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
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
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
a6da027c18
CMake: Corrected detection of `nm'.
...
llvm-svn: 58941
2008-11-09 20:26:31 +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
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
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
09991ada2d
StoreInst does not produce any result thus it's useless to create new
...
variable for it. This greatly reduces amount of unused variables in
llvm2cpp-generated code
llvm-svn: 58905
2008-11-08 12:58:07 +00:00
9278247502
Properly escape dashes in TableGen's LLVMC2 emitter.
...
Patch by Patrick Walton!
llvm-svn: 58901
2008-11-08 10:16:21 +00:00
6e670388c0
Fix syntax of iterate_complex example. Noticed by Martin!
...
llvm-svn: 58900
2008-11-08 08:20:49 +00:00
436bdcdcca
Moved InvalidateInstructionCache to ARMJITInfo::emitFunctionStub which knows size of stub.
...
llvm-svn: 58899
2008-11-08 08:16:49 +00:00
686a725b45
Remove a InvalidateInstructionCache call with incorrect size.
...
llvm-svn: 58898
2008-11-08 08:15:39 +00:00
b31a717527
Rename startFunctionStub to startGVStub since it's also used for GV non-lazy ptr.
...
llvm-svn: 58897
2008-11-08 08:02:53 +00:00
98161f5f34
Tell ARMJITInfo if codegen relocation is PIC. It changes how function stubs are generated.
...
llvm-svn: 58896
2008-11-08 07:38:22 +00:00
1b889b16da
Rename isString -> isExternalSymbol; getString -> getExternalSymbol since these work on externsym machine relocations.
...
llvm-svn: 58895
2008-11-08 07:37:34 +00:00
776f5922fb
More debug output.
...
llvm-svn: 58894
2008-11-08 07:22:53 +00:00
bb373c4637
Fix relocation for calls to external symbols.
...
llvm-svn: 58893
2008-11-08 07:22:33 +00:00
1ccbbc3d07
CellSPU: Fix prologue/epilogue emission when function contains calls but
...
theframe size is 0; the prologue and epilogue should be emitted in this case.
llvm-svn: 58890
2008-11-08 05:16:20 +00:00
2b9dce2669
Rework r58829, allowing removal of dbg info intrinsics during alloca
...
promotion.
- Eliminate uses after free and simplify tests.
Devang: Please check that this is still doing what you intended.
llvm-svn: 58887
2008-11-08 04:12:17 +00:00
06ad209fb1
Add LLVMC2 tool definitions for Objective-C and Objective-C++.
...
llvm-svn: 58885
2008-11-08 03:25:47 +00:00
077c8f8832
Skip over two-address use operands.
...
llvm-svn: 58883
2008-11-08 01:44:13 +00:00
ffdd91e3b8
Handle ARM machine constantpool entry with non-lazy ptr.
...
llvm-svn: 58882
2008-11-08 01:31:27 +00:00
b126422533
Indentation.
...
llvm-svn: 58881
2008-11-08 01:30:20 +00:00
865da3cae0
remove unavailable clang project
...
llvm-svn: 58879
2008-11-08 01:02:44 +00:00
454ff53d58
Use ARMFunctionInfo to track number of constpool entries and jumptables.
...
llvm-svn: 58877
2008-11-08 00:51:41 +00:00
d70bd61758
Generated code for generic expansion of SETUGT etc.
...
is noticeably worse than previous PPC-specific code.
Since the latter was also wrong in some cases and
correctness is more important than efficiency, I'm
disabling this test temporarily while I fix it.
llvm-svn: 58876
2008-11-08 00:49:19 +00:00
ee04c24bd5
Xfail an incorrect test.
...
llvm-svn: 58875
2008-11-08 00:40:24 +00:00
bb5c9b4b68
Make testb optimization work on big-endian targets.
...
llvm-svn: 58874
2008-11-08 00:01:16 +00:00
ef4d78ba67
More code clean up.
...
llvm-svn: 58872
2008-11-07 22:57:53 +00:00
160be0ffda
Make FP tests requiring two compares work on PPC (PR 642).
