97a5bb1157
fix some validation errors <it> -> <i>
...
llvm-svn: 59070
2008-11-11 19:35:15 +00:00
5f04ce98f2
fix some validation errors.
...
llvm-svn: 59069
2008-11-11 19:34:28 +00:00
6096f26bd4
Add utility pass to remove dbg info.
...
llvm-svn: 59068
2008-11-11 19:33:39 +00:00
6ce09d73f0
remove an extraneous tag
...
llvm-svn: 59067
2008-11-11 19:31:26 +00:00
d402cc7b6a
Make this document *substantially* better and cover a lot more territory.
...
Document written by Mason Woo (http://www.woo.com )!
llvm-svn: 59066
2008-11-11 19:30:41 +00:00
38d2c7e0e8
Silence unused variable warning.
...
llvm-svn: 59064
2008-11-11 19:17:41 +00:00
95b18126ee
Use actual function name in comments.
...
llvm-svn: 59063
2008-11-11 19:16:41 +00:00
5499e89d06
Change the scheduler accessor methods to accept an explicit TargetMachine
...
argument instead of taking the SelectionDAG's TargetMachine. This is
needed for some upcoming scheduler changes.
llvm-svn: 59055
2008-11-11 17:50:47 +00:00
2d1937ede5
Add a README entry.
...
llvm-svn: 59052
2008-11-11 17:35:52 +00:00
93bf988701
CMake: forces rebuild of llvm-config's library dependency info when a
...
library is added or changed.
llvm-svn: 59051
2008-11-11 17:10:58 +00:00
a08c2905ad
CMake: corrected split of Alpha and Sparc AsmPrinters.
...
llvm-svn: 59050
2008-11-11 17:10:13 +00:00
90cf22e013
CMake: Removed unnecessary library path setting that was breaking the
...
build on OS X.
Fix by Jjgod Jiang!
llvm-svn: 59048
2008-11-11 16:56:52 +00:00
03e084d482
Separate sparc asmprinter. This should unbreak the native build
...
llvm-svn: 59047
2008-11-11 16:42:57 +00:00
f4caceb668
Separate alpha asmprinter. This should unbreak native build.
...
llvm-svn: 59046
2008-11-11 16:42:17 +00:00
059c4fa8d8
The 32-bit displacement field in an x86 address is signed. Arrange for it
...
to be sign-extended when it is promoted to 64 bits for intermediate
offset calculations. The offset calculations are done as uint64_t so that
overflow conditions are well defined.
This fixes a problem which is currently hidden by the x86 AsmPrinter but
which was exposed by r58917 (which is temporarily reverted). See PR3027
for details.
llvm-svn: 59044
2008-11-11 15:52:29 +00:00
8cb2e28e43
Update CMakeLists.txt
...
llvm-svn: 59039
2008-11-11 09:55:48 +00:00
49a5ce863e
Fix for PR3040:
...
The CC was changed, but wasn't checked to see if it was legal if the DAG
combiner was being run after legalization. Threw in a couple of checks just to
make sure that it's okay. As far as the PR is concerned, no back-end target
actually exhibited this problem, so there isn't an associated testcase.
llvm-svn: 59035
2008-11-11 08:25:46 +00:00
2126a6d3c4
fix another libgcc blocker
...
llvm-svn: 59026
2008-11-11 06:06:07 +00:00
774e9ac433
Cleaned up and fix bugs in convert_rndsat node
...
llvm-svn: 59025
2008-11-11 05:40:06 +00:00
4942f296c9
Un-XFAIL tests now that they're fixed.
...
llvm-svn: 59023
2008-11-11 04:44:42 +00:00
aab89ca749
Unbreak the buildbot and back out (inadvertant) casting edits in CellSPU
...
backend.
llvm-svn: 59018
2008-11-11 03:06:06 +00:00
ac2af2fdb2
Encode VFP arithmetic instructions.
...
llvm-svn: 59016
2008-11-11 02:11:05 +00:00
53b39b5467
Cleanup debug info. assocated with deleted instructions.
...
llvm-svn: 59012
2008-11-11 00:54:10 +00:00
dc6699e82f
Add utility routines to remove dead debug info.
...
llvm-svn: 59011
2008-11-11 00:53:02 +00:00
6fcefa065e
r59009 broke these tests. XFAIL for now.
...
llvm-svn: 59010
2008-11-11 00:36:10 +00:00
abad22cf45
CellSPU: Fix bug 3606, as well as some ongoing work.
