affb37337f
reimplement debug info generation in terms of DebugInfo.h instead of
...
using MachineModuleInfo. This runs at about the same speed as the old
code, but fixes a bunch of bugs and is simpler and shorter.
llvm-svn: 58971
2008-11-10 06:08:34 +00:00
2a09239563
final edits
...
llvm-svn: 58966
2008-11-10 05:40:34 +00:00
1c31dbe417
Print integer value instead of raw pointer. This is a hack to be fixed by migrating the output in analyzer to llvm::raw_ostream.
...
llvm-svn: 58965
2008-11-10 05:00:06 +00:00
25f0106fd9
Added support for the following definition of shufflevector
...
<result> = shufflevector <n x <ty>> <v1>, <n x <ty>> <v2>, <m x i32> <mask>
llvm-svn: 58964
2008-11-10 04:46:22 +00:00
09487cd437
eliminate a couple more uses of utohexstr.
...
llvm-svn: 58963
2008-11-10 04:35:24 +00:00
5505eed5ac
Use utohex_buffer instead of utohexstr to avoid creating a temporary
...
string in the .ll and .s printers.
llvm-svn: 58962
2008-11-10 04:30:26 +00:00
90cdddec75
split out the functionality of utohexstr into a new utohex_buffer
...
helper. This allows us to convert numbers to hex without necessarily
needing to make a std::string to hold the result.
llvm-svn: 58961
2008-11-10 04:22:46 +00:00
53c56e4176
Move getCastToEmpty out of DIDescriptor into DIFactory. It is an
...
implementation detail of DIFactory anyway, and this allows it to avoid
recomputing the same type over and over.
llvm-svn: 58960
2008-11-10 04:10:34 +00:00
bc09b36016
Fix an over aggressive assumption that struct decls will have a pointer to
...
an array that is empty. Instead of requiring this array, allow a null pointer.
This shrinks all forward references of structs.
llvm-svn: 58959
2008-11-10 03:48:55 +00:00
85af1ee10d
Fix a bug with default arguments that apple gcc doesn't notice that llvmbb does.
...
llvm-svn: 58958
2008-11-10 03:11:39 +00:00
9d5771ea17
move some cases around to silence these sorts of warnings in
...
release-asserts build:
llvm/CodeGen/SelectionDAGNodes.h:1298: warning: control may reach end of non-void function 'unsigned int llvm::MVT::getSizeInBits() const' being inlined
what an unhelpful warning.
llvm-svn: 58957
2008-11-10 03:05:41 +00:00
231f7bbdbe
silence a warning from gcc.
...
llvm-svn: 58956
2008-11-10 03:00:37 +00:00
4978d35967
add new file
...
llvm-svn: 58955
2008-11-10 02:58:28 +00:00
6d3893359e
Add a new set of helper classes for creating and reading debug
...
information. This logically replaces the "Desc" classes in
MachineModuleInfo. Nice features of these classes are that they:
1. Are much more efficient than MMI because they don't create a
temporary parallel data structure for debug info that has to be
'serialized' and 'deserialized' into/out of the module.
2. These provide a much cleaner abstraction for debug info than
MMI, which will make it easier to change the implementation in
the future (to be MDNode-based).
3. These are much easier to use than the MMI interfaces, requiring
a lot less code in the front-ends.
4. These can be used to both create (for frontends) and read (for
codegen) debug information. DebugInfoBuilder can only be used
to create the nodes.
So far, this is implemented just enough to support the debug info
generation needs of clang. This can and should be extended to
support the full set of debug info constructs, and we should switch
llvm-gcc and llc over to using this in the near future.
This code also has a ton of FIXMEs in it, because the way we
currently represent debug info in LLVM IR is basically insane in a
variety of details. This sort of issue should be fixed when we
eventually reimplement debug info on top of MDNodes.
llvm-svn: 58954
2008-11-10 02:56:27 +00:00
9530edd1f4
CMake: Builds a native tblgen when cross-compiling and the user didn't
...
set LLVM_TABLEGEN.
llvm-svn: 58953
2008-11-10 02:35:55 +00:00
0d9db40994
Forgot these.