...
This is Chris' patch from the PR, modified to realize that
SETUGT/SETULT occur legitimately with integers, plus
two fixes in LegalizeDAG to pass a valid result type into
LegalizeSetCC. The argument of TLI.getSetCCResultType is
ignored on PPC, but I think I'm following usage elsewhere.
llvm-svn: 58871
2008-11-07 22:54:33 +00:00
8467e2459a
Get PIC jump table working.
...
llvm-svn: 58869
2008-11-07 22:30:53 +00:00
077f686d4b
More debug output.
...
llvm-svn: 58868
2008-11-07 22:30:29 +00:00
cc0d2cfa01
Make tablegen print out a nice error message for a const char*
...
exception, like it does for a std::string exception.
llvm-svn: 58865
2008-11-07 21:01:13 +00:00
67feab3b5a
Document the acronym RAUW. Patch by Jonathan Brandmeyer!
...
llvm-svn: 58863
2008-11-07 20:29:17 +00:00
2d636b5265
Sign-extend rather than zero-extend when promoting
...
the condition for a BRCOND, according to what is
returned by getSetCCResultContents. Since all
targets return the same thing (ZeroOrOneSetCCResult),
this should be harmless! The point is that all over
the place the result of SETCC is fed directly into
BRCOND. On machines for which getSetCCResultContents
returns ZeroOrNegativeOneSetCCResult, this is a
sign-extended boolean. So it seems dangerous to
also feed BRCOND zero-extended booleans in some
circumstances - for example, when promoting the
condition.
llvm-svn: 58861
2008-11-07 20:13:04 +00:00
cb0df597e0
Flush the raw_ostream after emitting the assembly for a function.
...
This is a temporary fix for the -print-emitted-asm option, where
errs() is used as the stream, in the case where other code is
using stderr without using errs()' buffer. Hopefully soon we'll
fix errs() to be non-buffered instead. Patch by Preston Gurd.
llvm-svn: 58859
2008-11-07 19:49:17 +00:00
9016882d67
Fix unsigned->ppcf128 conversion.
...
llvm-svn: 58856
2008-11-07 19:11:43 +00:00
3707f1e6f3
Update to add newer bitcodes.
...
llvm-svn: 58852
2008-11-07 14:52:51 +00:00
75edafc672
Keep CREDITS.TXT sorted by name.
...
llvm-svn: 58845
2008-11-07 12:44:36 +00:00
5923f60099
Add contributer information for XCore backend to CREDITS.TXT
...
llvm-svn: 58844
2008-11-07 12:41:14 +00:00
7b2eae9bdd
Add XCore backend to CMake build.
...
llvm-svn: 58843
2008-11-07 12:37:45 +00:00
86d68a492a
Add basic test for XCore backend
...
llvm-svn: 58841
2008-11-07 11:24:12 +00:00
3219819ffe
Fix compile warnings.
...
llvm-svn: 58840
2008-11-07 11:21:09 +00:00
3395d4485d
CellSPU: Ensure that C strings are always put in the .rodata section
...
llvm-svn: 58839
2008-11-07 11:06:44 +00:00
ca08e0645a
Add XCore backend.
...
llvm-svn: 58838
2008-11-07 10:59:00 +00:00
7095cd2af2
Jump table JIT support. Work in progress.
...
llvm-svn: 58836
2008-11-07 09:06:08 +00:00
00203155ad
Jump tables may be emitted by target.
...
llvm-svn: 58835
2008-11-07 09:02:17 +00:00
a2d1605ac3
Jump table relocation addresses may be resolved by target.
...
llvm-svn: 58834
2008-11-07 09:01:15 +00:00
34d93f8572
Teach CellSPU about ELF sections and new section emitter classes.
...
NB: This is likely to need more work.
llvm-svn: 58832
2008-11-07 04:36:25 +00:00
b9656df4ac
BCUI + 1 doesn't work. Use next instead.
...
llvm-svn: 58830
2008-11-07 01:59:41 +00:00
1af23b035f
Refactor code that adjusts the offsets of stack objects.
