| Commit message (Expand) | Author | Age | Files | Lines |
* | DeadStoreElimination can now trim the size of a store if the end of the store... | Pete Cooper | 2011-11-09 | 1 | -0/+78 |
* | Add check so we don't try to perform an impossible transformation. Fixes issu... | Eli Friedman | 2011-11-09 | 1 | -0/+15 |
* | AVX2: Add patterns for variable shift operations | Nadav Rotem | 2011-11-09 | 1 | -2/+73 |
* | Use REs to remove dependencies on the register allocation order. | Chad Rosier | 2011-11-09 | 1 | -24/+24 |
* | Speculatively revert commit 144124 (djg) in the hope that the 32 bit | Duncan Sands | 2011-11-09 | 2 | -17/+7 |
* | Add AVX2 support for vselect of v32i8 | Nadav Rotem | 2011-11-09 | 1 | -0/+19 |
* | Enable execution dependency fix pass for YMM registers when AVX2 is enabled. ... | Craig Topper | 2011-11-09 | 1 | -0/+38 |
* | Add instruction selection for AVX2 integer comparisons. | Craig Topper | 2011-11-09 | 1 | -0/+58 |
* | Add AVX2 instruction lowering for add, sub, and mul. | Craig Topper | 2011-11-09 | 1 | -0/+76 |
* | Don't forget to check FlagNW when determining whether an AddRecExpr will wrap | Nick Lewycky | 2011-11-09 | 1 | -0/+35 |
* | Add support for encoding immediates in icmp and fcmp. Hopefully, this will | Chad Rosier | 2011-11-09 | 1 | -0/+214 |
* | Collapse DomainValues across loop back-edges. | Jakob Stoklund Olesen | 2011-11-09 | 1 | -0/+45 |
* | Add a hack to the scheduler to disable pseudo-two-address dependencies in | Dan Gohman | 2011-11-08 | 2 | -7/+17 |
* | Add workaround for Cortex-M3 errata 602117 by replacing ldrd x, y, [x] with l... | Evan Cheng | 2011-11-08 | 1 | -11/+12 |
* | Fix code to match comment. Fixes PR11340, a regression from r143209. | Eli Friedman | 2011-11-08 | 1 | -0/+10 |
* | LICM pass now understands invariant load metadata. Nothing generates this ye... | Pete Cooper | 2011-11-08 | 1 | -0/+39 |
* | Adding test for machine-licm operating on invariant load instructions | Pete Cooper | 2011-11-08 | 1 | -0/+29 |
* | Lower mem-ops to unaligned i32/i16 load/stores on ARM where supported. | Lang Hames | 2011-11-08 | 1 | -6/+9 |
* | test/CodeGen/X86/vec_shuffle-39.ll: Add explicit -mtriple=x86_64-linux. Passi... | NAKAMURA Takumi | 2011-11-08 | 1 | -1/+1 |
* | test/CodeGen/X86/vec_shuffle-38.ll: Relax expression for Win32 x64. | NAKAMURA Takumi | 2011-11-08 | 1 | -1/+1 |
* | test/CodeGen/X86/vec_shuffle.ll: Add explicit -mtriple=i686-linux. We may see... | NAKAMURA Takumi | 2011-11-08 | 1 | -1/+1 |
* | Make sure to mark vector extload's as expand on ARM. Fixes PR11319. | Eli Friedman | 2011-11-08 | 1 | -0/+15 |
* | Add a bunch of calls to RemoveDeadNode in LegalizeDAG, so legalization doesn'... | Eli Friedman | 2011-11-08 | 1 | -0/+14 |
* | Add x86 isel logic and patterns to match movlps from clang generated IR for _... | Evan Cheng | 2011-11-08 | 2 | -2/+52 |
* | Convert to the new EH model. | Bill Wendling | 2011-11-08 | 2 | -20/+15 |
* | Convert to the new EH model. | Bill Wendling | 2011-11-08 | 3 | -28/+20 |
* | Convert tests to the new EH model. | Bill Wendling | 2011-11-08 | 6 | -51/+29 |
* | Enable support for returning i1, i8, and i16. Nothing special todo as it's the | Chad Rosier | 2011-11-08 | 1 | -0/+15 |
* | Added missing newline | Pete Cooper | 2011-11-08 | 1 | -1/+1 |
* | Revert r144034 while I try to track down a crash. | Eli Friedman | 2011-11-07 | 1 | -14/+0 |
* | Fix test for Windows as well. | Jakob Stoklund Olesen | 2011-11-07 | 1 | -1/+0 |
* | Kill and collapse outstanding DomainValues. | Jakob Stoklund Olesen | 2011-11-07 | 7 | -23/+44 |
* | InstCombine now optimizes vector udiv by power of 2 to shifts | Pete Cooper | 2011-11-07 | 1 | -0/+15 |
* | Add a bunch of calls to RemoveDeadNode in LegalizeDAG, so legalization doesn'... | Eli Friedman | 2011-11-07 | 1 | -0/+14 |
* | Simplify some uses of utohexstr. | Benjamin Kramer | 2011-11-07 | 8 | -51/+51 |
* | Fix test for Linux. | Jakob Stoklund Olesen | 2011-11-07 | 1 | -1/+1 |
* | Expand V_SET0 to xorps by default. | Jakob Stoklund Olesen | 2011-11-07 | 7 | -10/+31 |
* | Add AVX2 variable shift instructions and intrinsics. | Craig Topper | 2011-11-07 | 1 | -0/+80 |
* | Add AVX2 VPMOVMASK instructions and intrinsics. | Craig Topper | 2011-11-07 | 1 | -0/+64 |
* | Add AVX2 VEXTRACTI128 and VINSERTI128 instructions. Fix VPERM2I128 to be qual... | Craig Topper | 2011-11-07 | 1 | -0/+16 |
* | More AVX2 instructions and their intrinsics. | Craig Topper | 2011-11-06 | 1 | -0/+40 |
* | Add more AVX2 instructions and intrinsics. | Craig Topper | 2011-11-06 | 1 | -0/+80 |
* | Add support for passing i1, i8, and i16 call parameters. Also, be sure to | Chad Rosier | 2011-11-05 | 1 | -0/+67 |
* | Update lit's list of tools. | Benjamin Kramer | 2011-11-05 | 1 | -4/+6 |
* | Add an option to pad an uleb128 to MCObjectWriter and remove the uleb128 enco... | Benjamin Kramer | 2011-11-05 | 3 | -7/+4 |
* | Do simple cross-block DSE when we encounter a free statement. Fixes PR11240. | Nick Lewycky | 2011-11-05 | 1 | -4/+22 |
* | Enhanced vzeroupper insertion pass that avoids inserting vzeroupper where it ... | Eli Friedman | 2011-11-04 | 1 | -13/+70 |
* | build/cmake: Change to require Python be available. | Daniel Dunbar | 2011-11-04 | 1 | -51/+47 |
* | Add triple to test. | Rafael Espindola | 2011-11-04 | 1 | -1/+1 |
* | Emit declarations before definitions if they are available. This causes DW_AT... | Rafael Espindola | 2011-11-04 | 1 | -0/+65 |