...
llvm-svn: 58952
2008-11-10 01:52:24 +00:00
e9edc2cd15
CMake: Implement magic word `all' for selecting all targets. Check
...
that specified targets are known.
llvm-svn: 58951
2008-11-10 01:47:07 +00:00
e352ca077c
CMake: Non-working code for auto-building the native tblgen util when
...
cross-compiling.
llvm-svn: 58950
2008-11-10 01:32:14 +00:00
9f3058f3be
Rename isGVNonLazyPtr to isIndirectSym to reflect how it will be used.
...
llvm-svn: 58949
2008-11-10 01:08:07 +00:00
9e59b577d8
Introduce ScopedDecl::getLexicalDeclContext() which is different from ScopedDecl::getDeclContext() when there are nested-names.
...
e.g.:
namespace A {
void f(); // SemanticDC (getDeclContext) == LexicalDC (getLexicalDeclContext) == 'namespace A'
}
void A::f(); // SemanticDC == namespace 'A'
// LexicalDC == global namespace
llvm-svn: 58948
2008-11-09 23:41:00 +00:00
4fb13c051d
Correction for the last patch. Should match the conditional in the first part
...
of the select match, not the select instruction itself.
llvm-svn: 58947
2008-11-09 23:37:53 +00:00
1579287550
The method of doing the matching with a 'select' instruction was wrong. The
...
original code was matching like this:
if (match(A, m_Not(m_Value(B))))
B was already matched as a 'select' instruction. However, this isn't matching
what we think it's matching. It would match B as a 'Value', so basically
anything would match to it. In this case, a Constant matched. B was replaced
with a constant representation. And then the wrong value would be used in the
SelectInst::Create statement, causing a crash.
After thinking on this for a moment, and after Nick L. told me how the pattern
matching stuff was supposed to work, the solution was to match NOT an m_Value,
but an m_Select.
llvm-svn: 58946
2008-11-09 23:17:42 +00:00
8ad00b26ee
When a tag has nested-name ('struct foo::bar'), use not 'CurContext' but the context of the nested-name ('foo::').
...
llvm-svn: 58945
2008-11-09 22:53:32 +00:00
e02eb2bac2
Simplify handling of nested-names in tags ('struct foo::bar').
...
-Use more of the non nested-name code path.
-Also use the ActOnTagStruct code path.
llvm-svn: 58944
2008-11-09 22:09:58 +00:00
7aee5cf8fd
suppress build products
...
llvm-svn: 58943
2008-11-09 21:33:37 +00:00
a6da027c18
CMake: Corrected detection of `nm'.
...
llvm-svn: 58941
2008-11-09 20:26:31 +00:00
3442f82c2f
Support named operands in inline asm statements.
...
llvm-svn: 58940
2008-11-09 18:54:14 +00:00
b45a43aec4
CMake: Support for cross-compiling. For now, requires a previously
...
built native tblgen which is passed to cmake in the variable
LLVM_TABLEGEN.
See
http://www.cmake.org/Wiki/CmakeMingw
for a quick example on how to cross-compile with CMake.
llvm-svn: 58939
2008-11-09 18:53:19 +00:00
26c744492f
fix validation problem.
...
llvm-svn: 58938
2008-11-09 17:19:14 +00:00
3b36fd87a4
XFAIL this while waiting for a fix.
...
llvm-svn: 58934
2008-11-09 13:07:47 +00:00
2e42927e7c
fix leakage of ValueNumbering
...
llvm-svn: 58933
2008-11-09 12:45:23 +00:00
e0b2b1bf8c
Update C++ status: class support improved due to nested name parsing.
