RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 20:23:11 +01:00
Code Issues Projects Releases Wiki Activity
41,639 Commits 4 Branches 5 Tags 704 MiB
61f8207ac9
Commit Graph

25101 Commits

Author SHA1 Message Date
Jim Grosbach
61f8207ac9 Clarify naming and correct conditional so that CMP and CMN instructions get the Rn operand encoded properly 
llvm-svn: 57252
 2008-10-07 17:42:09 +00:00
Jim Grosbach
a52546fec4 Fix Opcode values of CMP and CMN 
llvm-svn: 57251
 2008-10-07 17:40:46 +00:00
Andrew Lenharth
950618a347 No need for |= 
llvm-svn: 57249
 2008-10-07 17:11:29 +00:00
Andrew Lenharth
2399c6cb95 Use ADDC if it is valid at any smaller size. Do it right this time 
llvm-svn: 57248
 2008-10-07 17:09:16 +00:00
Andrew Lenharth
84166420cc Use ADDC if it is valid at any smaller size. fixes test/Codegen/Generic/i128-addsub.ll on x86 
llvm-svn: 57247
 2008-10-07 17:03:15 +00:00
Anders Carlsson
a9c42526f8 Certain patterns involving the "movss" instruction were marked as requiring SSE2, when in reality movss is an SSE1 instruction. 
llvm-svn: 57246
 2008-10-07 16:14:11 +00:00
Andrew Lenharth
c00c2a0058 Expand arith on machines without carry flags 
llvm-svn: 57243
 2008-10-07 14:15:42 +00:00
Andrew Lenharth
7a997d1cfd Note that ADDC and company don't actually expand yet (missing in legalize 
llvm-svn: 57226
 2008-10-07 02:10:26 +00:00
Dale Johannesen
3b86d974bc Mark negative-zero-to-int conversion as Inexact, 
since -0.0 can't be represented as an int.
This prevents llvm from reducing -0.0 to a
load-and-convert of int 0.  Fixes
ieee.exp/mzero[2356].c in gcc testsuite.

llvm-svn: 57224
 2008-10-07 00:40:01 +00:00
Dan Gohman
188af3ae0d Correctly handle calls with no return values. This fixes 
2006-01-23-UnionInit on x86-64 when inlining is not enabled.

llvm-svn: 57223
 2008-10-07 00:12:37 +00:00
Devang Patel
378c8633e5 Fix typo, fix PR 2865. 
llvm-svn: 57221
 2008-10-06 23:22:54 +00:00
Dale Johannesen
40d00c0979 Be more precise about which conversions of NaNs 
are Inexact.  (These are not Inexact as defined
by IEEE754, but that seems like a reasonable way
to abstract what happens:  information is lost.)

llvm-svn: 57218
 2008-10-06 22:59:10 +00:00
Evan Cheng
88d76ffe8a Fix PR2850 and PR2863. Only generate movddup for 128-bit SSE vector shuffles. 
llvm-svn: 57210
 2008-10-06 21:13:08 +00:00
Dale Johannesen
24ea5f2be7 Temporarily revert functionality change from my previous patch; 
it is too aggressive.

llvm-svn: 57203
 2008-10-06 20:43:48 +00:00
Devang Patel
ca66d093c0 Remove interfaces implemented by dead pass from the list of available passes. 
Patch By Matthijs Kooijman.

llvm-svn: 57202
 2008-10-06 20:36:36 +00:00
Dale Johannesen
89329a1d0a Mark shortening NaN conversions as Inexact. PR 2856. 
Improve description of unsupported formats.

llvm-svn: 57185
 2008-10-06 18:22:29 +00:00
Devang Patel
07a9ce22e4 It is possible that all functions in one module are not being 
optimized for size. Set OptForSize for each function separately.

llvm-svn: 57182
 2008-10-06 18:03:39 +00:00
Dan Gohman
8b33abdd5b Don't dereference the end() iterator. Thanks to 
ENABLE_EXPENSIVE_CHECKS for finding this.

llvm-svn: 57181
 2008-10-06 18:00:07 +00:00
Devang Patel
4f91b766d2 Remove unncessary isDeclaration() checks. 
llvm-svn: 57179
 2008-10-06 17:30:07 +00:00
Matthijs Kooijman
12cd5d041d Allow scalarrepl to treat an all-zero GEP just as bitcast. 
This includes not marking a GEP involving a vector as unsafe, but only when it
has all zero indices. This allows scalarrepl to work in a few more cases.

llvm-svn: 57177
 2008-10-06 16:23:31 +00:00
Chris Lattner
8e41e3ac13 reorder #include order, patch by Kenneth Boyd! 
llvm-svn: 57148
 2008-10-06 03:54:25 +00:00
Chris Lattner
5d6871b940 Add #include to get alloca, patch by Kenneth Boyd! 
llvm-svn: 57147
 2008-10-06 03:53:16 +00:00
Chris Lattner
4622ca2262 fix an incorrect and extremely confusing error message 
llvm-svn: 57123
 2008-10-05 18:24:03 +00:00
Chris Lattner
1e4f7de3b6 make the autoupgrade code for ret attributes dramatically simpler 
and actually work.  We can now read the llvm 2.3 bc file from PR2849

llvm-svn: 57122
 2008-10-05 18:22:09 +00:00
Nuno Lopes
4cf7f0e3cd regenerate 
llvm-svn: 57114
 2008-10-05 16:49:34 +00:00
Nuno Lopes
9e274c3532 clean ArgTypeListI production: free the PATypeHolder 
llvm-svn: 57113
 2008-10-05 16:49:03 +00:00
Anton Korobeynikov
8106145480 Emit type-correct constant null. Also fix a typo. 
Patch by Robert G. Jakabosky!

