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.h

453 lines
18 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.h - Parser Class -------------------------------*- C++ -*-===//
//
// 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.
//
//===----------------------------------------------------------------------===//
Canonicalize header guards into a common format. Add header guards to files that were missing guards. Remove #endif comments as they don't seem common in LLVM (we can easily add them back if we decide they're useful) Changes made by clang-tidy with minor tweaks. llvm-svn: 215558
2014-08-14 00:26:38 +08:00
#ifndef LLVM_LIB_ASMPARSER_LLPARSER_H
#define LLVM_LIB_ASMPARSER_LLPARSER_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 "LLLexer.h"
Sort includes for all of the .h files under the 'lib' tree. These were missed in the first pass because the script didn't yet handle include guards. Note that the script is now able to handle all of these headers without manual edits. =] llvm-svn: 169224
2012-12-04 15:12:27 +08:00
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/StringMap.h"
Move all of the header files which are involved in modelling the LLVM IR into their new header subdirectory: include/llvm/IR. This matches the directory structure of lib, and begins to correct a long standing point of file layout clutter in LLVM. There are still more header files to move here, but I wanted to handle them in separate commits to make tracking what files make sense at each layer easier. The only really questionable files here are the target intrinsic tablegen files. But that's a battle I'd rather not fight today. I've updated both CMake and Makefile build systems (I think, and my tests think, but I may have missed something). I've also re-sorted the includes throughout the project. I'll be committing updates to Clang, DragonEgg, and Polly momentarily. llvm-svn: 171366
2013-01-02 19:36:10 +08:00
#include "llvm/IR/Attributes.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/Operator.h"
#include "llvm/IR/Type.h"
[Modules] Move ValueHandle into the IR library where Value itself lives. Move the test for this class into the IR unittests as well. This uncovers that ValueMap too is in the IR library. Ironically, the unittest for ValueMap is useless in the Support library (honestly, so was the ValueHandle test) and so it already lives in the IR unittests. Mmmm, tasty layering. llvm-svn: 202821
2014-03-04 19:17:44 +08:00
#include "llvm/IR/ValueHandle.h"
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
#include <map>
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
namespace llvm {
class Module;
class OpaqueType;
class Function;
class Value;
class BasicBlock;
class Instruction;
class Constant;
class GlobalValue;
IR: Add COMDATs to the IR This new IR facility allows us to represent the object-file semantic of a COMDAT group. COMDATs allow us to tie together sections and make the inclusion of one dependent on another. This is required to implement features like MS ABI VFTables and optimizing away certain kinds of initialization in C++. This functionality is only representable in COFF and ELF, Mach-O has no similar mechanism. Differential Revision: http://reviews.llvm.org/D4178 llvm-svn: 211920
2014-06-28 02:19:56 +08:00
class Comdat;
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
class MDString;
class MDNode;
Land the long talked about "type system rewrite" patch. This patch brings numerous advantages to LLVM. One way to look at it is through diffstat: 109 files changed, 3005 insertions(+), 5906 deletions(-) Removing almost 3K lines of code is a good thing. Other advantages include: 1. Value::getType() is a simple load that can be CSE'd, not a mutating union-find operation. 2. Types a uniqued and never move once created, defining away PATypeHolder. 3. Structs can be "named" now, and their name is part of the identity that uniques them. This means that the compiler doesn't merge them structurally which makes the IR much less confusing. 4. Now that there is no way to get a cycle in a type graph without a named struct type, "upreferences" go away. 5. Type refinement is completely gone, which should make LTO much MUCH faster in some common cases with C++ code. 6. Types are now generally immutable, so we can use "Type *" instead "const Type *" everywhere. Downsides of this patch are that it removes some functions from the C API, so people using those will have to upgrade to (not yet added) new API. "LLVM 3.0" is the right time to do this. There are still some cleanups pending after this, this patch is large enough as-is. llvm-svn: 134829
2011-07-10 01:41:24 +08:00
class StructType;
Down with trailing whitespace! llvm-svn: 61594
2009-01-03 06:46:48 +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
/// ValID - Represents a reference of a definition of some sort with no type.
/// There are several cases where we have to parse the value but where the
/// type can depend on later context. This may either be a numeric reference
/// or a symbolic (%var) reference. This is just a discriminated union.
Revert "Give internal classes hidden visibility." It works with clang, but GCC has different rules so we can't make all of those hidden. This reverts commit r190534. llvm-svn: 190536
2013-09-12 02:05:11 +08:00
struct ValID {
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
enum {
t_LocalID, t_GlobalID, // ID in UIntVal.
t_LocalName, t_GlobalName, // Name in StrVal.
t_APSInt, t_APFloat, // Value in APSIntVal/APFloatVal.
t_Null, t_Undef, t_Zero, // No value.
t_EmptyArray, // No value: []
t_Constant, // Value in ConstantVal.
t_InlineAsm, // Value in StrVal/StrVal2/UIntVal.
split t_Metadata into t_MDNode and t_MDString, eliminating some unsafe casting. llvm-svn: 92287
2009-12-30 10:11:14 +08:00
t_MDNode, // Value in MDNodeVal.
Land the long talked about "type system rewrite" patch. This patch brings numerous advantages to LLVM. One way to look at it is through diffstat: 109 files changed, 3005 insertions(+), 5906 deletions(-) Removing almost 3K lines of code is a good thing. Other advantages include: 1. Value::getType() is a simple load that can be CSE'd, not a mutating union-find operation. 2. Types a uniqued and never move once created, defining away PATypeHolder. 3. Structs can be "named" now, and their name is part of the identity that uniques them. This means that the compiler doesn't merge them structurally which makes the IR much less confusing. 4. Now that there is no way to get a cycle in a type graph without a named struct type, "upreferences" go away. 5. Type refinement is completely gone, which should make LTO much MUCH faster in some common cases with C++ code. 6. Types are now generally immutable, so we can use "Type *" instead "const Type *" everywhere. Downsides of this patch are that it removes some functions from the C API, so people using those will have to upgrade to (not yet added) new API. "LLVM 3.0" is the right time to do this. There are still some cleanups pending after this, this patch is large enough as-is. llvm-svn: 134829
2011-07-10 01:41:24 +08:00
t_MDString, // Value in MDStringVal.
t_ConstantStruct, // Value in ConstantStructElts.
t_PackedConstantStruct // Value in ConstantStructElts.