...
llvm-svn: 58829
2008-11-07 01:48:58 +00:00
98dc53e926
Encode misc arithmetic instructions.
...
llvm-svn: 58828
2008-11-07 01:41:35 +00:00
a129e0b826
Testcase for testb optimization.
...
llvm-svn: 58827
2008-11-07 01:30:18 +00:00
b8e0d59ceb
Handle (delete) dbg intrinsics while promoting alloca.
...
llvm-svn: 58826
2008-11-07 01:30:07 +00:00
7aad542d35
When we're doing a compare of load-AND-constant to 0
...
(e.g. a bitfield test) narrow the load as much as possible.
The has the potential to avoid unnecessary partial-word
load-after-store conflicts, which cause stalls on several targets.
Also a size win on x86 (testb vs testl).
llvm-svn: 58825
2008-11-07 01:28:02 +00:00
eb4268d72f
- Modify the stack protector algorithm so that the stack slot is allocated in
...
LLVM IR code and not in the selection DAG ISel. This is a cleaner solution.
- Fix the heuristic for determining if protectors are necessary. The previous
one wasn't checking the proper type size.
llvm-svn: 58824
2008-11-07 01:23:58 +00:00
87d0746e71
Remove unneeded header file.
...
llvm-svn: 58823
2008-11-06 23:56:59 +00:00
a0826e1855
Don't build a vector of returns. Just modify the Function in the loop.
...
llvm-svn: 58822
2008-11-06 23:55:49 +00:00
5ca2ec65bd
Fixed scalarizing an extract subvector and prevent an infinite loop
...
when simplify a vector.
llvm-svn: 58820
2008-11-06 22:52:21 +00:00
d939a7b305
The size limit is for individual arrays. So if any array has more than 8 bytes
...
in it, then emit stack protectors.
llvm-svn: 58819
2008-11-06 22:18:44 +00:00
49d665218c
Encode extend instructions; more clean up.
...
llvm-svn: 58818
2008-11-06 22:15:19 +00:00
193e4c025e
Fix a use of an invalid iterator when -debug-pass=Details is used.
...
llvm-svn: 58816
2008-11-06 21:57:17 +00:00
8b47c1e0a2
Don't recalculate the stack position of the stack protector.
...
llvm-svn: 58815
2008-11-06 21:37:09 +00:00
8af0a362f1
Emit label for llvm.dbg.func.start of the inlined function.
...
llvm-svn: 58814
2008-11-06 21:28:20 +00:00
ef21de946b
Clarify documentation. A module pass MP can require a function paqss FP only if FP does not require any module pass.
...
llvm-svn: 58813
2008-11-06 19:47:49 +00:00
aa03cd3336
- Improve naming consistency: Branch -> BrFrm, BranchMisc -> BrMiscFrm.
...
- Consolidate instruction formats.
- Other clean up.
llvm-svn: 58808
2008-11-06 17:48:05 +00:00
972fd1a1e0
Improve JIT debugging outputs format consistency.
...
llvm-svn: 58807
2008-11-06 17:46:04 +00:00
2817338558
plug leakage of mutex data. pthread_mutex_destroy() doesnt free our malloc'ed memory.
...
llvm-svn: 58805
2008-11-06 16:21:49 +00:00
f178f8300d
Formating/comment changes - no functionality change.
...
llvm-svn: 58801
2008-11-06 08:51:32 +00:00
47b546d75f
Remove opcode from instruction TS flags; add MOVCC support; fix addrmode3 encoding bug.
...
llvm-svn: 58800
2008-11-06 08:47:38 +00:00
b3f7a39877
- Rename stackprotector_{prologue,epilogue} to stackprotector_{create,check}.
...
- Get rid of "HasStackProtector" in MachineFrameInfo.
- Modify intrinsics to tell which are doing what with memory.
llvm-svn: 58799
2008-11-06 07:23:03 +00:00
ef625263ef
Update VC++ projects.
