatile, Alignment);
reimplement ParseOptionalInfo as ParseOptionalCommaAlign, correctly handle the comma case for metadata. llvm-svn: 92301
2009-12-30 13:44:30 +08:00
return AteExtraComma ? InstExtraComma : InstNormal;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
/// ParseGetResult
Fix old-style type names in comments. llvm-svn: 73362
2009-06-15 07:30:43 +08:00
/// ::= 'getresult' TypeAndValue ',' i32
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
/// FIXME: Remove support for getresult in LLVM 3.0
bool LLParser::ParseGetResult(Instruction *&Inst, PerFunctionState &PFS) {
Value *Val; LocTy ValLoc, EltLoc;
unsigned Element;
if (ParseTypeAndValue(Val, ValLoc, PFS) ||
ParseToken(lltok::comma, "expected ',' after getresult operand") ||
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
ParseUInt32(Element, EltLoc))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
There are two ways of checking for a given type, for example isa<PointerType>(T) and T->isPointerTy(). Convert most instances of the first form to the second form. Requested by Chris. llvm-svn: 96344
2010-02-16 19:11:14 +08:00
if (!Val->getType()->isStructTy() && !Val->getType()->isArrayTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(ValLoc, "getresult inst requires an aggregate operand");
if (!ExtractValueInst::getIndexedType(Val->getType(), Element))
return Error(EltLoc, "invalid getresult index for value");
Inst = ExtractValueInst::Create(Val, Element);
return false;
}
/// ParseGetElementPtr
Add a new keyword 'inbounds' for use with getelementptr. See the LangRef.html changes for details. llvm-svn: 77259
2009-07-28 05:53:46 +08:00
/// ::= 'getelementptr' 'inbounds'? TypeAndValue (',' TypeAndValue)*
convert 4 more instructions over. llvm-svn: 92299
2009-12-30 13:27:33 +08:00
int LLParser::ParseGetElementPtr(Instruction *&Inst, PerFunctionState &PFS) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Value *Ptr, *Val; LocTy Loc, EltLoc;
Add a new keyword 'inbounds' for use with getelementptr. See the LangRef.html changes for details. llvm-svn: 77259
2009-07-28 05:53:46 +08:00
Minor code simplification. llvm-svn: 77459
2009-07-29 23:58:36 +08:00
bool InBounds = EatIfPresent(lltok::kw_inbounds);
Add a new keyword 'inbounds' for use with getelementptr. See the LangRef.html changes for details. llvm-svn: 77259
2009-07-28 05:53:46 +08:00
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
if (ParseTypeAndValue(Ptr, Loc, PFS)) return true;
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
There are two ways of checking for a given type, for example isa<PointerType>(T) and T->isPointerTy(). Convert most instances of the first form to the second form. Requested by Chris. llvm-svn: 96344
2010-02-16 19:11:14 +08:00
if (!Ptr->getType()->isPointerTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(Loc, "base of getelementptr must be a pointer");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
SmallVector<Value*, 16> Indices;
convert 4 more instructions over. llvm-svn: 92299
2009-12-30 13:27:33 +08:00
bool AteExtraComma = false;
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
while (EatIfPresent(lltok::comma)) {
convert 4 more instructions over. llvm-svn: 92299
2009-12-30 13:27:33 +08:00
if (Lex.getKind() == lltok::MetadataVar) {
AteExtraComma = true;
Parse GEP with attached custom metadata. This happens during libprofile_rt.bca build. llvm-svn: 84002
2009-10-14 02:49:55 +08:00
break;
convert 4 more instructions over. llvm-svn: 92299
2009-12-30 13:27:33 +08:00
}
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
if (ParseTypeAndValue(Val, EltLoc, PFS)) return true;
There are two ways of checking for a given type, for example isa<PointerType>(T) and T->isPointerTy(). Convert most instances of the first form to the second form. Requested by Chris. llvm-svn: 96344
2010-02-16 19:11:14 +08:00
if (!Val->getType()->isIntegerTy())
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return Error(EltLoc, "getelementptr index must be an integer");
Indices.push_back(Val);
}
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (!GetElementPtrInst::getIndexedType(Ptr->getType(),