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
} Kind;
Remove trailing whitespace llvm-svn: 168103
2012-11-16 06:34:00 +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
LLLexer::LocTy Loc;
unsigned UIntVal;
std::string StrVal, StrVal2;
APSInt APSIntVal;
APFloat APFloatVal;
Constant *ConstantVal;
split t_Metadata into t_MDNode and t_MDString, eliminating some unsafe casting. llvm-svn: 92287
2009-12-30 10:11:14 +08:00
MDNode *MDNodeVal;
MDString *MDStringVal;
Land the long talked about "type system rewrite" patch. This patch brings numerous advantages to LLVM. One way to look at it is through diffstat: 109 files changed, 3005 insertions(+), 5906 deletions(-) Removing almost 3K lines of code is a good thing. Other advantages include: 1. Value::getType() is a simple load that can be CSE'd, not a mutating union-find operation. 2. Types a uniqued and never move once created, defining away PATypeHolder. 3. Structs can be "named" now, and their name is part of the identity that uniques them. This means that the compiler doesn't merge them structurally which makes the IR much less confusing. 4. Now that there is no way to get a cycle in a type graph without a named struct type, "upreferences" go away. 5. Type refinement is completely gone, which should make LTO much MUCH faster in some common cases with C++ code. 6. Types are now generally immutable, so we can use "Type *" instead "const Type *" everywhere. Downsides of this patch are that it removes some functions from the C API, so people using those will have to upgrade to (not yet added) new API. "LLVM 3.0" is the right time to do this. There are still some cleanups pending after this, this patch is large enough as-is. llvm-svn: 134829
2011-07-10 01:41:24 +08:00
Constant **ConstantStructElts;
Remove trailing whitespace llvm-svn: 168103
2012-11-16 06:34:00 +08:00
Land the long talked about "type system rewrite" patch. This patch brings numerous advantages to LLVM. One way to look at it is through diffstat: 109 files changed, 3005 insertions(+), 5906 deletions(-) Removing almost 3K lines of code is a good thing. Other advantages include: 1. Value::getType() is a simple load that can be CSE'd, not a mutating union-find operation. 2. Types a uniqued and never move once created, defining away PATypeHolder. 3. Structs can be "named" now, and their name is part of the identity that uniques them. This means that the compiler doesn't merge them structurally which makes the IR much less confusing. 4. Now that there is no way to get a cycle in a type graph without a named struct type, "upreferences" go away. 5. Type refinement is completely gone, which should make LTO much MUCH faster in some common cases with C++ code. 6. Types are now generally immutable, so we can use "Type *" instead "const Type *" everywhere. Downsides of this patch are that it removes some functions from the C API, so people using those will have to upgrade to (not yet added) new API. "LLVM 3.0" is the right time to do this. There are still some cleanups pending after this, this patch is large enough as-is. llvm-svn: 134829
2011-07-10 01:41:24 +08:00
ValID() : Kind(t_LocalID), APFloatVal(0.0) {}
~ValID() {
if (Kind == t_ConstantStruct || Kind == t_PackedConstantStruct)
delete [] ConstantStructElts;
}
Remove trailing whitespace llvm-svn: 168103
2012-11-16 06:34:00 +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
bool operator<(const ValID &RHS) const {
if (Kind == t_LocalID || Kind == t_GlobalID)
return UIntVal < RHS.UIntVal;
Land the long talked about "type system rewrite" patch. This patch brings numerous advantages to LLVM. One way to look at it is through diffstat: 109 files changed, 3005 insertions(+), 5906 deletions(-) Removing almost 3K lines of code is a good thing. Other advantages include: 1. Value::getType() is a simple load that can be CSE'd, not a mutating union-find operation. 2. Types a uniqued and never move once created, defining away PATypeHolder. 3. Structs can be "named" now, and their name is part of the identity that uniques them. This means that the compiler doesn't merge them structurally which makes the IR much less confusing. 4. Now that there is no way to get a cycle in a type graph without a named struct type, "upreferences" go away. 5. Type refinement is completely gone, which should make LTO much MUCH faster in some common cases with C++ code. 6. Types are now generally immutable, so we can use "Type *" instead "const Type *" everywhere. Downsides of this patch are that it removes some functions from the C API, so people using those will have to upgrade to (not yet added) new API. "LLVM 3.0" is the right time to do this. There are still some cleanups pending after this, this patch is large enough as-is. llvm-svn: 134829
2011-07-10 01:41:24 +08:00
assert((Kind == t_LocalName || Kind == t_GlobalName ||
Remove trailing whitespace llvm-svn: 168103
2012-11-16 06:34:00 +08:00
Kind == t_ConstantStruct || Kind == t_PackedConstantStruct) &&
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
"Ordering not defined for this ValID kind yet");
return StrVal < RHS.StrVal;
}
};
Remove trailing whitespace llvm-svn: 168103
2012-11-16 06:34:00 +08:00
Revert "Give internal classes hidden visibility." It works with clang, but GCC has different rules so we can't make all of those hidden. This reverts commit r190534. llvm-svn: 190536
2013-09-12 02:05:11 +08:00
class LLParser {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
public:
typedef LLLexer::LocTy LocTy;
private:
fix a crash on invalid metadata, e.g.: call i32 @foo(), XXXX We would return the error without inserting the new instruction into the program, so it wouldn't get deallocated, and an abort would trigger when the module was deleted. llvm-svn: 100602
2010-04-07 12:08:57 +08:00
LLVMContext &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
LLLexer Lex;
Module *M;
Remove trailing whitespace llvm-svn: 168103
2012-11-16 06:34:00 +08:00
rewrite handling of forward ref'd instruction metadata to used deferred resolution instead of creating a temporary node + rauw. There is no reason to create the temporary mdnode, then do rauw, then destroy it. llvm-svn: 100086
2010-04-01 13:14:45 +08:00
// Instruction metadata resolution. Each instruction can have a list of
// MDRef info associated with them.
Add a comment explaining why this code is more complex than it initially seems it should require. llvm-svn: 111913
2010-08-24 22:31:06 +08:00
//
// The simpler approach of just creating temporary MDNodes and then calling
// RAUW on them when the definition is processed doesn't work because some
// instruction metadata kinds, such as dbg, get stored in the IR in an
// "optimized" format which doesn't participate in the normal value use
// lists. This means that RAUW doesn't work, even on temporary MDNodes
// which otherwise support RAUW. Instead, we defer resolving MDNode
// references until the definitions have been processed.
rewrite handling of forward ref'd instruction metadata to used deferred resolution instead of creating a temporary node + rauw. There is no reason to create the temporary mdnode, then do rauw, then destroy it. llvm-svn: 100086
2010-04-01 13:14:45 +08:00
struct MDRef {
SMLoc Loc;
unsigned MDKind, MDSlot;
};
DenseMap<Instruction*, std::vector<MDRef> > ForwardRefInstMetadata;
Down with trailing whitespace! llvm-svn: 61594
2009-01-03 06:46:48 +08:00
AutoUpgrade: upgrade from scalar TBAA format to struct-path aware TBAA format. We treat TBAA tags as struct-path aware TBAA format when the first operand is a MDNode and the tag has 3 or more operands. llvm-svn: 191593
2013-09-28 08:22:27 +08:00
SmallVector<Instruction*, 64> InstsWithTBAATag;
Land the long talked about "type system rewrite" patch. This patch brings numerous advantages to LLVM. One way to look at it is through diffstat: 109 files changed, 3005 insertions(+), 5906 deletions(-) Removing almost 3K lines of code is a good thing. Other advantages include: 1. Value::getType() is a simple load that can be CSE'd, not a mutating union-find operation. 2. Types a uniqued and never move once created, defining away PATypeHolder. 3. Structs can be "named" now, and their name is part of the identity that uniques them. This means that the compiler doesn't merge them structurally which makes the IR much less confusing. 4. Now that there is no way to get a cycle in a type graph without a named struct type, "upreferences" go away. 5. Type refinement is completely gone, which should make LTO much MUCH faster in some common cases with C++ code. 6. Types are now generally immutable, so we can use "Type *" instead "const Type *" everywhere. Downsides of this patch are that it removes some functions from the C API, so people using those will have to upgrade to (not yet added) new API. "LLVM 3.0" is the right time to do this. There are still some cleanups pending after this, this patch is large enough as-is. llvm-svn: 134829
2011-07-10 01:41:24 +08:00
// Type resolution handling data structures. The location is set when we
// have processed a use of the type but not a definition yet.
StringMap<std::pair<Type*, LocTy> > NamedTypes;
std::vector<std::pair<Type*, LocTy> > NumberedTypes;
Remove trailing whitespace llvm-svn: 168103
2012-11-16 06:34:00 +08:00
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
std::vector<TrackingVH<MDNode> > NumberedMetadata;
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> > ForwardRefMDNodes;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
// Global Value reference information.
std::map<std::string, std::pair<GlobalValue*, LocTy> > ForwardRefVals;
std::map<unsigned, std::pair<GlobalValue*, LocTy> > ForwardRefValIDs;
std::vector<GlobalValue*> NumberedVals;
Remove trailing whitespace llvm-svn: 168103
2012-11-16 06:34:00 +08:00
IR: Add COMDATs to the IR This new IR facility allows us to represent the object-file semantic of a COMDAT group. COMDATs allow us to tie together sections and make the inclusion of one dependent on another. This is required to implement features like MS ABI VFTables and optimizing away certain kinds of initialization in C++. This functionality is only representable in COFF and ELF, Mach-O has no similar mechanism. Differential Revision: http://reviews.llvm.org/D4178 llvm-svn: 211920
2014-06-28 02:19:56 +08:00
// Comdat forward reference information.
std::map<std::string, LocTy> ForwardRefComdats;
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
// References to blockaddress. The key is the function ValID, the value is
// a list of references to blocks in that function.
