| Commit message (Expand) | Author | Age | Files | Lines |
* | Filecheck-ize. | Bill Wendling | 2011-09-30 | 1 | -1/+3 |
* | Add new line at end of file. | Bill Wendling | 2011-09-30 | 1 | -1/+1 |
* | When inferring the pointer alignment, if the global doesn't have an initializer | Bill Wendling | 2011-09-30 | 1 | -0/+26 |
* | LSR: rewrite inner loops only. | Andrew Trick | 2011-09-29 | 5 | -8/+20 |
* | PR11033: Make sure we don't generate PCMPGTQ and PCMPEQQ if the target CPU do... | Eli Friedman | 2011-09-28 | 1 | -0/+35 |
* | Remove X86-dependent stuff from SSEDomainFix. | Jakob Stoklund Olesen | 2011-09-27 | 2 | -3/+3 |
* | Last batch of test conversions to new atomic instructions. | Eli Friedman | 2011-09-27 | 10 | -1923/+963 |
* | Convert a bunch more tests over to the new atomic instructions. | Eli Friedman | 2011-09-26 | 10 | -1088/+69 |
* | Only run MF.verify() with EXPENSIVE_CHECKS=1. | Jakob Stoklund Olesen | 2011-09-24 | 1 | -3/+0 |
* | Verify that terminators follow non-terminators. | Jakob Stoklund Olesen | 2011-09-23 | 1 | -0/+3 |
* | PR10998: It is not legal to sink an instruction past the terminator of a bloc... | Eli Friedman | 2011-09-23 | 1 | -0/+43 |
* | PR10989: Don't print .hidden on Windows. | Eli Friedman | 2011-09-23 | 1 | -6/+13 |
* | PR10991: make fast-isel correctly check whether accessing a global through an... | Eli Friedman | 2011-09-22 | 1 | -1/+17 |
* | Synthesize SSE3/AVX 128 bit horizontal add/sub instructions from | Duncan Sands | 2011-09-22 | 1 | -0/+194 |
* | Do not unnecessarily use AT_specification DIE because it does not add any value. | Devang Patel | 2011-09-21 | 1 | -0/+20 |
* | add another testcase for pr10902 | Nadav Rotem | 2011-09-21 | 1 | -0/+12 |
* | [VECTOR-SELECT] Address one of the bugs in pr10902. | Nadav Rotem | 2011-09-21 | 1 | -0/+15 |
* | Add a DAGCombine for subvector extracts to remove useless chains of | Bruno Cardoso Lopes | 2011-09-20 | 1 | -0/+19 |
* | Revert r140097, working on a better approach | Bruno Cardoso Lopes | 2011-09-20 | 1 | -7/+0 |
* | test/CodeGen/X86/avx-minmax.ll: Unbreak Win32. | NAKAMURA Takumi | 2011-09-20 | 1 | -4/+4 |
* | Extend changes from r139986 to produce 256-bit AVX minps/minpd/maxps/maxpd. | Craig Topper | 2011-09-20 | 1 | -0/+65 |
* | Attempt to fix -mtriple=i686-{cygwin|mingw|win32} regressions. Nakamura, | Bruno Cardoso Lopes | 2011-09-20 | 5 | -7/+7 |
* | Based on the small opt Zvi's patch was trying to achieve, eliminate | Bruno Cardoso Lopes | 2011-09-19 | 1 | -0/+8 |
* | Match X86ISD::FSETCCsd and X86ISD::FSETCCss while in AVX mode. This fix | Bruno Cardoso Lopes | 2011-09-19 | 1 | -0/+18 |
* | setOperationAction should be done on the return value of the type, not the op... | Nadav Rotem | 2011-09-18 | 1 | -0/+12 |
* | When promoting integer vectors we often create ext-loads. This patch adds a | Nadav Rotem | 2011-09-18 | 1 | -0/+82 |
* | Apply Duncan's test fix from r139986 to the avx version of that test too. | Benjamin Kramer | 2011-09-18 | 1 | -4/+4 |
* | Synthesize x86 max/min instructions also for vectors (i.e. produce | Duncan Sands | 2011-09-17 | 2 | -7/+39 |
* | Test case trial and error. Not sure the proper way to check MBB names. | Andrew Trick | 2011-09-16 | 1 | -7/+7 |
* | Reduced a stronger test case for coalescer bug PR10920. | Andrew Trick | 2011-09-16 | 1 | -22/+81 |
* | VirtRegMap is counting spill slots, not register spills. | Jakob Stoklund Olesen | 2011-09-15 | 1 | -1/+1 |
* | Change all checks regarding the presence of any SSE level to always | Bruno Cardoso Lopes | 2011-09-15 | 1 | -1/+1 |
* | [regcoalescing] bug fix for RegistersDefinedFromSameValue. | Andrew Trick | 2011-09-15 | 1 | -0/+115 |
* | Add integer promotion support for vselect | Nadav Rotem | 2011-09-14 | 1 | -0/+17 |
* | Vector shuffle mask <i32 4, i32 5, i32 2, i32 3> should yield "movsd", not "m... | Bruno Cardoso Lopes | 2011-09-14 | 1 | -0/+14 |
* | Remove unnecessary old test. | Devang Patel | 2011-09-14 | 1 | -49/+0 |
* | Error out on CodeGen of unaligned load/store. Fix test so it isn't accidenta... | Eli Friedman | 2011-09-13 | 1 | -2/+2 |
* | update checked pattern | Nadav Rotem | 2011-09-13 | 1 | -1/+19 |
* | Add vselect target support for targets that do not support blend but do support | Nadav Rotem | 2011-09-13 | 1 | -0/+37 |
* | Change testcase commandline to be more strict and silence buildbots | Bruno Cardoso Lopes | 2011-09-12 | 1 | -1/+1 |
* | Fix PR10845. SUBREG_TO_REG shouldn't be used when the input and | Bruno Cardoso Lopes | 2011-09-12 | 1 | -0/+14 |
* | Revert the wrong part of r139528, and fix testcases. | Bruno Cardoso Lopes | 2011-09-12 | 2 | -4/+4 |
* | Not sure how CMPPS and CMPPD had already ever worked, I guess it didn't. | Bruno Cardoso Lopes | 2011-09-12 | 2 | -0/+37 |
* | Really un-XFAIL the testcase, like I said I would in r139458. | Eli Friedman | 2011-09-10 | 1 | -1/+0 |
* | Fixed an assert from: | Richard Trieu | 2011-09-10 | 1 | -0/+1 |
* | Implement vector-select support for avx256. Refactor the vblend implementatio... | Nadav Rotem | 2011-09-09 | 1 | -0/+38 |
* | Add a AVX version of a simple i64 -> f64 bitcast. This could be | Bruno Cardoso Lopes | 2011-09-08 | 1 | -0/+10 |
* | Reapply testcase from r139309! | Bruno Cardoso Lopes | 2011-09-08 | 1 | -0/+47 |
* | Remove this crashing test, until I figure out what's going wrong here | Bruno Cardoso Lopes | 2011-09-08 | 1 | -47/+0 |
* | Add AVX versions of blend vector operations and fix some issues noticed | Bruno Cardoso Lopes | 2011-09-08 | 2 | -0/+47 |