Indices.begin(), Indices.end()))
return Error(Loc, "invalid getelementptr indices");
Inst = GetElementPtrInst::Create(Ptr, Indices.begin(), Indices.end());
Add a new keyword 'inbounds' for use with getelementptr. See the LangRef.html changes for details. llvm-svn: 77259
2009-07-28 05:53:46 +08:00
if (InBounds)
Reappy r80998, now that the GlobalOpt bug that it exposed on MiniSAT is fixed. llvm-svn: 81172
2009-09-08 07:54:19 +08:00
cast<GetElementPtrInst>(Inst)->setIsInBounds(true);
convert 4 more instructions over. llvm-svn: 92299
2009-12-30 13:27:33 +08:00
return AteExtraComma ? InstExtraComma : InstNormal;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
/// ParseExtractValue
/// ::= 'extractvalue' TypeAndValue (',' uint32)+
convert 4 more instructions over. llvm-svn: 92299
2009-12-30 13:27:33 +08:00
int LLParser::ParseExtractValue(Instruction *&Inst, PerFunctionState &PFS) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Value *Val; LocTy Loc;
SmallVector<unsigned, 4> Indices;
convert 4 more instructions over. llvm-svn: 92299
2009-12-30 13:27:33 +08:00
bool AteExtraComma;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ParseTypeAndValue(Val, Loc, PFS) ||
convert 4 more instructions over. llvm-svn: 92299
2009-12-30 13:27:33 +08:00
ParseIndexList(Indices, AteExtraComma))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return true;
Add support for a union type in LLVM IR. Patch by Talin! llvm-svn: 96011
2010-02-13 04:49:41 +08:00
if (!Val->getType()->isAggregateType())
return Error(Loc, "extractvalue operand must be aggregate type");
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (!ExtractValueInst::getIndexedType(Val->getType(), Indices.begin(),
Indices.end()))
return Error(Loc, "invalid indices for extractvalue");
Inst = ExtractValueInst::Create(Val, Indices.begin(), Indices.end());
convert 4 more instructions over. llvm-svn: 92299
2009-12-30 13:27:33 +08:00
return AteExtraComma ? InstExtraComma : InstNormal;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
/// ParseInsertValue
/// ::= 'insertvalue' TypeAndValue ',' TypeAndValue (',' uint32)+
convert 4 more instructions over. llvm-svn: 92299
2009-12-30 13:27:33 +08:00
int LLParser::ParseInsertValue(Instruction *&Inst, PerFunctionState &PFS) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
Value *Val0, *Val1; LocTy Loc0, Loc1;
SmallVector<unsigned, 4> Indices;
convert 4 more instructions over. llvm-svn: 92299
2009-12-30 13:27:33 +08:00
bool AteExtraComma;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (ParseTypeAndValue(Val0, Loc0, PFS) ||
ParseToken(lltok::comma, "expected comma after insertvalue operand") ||
ParseTypeAndValue(Val1, Loc1, PFS) ||
convert 4 more instructions over. llvm-svn: 92299
2009-12-30 13:27:33 +08:00
ParseIndexList(Indices, AteExtraComma))
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
return true;
reimplement insertvalue/extractvalue metadata handling to not blindly accept invalid input. Actually add a testcase. llvm-svn: 92297
2009-12-30 13:14:00 +08:00
Add support for a union type in LLVM IR. Patch by Talin! llvm-svn: 96011
2010-02-13 04:49:41 +08:00
if (!Val0->getType()->isAggregateType())
return Error(Loc0, "insertvalue operand must be aggregate type");
Tabs -> spaces, and remove trailing whitespace. llvm-svn: 82355
2009-09-20 10:20:51 +08:00
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
if (!ExtractValueInst::getIndexedType(Val0->getType(), Indices.begin(),
Indices.end()))
return Error(Loc0, "invalid indices for insertvalue");
Inst = InsertValueInst::Create(Val0, Val1, Indices.begin(), Indices.end());
convert 4 more instructions over. llvm-svn: 92299
2009-12-30 13:27:33 +08:00
return AteExtraComma ? InstExtraComma : InstNormal;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
Add support for embedded metadata to LLVM. This introduces two new types of Constant, MDString and MDNode which can only be used by globals with a name that starts with "llvm." or as arguments to a function with the same naming restriction. llvm-svn: 68420
2009-04-04 15:22:01 +08:00
//===----------------------------------------------------------------------===//
// Embedded metadata.