LLParser: Handle BlockAddresses on-the-fly Previously all `blockaddress()` constants were treated as forward references. They were resolved twice: once at the end of the function in question, and again at the end of the module. Furthermore, if the same blockaddress was referenced N times, the parser created N distinct `GlobalVariable`s (one for each reference). Instead, resolve all block addresses at the beginning of the function, creating the standard `BasicBlock` forward references used for all other basic block references. After the function, all references can be resolved immediately. To check for the condition of parsing block addresses from within the same function, I created a reference to the current per-function-state in `BlockAddressPFS`. Also, create only one forward-reference per basic block. Because forward references to block addresses are rare, the data structure here shouldn't matter. If somehow it does someday, this can be pretty easily changed to a `DenseMap<std::pair<ValID, ValID>, GV>`. This is part of PR20515. llvm-svn: 215952
2014-08-19 08:13:19 +08:00
std::map<ValID, std::map<ValID, GlobalValue *>> ForwardRefBlockAddresses;
class PerFunctionState;
/// Reference to per-function state to allow basic blocks to be
/// forward-referenced by blockaddress instructions within the same
/// function.
PerFunctionState *BlockAddressPFS;
Remove trailing whitespace llvm-svn: 168103
2012-11-16 06:34:00 +08:00
Initial submission for the attribute group feature. Attribute groups are of the form: #0 = attributes { noinline "no-sse" "cpu"="cortex-a8" alignstack=4 } Target-dependent attributes are represented as strings. Attributes can have optional values associated with them. E.g., the "cpu" attribute has the value "cortex-a8". Target-independent attributes are listed as enums inside the attribute classes. Multiple attribute groups can be referenced by the same object. In that case, the attributes are merged together. llvm-svn: 174493
2013-02-06 14:52:58 +08:00
// Attribute builder reference information.
Parse the attribute group reference on a function. Attribute references are of this form: define void @foo() #0 #1 #2 { ... } Parse them for function attributes. If there's more than one reference, then they are merged together. llvm-svn: 174697
2013-02-08 14:32:06 +08:00
std::map<Value*, std::vector<unsigned> > ForwardRefAttrGroups;
std::map<unsigned, AttrBuilder> NumberedAttrBuilders;
Initial submission for the attribute group feature. Attribute groups are of the form: #0 = attributes { noinline "no-sse" "cpu"="cortex-a8" alignstack=4 } Target-dependent attributes are represented as strings. Attributes can have optional values associated with them. E.g., the "cpu" attribute has the value "cortex-a8". Target-independent attributes are listed as enums inside the attribute classes. Multiple attribute groups can be referenced by the same object. In that case, the attributes are merged together. llvm-svn: 174493
2013-02-06 14:52:58 +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
public:
LLParser: Handle BlockAddresses on-the-fly Previously all `blockaddress()` constants were treated as forward references. They were resolved twice: once at the end of the function in question, and again at the end of the module. Furthermore, if the same blockaddress was referenced N times, the parser created N distinct `GlobalVariable`s (one for each reference). Instead, resolve all block addresses at the beginning of the function, creating the standard `BasicBlock` forward references used for all other basic block references. After the function, all references can be resolved immediately. To check for the condition of parsing block addresses from within the same function, I created a reference to the current per-function-state in `BlockAddressPFS`. Also, create only one forward-reference per basic block. Because forward references to block addresses are rare, the data structure here shouldn't matter. If somehow it does someday, this can be pretty easily changed to a `DenseMap<std::pair<ValID, ValID>, GV>`. This is part of PR20515. llvm-svn: 215952
2014-08-19 08:13:19 +08:00
LLParser(StringRef F, SourceMgr &SM, SMDiagnostic &Err, Module *m)
: Context(m->getContext()), Lex(F, SM, Err, m->getContext()), M(m),
BlockAddressPFS(nullptr) {}
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 Run();
Down with trailing whitespace! llvm-svn: 61594
2009-01-03 06:46:48 +08:00
Land the long talked about "type system rewrite" patch. This patch brings numerous advantages to LLVM. One way to look at it is through diffstat: 109 files changed, 3005 insertions(+), 5906 deletions(-) Removing almost 3K lines of code is a good thing. Other advantages include: 1. Value::getType() is a simple load that can be CSE'd, not a mutating union-find operation. 2. Types a uniqued and never move once created, defining away PATypeHolder. 3. Structs can be "named" now, and their name is part of the identity that uniques them. This means that the compiler doesn't merge them structurally which makes the IR much less confusing. 4. Now that there is no way to get a cycle in a type graph without a named struct type, "upreferences" go away. 5. Type refinement is completely gone, which should make LTO much MUCH faster in some common cases with C++ code. 6. Types are now generally immutable, so we can use "Type *" instead "const Type *" everywhere. Downsides of this patch are that it removes some functions from the C API, so people using those will have to upgrade to (not yet added) new API. "LLVM 3.0" is the right time to do this. There are still some cleanups pending after this, this patch is large enough as-is. llvm-svn: 134829
2011-07-10 01:41:24 +08:00
LLVMContext &getContext() { return Context; }
Use LLVMContext for generating UndefValue constants too! llvm-svn: 74703
2009-07-03 01:04:01 +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
private:
Push twines deeper into SourceMgr's error handling methods. llvm-svn: 114847
2010-09-28 01:42:11 +08:00
bool Error(LocTy L, const Twine &Msg) const {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but 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 Lex.Error(L, Msg);
}
Push twines deeper into SourceMgr's error handling methods. llvm-svn: 114847
2010-09-28 01:42:11 +08:00
bool TokError(const Twine &Msg) const {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but 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(Lex.getLoc(), Msg);
}
Down with trailing whitespace! llvm-svn: 61594
2009-01-03 06:46:48 +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
/// 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.
land David Blaikie's patch to de-constify Type, with a few tweaks. llvm-svn: 135375
2011-07-18 12:54:35 +08:00
GlobalValue *GetGlobalVal(const std::string &N, Type *Ty, LocTy Loc);
GlobalValue *GetGlobalVal(unsigned ID, Type *Ty, LocTy Loc);
Down with trailing whitespace! llvm-svn: 61594
2009-01-03 06:46:48 +08:00
IR: Add COMDATs to the IR This new IR facility allows us to represent the object-file semantic of a COMDAT group. COMDATs allow us to tie together sections and make the inclusion of one dependent on another. This is required to implement features like MS ABI VFTables and optimizing away certain kinds of initialization in C++. This functionality is only representable in COFF and ELF, Mach-O has no similar mechanism. Differential Revision: http://reviews.llvm.org/D4178 llvm-svn: 211920
2014-06-28 02:19:56 +08:00
/// Get a Comdat with the specified name, creating a forward reference
/// record if needed.
Comdat *getComdat(const std::string &N, LocTy 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
// Helper Routines.
