Commits · e8b3ffa532b8ebac5dcdf17bb91b47817382c14d · Roger Ferrer / llvm-epi · GitLab

Oct 23, 2022
- [DAGCombiner] Fold (mul (sra X, BW-1), Y) -> (neg (and (sra X, BW-1), Y)) · e8b3ffa5
  Craig Topper authored Oct 22, 2022
  e8b3ffa5
Oct 22, 2022
- [X86] Add test coverage for shuffle with freeze · 6a28fa35
  Simon Pilgrim authored Oct 22, 2022
  
  6a28fa35
- [DAG] canCreateUndefOrPoison - add freeze(fsh(x,y,z)) -> fsh(freeze(x),freeze(y),freeze(z)) support · 7511303c
  Simon Pilgrim authored Oct 22, 2022
  7511303c
- [X86] Add test coverage for fshl/fshr with freeze · 01acdea9
  Simon Pilgrim authored Oct 22, 2022
  01acdea9
- [DAG] canCreateUndefOrPoison - add freeze(rot(x,y)) -> rot(freeze(x),freeze(y)) support · 89111707
  Simon Pilgrim authored Oct 22, 2022
  89111707
- [X86] Add test coverage for rotl/rotr with freeze · ae946aea
  Simon Pilgrim authored Oct 22, 2022
  
  ae946aea
- [X86] Add v2i64/v8i16/v16i8 + AVX2 coverage to saturated shift tests · b483349c
  Simon Pilgrim authored Oct 22, 2022
  b483349c
- [X86] Add AMX-FP16 instructions. · 661881d4
  Xiang1 Zhang authored Oct 22, 2022
  661881d4
Oct 21, 2022
- [X86] Fold scalar_to_vector(i64 zext(x)) -> bitcast(vzext_movl(scalar_to_vector(i32 x))) · 5ca77541
  Simon Pilgrim authored Oct 21, 2022
  5ca77541
- [X86][AVX] Eliminate redundant movzbl instruction. · 889911ec
  Luo, Yuanke authored Oct 19, 2022
  889911ec
Oct 20, 2022
- [X86][1/2] Support PREFETCHI instructions · 62ca7910
  Phoebe Wang authored Oct 20, 2022
  62ca7910
Oct 19, 2022
- [X86][RFC] Using `__bf16` for AVX512_BF16 intrinsics · bc181938
  Phoebe Wang authored Oct 19, 2022
  bc181938
Oct 17, 2022
- [X86] Lower vector interleave into unpck and perm · d0d48a91
  Han Zhu authored Sep 21, 2022
  d0d48a91
Oct 16, 2022
- [NFC][X86] Test commit, add test with bad mask vector legalization · 3c5a1649
  Roman Lebedev authored Oct 16, 2022
  3c5a1649
- [CodeGen] Using ZExt for extractelement indices. · c2e7c9cb
  Peter Rong authored Aug 30, 2022
  c2e7c9cb
Oct 14, 2022
- [AArch64][SME] Add support for arm_locally_streaming functions. · 02df03c5
  Sander de Smalen authored Oct 14, 2022
  02df03c5
- [InlineAsm][bugfix] Correct function addressing in inline asm · aad013de
  Xiang1 Zhang authored Sep 13, 2022
  aad013de
Oct 13, 2022
- [X86] Attempt to combine binary shuffles where both operands come from the same larger vector · fa9c12ed
  Simon Pilgrim authored Oct 13, 2022
  fa9c12ed
- [X86][AVX2] Add shuffle test case where we fail to merge... · 70557511
  Simon Pilgrim authored Oct 13, 2022
  70557511
Oct 12, 2022
- [X86] Pre-commit more unit tests for D134477 · 20be96b1
  Han Zhu authored Oct 11, 2022
  
  20be96b1
- Don't widen shuffle element with AVX512 · f885c080
  Luo, Yuanke authored Oct 12, 2022
  f885c080
- Revert "[DAGCombiner] Fold (mul (sra X, BW-1), Y) -> (neg (and (sra X, BW-1), Y))" · ac920975
  Craig Topper authored Oct 11, 2022
  ac920975
- [DAGCombiner] Fold (mul (sra X, BW-1), Y) -> (neg (and (sra X, BW-1), Y)) · 0148df81
  Craig Topper authored Oct 11, 2022
  0148df81
Oct 11, 2022
- Reland "[Clang][LoongArch] Add inline asm support for constraints k/m/ZB/ZC" · 42b70793
  Weining Lu authored Oct 11, 2022
  42b70793
Oct 10, 2022
- Revert "[TargetLowering][RISCV][X86] Support even divisors in expandDIVREMByConstant." · 0121b1a4
  Craig Topper authored Oct 10, 2022
  0121b1a4
- [TargetLowering][RISCV][X86] Support even divisors in expandDIVREMByConstant. · d4facda4
  Craig Topper authored Oct 10, 2022
  d4facda4
Oct 08, 2022
- [DAGCombine] Deduplicate addcarry node using commutativity. · 62ea6c5b
  Amaury Séchet authored Oct 08, 2022
  62ea6c5b
Oct 06, 2022
- [X86] Do not emit JCC to __x86_indirect_thunk · eac3e5c3
  Joao Moreira authored Oct 04, 2022
  eac3e5c3
Oct 04, 2022
- [SDAG] don't hoist div/rem through a select with neutral constant · 17dcbd81
  Sanjay Patel authored Oct 04, 2022
  17dcbd81
- [x86] add test for select + sdiv neutral constant; NFC · b2041494
  Sanjay Patel authored Oct 04, 2022
  
  b2041494
Oct 01, 2022
- [DAGCombine] Add tests for D57317 · e399c587
  Paweł Bylica authored Oct 01, 2022
  e399c587
- X86: Stop assigning register costs for longer encodings. · 189900eb
  Matthias Braun authored Aug 16, 2022
  189900eb
Sep 30, 2022
- [X86] Tweak avx512-gfni-intrinsics.ll tests to avoid xor(select(c,x,0)) 'passthrough' patterns · ba8e2cb9
  Simon Pilgrim authored Sep 30, 2022
  ba8e2cb9
- [GlobalISel] Do not crash on widening vector result · b3913a9c
  Serge Pavlov authored Jun 25, 2022
  b3913a9c
- [DAG] select Cond, C, -1 --> or (sext (not Cond)), C when C is MVT::i1 · d7600c7c
  Amaury Séchet authored Aug 06, 2022
  d7600c7c
Sep 29, 2022
- [X86] Avoid miscompile in combineOr (X86ISelLowering.cpp) · 0513b030
  Bjorn Pettersson authored Sep 29, 2022
  0513b030
- [X86] Pre-commit test case showing bug in combineOr (X86ISelLowering.cpp) · e4fcbf39
  Bjorn Pettersson authored Sep 29, 2022
  e4fcbf39
- [WinEH] Prepare test win64-funclet-preisel-intrinsics.ll for extension to... · 4a617c42
  Stefan Gränitz authored Sep 29, 2022
  4a617c42
Sep 27, 2022
- Change constant in cmov-promotion to avoid optimizations · c78e947d
  Amaury Séchet authored Sep 27, 2022
  
  c78e947d
- [X86] Add test case for D134736. NFC · 4bab490d
  Amaury Séchet authored Sep 27, 2022
  
  4bab490d