//===----------------------------------------------------------------------===//
/// ParseMDNodeVector
Make MDNode use CallbackVH. Also change MDNode to store Value* instead of Constant* in preperation of a future change to support holding non-Constants in an MDNode. llvm-svn: 71407
2009-05-11 04:57:05 +08:00
/// ::= Element (',' Element)*
/// Element
/// ::= 'null' | TypeAndValue
Re-add parsing of function-local metadata; this time with testcase. llvm-svn: 92793
2010-01-06 06:22:14 +08:00
bool LLParser::ParseMDNodeVector(SmallVectorImpl<Value*> &Elts,
Compute isFunctionLocal in MDNode ctor or via argument in new function getWhenValsUnresolved(). Document PFS argument to ParseValID() and ConvertGlobalOrMetadataValIDToValue(). llvm-svn: 93108
2010-01-10 15:14:18 +08:00
PerFunctionState *PFS) {
Add support for embedded metadata to LLVM. This introduces two new types of Constant, MDString and MDNode which can only be used by globals with a name that starts with "llvm." or as arguments to a function with the same naming restriction. llvm-svn: 68420
2009-04-04 15:22:01 +08:00
do {
rewrite ParseMDNodeVector to follow the normal patter used in the .ll parser. llvm-svn: 92292
2009-12-30 12:42:57 +08:00
// Null is a special case since it is typeless.
if (EatIfPresent(lltok::kw_null)) {
Elts.push_back(0);
continue;
Make MDNode use CallbackVH. Also change MDNode to store Value* instead of Constant* in preperation of a future change to support holding non-Constants in an MDNode. llvm-svn: 71407
2009-05-11 04:57:05 +08:00
}
rewrite ParseMDNodeVector to follow the normal patter used in the .ll parser. llvm-svn: 92292
2009-12-30 12:42:57 +08:00
Value *V = 0;
PATypeHolder Ty(Type::getVoidTy(Context));
ValID ID;
Re-add parsing of function-local metadata; this time with testcase. llvm-svn: 92793
2010-01-06 06:22:14 +08:00
if (ParseType(Ty) || ParseValID(ID, PFS) ||
Consolidate ConvertGlobalValIDToValue, ConvertGlobalOrMetadataValIDToValue, and ConvertValIDToValue into a more powerful ConvertValIDToValue() that does all three's work llvm-svn: 93197
2010-01-12 06:31:58 +08:00
ConvertValIDToValue(Ty, ID, V, PFS))
rewrite ParseMDNodeVector to follow the normal patter used in the .ll parser. llvm-svn: 92292
2009-12-30 12:42:57 +08:00
return true;
Make MDNode use CallbackVH. Also change MDNode to store Value* instead of Constant* in preperation of a future change to support holding non-Constants in an MDNode. llvm-svn: 71407
2009-05-11 04:57:05 +08:00
Elts.push_back(V);
Add support for embedded metadata to LLVM. This introduces two new types of Constant, MDString and MDNode which can only be used by globals with a name that starts with "llvm." or as arguments to a function with the same naming restriction. llvm-svn: 68420
2009-04-04 15:22:01 +08:00
} while (EatIfPresent(lltok::comma));
return false;
}