bool ParseToken(lltok::Kind T, const char *ErrMsg);
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
bool EatIfPresent(lltok::Kind T) {
if (Lex.getKind() != T) return false;
Lex.Lex();
return true;
}
Fast-math flags for LLVM IR parsing and printing Added in the ability to read LLVM IR text that contains fast-math flags as a sequence of capital letters separated by spaces in any order. Added in the printing of the fast-math flags in a canonical order, and don't print the other flags when 'fast' is specified, as 'fast' implies all the others. llvm-svn: 168645
2012-11-27 08:42:44 +08:00
FastMathFlags EatFastMathFlagsIfPresent() {
FastMathFlags FMF;
while (true)
switch (Lex.getKind()) {
Reorganize FastMathFlags to be a wrapper around unsigned, and streamline some interfaces. llvm-svn: 169712
2012-12-10 05:12:04 +08:00
case lltok::kw_fast: FMF.setUnsafeAlgebra(); Lex.Lex(); continue;
case lltok::kw_nnan: FMF.setNoNaNs(); Lex.Lex(); continue;
case lltok::kw_ninf: FMF.setNoInfs(); Lex.Lex(); continue;
case lltok::kw_nsz: FMF.setNoSignedZeros(); Lex.Lex(); continue;
case lltok::kw_arcp: FMF.setAllowReciprocal(); Lex.Lex(); continue;
Fast-math flags for LLVM IR parsing and printing Added in the ability to read LLVM IR text that contains fast-math flags as a sequence of capital letters separated by spaces in any order. Added in the printing of the fast-math flags in a canonical order, and don't print the other flags when 'fast' is specified, as 'fast' implies all the others. llvm-svn: 168645
2012-11-27 08:42:44 +08:00
default: return FMF;
}
return FMF;
}
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206356
2014-04-16 12:21:27 +08:00
bool ParseOptionalToken(lltok::Kind T, bool &Present,
LocTy *Loc = nullptr) {
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but 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() != T) {
Present = false;
} else {
Reject uses of unnamed_addr in declarations. llvm-svn: 123358
2011-01-13 09:30:30 +08:00
if (Loc)
*Loc = 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
Lex.Lex();
Present = true;
}
return false;
}
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
bool ParseStringConstant(std::string &Result);
bool ParseUInt32(unsigned &Val);
bool ParseUInt32(unsigned &Val, LocTy &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
Loc = Lex.getLoc();
minor cleanups and comment improvements. llvm-svn: 61564
2009-01-02 16:05:26 +08:00
return ParseUInt32(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
}
Add a dereferenceable attribute This attribute indicates that the parameter or return pointer is dereferenceable. Practically speaking, loads from such a pointer within the associated byte range are safe to speculatively execute. Such pointer parameters are common in source languages (C++ references, for example). llvm-svn: 213385
2014-07-18 23:51:28 +08:00
bool ParseUInt64(uint64_t &Val);
bool ParseUInt64(uint64_t &Val, LocTy &Loc) {
Loc = Lex.getLoc();
return ParseUInt64(Val);
}
Extend the IL for selecting TLS models (PR9788) This allows the user/front-end to specify a model that is better than what LLVM would choose by default. For example, a variable might be declared as @x = thread_local(initialexec) global i32 42 if it will not be used in a shared library that is dlopen'ed. If the specified model isn't supported by the target, or if LLVM can make a better choice, a different model may be used. llvm-svn: 159077
2012-06-23 19:37:03 +08:00
bool ParseTLSModel(GlobalVariable::ThreadLocalMode &TLM);
bool ParseOptionalThreadLocal(GlobalVariable::ThreadLocalMode &TLM);
Allow aliases to be unnamed_addr. Alias with unnamed_addr were in a strange state. It is stored in GlobalValue, the language reference talks about "unnamed_addr aliases" but the verifier was rejecting them. It seems natural to allow unnamed_addr in aliases: * It is a property of how it is accessed, not of the data itself. * It is perfectly possible to write code that depends on the address of an alias. This patch then makes unname_addr legal for aliases. One side effect is that the syntax changes for a corner case: In globals, unnamed_addr is now printed before the address space. llvm-svn: 210302
2014-06-06 09:20:28 +08:00
bool parseOptionalUnnamedAddr(bool &UnnamedAddr) {
return ParseOptionalToken(lltok::kw_unnamed_addr, UnnamedAddr);
}
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but 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 ParseOptionalAddrSpace(unsigned &AddrSpace);
Split up the ParseOptionalAttrs method into three different methods for each class of attributes. This makes it much easier to check for errors and to reuse the code. llvm-svn: 169336
2012-12-05 07:40:58 +08:00
bool ParseOptionalParamAttrs(AttrBuilder &B);
bool ParseOptionalReturnAttrs(AttrBuilder &B);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but 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 ParseOptionalLinkage(unsigned &Linkage, bool &HasLinkage);
bool ParseOptionalLinkage(unsigned &Linkage) {
bool HasLinkage; return ParseOptionalLinkage(Linkage, HasLinkage);
}
bool ParseOptionalVisibility(unsigned &Visibility);
Decouple dllexport/dllimport from linkage Representing dllexport/dllimport as distinct linkage types prevents using these attributes on templates and inline functions. Instead of introducing further mixed linkage types to include linkonce and weak ODR, the old import/export linkage types are replaced with a new separate visibility-like specifier: define available_externally dllimport void @f() {} @Var = dllexport global i32 1, align 4 Linkage for dllexported globals and functions is now equal to their linkage without dllexport. Imported globals and functions must be either declarations with external linkage, or definitions with AvailableExternallyLinkage. llvm-svn: 199218
2014-01-14 23:22:47 +08:00
bool ParseOptionalDLLStorageClass(unsigned &DLLStorageClass);
Retype from unsigned to CallingConv::ID accordingly. Approved by Bob Wilson. llvm-svn: 80773
2009-09-02 16:44:58 +08:00
bool 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
bool ParseOptionalAlignment(unsigned &Alignment);
Add a dereferenceable attribute This attribute indicates that the parameter or return pointer is dereferenceable. Practically speaking, loads from such a pointer within the associated byte range are safe to speculatively execute. Such pointer parameters are common in source languages (C++ references, for example). llvm-svn: 213385
2014-07-18 23:51:28 +08:00
bool ParseOptionalDereferenceableBytes(uint64_t &Bytes);
Initial implementation of 'fence' instruction, the new C++0x-style replacement for llvm.memory.barrier. This is just a LangRef entry and reading/writing/memory representation; optimizer+codegen support coming soon. llvm-svn: 136009
2011-07-26 07:16:38 +08:00
bool ParseScopeAndOrdering(bool isAtomic, SynchronizationScope &Scope,
AtomicOrdering &Ordering);
IR: add a second ordering operand to cmpxhg for failure The syntax for "cmpxchg" should now look something like: cmpxchg i32* %addr, i32 42, i32 3 acquire monotonic where the second ordering argument gives the required semantics in the case that no exchange takes place. It should be no stronger than the first ordering constraint and cannot be either "release" or "acq_rel" (since no store will have taken place). rdar://problem/15996804 llvm-svn: 203559
2014-03-11 18:48:52 +08:00
bool ParseOrdering(AtomicOrdering &Ordering);
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
bool ParseOptionalStackAlignment(unsigned &Alignment);
reimplement ParseOptionalInfo as ParseOptionalCommaAlign, correctly handle the comma case for metadata. llvm-svn: 92301
2009-12-30 13:44:30 +08:00
bool ParseOptionalCommaAlign(unsigned &Alignment, bool &AteExtraComma);
Add an inalloca flag to allocas Summary: The only current use of this flag is to mark the alloca as dynamic, even if its in the entry block. The stack adjustment for the alloca can never be folded into the prologue because the call may clear it and it has to be allocated at the top of the stack. Reviewers: majnemer CC: llvm-commits Differential Revision: http://llvm-reviews.chandlerc.com/D2571 llvm-svn: 199525
2014-01-18 07:58:17 +08:00
bool ParseOptionalCommaInAlloca(bool &IsInAlloca);
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 ParseIndexList(SmallVectorImpl<unsigned> &Indices,bool &AteExtraComma);
bool ParseIndexList(SmallVectorImpl<unsigned> &Indices) {
bool AteExtraComma;
if (ParseIndexList(Indices, AteExtraComma)) return true;
if (AteExtraComma)
return TokError("expected index");
return false;
}
Down with trailing whitespace! llvm-svn: 61594
2009-01-03 06:46:48 +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
// Top-Level Entities
bool ParseTopLevelEntities();
bool ValidateEndOfModule();
bool ParseTargetDefinition();
bool ParseModuleAsm();
Add back support for reading and parsing 'deplibs'. This is for backwards compatibility for pre-3.x bc files. The code reads the code, but does nothing with it. llvm-svn: 168779
2012-11-28 16:41:48 +08:00
bool ParseDepLibs(); // FIXME: Remove in 4.0.