...
llvm-svn: 58932
2008-11-09 11:32:32 +00:00
aa4d82d244
Temporarily revert 58825, which breaks PPC bootstrap.
...
xs
llvm-svn: 58930
2008-11-09 06:48:10 +00:00
3f547be28f
If the LHS of the FCMP is coming from a UIToFP instruction, then we don't want
...
to generate signed ICMP instructions to replace the FCMP. This would violate
the following:
define i1 @test1(i32 %val) {
%1 = uitofp i32 %val to double
%2 = fcmp ole double %1, 0.000000e+00
ret i1 %2
}
would be transformed into:
define i1 @test1(i32 %val) {
%1 = icmp slt i33 %val, 1
ret i1 %1
}
which is obviously wrong. This patch modifes InstCombiner::FoldFCmp_IntToFP_Cst
to handle when the LHS comes from UIToFP.
llvm-svn: 58929
2008-11-09 04:26:50 +00:00
cfb3bc4a45
Typo fix
...
llvm-svn: 58928
2008-11-09 02:54:13 +00:00
5c0378db8e
CellSPU: Update expected counts on expected patterns
...
llvm-svn: 58927
2008-11-09 01:03:41 +00:00
9833d8c369
Temporary revert my last commit: it seems it's triggering some subtle bug in backend
...
and breaks llvm-gcc
llvm-svn: 58926
2008-11-08 23:05:05 +00:00
4829941a51
CMake: corrected library target name for dependency: LLVMCellSPU ->
...
LLVMCellSPUCodeGen.
llvm-svn: 58925
2008-11-08 21:23:15 +00:00
676e5194d0
CMake: Reflected changes on the CellSPU target build. May require a
...
clean start.
llvm-svn: 58924
2008-11-08 20:37:19 +00:00
b200b648c4
Fixed a pasto.
...
llvm-svn: 58923
2008-11-08 20:34:18 +00:00
f5a294d08d
Allow $CALL and $ENV in command names. Fixes #3025 .
...
llvm-svn: 58922
2008-11-08 19:43:32 +00:00
a872e5af8a
CellSPU: Bring SPU's assembly printer more in-line with current LLVM code
...
structure. Assembly printer now outputs the correct section for strings.
llvm-svn: 58921
2008-11-08 18:59:02 +00:00
0f3937115d
Try to produce better code when scalarizing VSETCC.
...
llvm-svn: 58920
2008-11-08 18:26:48 +00:00
09f51d1fd4
Factor out offset printing code into generic AsmPrinter.
...
FIXME: it seems, that most of targets don't support
offsets wrt CPI/GlobalAddress', was it intentional?
llvm-svn: 58917
2008-11-08 17:21:38 +00:00
16ac9be7f0
Implement Sema support for C++ nested-name-specifiers.
...
llvm-svn: 58916
2008-11-08 17:17:31 +00:00
430a58edd8
Silence a GCC member initialization order warning.
...
llvm-svn: 58914
2008-11-08 16:47:38 +00:00
32a0379575
Implement support for C++ nested-name-specifiers ('foo::bar::x') in the Parser side.
...
No Sema functionality change, just the signatures of the Action/Sema methods.
llvm-svn: 58913
2008-11-08 16:45:02 +00:00
c7e67a04c3
Introduce annotation tokens, a special kind of token, created and used only by the parser to replace a group of tokens with a single token encoding semantic information.
...
Will be fully utilized later for C++ nested-name-specifiers.
llvm-svn: 58911
2008-11-08 16:17:04 +00:00
f4485de48a
Update C++ status to reflect parser capabilities for chapter 9 (classes). Slightly extend the class parser test.
...
llvm-svn: 58909
2008-11-08 15:40:37 +00:00
5a48f232f7
The Index field of an AttributeWithIndex is of type unsigned, not uint16_t.
...
llvm-svn: 58908
2008-11-08 15:36:01 +00:00
Chris Lattner