Commits · 68a8efa374740a0829e77f57c8a2b13bead85d7f · Roger Ferrer / llvm-epi-0.8 · GitLab

This project is archived. Its data is read-only.

Feb 02, 2016
- [X86][FastISel] Don't force Nearest-Even rounding for VCVTPS2PH, use MXCSR. · 68a8efa3
  Ahmed Bougacha authored Feb 02, 2016
  68a8efa3
- [X86] Don't force Nearest-Even rounding for VCVTPS2PH, use MXCSR. · 55c6682a
  Ahmed Bougacha authored Feb 02, 2016
  55c6682a
- [X86][AVX512] Add support for AVX512 VMOVD (load) shuffle decoding · 5be17b6e
  Simon Pilgrim authored Feb 01, 2016
  5be17b6e
Feb 01, 2016
- [X86][AVX512] Add support for AVX512 VMOVSD/VMOVSS shuffle decoding · f5c23ad3
  Simon Pilgrim authored Feb 01, 2016
  f5c23ad3
- [X86][AVX512] Add support for AVX512 VINSERTPS shuffle decoding · 025a3d85
  Simon Pilgrim authored Feb 01, 2016
  025a3d85
- [X86][SSE] Regenerated load vector + element extraction tests. · e9848d4a
  Simon Pilgrim authored Feb 01, 2016
  e9848d4a
- [X86][SSE] Add AVX512 merge consecutive load tests · 068e38f7
  Simon Pilgrim authored Feb 01, 2016
  068e38f7
- Regenerate vector blend tests. · f3c37cc8
  Simon Pilgrim authored Feb 01, 2016
  f3c37cc8
- Regenerate vector sext/zext constant folding tests. · 32b25549
  Simon Pilgrim authored Feb 01, 2016
  32b25549
- [X86][AVX512VBMI] add encoding and intrinsics for Multishift · 5a3a0231
  Asaf Badouh authored Feb 01, 2016
  5a3a0231
- AVX512: fix mask handling for gather/scatter/prefetch intrinsics. · 56b039ea
  Igor Breger authored Feb 01, 2016
  56b039ea
- [X86][SSE] Find source of the inserted element of INSERTPS · 1358d866
  Simon Pilgrim authored Feb 01, 2016
  1358d866
- AVX512 : Fix SETCCE lowering for KNL 32 bit. · 6cc9115c
  Igor Breger authored Feb 01, 2016
  6cc9115c
Jan 29, 2016
- [X86] Add missing "CHECK" colon in r259065 test. · 0df98ff9
  Ahmed Bougacha authored Jan 29, 2016
  0df98ff9
- [WinEH] Don't perform state stores in cleanups · f2bb710d
  David Majnemer authored Jan 29, 2016
  f2bb710d
Jan 28, 2016
- [X86][AVX] Added more thorough 256-bit vector consecutive load tests. · 04241cef
  Simon Pilgrim authored Jan 28, 2016
  04241cef
- [X86] Don't transform X << 1 to X + X during type legalization · 4543ff09
  David Majnemer authored Jan 28, 2016
  4543ff09
- AVX512: Fix truncate v32i8 to v32i1 lowering implementation. · fca0a343
  Igor Breger authored Jan 28, 2016
  fca0a343
- [X86][AVX512] small fix in ptestm intrinsics · 42852d99
  Asaf Badouh authored Jan 28, 2016
  42852d99
Jan 27, 2016
- [X86][SSE] Test insertps instrinsic calls with masks that can't combine to something simpler · a73a0cfa
  Simon Pilgrim authored Jan 27, 2016
  a73a0cfa
- Revert "Allow X86::COND_NE_OR_P and X86::COND_NP_OR_E to be reversed." · d477e9e3
  Benjamin Kramer authored Jan 27, 2016
  d477e9e3
- AVX512: Fix vpmovzxbw predicate for AVX1/2 instructions. · b1bd47ca
  Igor Breger authored Jan 27, 2016
  b1bd47ca
- AVX512: Add store mask patterns. · d6c187b0
  Igor Breger authored Jan 27, 2016
  d6c187b0
Jan 26, 2016
- [X86][SSE] Added 8i8 to 8i64 sext/zext tests · 12e71db8
  Simon Pilgrim authored Jan 26, 2016
  12e71db8
- [X86] Add support for zeroed shuffle elements to getShuffleScalarElt · 00adc1e1
  Simon Pilgrim authored Jan 26, 2016
  00adc1e1
- Add a missing test case for r258847. · 26d04ef9
  Cong Hou authored Jan 26, 2016
  26d04ef9
- Allow X86::COND_NE_OR_P and X86::COND_NP_OR_E to be reversed. · 551a57f7
  Cong Hou authored Jan 26, 2016
  551a57f7
- [x86, AVX] tighten checks · 10e82d1d
  Sanjay Patel authored Jan 26, 2016
  10e82d1d
- [X86][SSE] Add zero element and general 64-bit VZEXT_LOAD support to EltsFromConsecutiveLoads · 46696ef9
  Simon Pilgrim authored Jan 26, 2016
  46696ef9
- [MC] Use .p2align instead of .align · 61d15ae4
  Dan Gohman authored Jan 26, 2016
  61d15ae4
Jan 25, 2016
- X86ISelLowering: Fix cmov(cmov) special lowering bug · 4e67e5c9
  Matthias Braun authored Jan 25, 2016
  4e67e5c9
- [X86][AVX] Add commutation support for VPERM2X128 instructions · d1d11809
  Simon Pilgrim authored Jan 25, 2016
  d1d11809
- [AVX512] Adding PTESTNMB/D/W/Q instruction · 1bd7f993
  Michael Zuckerman authored Jan 25, 2016
  1bd7f993
- [AVX512] Adding PTESTMB/W/D/Q instruction · 19670d47
  Michael Zuckerman authored Jan 25, 2016
  19670d47
- [X86][IFMA] adding intrinsics and encoding for multiply and add of unsigned 52bit integer · 655822ab
  Asaf Badouh authored Jan 25, 2016
  655822ab
- AVX1 : Enable vector masked_load/store to AVX1. · 6d421419
  Igor Breger authored Jan 25, 2016
  6d421419
Jan 24, 2016
- Added Skylake client to X86 targets and features · 29cde35b
  Elena Demikhovsky authored Jan 24, 2016
  29cde35b
- AVX512: VMOVDQU8/16/32/64 (load) intrinsic implementation. · 1e5bafbc
  Igor Breger authored Jan 24, 2016
  1e5bafbc
Jan 23, 2016
- [SelectionDAG] Generalised the CONCAT_VECTORS creation to support BUILD_VECTOR and UNDEF folding. · 02c1b54a
  Simon Pilgrim authored Jan 23, 2016
  02c1b54a
- regenerate checks and note some near-term improvements · a41ecae4
  Sanjay Patel authored Jan 23, 2016
  a41ecae4