...
llvm-svn: 58798
2008-11-06 06:24:59 +00:00
9a8d60a7c0
Widening cleanup
...
llvm-svn: 58796
2008-11-06 05:31:54 +00:00
36ae40342f
Handle smul<x><y>, smulw<y>, smla<x><y>, smlaw<y>.
...
llvm-svn: 58793
2008-11-06 03:35:07 +00:00
43de293d75
Adjust the stack protector heuristic to care about only arrays or calls to
...
"alloca".
llvm-svn: 58792
2008-11-06 02:38:58 +00:00
d970ea3eac
Implement the stack protector stack accesses via intrinsics:
...
- stackprotector_prologue creates a stack object and stores the guard there.
- stackprotector_epilogue reads the stack guard from the stack position created
by stackprotector_prologue.
- The PrologEpilogInserter was changed to make sure that the stack guard is
first on the stack frame.
llvm-svn: 58791
2008-11-06 02:29:10 +00:00
b870fd8874
Fix so_imm encoding bug; add support for MOVi2pieces.
...
llvm-svn: 58790
2008-11-06 02:25:39 +00:00
2686c8fb34
Fix encoding of multiple instructions with 3 src operands; also handle smmul, smmla, and smmls.
...
llvm-svn: 58789
2008-11-06 01:21:28 +00:00
3aeeb3a47c
Need a \n.
...
llvm-svn: 58788
2008-11-06 01:18:29 +00:00
5a5ab730e0
InstructionNamer preserves everything.
...
llvm-svn: 58787
2008-11-06 01:00:16 +00:00
9e3e776e28
Emit label for llvm.dbg.func.start of the inlined function.
...
llvm-svn: 58786
2008-11-06 00:30:09 +00:00
0b0c99610c
Add post-build event for clangDriver (to copy clang.exe into "dstroot").
...
llvm-svn: 58783
2008-11-06 00:11:31 +00:00
d1c5c7f499
Undo 58778 but makes the binary dump prettier.
...
llvm-svn: 58782
2008-11-05 23:44:08 +00:00
f5f6f74c16
Add comments to function.
...
llvm-svn: 58781
2008-11-05 23:42:27 +00:00
fd2adbfa28
Encode pic load / store instructions; fix some encoding bugs.
...
llvm-svn: 58780
2008-11-05 23:22:34 +00:00
6158254d1d
Add command line option -entry-funcion to override entry function (default is main).
...
llvm-svn: 58779
2008-11-05 23:21:52 +00:00
51b9b9f6e2
Remove debug output that's not really useful.
...
llvm-svn: 58778
2008-11-05 23:21:11 +00:00
3777ed765f
Make ISel ignore dead nodes. The DAGCombiner normally eliminates
...
dead nodes, but in this case its missing one. Fixing the DAGCombiner
is desirable, but it's somewhat involved.
llvm-svn: 58777
2008-11-05 22:56:47 +00:00
912e7131a4
opt was not exporting the Mangler symbols
...
llvm-svn: 58775
2008-11-05 22:42:50 +00:00
f53d7ff870
Add PR number.
...
llvm-svn: 58765
2008-11-05 18:41:15 +00:00
81889d010c
Restructure ARM code emitter to use instruction formats instead of addressing modes to determine how to encode instructions.
...
llvm-svn: 58764
2008-11-05 18:35:52 +00:00
ce2417f4e1
Use an assert to check that SelectCode isn't called on
...
nodes that are already selected.
llvm-svn: 58763
2008-11-05 18:30:52 +00:00
87002dbea1
The HadDelete field is no longer used.
...
llvm-svn: 58761
2008-11-05 17:35:14 +00:00
7a638a8c7e
Reintroduce a comment that was removed with the AddToISelQueue
...
changes.
llvm-svn: 58760
2008-11-05 17:16:24 +00:00
22079067e1
Update some comments to reflect the new code.
...
llvm-svn: 58759
2008-11-05 17:13:57 +00:00
bfd58d87f3
Test commit, add Makefile for XCore target, more to follow.
...
llvm-svn: 58755
2008-11-05 09:53:58 +00:00
68035d4076
Fix thinko in ppcf128 expansion of truncating store.