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 ParseUnnamedType();
bool ParseNamedType();
bool ParseDeclare();
bool ParseDefine();
Down with trailing whitespace! llvm-svn: 61594
2009-01-03 06:46:48 +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
bool ParseGlobalType(bool &IsConstant);
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
bool ParseUnnamedGlobal();
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but 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 ParseNamedGlobal();
bool ParseGlobal(const std::string &Name, LocTy Loc, unsigned Linkage,
Decouple dllexport/dllimport from linkage Representing dllexport/dllimport as distinct linkage types prevents using these attributes on templates and inline functions. Instead of introducing further mixed linkage types to include linkonce and weak ODR, the old import/export linkage types are replaced with a new separate visibility-like specifier: define available_externally dllimport void @f() {} @Var = dllexport global i32 1, align 4 Linkage for dllexported globals and functions is now equal to their linkage without dllexport. Imported globals and functions must be either declarations with external linkage, or definitions with AvailableExternallyLinkage. llvm-svn: 199218
2014-01-14 23:22:47 +08:00
bool HasLinkage, unsigned Visibility,
[pr19844] Add thread local mode to aliases. This matches gcc's behavior. It also seems natural given that aliases contain other properties that govern how it is accessed (linkage, visibility, dll storage). Clang still has to be updated to expose this feature to C. llvm-svn: 209759
2014-05-29 02:15:43 +08:00
unsigned DLLStorageClass,
Allow aliases to be unnamed_addr. Alias with unnamed_addr were in a strange state. It is stored in GlobalValue, the language reference talks about "unnamed_addr aliases" but the verifier was rejecting them. It seems natural to allow unnamed_addr in aliases: * It is a property of how it is accessed, not of the data itself. * It is perfectly possible to write code that depends on the address of an alias. This patch then makes unname_addr legal for aliases. One side effect is that the syntax changes for a corner case: In globals, unnamed_addr is now printed before the address space. llvm-svn: 210302
2014-06-06 09:20:28 +08:00
GlobalVariable::ThreadLocalMode TLM, bool UnnamedAddr);
Use "weak alias" instead of "alias weak" Before this patch we had @a = weak global ... but @b = alias weak ... The patch changes aliases to look more like global variables. Looking at some really old code suggests that the reason was that the old bison based parser had a reduction for alias linkages and another one for global variable linkages. Putting the alias first avoided the reduce/reduce conflict. The days of the old .ll parser are long gone. The new one parses just "linkage" and a later check is responsible for deciding if a linkage is valid in a given context. llvm-svn: 214355
2014-07-31 06:51:54 +08:00
bool ParseAlias(const std::string &Name, LocTy Loc, unsigned Linkage,
unsigned Visibility, unsigned DLLStorageClass,
Allow aliases to be unnamed_addr. Alias with unnamed_addr were in a strange state. It is stored in GlobalValue, the language reference talks about "unnamed_addr aliases" but the verifier was rejecting them. It seems natural to allow unnamed_addr in aliases: * It is a property of how it is accessed, not of the data itself. * It is perfectly possible to write code that depends on the address of an alias. This patch then makes unname_addr legal for aliases. One side effect is that the syntax changes for a corner case: In globals, unnamed_addr is now printed before the address space. llvm-svn: 210302
2014-06-06 09:20:28 +08:00
GlobalVariable::ThreadLocalMode TLM, bool UnnamedAddr);
IR: Add COMDATs to the IR This new IR facility allows us to represent the object-file semantic of a COMDAT group. COMDATs allow us to tie together sections and make the inclusion of one dependent on another. This is required to implement features like MS ABI VFTables and optimizing away certain kinds of initialization in C++. This functionality is only representable in COFF and ELF, Mach-O has no similar mechanism. Differential Revision: http://reviews.llvm.org/D4178 llvm-svn: 211920
2014-06-28 02:19:56 +08:00
bool parseComdat();
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 ParseStandaloneMetadata();
Parse named metadata. llvm-svn: 77410
2009-07-29 08:34:02 +08:00
bool ParseNamedMetadata();
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 ParseMDString(MDString *&Result);
rename ParseMDNode -> ParseMDNodeID, since it parses !42, not !{... } as you'd expect. llvm-svn: 92291
2009-12-30 12:15:23 +08:00
bool ParseMDNodeID(MDNode *&Result);
rewrite handling of forward ref'd instruction metadata to used deferred resolution instead of creating a temporary node + rauw. There is no reason to create the temporary mdnode, then do rauw, then destroy it. llvm-svn: 100086
2010-04-01 13:14:45 +08:00
bool ParseMDNodeID(MDNode *&Result, unsigned &SlotNo);
Initial submission for the attribute group feature. Attribute groups are of the form: #0 = attributes { noinline "no-sse" "cpu"="cortex-a8" alignstack=4 } Target-dependent attributes are represented as strings. Attributes can have optional values associated with them. E.g., the "cpu" attribute has the value "cortex-a8". Target-independent attributes are listed as enums inside the attribute classes. Multiple attribute groups can be referenced by the same object. In that case, the attributes are merged together. llvm-svn: 174493
2013-02-06 14:52:58 +08:00
bool ParseUnnamedAttrGrp();
Parse the attribute group reference on a function. Attribute references are of this form: define void @foo() #0 #1 #2 { ... } Parse them for function attributes. If there's more than one reference, then they are merged together. llvm-svn: 174697
2013-02-08 14:32:06 +08:00
bool ParseFnAttributeValuePairs(AttrBuilder &B,
std::vector<unsigned> &FwdRefAttrGrps,
Added support for the Builtin attribute. The Builtin attribute is an attribute that can be placed on function call site that signal that even though a function is declared as being a builtin, rdar://problem/13727199 llvm-svn: 185049
2013-06-27 08:25:01 +08:00
bool inAttrGrp, LocTy &BuiltinLoc);
Down with trailing whitespace! llvm-svn: 61594
2009-01-03 06:46:48 +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
// Type Parsing.
Land the long talked about "type system rewrite" patch. This patch brings numerous advantages to LLVM. One way to look at it is through diffstat: 109 files changed, 3005 insertions(+), 5906 deletions(-) Removing almost 3K lines of code is a good thing. Other advantages include: 1. Value::getType() is a simple load that can be CSE'd, not a mutating union-find operation. 2. Types a uniqued and never move once created, defining away PATypeHolder. 3. Structs can be "named" now, and their name is part of the identity that uniques them. This means that the compiler doesn't merge them structurally which makes the IR much less confusing. 4. Now that there is no way to get a cycle in a type graph without a named struct type, "upreferences" go away. 5. Type refinement is completely gone, which should make LTO much MUCH faster in some common cases with C++ code. 6. Types are now generally immutable, so we can use "Type *" instead "const Type *" everywhere. Downsides of this patch are that it removes some functions from the C API, so people using those will have to upgrade to (not yet added) new API. "LLVM 3.0" is the right time to do this. There are still some cleanups pending after this, this patch is large enough as-is. llvm-svn: 134829
2011-07-10 01:41:24 +08:00
bool ParseType(Type *&Result, bool AllowVoid = false);
bool ParseType(Type *&Result, LocTy &Loc, bool AllowVoid = 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
Loc = 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
return ParseType(Result, AllowVoid);
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
}
Land the long talked about "type system rewrite" patch. This patch brings numerous advantages to LLVM. One way to look at it is through diffstat: 109 files changed, 3005 insertions(+), 5906 deletions(-) Removing almost 3K lines of code is a good thing. Other advantages include: 1. Value::getType() is a simple load that can be CSE'd, not a mutating union-find operation. 2. Types a uniqued and never move once created, defining away PATypeHolder. 3. Structs can be "named" now, and their name is part of the identity that uniques them. This means that the compiler doesn't merge them structurally which makes the IR much less confusing. 4. Now that there is no way to get a cycle in a type graph without a named struct type, "upreferences" go away. 5. Type refinement is completely gone, which should make LTO much MUCH faster in some common cases with C++ code. 6. Types are now generally immutable, so we can use "Type *" instead "const Type *" everywhere. Downsides of this patch are that it removes some functions from the C API, so people using those will have to upgrade to (not yet added) new API. "LLVM 3.0" is the right time to do this. There are still some cleanups pending after this, this patch is large enough as-is. llvm-svn: 134829
2011-07-10 01:41:24 +08:00
bool ParseAnonStructType(Type *&Result, bool Packed);
bool ParseStructBody(SmallVectorImpl<Type*> &Body);
bool ParseStructDefinition(SMLoc TypeLoc, StringRef Name,
std::pair<Type*, LocTy> &Entry,
Type *&ResultTy);
bool ParseArrayVectorType(Type *&Result, bool isVector);
bool ParseFunctionType(Type *&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
// Function Semantic Analysis.
