| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | [AVX] Fix mask predicates for 256-bit UNPCKLPS/D and implement | David Greene | 2011-03-02 | 1 | -0/+8 |
| * | Recognize monitor/mwait with explicit register arguments | Joerg Sonnenberger | 2011-02-18 | 1 | -0/+8 |
| * | [AVX] Support VSINSERTF128 with more patterns and appropriate | David Greene | 2011-02-04 | 1 | -0/+17 |
| * | [AVX] VEXTRACTF128 support. This commit includes patterns for | David Greene | 2011-02-03 | 1 | -0/+17 |
| * | fix a missing shuffle pattern, PR9009. Patch by Artiom Myaskouvskey! | Chris Lattner | 2011-01-24 | 1 | -0/+3 |
| * | Fix PR8946, a missing reg/reg form of movdqu. | Chris Lattner | 2011-01-11 | 1 | -0/+4 |
| * | fix PR8900, a shuffle miscompilation. Patch by Nadav Rotem! | Chris Lattner | 2011-01-05 | 1 | -4/+4 |
| * | Implement feedback from Bruno on making pblendvb an x86-specific ISD node in ... | Nate Begeman | 2010-12-20 | 1 | -0/+3 |
| * | Add support for matching psign & plendvb to the x86 target | Nate Begeman | 2010-12-17 | 1 | -37/+13 |
| * | Add some missing predicates. | Nate Begeman | 2010-12-10 | 1 | -2/+4 |
| * | Formalize the notion that AVX and SSE are non-overlapping extensions from the... | Nate Begeman | 2010-12-10 | 1 | -1/+9 |
| * | Add support for AVX to materialize +0.0 when doing scalar FP. | Nate Begeman | 2010-12-09 | 1 | -0/+6 |
| * | Add patterns for the x86 popcnt instruction. | Benjamin Kramer | 2010-12-04 | 1 | -9/+12 |
| * | Scalar f32/f64 are also subregs of ymm regs | Nate Begeman | 2010-12-03 | 1 | -0/+6 |
| * | Implement a PseudoI class and transfer the sse instructions over to use | Eric Christopher | 2010-11-30 | 1 | -12/+10 |
| * | Rewrite mwait and monitor support and custom lower arguments. | Eric Christopher | 2010-11-30 | 1 | -4/+15 |
| * | Fix PR8211 | Bruno Cardoso Lopes | 2010-11-08 | 1 | -0/+6 |
| * | Fix pastos in handling of AVX cvttsd2si, PR8491. | Dale Johannesen | 2010-10-28 | 1 | -4/+4 |
| * | simplify some map operations. | Chris Lattner | 2010-10-07 | 1 | -1/+1 |
| * | Canonicalize X86ISD::MOVDDUP nodes to v2f64 to make sure all cases match. Als... | Evan Cheng | 2010-10-07 | 1 | -14/+8 |
| * | remove the !nameconcat tblgen feature. It "shorthand" and only used in 4 places | Chris Lattner | 2010-10-06 | 1 | -8/+8 |
| * | allow !strconcat to take more than two operands to eliminate | Chris Lattner | 2010-10-05 | 1 | -10/+6 |
| * | distribute the rest of the contents of X86Instr64bit.td out to | Chris Lattner | 2010-10-05 | 1 | -0/+22 |
| * | move CMOV_FR32 and friends to InstrCompiler, since they are | Chris Lattner | 2010-10-05 | 1 | -37/+20 |
| * | fix rdar://8490728 - llvm-mc rejects gpr64 form of 'movmskpd' | Chris Lattner | 2010-09-29 | 1 | -2/+4 |
| * | add assembler support for the cvtsd2sil/cvtsd2siq mnemonics, rdar://8456382 | Chris Lattner | 2010-09-29 | 1 | -2/+2 |
| * | add basic avx support to the disassembler, also teach it about ssmem/sdmem | Chris Lattner | 2010-09-29 | 1 | -16/+16 |
| * | add asmparser support for cvttpd2dq by removing some Int_ prefixes. | Chris Lattner | 2010-09-29 | 1 | -20/+14 |
| * | implement rdar://8456382 - cvtsd2si support, by removing some Int_ prefixes. | Chris Lattner | 2010-09-29 | 1 | -6/+4 |
| * | Fix typos. 128-bit PSHUFB takes 128-bit memory op. | Dale Johannesen | 2010-09-13 | 1 | -1/+1 |
| * | Add one more pattern to fallback movddup | Bruno Cardoso Lopes | 2010-09-09 | 1 | -0/+2 |
| * | Move remaining MMX instructions from SSE to MMX. | Dale Johannesen | 2010-09-09 | 1 | -45/+0 |
| * | Move most MMX instructions (defined as anything that | Dale Johannesen | 2010-09-09 | 1 | -120/+16 |
| * | x86 vector shuffle lowering now relies only on target specific | Bruno Cardoso Lopes | 2010-09-08 | 1 | -0/+8 |
| * | Add patterns for MMX that use the new intrinsics. | Dale Johannesen | 2010-09-07 | 1 | -2/+11 |
| * | Remove unused target specific node | Bruno Cardoso Lopes | 2010-09-07 | 1 | -4/+0 |
| * | Remove the rest of the nonexistent 64-bit AVX instructions. | Dale Johannesen | 2010-09-03 | 1 | -79/+76 |
| * | Reapply last harmless part of r112934, the pattern fragment to match X86Unpcklpd | Bruno Cardoso Lopes | 2010-09-03 | 1 | -0/+7 |
| * | Revert r112934, "- Use specific nodes to match unpckl masks.", which introduced | Daniel Dunbar | 2010-09-03 | 1 | -7/+0 |
| * | AVX doesn't support mm operations neither its instrinsics. | Bruno Cardoso Lopes | 2010-09-03 | 1 | -32/+32 |
| * | - Use specific nodes to match unpckl masks. | Bruno Cardoso Lopes | 2010-09-03 | 1 | -0/+7 |
| * | become more strict about when it's safe to use X86ISD::MOVLPS | Bruno Cardoso Lopes | 2010-09-02 | 1 | -3/+7 |
| * | Using target specific nodes for shuffle nodes makes the mask | Bruno Cardoso Lopes | 2010-09-01 | 1 | -0/+3 |
| * | Use movlps, movlpd, movss and movsd specific nodes instead of pattern matchin... | Bruno Cardoso Lopes | 2010-09-01 | 1 | -3/+31 |
| * | Use x86 specific MOVSLDUP node, add more patterns to match it and remove usel... | Bruno Cardoso Lopes | 2010-08-31 | 1 | -3/+3 |
| * | Use x86 specific MOVSHDUP node and add more patterns to match it | Bruno Cardoso Lopes | 2010-08-31 | 1 | -2/+2 |
| * | Use MOVLHPS and MOVHLPS x86 nodes whenever possible. Also remove some useless... | Bruno Cardoso Lopes | 2010-08-31 | 1 | -43/+14 |
| * | Use pshufhw and pshuflw in more cases and fix getTargetShuffleNode number of ... | Bruno Cardoso Lopes | 2010-08-24 | 1 | -0/+4 |
| * | This is the first step towards refactoring the x86 vector shuffle code. The | Bruno Cardoso Lopes | 2010-08-20 | 1 | -0/+349 |
| * | Revert 110491. While not wrong, it was based on a | Dale Johannesen | 2010-08-13 | 1 | -13/+8 |