...
llvm-svn: 58753
2008-11-05 07:17:27 +00:00
27889ab29f
Add more vector move low and zero-extend patterns.
...
llvm-svn: 58752
2008-11-05 06:04:51 +00:00
c7b04a12bb
Type of shuffle mask has changed.
...
llvm-svn: 58751
2008-11-05 06:04:18 +00:00
3cd5e8c97b
Indentation.
...
llvm-svn: 58750
2008-11-05 06:03:38 +00:00
f14b77ebf1
Eliminate the ISel priority queue, which used the topological order for a
...
priority function. Instead, just iterate over the AllNodes list, which is
already in topological order. This eliminates a fair amount of bookkeeping,
and speeds up the isel phase by about 15% on many testcases.
The impact on most targets is that AddToISelQueue calls can be simply removed.
In the x86 target, there are two additional notable changes.
The rule-bending AND+SHIFT optimization in MatchAddress that creates new
pre-isel nodes during isel is now a little more verbose, but more robust.
Instead of either creating an invalid DAG or creating an invalid topological
sort, as it has historically done, it can now just insert the new nodes into
the node list at a position where they will be consistent with the topological
ordering.
Also, the address-matching code has logic that checked to see if a node was
"already selected". However, when a node is selected, it has all its uses
taken away via ReplaceAllUsesWith or equivalent, so it won't recieve any
further visits from MatchAddress. This code is now removed.
llvm-svn: 58748
2008-11-05 04:14:16 +00:00
fd820528ab
Use getTargetConstant instead of getConstant for nodes that should not be visited
...
by isel and potentially forced into registers.
llvm-svn: 58747
2008-11-05 02:06:09 +00:00
132de1983f
Rename isGVLazyPtr to isGVNonLazyPtr relocation. This represents Mac OS X
...
indirect gv reference. Please don't call it lazy.
llvm-svn: 58746
2008-11-05 01:50:32 +00:00
f04bfc6989
New test case.
...
llvm-svn: 58745
2008-11-05 01:40:30 +00:00
f0ef35738c
Do now allow InlineAlways pass to remove dead functions.
...
llvm-svn: 58744
2008-11-05 01:39:16 +00:00
e94321305f
Silence unused variable warnings.
...
llvm-svn: 58743
2008-11-05 01:37:40 +00:00
7a848b0ee3
Check Attribute::NoInline.
...
llvm-svn: 58742
2008-11-05 01:37:05 +00:00
db045a3048
Remove dead variable.
...
llvm-svn: 58741
2008-11-05 00:56:35 +00:00
f1b4e2626b
Simplify the allocated size calculation.
...
llvm-svn: 58740
2008-11-05 00:54:27 +00:00
75e38fedc8
Fix comment
...
llvm-svn: 58739
2008-11-05 00:46:15 +00:00
26c10f1b4a
Use the new predicate to control when we do prealloc splitting. Fix a small bug.
...
llvm-svn: 58738
2008-11-05 00:32:13 +00:00
33ba5e78d2
Debugging output tweak.
...
llvm-svn: 58737
2008-11-05 00:22:28 +00:00
076e048cf7
CMake: updated list of source files.
...
llvm-svn: 58736
2008-11-05 00:11:22 +00:00
782e8346a5
Some code simplification. It now doesn't generate a prologue if the epilogue
...
isn't going to be generated.
llvm-svn: 58734
2008-11-05 00:00:21 +00:00
8cdea717a3
Add a new pass to simplify specific half_powr function calls. This is
...
a specialized pass that it not likely to be generally useful.
llvm-svn: 58732
2008-11-04 23:41:45 +00:00
db9d785338
On darwin, 32-bit x86 target is i386-apple-darwin...
...
llvm-svn: 58731
2008-11-04 23:13:50 +00:00
0460bb27e0
fix memory leak in pass manager when adding an analysis pass that already existed. as pass manager takes ownership of the added passes, it has to delete the pass if it isnt added to the pass list
...
tweak the opt tool so that it doesnt access a Pass after the ownership was taken by the pass manager
llvm-svn: 58730
2008-11-04 23:03:58 +00:00
d6948315b7
Fix tests not to emit IR output
...
llvm-svn: 58729
2008-11-04 23:02:39 +00:00
d31fc54f34
Small simplification of the stack guard type.