class PerFunctionState {
LLParser &P;
Function &F;
std::map<std::string, std::pair<Value*, LocTy> > ForwardRefVals;
std::map<unsigned, std::pair<Value*, LocTy> > ForwardRefValIDs;
std::vector<Value*> NumberedVals;
Remove trailing whitespace llvm-svn: 168103
2012-11-16 06:34:00 +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
/// FunctionNumber - If this is an unnamed function, this is the slot
/// number of it, otherwise it is -1.
int 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
public:
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
PerFunctionState(LLParser &p, Function &f, int 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
~PerFunctionState();
Down with trailing whitespace! llvm-svn: 61594
2009-01-03 06:46:48 +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
Function &getFunction() const { return F; }
Down with trailing whitespace! llvm-svn: 61594
2009-01-03 06:46:48 +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
bool FinishFunction();
Down with trailing whitespace! llvm-svn: 61594
2009-01-03 06:46:48 +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
/// 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.
land David Blaikie's patch to de-constify Type, with a few tweaks. llvm-svn: 135375
2011-07-18 12:54:35 +08:00
Value *GetVal(const std::string &Name, Type *Ty, LocTy Loc);
Value *GetVal(unsigned ID, Type *Ty, LocTy Loc);
Down with trailing whitespace! llvm-svn: 61594
2009-01-03 06:46:48 +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
/// SetInstName - After an instruction is parsed and inserted into its
/// basic block, this installs its name.
bool SetInstName(int NameID, const std::string &NameStr, LocTy NameLoc,
Instruction *Inst);
Down with trailing whitespace! llvm-svn: 61594
2009-01-03 06:46:48 +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
/// GetBB - Get a basic block with the specified name or ID, creating a
/// forward reference record if needed. This can return null if the value
/// is not a BasicBlock.
BasicBlock *GetBB(const std::string &Name, LocTy Loc);
BasicBlock *GetBB(unsigned ID, LocTy Loc);
Down with trailing whitespace! llvm-svn: 61594
2009-01-03 06:46:48 +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
/// 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 *DefineBB(const std::string &Name, LocTy Loc);
LLParser: Handle BlockAddresses on-the-fly Previously all `blockaddress()` constants were treated as forward references. They were resolved twice: once at the end of the function in question, and again at the end of the module. Furthermore, if the same blockaddress was referenced N times, the parser created N distinct `GlobalVariable`s (one for each reference). Instead, resolve all block addresses at the beginning of the function, creating the standard `BasicBlock` forward references used for all other basic block references. After the function, all references can be resolved immediately. To check for the condition of parsing block addresses from within the same function, I created a reference to the current per-function-state in `BlockAddressPFS`. Also, create only one forward-reference per basic block. Because forward references to block addresses are rare, the data structure here shouldn't matter. If somehow it does someday, this can be pretty easily changed to a `DenseMap<std::pair<ValID, ValID>, GV>`. This is part of PR20515. llvm-svn: 215952
2014-08-19 08:13:19 +08:00
bool resolveForwardRefBlockAddresses();
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
};
Down with trailing whitespace! llvm-svn: 61594
2009-01-03 06:46:48 +08:00
land David Blaikie's patch to de-constify Type, with a few tweaks. llvm-svn: 135375
2011-07-18 12:54:35 +08:00
bool ConvertValIDToValue(Type *Ty, ValID &ID, Value *&V,
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
PerFunctionState *PFS);
Down with trailing whitespace! llvm-svn: 61594
2009-01-03 06:46:48 +08:00
land David Blaikie's patch to de-constify Type, with a few tweaks. llvm-svn: 135375
2011-07-18 12:54:35 +08:00
bool ParseValue(Type *Ty, Value *&V, PerFunctionState *PFS);
bool ParseValue(Type *Ty, Value *&V, PerFunctionState &PFS) {
Land the long talked about "type system rewrite" patch. This patch brings numerous advantages to LLVM. One way to look at it is through diffstat: 109 files changed, 3005 insertions(+), 5906 deletions(-) Removing almost 3K lines of code is a good thing. Other advantages include: 1. Value::getType() is a simple load that can be CSE'd, not a mutating union-find operation. 2. Types a uniqued and never move once created, defining away PATypeHolder. 3. Structs can be "named" now, and their name is part of the identity that uniques them. This means that the compiler doesn't merge them structurally which makes the IR much less confusing. 4. Now that there is no way to get a cycle in a type graph without a named struct type, "upreferences" go away. 5. Type refinement is completely gone, which should make LTO much MUCH faster in some common cases with C++ code. 6. Types are now generally immutable, so we can use "Type *" instead "const Type *" everywhere. Downsides of this patch are that it removes some functions from the C API, so people using those will have to upgrade to (not yet added) new API. "LLVM 3.0" is the right time to do this. There are still some cleanups pending after this, this patch is large enough as-is. llvm-svn: 134829
2011-07-10 01:41:24 +08:00
return ParseValue(Ty, V, &PFS);
}
land David Blaikie's patch to de-constify Type, with a few tweaks. llvm-svn: 135375
2011-07-18 12:54:35 +08:00
bool ParseValue(Type *Ty, Value *&V, LocTy &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
PerFunctionState &PFS) {
Loc = Lex.getLoc();
Land the long talked about "type system rewrite" patch. This patch brings numerous advantages to LLVM. One way to look at it is through diffstat: 109 files changed, 3005 insertions(+), 5906 deletions(-) Removing almost 3K lines of code is a good thing. Other advantages include: 1. Value::getType() is a simple load that can be CSE'd, not a mutating union-find operation. 2. Types a uniqued and never move once created, defining away PATypeHolder. 3. Structs can be "named" now, and their name is part of the identity that uniques them. This means that the compiler doesn't merge them structurally which makes the IR much less confusing. 4. Now that there is no way to get a cycle in a type graph without a named struct type, "upreferences" go away. 5. Type refinement is completely gone, which should make LTO much MUCH faster in some common cases with C++ code. 6. Types are now generally immutable, so we can use "Type *" instead "const Type *" everywhere. Downsides of this patch are that it removes some functions from the C API, so people using those will have to upgrade to (not yet added) new API. "LLVM 3.0" is the right time to do this. There are still some cleanups pending after this, this patch is large enough as-is. llvm-svn: 134829
2011-07-10 01:41:24 +08:00
return ParseValue(Ty, 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
}
Down with trailing whitespace! llvm-svn: 61594
2009-01-03 06:46:48 +08:00
Land the long talked about "type system rewrite" patch. This patch brings numerous advantages to LLVM. One way to look at it is through diffstat: 109 files changed, 3005 insertions(+), 5906 deletions(-) Removing almost 3K lines of code is a good thing. Other advantages include: 1. Value::getType() is a simple load that can be CSE'd, not a mutating union-find operation. 2. Types a uniqued and never move once created, defining away PATypeHolder. 3. Structs can be "named" now, and their name is part of the identity that uniques them. This means that the compiler doesn't merge them structurally which makes the IR much less confusing. 4. Now that there is no way to get a cycle in a type graph without a named struct type, "upreferences" go away. 5. Type refinement is completely gone, which should make LTO much MUCH faster in some common cases with C++ code. 6. Types are now generally immutable, so we can use "Type *" instead "const Type *" everywhere. Downsides of this patch are that it removes some functions from the C API, so people using those will have to upgrade to (not yet added) new API. "LLVM 3.0" is the right time to do this. There are still some cleanups pending after this, this patch is large enough as-is. llvm-svn: 134829
2011-07-10 01:41:24 +08:00
bool ParseTypeAndValue(Value *&V, PerFunctionState *PFS);
bool ParseTypeAndValue(Value *&V, PerFunctionState &PFS) {
return ParseTypeAndValue(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 ParseTypeAndValue(Value *&V, LocTy &Loc, PerFunctionState &PFS) {
Loc = Lex.getLoc();
return ParseTypeAndValue(V, 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
bool ParseTypeAndBasicBlock(BasicBlock *&BB, LocTy &Loc,
PerFunctionState &PFS);
bool ParseTypeAndBasicBlock(BasicBlock *&BB, PerFunctionState &PFS) {
LocTy Loc;
return ParseTypeAndBasicBlock(BB, Loc, PFS);
}
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
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
struct ParamInfo {
LocTy Loc;
Value *V;
Make sure that the Attribute object represents one attribute only. Several places were still treating the Attribute object as respresenting multiple attributes. Those places now use the AttributeSet to represent multiple attributes. llvm-svn: 174003
2013-01-31 08:29:54 +08:00
AttributeSet Attrs;
ParamInfo(LocTy loc, Value *v, AttributeSet attrs)
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but this passes dejagnu testing and is ready for its time in the limelight. llvm-svn: 61558
2009-01-02 15:01:27 +08:00
: Loc(loc), V(v), Attrs(attrs) {}
};
bool ParseParameterList(SmallVectorImpl<ParamInfo> &ArgList,
Declare that musttail calls in variadic functions forward the ellipsis Summary: There is no functionality change here except in the way we assemble and dump musttail calls in variadic functions. There's really no need to separate out the bits for musttail and "is forwarding varargs" on call instructions. A musttail call by definition has to forward the ellipsis or it would fail verification. Reviewers: chandlerc, nlewycky Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D4892 llvm-svn: 216423
2014-08-26 08:33:28 +08:00
PerFunctionState &PFS,
bool IsMustTailCall = false,
bool InVarArgsFunc = false);
Down with trailing whitespace! llvm-svn: 61594
2009-01-03 06:46:48 +08:00
Re-add parsing of function-local metadata; this time with testcase. llvm-svn: 92793
2010-01-06 06:22:14 +08:00
// Constant Parsing.