...
llvm-svn: 59009
2008-11-10 23:43:06 +00:00
cfa3e287bb
Small simplification. Use the iterator already present as the insertion point.
...
llvm-svn: 59008
2008-11-10 23:38:59 +00:00
b172c66af3
Comments and indentation.
...
llvm-svn: 59007
2008-11-10 23:26:16 +00:00
02771dc473
Correct PIC function stub codegen.
...
llvm-svn: 59006
2008-11-10 23:14:47 +00:00
54c1dedd42
CMake: Fixed cross-compiling.
...
`clean' makefile target removes add-hoc directory created for building
the native tablegen.
llvm-svn: 59005
2008-11-10 22:09:59 +00:00
d3b33fea65
Fix indentation.
...
llvm-svn: 59004
2008-11-10 22:09:58 +00:00
b85755c829
Temporarily revert r58979 and related patch. It's causing a failure in X86 bootstrap:
...
Comparing stages 2 and 3
warning: ./cc1-checksum.o differs
warning: ./cc1obj-checksum.o differs
warning: ./cc1objplus-checksum.o differs
warning: ./cc1plus-checksum.o differs
Bootstrap comparison failure!
./alias.o differs
./alloc-pool.o differs
./attribs.o differs
./bb-reorder.o differs
./bitmap.o differs
./build/errors.o differs
./build/genattrtab.o differs
./build/genautomata.o differs
./build/genemit.o differs
./build/genextract.o differs
...
-bw
llvm-svn: 59003
2008-11-10 21:22:06 +00:00
747f59f0f7
- Make sure that we don't over-increment the iterator when going through the
...
basic blocks.
- Minor code clean-up.
llvm-svn: 59002
2008-11-10 21:13:10 +00:00
58fb9135e2
Added CONVERT_RNDSAT (conversion with rounding and saturation) SDNode to
...
support targets that support these conversions. Users should avoid using
this node as the current targets don't generating code for it.
llvm-svn: 59001
2008-11-10 20:54:11 +00:00
74eefb5722
Update VC++ project file.
...
llvm-svn: 58997
2008-11-10 20:03:21 +00:00
d0ce981372
If the sign of exit condition and split condition does not match
...
then do not split loop index.
llvm-svn: 58995
2008-11-10 19:48:34 +00:00
ddacbb39ab
Fix PR2667: add soft float support for sint_to_fp/uint_to_fp
...
where the argument is an apint, or smaller than the minimum
size for which there is a libcall (i32).
llvm-svn: 58994
2008-11-10 17:36:26 +00:00
13b2e3634b
Tweak some comments.
...
llvm-svn: 58993
2008-11-10 17:31:56 +00:00
7da4b44dd1
Small cleanups. No functionality change intended!
...
llvm-svn: 58992
2008-11-10 17:29:56 +00:00
d5b53e1c6c
When promoting the result of fp_to_uint/fp_to_sint,
...
inform the optimizers that the result must be zero/
sign extended from the smaller type. For example,
if a fp to unsigned i16 is promoted to fp to i32,
then we are allowed to assume that the extra 16 bits
are zero (because the result of fp to i16 is undefined
if the result does not fit in an i16). This is
quite aggressive, but should help the optimizers
produce better code. This requires correcting a
test which thought that fp_to_uint is some kind
of truncation, which it is not: in the testcase
(which does fp to i1), either the fp value converts
to 0 or 1 or the result is undefined, which is
quite different to truncation.
llvm-svn: 58991
2008-11-10 17:28:30 +00:00
0a758fae91
Work around PR1000.
...
llvm-svn: 58984
2008-11-10 10:05:09 +00:00
8e58c52b37
Proper way of doing llvm canadian-cross compilation.
...
Patch by Jim Grosbach!
llvm-svn: 58981
2008-11-10 07:33:13 +00:00
23be3fd970
Reenable test.
...
llvm-svn: 58980
2008-11-10 07:30:32 +00:00
671743369c
Really fix testb optimization on big-endian.
...
Fixes ppc32 bootstrap.
llvm-svn: 58979
2008-11-10 07:16:42 +00:00
7ef7314d1a
Third time's a charm.
...
The previous patches didn't match correctly. Also, we need to make sure that
the conditional is the same before doing the transformation.
llvm-svn: 58978
2008-11-10 06:59:06 +00:00
2a09239563
final edits
...
llvm-svn: 58966
2008-11-10 05:40:34 +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
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
Chris Lattner