...
llvm-svn: 58728
2008-11-04 22:54:43 +00:00
2f40956c68
- Add a "getOrInsertGlobal" method to the Module class. This acts similarly to
...
"getOrInsertFunction" in that it either adds a new declaration of the global
and returns it, or returns the current one -- optionally casting it to the
correct type.
- Use the new getOrInsertGlobal in the stack protector code.
- Use "splitBasicBlock" in the stack protector code.
llvm-svn: 58727
2008-11-04 22:51:24 +00:00
a926ed4b50
First pass at checking for the creation of a new join point when doing pre-alloc splitting. This is not turned on yet.
...
llvm-svn: 58726
2008-11-04 22:22:41 +00:00
e3827d9061
Actually ARM / Mac OS X does have UINTTOFP_I64_F{64|32} libcalls.
...
llvm-svn: 58725
2008-11-04 22:19:55 +00:00
64adc71e9a
Update in response to feedback from Chris:
...
- Use enums instead of magic numbers.
- Rework algorithm to use the bytes size from the target to determine when to
emit stack protectors.
- Get rid of "propolice" in any comments.
- Renamed an option to its expanded form.
- Other miscellanenous changes.
More changes will come after this.
llvm-svn: 58723
2008-11-04 21:53:09 +00:00
e5f9d67a68
fix two validation errors
...
llvm-svn: 58722
2008-11-04 21:50:59 +00:00
6b7bb1f127
fix typos, harmonize formatting
...
llvm-svn: 58721
2008-11-04 21:48:10 +00:00
e842074c48
Revert 58687. This breaks mingw.
...
llvm-svn: 58719
2008-11-04 21:06:11 +00:00
0a7b4f5800
Allow SROA of vectors. Removing this caused a
...
huge performance regression in something we care
about. This may not be final fix.
llvm-svn: 58718
2008-11-04 20:54:03 +00:00
db6b956585
80 columns
...
llvm-svn: 58717
2008-11-04 20:52:49 +00:00
297b32a367
Custom lower bit_convert i64 -> f64 into FMDRR. This is now happening with legalizetypes.
...
llvm-svn: 58714
2008-11-04 19:57:48 +00:00
81edfc172e
Add note about cmake. Patch by Oscar Fuentes.
...
llvm-svn: 58712
2008-11-04 18:40:27 +00:00
daca2240b1
Give tablegen's Type a destructor, to suppress spurious
...
"Type has virtual functions but non-virtual destructor"
warnings.
llvm-svn: 58710
2008-11-04 18:09:07 +00:00
dd571d325e
Fix typo. Patch by nlewycky.
...
llvm-svn: 58709
2008-11-04 18:05:30 +00:00
4eaff40147
Debug output tweak.
...
llvm-svn: 58708
2008-11-04 17:58:53 +00:00
453844c352
LDM_RET restores pc, do not set 's' bit which would restore CPSR from SPSR.
...
llvm-svn: 58707
2008-11-04 17:57:07 +00:00
d5f935921a
Fix PR3011: LegalizeTypes support for scalarizing
...
SELECT_CC.
llvm-svn: 58706
2008-11-04 17:31:08 +00:00
20687e99b7
Duncan pointed out that the Extended case in getTypeForMVT could
...
be considerably simplified.
llvm-svn: 58703
2008-11-04 16:19:44 +00:00
72d10ab9ad
Add a return statement to suppress warnings in NDEBUG builds.
...
llvm-svn: 58702
2008-11-04 16:08:57 +00:00
ade09cd9d3
Add some asserts to verify MVT invariant assumptions.