[C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr. llvm-svn: 206356
2014-04-16 12:21:27 +08:00
bool ParseValID(ValID &ID, PerFunctionState *PFS = nullptr);
land David Blaikie's patch to de-constify Type, with a few tweaks. llvm-svn: 135375
2011-07-18 12:54:35 +08:00
bool ParseGlobalValue(Type *Ty, Constant *&V);
Re-add parsing of function-local metadata; this time with testcase. llvm-svn: 92793
2010-01-06 06:22:14 +08:00
bool ParseGlobalTypeAndValue(Constant *&V);
LLParser: Handle BlockAddresses on-the-fly Previously all `blockaddress()` constants were treated as forward references. They were resolved twice: once at the end of the function in question, and again at the end of the module. Furthermore, if the same blockaddress was referenced N times, the parser created N distinct `GlobalVariable`s (one for each reference). Instead, resolve all block addresses at the beginning of the function, creating the standard `BasicBlock` forward references used for all other basic block references. After the function, all references can be resolved immediately. To check for the condition of parsing block addresses from within the same function, I created a reference to the current per-function-state in `BlockAddressPFS`. Also, create only one forward-reference per basic block. Because forward references to block addresses are rare, the data structure here shouldn't matter. If somehow it does someday, this can be pretty easily changed to a `DenseMap<std::pair<ValID, ValID>, GV>`. This is part of PR20515. llvm-svn: 215952
2014-08-19 08:13:19 +08:00
bool ParseGlobalValueVector(SmallVectorImpl<Constant *> &Elts);
IR: Add COMDATs to the IR This new IR facility allows us to represent the object-file semantic of a COMDAT group. COMDATs allow us to tie together sections and make the inclusion of one dependent on another. This is required to implement features like MS ABI VFTables and optimizing away certain kinds of initialization in C++. This functionality is only representable in COFF and ELF, Mach-O has no similar mechanism. Differential Revision: http://reviews.llvm.org/D4178 llvm-svn: 211920
2014-06-28 02:19:56 +08:00
bool parseOptionalComdat(Comdat *&C);
Extend function-local metadata to be usable as attachments. llvm-svn: 111895
2010-08-24 10:24:03 +08:00
bool ParseMetadataListValue(ValID &ID, PerFunctionState *PFS);
Factor out metadata parsing into a separate function. llvm-svn: 108343
2010-07-15 02:26:50 +08:00
bool ParseMetadataValue(ValID &ID, PerFunctionState *PFS);
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
bool ParseMDNodeVector(SmallVectorImpl<Value*> &, PerFunctionState *PFS);
Give ParseInstructionMetadata access to the PerFunctionState object. This is in preparation for generalizing its parsing of function-local values. llvm-svn: 111893
2010-08-24 10:05:17 +08:00
bool ParseInstructionMetadata(Instruction *Inst, PerFunctionState *PFS);
Re-add parsing of function-local metadata; this time with testcase. llvm-svn: 92793
2010-01-06 06:22:14 +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 Parsing.
struct ArgInfo {
LocTy Loc;
Land the long talked about "type system rewrite" patch. This patch brings numerous advantages to LLVM. One way to look at it is through diffstat: 109 files changed, 3005 insertions(+), 5906 deletions(-) Removing almost 3K lines of code is a good thing. Other advantages include: 1. Value::getType() is a simple load that can be CSE'd, not a mutating union-find operation. 2. Types a uniqued and never move once created, defining away PATypeHolder. 3. Structs can be "named" now, and their name is part of the identity that uniques them. This means that the compiler doesn't merge them structurally which makes the IR much less confusing. 4. Now that there is no way to get a cycle in a type graph without a named struct type, "upreferences" go away. 5. Type refinement is completely gone, which should make LTO much MUCH faster in some common cases with C++ code. 6. Types are now generally immutable, so we can use "Type *" instead "const Type *" everywhere. Downsides of this patch are that it removes some functions from the C API, so people using those will have to upgrade to (not yet added) new API. "LLVM 3.0" is the right time to do this. There are still some cleanups pending after this, this patch is large enough as-is. llvm-svn: 134829
2011-07-10 01:41:24 +08:00
Type *Ty;
Make sure that the Attribute object represents one attribute only. Several places were still treating the Attribute object as respresenting multiple attributes. Those places now use the AttributeSet to represent multiple attributes. llvm-svn: 174003
2013-01-31 08:29:54 +08:00
AttributeSet Attrs;
Reimplement the old and horrible bison parser for .ll files with a nice and clean recursive descent parser. This change has a couple of ramifications: 1. The parser code is about 400 lines shorter (in what we maintain, not including what is autogenerated). 2. The code should be significantly faster than the old code because we don't have to work around bison's poor handling of datatypes with ctors/dtors. This also makes the code much more resistant to memory leaks. 3. We now get caret diagnostics from the .ll parser, woo. 4. The actual diagnostics emited from the parser are completely different so a bunch of testcases had to be updated. 5. I now disallow "%ty = type opaque %ty = type i32". There was no good reason to support this, it was just an accident of the old implementation. I have no reason to think that anyone is actually using this. 6. The syntax for sticking a global variable has changed to make it unambiguous. I don't think anyone is depending on this since only clang supports this and it is not solid yet, so I'm not worried about anything breaking. 7. This gets rid of the last use of bison, and along with it the .cvs files. I'll prune this from the makefiles as a subsequent commit. There are a few minor cleanups that can be done after this commit (suggestions welcome!) but 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 Name;
Make sure that the Attribute object represents one attribute only. Several places were still treating the Attribute object as respresenting multiple attributes. Those places now use the AttributeSet to represent multiple attributes. llvm-svn: 174003
2013-01-31 08:29:54 +08:00
ArgInfo(LocTy L, Type *ty, AttributeSet Attr, const std::string &N)
Land the long talked about "type system rewrite" patch. This patch brings numerous advantages to LLVM. One way to look at it is through diffstat: 109 files changed, 3005 insertions(+), 5906 deletions(-) Removing almost 3K lines of code is a good thing. Other advantages include: 1. Value::getType() is a simple load that can be CSE'd, not a mutating union-find operation. 2. Types a uniqued and never move once created, defining away PATypeHolder. 3. Structs can be "named" now, and their name is part of the identity that uniques them. This means that the compiler doesn't merge them structurally which makes the IR much less confusing. 4. Now that there is no way to get a cycle in a type graph without a named struct type, "upreferences" go away. 5. Type refinement is completely gone, which should make LTO much MUCH faster in some common cases with C++ code. 6. Types are now generally immutable, so we can use "Type *" instead "const Type *" everywhere. Downsides of this patch are that it removes some functions from the C API, so people using those will have to upgrade to (not yet added) new API. "LLVM 3.0" is the right time to do this. There are still some cleanups pending after this, this patch is large enough as-is. llvm-svn: 134829
2011-07-10 01:41:24 +08:00
: Loc(L), Ty(ty), Attrs(Attr), Name(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
};
Land the long talked about "type system rewrite" patch. This patch brings numerous advantages to LLVM. One way to look at it is through diffstat: 109 files changed, 3005 insertions(+), 5906 deletions(-) Removing almost 3K lines of code is a good thing. Other advantages include: 1. Value::getType() is a simple load that can be CSE'd, not a mutating union-find operation. 2. Types a uniqued and never move once created, defining away PATypeHolder. 3. Structs can be "named" now, and their name is part of the identity that uniques them. This means that the compiler doesn't merge them structurally which makes the IR much less confusing. 4. Now that there is no way to get a cycle in a type graph without a named struct type, "upreferences" go away. 5. Type refinement is completely gone, which should make LTO much MUCH faster in some common cases with C++ code. 6. Types are now generally immutable, so we can use "Type *" instead "const Type *" everywhere. Downsides of this patch are that it removes some functions from the C API, so people using those will have to upgrade to (not yet added) new API. "LLVM 3.0" is the right time to do this. There are still some cleanups pending after this, this patch is large enough as-is. llvm-svn: 134829
2011-07-10 01:41:24 +08:00
bool ParseArgumentList(SmallVectorImpl<ArgInfo> &ArgList, bool &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
bool ParseFunctionHeader(Function *&Fn, bool isDefine);
bool ParseFunctionBody(Function &Fn);
bool ParseBasicBlock(PerFunctionState &PFS);
Down with trailing whitespace! llvm-svn: 61594
2009-01-03 06:46:48 +08:00
Add 'musttail' marker to call instructions This is similar to the 'tail' marker, except that it guarantees that tail call optimization will occur. It also comes with convervative IR verification rules that ensure that tail call optimization is possible. Reviewers: nicholas Differential Revision: http://llvm-reviews.chandlerc.com/D3240 llvm-svn: 207143
2014-04-25 04:14:34 +08:00
enum TailCallType { TCT_None, TCT_Tail, TCT_MustTail };
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
// Instruction Parsing. Each instruction parsing routine can return with a
// normal result, an error result, or return having eaten an extra comma.
