Commits · fc13bdd2db3035fc3693fec6aa086db4d1db3e4c · Roger Ferrer / llvm-epi · GitLab

Nov 29, 2016
- Avoid repeated calls to MVT getSizeInBits and getScalarSizeInBits(). NFCI. · edccc125
  Simon Pilgrim authored Nov 29, 2016
  edccc125
- [X86] Moved getTargetConstantFromNode function so a future patch is more understandable. NFCI. · 001368ab
  Simon Pilgrim authored Nov 29, 2016
  001368ab
- [X86][SSE] Add initial support for combining target shuffles to (V)PMOVZX. · 35c47c49
  Simon Pilgrim authored Nov 29, 2016
  35c47c49
- Avoid repeated calls to MVT::getScalarSizeInBits(). NFCI. · 923020a6
  Simon Pilgrim authored Nov 29, 2016
  923020a6
Nov 28, 2016
- MachineScheduler: Export function to construct "default" scheduler. · 115efcd3
  Matthias Braun authored Nov 28, 2016
  115efcd3
- [X86][SSE] Add initial support for combining (V)PMOVZX with shuffles. · 2228f70a
  Simon Pilgrim authored Nov 28, 2016
  2228f70a
- [x86] fix formatting; NFC · 100bc01a
  Sanjay Patel authored Nov 28, 2016
  100bc01a
- [X86][SSE] Added support for combining bit-shifts with shuffles. · 3f10e669
  Simon Pilgrim authored Nov 28, 2016
  3f10e669
Nov 27, 2016
- [X86][FMA4] Remove isCommutable from FMA4 scalar intrinsics. They aren't... · 17786f77
  Craig Topper authored Nov 27, 2016
  17786f77
- [X86][FMA] Add missing Predicates qualifier around scalar FMA intrinsic patterns. · 13b27a27
  Craig Topper authored Nov 27, 2016
  13b27a27
- [X86][FMA4] Add load folding support for FMA4 scalar intrinsic instructions. · ff9d4587
  Craig Topper authored Nov 27, 2016
  ff9d4587
- [X86] Add SHL by 1 to the load folding tables. · 3674f44e
  Craig Topper authored Nov 27, 2016
  3674f44e
- [X86][SSE] Add support for combining target shuffles to 128/256-bit PSLL/PSRL bit shifts · 91d6f5fb
  Simon Pilgrim authored Nov 27, 2016
  91d6f5fb
- [AVX-512] Add integer and fp unpck instructions to load folding tables. · 4fab4872
  Craig Topper authored Nov 27, 2016
  4fab4872
- [X86][SSE] Split lowerVectorShuffleAsShift ready for combines. NFCI. · cdb2ce66
  Simon Pilgrim authored Nov 27, 2016
  cdb2ce66
- [X86] Add TB_NO_REVERSE to entries in the load folding table where the... · 7ad961cc
  Craig Topper authored Nov 27, 2016
  7ad961cc
- [AVX-512] Add masked EVEX vpmovzx/sx instructions to load folding tables. · c3b3926f
  Craig Topper authored Nov 27, 2016
  c3b3926f
- [X86] Remove alignment restrictions from load folding table for some... · fb64a25b
  Craig Topper authored Nov 27, 2016
  fb64a25b
Nov 26, 2016
- [X86] Remove hasOneUse check that is redundant with the one in IsProfitableToFold. · 837ff25d
  Craig Topper authored Nov 26, 2016
  837ff25d
- [X86] Fix the zero extending load detection in... · e266e126
  Craig Topper authored Nov 26, 2016
  e266e126
- [X86] Simplify control flow. NFCI · d3ab1a39
  Craig Topper authored Nov 26, 2016
  d3ab1a39
- [X86] Add a hasOneUse check to selectScalarSSELoad to keep the same load from... · 991d1ca3
  Craig Topper authored Nov 26, 2016
  991d1ca3
- [AVX-512] Add unmasked EVEX vpmovzx/sx instructions to load folding tables. · 10d5eec1
  Craig Topper authored Nov 26, 2016
  10d5eec1
- [AVX-512] Add masked 128/256-bit integer add/sub instructions to load folding tables. · 97169ea5
  Craig Topper authored Nov 26, 2016
  97169ea5
- [AVX-512] Add masked 512-bit integer add/sub instructions to load folding tables. · 53b33de1
  Craig Topper authored Nov 26, 2016
  53b33de1
- [AVX-512] Teach LowerFormalArguments to use the extended register class when... · 6677bb4e
  Craig Topper authored Nov 26, 2016
  6677bb4e
- [AVX-512] Add VLX versions of VDIVPD/PS and VMULPD/PS to load folding tables. · 39265bb1
  Craig Topper authored Nov 26, 2016
  39265bb1
- [X86][XOP] Add a reversed reg/reg form for VPROT instructions. · 7f76c237
  Craig Topper authored Nov 26, 2016
  7f76c237
- [X86] Add SSE, AVX, and AVX2 version of MOVDQU to the load/store folding tables for consistency. · 516fd7ab
  Craig Topper authored Nov 26, 2016
  516fd7ab
- [AVX-512] Put the AVX-512 sections of the load folding tables into mostly... · a363d429
  Craig Topper authored Nov 25, 2016
  a363d429
Nov 25, 2016
- Use SDValue helper instead of explicitly going via SDValue::getNode(). NFCI · 8e8ae721
  Simon Pilgrim authored Nov 25, 2016
  8e8ae721
- [AVX-512] Add support for changing VSHUFF64x2 to VSHUFF32x4 when its feeding a... · 88071b37
  Craig Topper authored Nov 25, 2016
  88071b37
- [AVX-512] Add VPERMT2* and VPERMI2* instructions to load folding tables. · 1e488297
  Craig Topper authored Nov 25, 2016
  1e488297
- [X86] Invert an 'if' and early out to fix a weird indentation. NFCI · d4091494
  Craig Topper authored Nov 25, 2016
  d4091494
- [X86] Size a SmallVector to the worst case mask size for a 512-bit shuffle. NFCI · a4693618
  Craig Topper authored Nov 25, 2016
  a4693618
Nov 24, 2016
- Fix unused variable warning · f1ee930d
  Simon Pilgrim authored Nov 24, 2016
  f1ee930d
- [X86] Don't round trip a unique_ptr through a raw pointer for assignment. · fc54e35d
  Benjamin Kramer authored Nov 24, 2016
  fc54e35d
- [X86][SSE] Improve UINT_TO_FP v2i32 -> v2f64 · 9c71e072
  Simon Pilgrim authored Nov 24, 2016
  9c71e072
- [X86][AVX512] Add support for v2i64 fptosi/fptoui/sitofp/uitofp on AVX512DQ-only targets · 841d7ca4
  Simon Pilgrim authored Nov 24, 2016
  841d7ca4
- [X86][AVX512DQVL] Add awareness of vcvtqq2ps and vcvtuqq2ps implicit zeroing... · 7c26a6f9
  Simon Pilgrim authored Nov 24, 2016
  7c26a6f9