...
llvm-svn: 58701
2008-11-04 16:03:56 +00:00
c6a5b0979f
regenerate
...
llvm-svn: 58697
2008-11-04 14:43:20 +00:00
0e92081b04
fix leakage of APFloats in getExistingVal()
...
llvm-svn: 58696
2008-11-04 14:42:19 +00:00
e4f5c9495f
regenerate
...
llvm-svn: 58694
2008-11-04 14:28:33 +00:00
724e67ec75
fix leakage of APSInt in getVal()
...
llvm-svn: 58693
2008-11-04 14:26:58 +00:00
57c6594e97
fix leakage of IfcvtTokens
...
llvm-svn: 58690
2008-11-04 13:02:59 +00:00
9340be4641
For some targets, it's not possible to place GVs in the same memory buffer as the MachineCodeEmitter allocated memory. Code and data has different read / write / execution privilege requirements.
...
This is a short term workaround. The current solution is for the JIT memory manager to manage code and data memory separately.
llvm-svn: 58688
2008-11-04 09:30:48 +00:00
a6dee4e28f
Don't "shell out" to resolve paths. Using pure perl makes llvm-config
...
friendlier to non-Unixes that happen to have perl. Patch from Sascha Othman!
llvm-svn: 58687
2008-11-04 08:05:21 +00:00
09053e62a9
80 col violation.
...
llvm-svn: 58684
2008-11-04 06:10:31 +00:00
2299c99d79
Stylistic change.
...
llvm-svn: 58683
2008-11-04 06:10:06 +00:00
c1d10e6b42
hasDisassembler should return false if disassembler isn't available.
...
llvm-svn: 58682
2008-11-04 06:09:38 +00:00
a69d8c50dc
CMakeLists: removed asmprinter component from
...
tools/llc/CMakeLists.txt.
llvm-svn: 58678
2008-11-04 03:28:37 +00:00
7751a7b78d
CMake: Support for building 32 bit mode libs and binaries on
...
Linux/x86-64.
llvm-svn: 58677
2008-11-04 03:27:24 +00:00
8881a91ae8
CMake: Updated list of source files.
...
llvm-svn: 58676
2008-11-04 03:24:04 +00:00
05d8417fa0
Initial checkin for stack protectors. Here's what it does:
...
* The prologue is modified to read the __stack_chk_guard global and insert it
onto the stack.
* The epilogue is modified to read the stored guard from the stack and compare
it to the original __stack_chk_guard value. If they differ, then the
__stack_chk_fail() function is called.
* The stack protector needs to be first on the stack (after the parameters) to
catch any stack-smashing activities.
Front-end support will follow after a round of beta testing.
llvm-svn: 58673
2008-11-04 02:10:20 +00:00
6dd08b6604
Handle ARM machine constantpool entries.
...
llvm-svn: 58671
2008-11-04 00:50:32 +00:00
b9110e7fbb
The ANDMask node folds to a constant, and isn't the node that needs to
...
have its node id set. The new and and shift nodes are the nodes that need
the IDs. This fixes PR2982.
llvm-svn: 58655
2008-11-03 23:43:55 +00:00
d26344d252
Fix unused variable warnings.
...
llvm-svn: 58653
2008-11-03 23:20:04 +00:00
f33f8a8606
Fix unused variable warnings.
...
llvm-svn: 58651
2008-11-03 23:14:09 +00:00
d5104a5de6
Add C bindings for extractvalue and insertvalue. Patch by Frits van Bommel!
...
llvm-svn: 58650
2008-11-03 22:55:43 +00:00
f60e5aaaac
Remove a dead switch statement.
...
llvm-svn: 58644
2008-11-03 21:26:52 +00:00
3620e685b5
Minor code restructuring. No functionality change.
...
llvm-svn: 58643
2008-11-03 21:02:39 +00:00
08535d2507
Fix some ppcf128 regressions: make ExpandFloatRes_LOAD
...
work correctly, and bring over a late change to ppcf128
SetCC handling.
llvm-svn: 58642
2008-11-03 20:47:45 +00:00
6692dec2a0
Make VAARG promotion work correctly with large funky
...
sized integers like i129, and also reduce the number
of assumptions made about how vaarg is implemented.