llvm-svn: 57110
 2008-10-05 15:07:06 +00:00
Anton Korobeynikov
1f7e8162d9 Fix weird think-o and unbreak build on all gcc-3.4.x-based platforms (e.g. mingw) 
llvm-svn: 57106
 2008-10-05 08:53:29 +00:00
Chris Lattner
ed0f84ee2d this case is matched now. 
llvm-svn: 57096
 2008-10-05 02:16:12 +00:00
Chris Lattner
107e8f8b60 rewrite bswap matching to be more general, allowing arbitrary 
shifting and masking inside a bswap expr.  This allows it to handle
the cases from PR2842, which involve the intermediate 'or' 
expressions being shifted, not just the input value.

llvm-svn: 57095
 2008-10-05 02:13:19 +00:00
Chris Lattner
6fae76bbf3 fix a bug where the bswap matcher could match a case involving 
ashr.  It should only apply to lshr.

llvm-svn: 57089
 2008-10-05 00:50:57 +00:00
Chris Lattner
576e29c87d wrap some long lines and expand i32 mul's to libcalls, inspired by a 
patch by Mikael Lepisto!

llvm-svn: 57077
 2008-10-04 21:27:46 +00:00
Oscar Fuentes
4bf1c53073 CMake: Reflected changes on source file structure. New plugin support 
for llvmc2 incomplete.

llvm-svn: 57076
 2008-10-04 21:18:50 +00:00
Duncan Sands
e22385630e Ignore loads from and stores to local memory (i.e. allocas) 
when deciding whether to mark a function readnone/readonly.
Since the pass is currently run before SROA, this may be
quite helpful.  Requested by Chris on IRC.

llvm-svn: 57050
 2008-10-04 13:24:24 +00:00
Nick Lewycky
53e751fcba Allow the construction of SCEVs with SCEVCouldNotCompute operands, by 
implementing folding. Fixes PR2857.

llvm-svn: 57049
 2008-10-04 11:19:07 +00:00
Anton Korobeynikov
4cc9051fbb Revert r56675 - it breaks unwinding runtime everywhere. 
llvm-svn: 57048
 2008-10-04 11:09:36 +00:00
Argyrios Kyrtzidis
8614f628d2 Add implementations for sys::Memory::setWritable and sys::Memory::setExecutable on Win32 platform. 
llvm-svn: 57047
 2008-10-04 08:15:32 +00:00
Argyrios Kyrtzidis
b9e76c172c Fix compilation error on MSVC. 
llvm-svn: 57046
 2008-10-04 08:11:49 +00:00
Dan Gohman
5944450d5f Fix fast-isel's handling of atomic instructions. They may 
expand to multiple basic blocks, in which case fast-isel
needs to informed of which block to use as it resumes
inserting instructions.

llvm-svn: 57040
 2008-10-04 00:56:36 +00:00
Dan Gohman
638a8001c8 Fix a bug in the local allocator's liveness computation where it 
was setting kill flags on tied uses in two-address instructions.
The kill flags were causing the allocator to think it could
allocate the use and its tied def in different registers.

llvm-svn: 57039
 2008-10-04 00:31:14 +00:00
Dale Johannesen
dc83b95ba5 Make atomic Swap work, 64-bit on x86-32. 
Make it all work in non-pic mode.

llvm-svn: 57034
 2008-10-03 22:25:52 +00:00
Dan Gohman
700611dfc6 Clean up some multiple-return-value code that is no longer 
applicable.

llvm-svn: 57033
 2008-10-03 22:21:24 +00:00
Devang Patel
0d22d8ebdb Fix function attribute verification check. 
Thanks Duncan!

llvm-svn: 57029
 2008-10-03 21:11:02 +00:00
Dale Johannesen
27d8955b8f Pass MemOperand through for 64-bit atomics on 32-bit, 
incidentally making the case where the memop is a
pointer deref work.  Fix cmp-and-swap regression.

llvm-svn: 57027
 2008-10-03 19:41:08 +00:00
Devang Patel
55401473f9 Nick Lewycky's patch. 
While hosting instruction check PHI node.

llvm-svn: 57025
 2008-10-03 18:57:37 +00:00
Dan Gohman
dc99a744fd Use -1ULL instead of uint64_t(-1), at Anton's suggestion. 
llvm-svn: 57021
 2008-10-03 17:56:45 +00:00
Devang Patel
2bed4d4ca0 Verify function attributes. 
llvm-svn: 57020
 2008-10-03 17:50:00 +00:00
Evan Cheng
d572afd76c Fix typos pointed out by Duncan. Also untabify these files. 
llvm-svn: 57018
 2008-10-03 17:11:58 +00:00
Daniel Dunbar
40fb36a42c Unbreak build. 
llvm-svn: 57017
 2008-10-03 17:11:57 +00:00
Dan Gohman
00034b1416 Avoid creating two TargetLowering objects for each target. 
Instead, just create one, and make sure everything that needs
it can access it. Previously most of the SelectionDAGISel
subclasses all had their own TargetLowering object, which was
redundant with the TargetLowering object in the TargetMachine
subclasses, except on Sparc, where SparcTargetMachine
didn't have a TargetLowering object. Change Sparc to work
more like the other targets here.

llvm-svn: 57016
 2008-10-03 16:55:19 +00:00