enum InstResult { InstNormal = 0, InstError = 1, InstExtraComma = 2 };
int 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
bool ParseCmpPredicate(unsigned &Pred, unsigned Opc);
Down with trailing whitespace! llvm-svn: 61594
2009-01-03 06:46:48 +08:00
remove parser support for the obsolete "multiple return values" syntax, which was replaced with return of a "first class aggregate". llvm-svn: 133245
2011-06-17 14:49:41 +08:00
bool ParseRet(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
bool ParseBr(Instruction *&Inst, PerFunctionState &PFS);
bool ParseSwitch(Instruction *&Inst, PerFunctionState &PFS);
rename indbr -> indirectbr to appease the residents of #llvm. llvm-svn: 85351
2009-10-28 08:19:10 +08:00
bool ParseIndirectBr(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
bool ParseInvoke(Instruction *&Inst, PerFunctionState &PFS);
Add the 'resume' instruction for the new EH rewrite. This adds the 'resume' instruction class, IR parsing, and bitcode reading and writing. The 'resume' instruction resumes propagation of an existing (in-flight) exception whose unwinding was interrupted with a 'landingpad' instruction (to be added later). llvm-svn: 136589
2011-07-31 14:30:59 +08:00
bool ParseResume(Instruction *&Inst, PerFunctionState &PFS);
Down with trailing whitespace! llvm-svn: 61594
2009-01-03 06:46:48 +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
bool ParseArithmetic(Instruction *&I, PerFunctionState &PFS, 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
bool ParseLogical(Instruction *&I, PerFunctionState &PFS, unsigned Opc);
bool ParseCompare(Instruction *&I, PerFunctionState &PFS, unsigned Opc);
bool ParseCast(Instruction *&I, PerFunctionState &PFS, unsigned Opc);
bool ParseSelect(Instruction *&I, PerFunctionState &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
bool ParseVA_Arg(Instruction *&I, 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
bool ParseExtractElement(Instruction *&I, PerFunctionState &PFS);
bool ParseInsertElement(Instruction *&I, PerFunctionState &PFS);
bool ParseShuffleVector(Instruction *&I, PerFunctionState &PFS);
convert 4 more instructions over. llvm-svn: 92299
2009-12-30 13:27:33 +08:00
int ParsePHI(Instruction *&I, PerFunctionState &PFS);
Initial commit of the 'landingpad' instruction. This implements the 'landingpad' instruction. It's used to indicate that a basic block is a landing pad. There are several restrictions on its use (see LangRef.html for more detail). These restrictions allow the exception handling code to gather the information it needs in a much more sane way. This patch has the definition, implementation, C interface, parsing, and bitcode support in it. llvm-svn: 137501
2011-08-13 04:24:12 +08:00
bool ParseLandingPad(Instruction *&I, PerFunctionState &PFS);
Add 'musttail' marker to call instructions This is similar to the 'tail' marker, except that it guarantees that tail call optimization will occur. It also comes with convervative IR verification rules that ensure that tail call optimization is possible. Reviewers: nicholas Differential Revision: http://llvm-reviews.chandlerc.com/D3240 llvm-svn: 207143
2014-04-25 04:14:34 +08:00
bool ParseCall(Instruction *&I, PerFunctionState &PFS,
CallInst::TailCallKind IsTail);
Remove old backwards compatibility support from the parser for autoupgrading the old malloc/free instructions, and for 'sext' and 'zext' as function attributes (they are spelled signext/zeroext now), and support for result value attributes being specified after a function. Additionally, diagnose invalid attributes on functions with an error message instead of an abort in the verifier. llvm-svn: 133229
2011-06-17 11:16:47 +08:00
int ParseAlloc(Instruction *&I, PerFunctionState &PFS);
remove asmparsing and documentation support for "volatile load", which was only produced by LLVM 2.9 and earlier. LLVM 3.0 and later prefers "load volatile". llvm-svn: 145172
2011-11-27 14:56:53 +08:00
int ParseLoad(Instruction *&I, PerFunctionState &PFS);
int ParseStore(Instruction *&I, PerFunctionState &PFS);
Move "atomic" and "volatile" designations on instructions after the opcode of the instruction. Note that this change affects the existing non-atomic load and store instructions; the parser now accepts both forms, and the change is noted in the release notes. llvm-svn: 137527
2011-08-13 06:50:01 +08:00
int ParseCmpXchg(Instruction *&I, PerFunctionState &PFS);
int ParseAtomicRMW(Instruction *&I, PerFunctionState &PFS);
Initial implementation of 'fence' instruction, the new C++0x-style replacement for llvm.memory.barrier. This is just a LangRef entry and reading/writing/memory representation; optimizer+codegen support coming soon. llvm-svn: 136009
2011-07-26 07:16:38 +08:00
int ParseFence(Instruction *&I, PerFunctionState &PFS);
convert 4 more instructions over. llvm-svn: 92299
2009-12-30 13:27:33 +08:00
int ParseGetElementPtr(Instruction *&I, PerFunctionState &PFS);
int ParseExtractValue(Instruction *&I, PerFunctionState &PFS);
int ParseInsertValue(Instruction *&I, PerFunctionState &PFS);
IR: Implement uselistorder assembly directives Implement `uselistorder` and `uselistorder_bb` assembly directives, which allow the use-list order to be recovered when round-tripping to assembly. This is the bulk of PR20515. llvm-svn: 216025
2014-08-20 05:30:15 +08:00
// Use-list order directives.
bool ParseUseListOrder(PerFunctionState *PFS = nullptr);
bool ParseUseListOrderBB();
bool ParseUseListOrderIndexes(SmallVectorImpl<unsigned> &Indexes);
bool sortUseListOrder(Value *V, ArrayRef<unsigned> Indexes, SMLoc 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
};
} // End llvm namespace
#endif