This still doesn't work correctly for small integers
like (eg) i1 on x86, since x86 passes each of them
(essentially an i8) in a 4 byte stack slot, so the
pointer needs to be advanced by 4 bytes not by 1 byte
as now. But this is no longer a LegalizeTypes problem
(it was also wrong in LT before): it is a bug in the
operation expansion in LegalizeDAG: now LegalizeTypes
turns an i1 vaarg into an i8 vaarg which would work
fine if only the i8 vaarg was turned into correct code
later.
llvm-svn: 58635
2008-11-03 20:22:12 +00:00
bde853911f
Overload AddInteger on int/long/long long instead of on int/int64_t,
...
to avoid overload ambiguities. This fixes build errors introduced
by r58623.
llvm-svn: 58632
2008-11-03 19:40:18 +00:00
fe57d109b6
Ignore conditions that are outside the loop.
...
llvm-svn: 58631
2008-11-03 19:38:07 +00:00
348f3fa6a7
add a period at the end of the comment, ignoring the fact that the comment would be hard pressed to be considered a sentence, but if it makes Bill happy...
...
llvm-svn: 58630
2008-11-03 19:29:29 +00:00
4d0549e3be
Add binary encoding support for multiply instructions. Some blanks left to fill in, but the basics are there.
...
llvm-svn: 58626
2008-11-03 18:38:31 +00:00
c1631db93b
Turn floating point IVs into integer IVs where possible.
...
This allows SCEV users to effectively calculate trip count.
LSR later on transforms back integer IVs to floating point IVs
later on to avoid int-to-float casts inside the loop.
llvm-svn: 58625
2008-11-03 18:32:19 +00:00
ac41d9f5d8
Refactor various TargetAsmInfo subclasses' TargetMachine members away
...
adding a TargetMachine member to the base TargetAsmInfo class instead.
llvm-svn: 58624
2008-11-03 18:22:42 +00:00
d7546abb8a
Change how extended types are represented in MVTs. Instead of fiddling
...
bits, use a union of a SimpleValueType enum and a regular Type*.
This increases the size of MVT on 64-bit hosts from 32 bits to 64 bits.
In most cases, this doesn't add significant overhead. There are places
in codegen that use arrays of MVTs, so these are now larger, but
they're small in common cases.
This eliminates restrictions on the size of integer types and vector
types that can be represented in codegen. As the included testcase
demonstrates, it's now possible to codegen very large add operations.
There are still some complications with using very large types. PR2880
is still open so they can't be used as return values on normal targets,
there are no libcalls defined for very large integers so operations
like multiply and divide aren't supported.
This also introduces a minimal tablgen Type library, capable of
handling IntegerType and VectorType. This will allow parts of
TableGen that don't depend on using SimpleValueType values to handle
arbitrary integer and vector types.
llvm-svn: 58623
2008-11-03 17:56:27 +00:00
d395a1722d
Comment fix.
...
llvm-svn: 58621
2008-11-03 17:33:36 +00:00
f9e7f69141
Remove redundant inline keywords from functions defined within
...
class definitions.
llvm-svn: 58620
2008-11-03 17:10:24 +00:00
45b86322f2
Ensure that we are checking only calls to the function we are interested in specializing
...
llvm-svn: 58615
2008-11-03 16:05:35 +00:00
fb2f87bbfe
Testcase for recent llvm-gcc fix
...
llvm-svn: 58611
2008-11-03 14:43:31 +00:00
0207a3f897
Make VAARG work with x86 long double (which is
...
10 bytes long, but is passed in 12/16 bytes).
llvm-svn: 58608
2008-11-03 11:51:11 +00:00
2530f5fe43
Make MachineFrameInfo::print not crash when no TargetFrameInfo is available.
...
llvm-svn: 58606
2008-11-03 11:16:43 +00:00
3a9aead4d4
Silence a compiler warning.
...
llvm-svn: 58598
2008-11-03 07:14:02 +00:00
7874fe900a
Typo
...
llvm-svn: 58594
2008-11-03 03:50:40 +00:00
Chris Lattner