Commits · 29abfe4a8fe08bdd2f1c3b9e139a4547eb9261cc · Roger Ferrer / llvm-epi · GitLab

Feb 28, 2018
- [GlobalIsel][X86] Support G_INTTOPTR instruction. · c01f7504
  Alexander Ivchenko authored Feb 28, 2018
  c01f7504
- [GlobalIsel][X86] Support G_PTRTOINT instruction. · 46e07e36
  Alexander Ivchenko authored Feb 28, 2018
  46e07e36
- [X86] Don't use EXTRACT_ELEMENT from v1i1 with i8/i32 result type when we need... · 48d5ed26
  Craig Topper authored Feb 28, 2018
  48d5ed26
Feb 27, 2018
- Re-enable "[MachineCopyPropagation] Extend pass to do COPY source forwarding" · a2b90112
  Geoff Berry authored Feb 27, 2018
  a2b90112
- [X86][AVX] combineLoopMAddPattern - support 256-bit cases on AVX1 via SplitBinaryOpsAndApply · ba43ec87
  Simon Pilgrim authored Feb 27, 2018
  ba43ec87
Feb 26, 2018
- [X86] Add constant folding to combineMOVMSK. · e5d39e42
  Craig Topper authored Feb 26, 2018
  e5d39e42
- [X86] Add a custom legalization for (i16 (bitcast v16i1)) and (i32 (bitcast... · 5e0ceb88
  Craig Topper authored Feb 26, 2018
  5e0ceb88
- [X86][AVX] createPSADBW - support 256-bit cases on AVX1 via SplitBinaryOpsAndApply · db0ed7d7
  Simon Pilgrim authored Feb 26, 2018
  db0ed7d7
- [X86][AVX] Add AVX1 PSAD tests · 2f0aab92
  Simon Pilgrim authored Feb 26, 2018
  2f0aab92
- [X86][SSE] Regenerate PSAD tests · 98fcd2eb
  Simon Pilgrim authored Feb 26, 2018
  98fcd2eb
- [X86] Add avx1 command line to madd.ll to show splitting and concatenating 256-bit operations. · f340a0e8
  Craig Topper authored Feb 26, 2018
  f340a0e8
- [X86] Don't use getZExtValue when we have no idea how large the input elements are. · 5c980eba
  Craig Topper authored Feb 26, 2018
  5c980eba
- [X86] Remove VT.isSimple() check from detectAVGPattern. · 79d189f5
  Craig Topper authored Feb 26, 2018
  79d189f5
Feb 24, 2018
- [TargetLowering] SimplifyDemandedVectorElts - pass demanded elts through ADD/SUB ops · 295e8b4e
  Simon Pilgrim authored Feb 24, 2018
  295e8b4e
- [TargetLowering] SimplifyDemandedVectorElts - pass demanded elts through TRUNCATE ops · c0dbdb86
  Simon Pilgrim authored Feb 24, 2018
  c0dbdb86
- [X86] Add cvt tests to avx512vl-intrinsics-fast-isel.ll · a6f81007
  Craig Topper authored Feb 24, 2018
  a6f81007
- [X86] Allow int_x86_sse2_cvtps2dq and int_x86_avx_cvt_ps2dq_256 to select EVEX... · 81c0eaf4
  Craig Topper authored Feb 24, 2018
  81c0eaf4
- [X86][SSE] combineSubToSubus - support v8i64 handling from SSSE3 · a4fb5694
  Simon Pilgrim authored Feb 24, 2018
  a4fb5694
- [X86][SSE] combineSubToSubus - support v8i32 handling from SSSE3 (not SSE41) · 8ad91261
  Simon Pilgrim authored Feb 24, 2018
  8ad91261
- [X86][SSE] combineSubToSubus - begun generalizing to work with any type sizes... · 744f008a
  Simon Pilgrim authored Feb 24, 2018
  744f008a
- [X86] Remove checks for '(scalar_to_vector (i8 (trunc GR32:)))' from scalar masked move patterns. · 7bcac492
  Craig Topper authored Feb 24, 2018
  7bcac492
- [DebugInfo] Support DWARF v5 source code embedding extension · 16c7bdaf
  Scott Linder authored Feb 23, 2018
  16c7bdaf
Feb 23, 2018
- Intrinsics calls should avoid the PLT when "RtLibUseGOT" metadata is present. · 609f8c01
  Sriraman Tallam authored Feb 23, 2018
  609f8c01
- [X86] Add DAG combine to remove (and X, 1) from in front of a v1i1 scalar to vector. · 61d6ddbf
  Craig Topper authored Feb 23, 2018
  61d6ddbf
- [X86][SSE] Generalize x > C-1 ? x+-C : 0 --> subus x, C combine for non-uniform constants · 425965be
  Simon Pilgrim authored Feb 23, 2018
  425965be
- [X86][SSE] Add x > C-1 ? x+-C : 0 --> subus x, C test caaes for non-uniform constants · 14686059
  Simon Pilgrim authored Feb 23, 2018
  14686059
- [X86] Custom split v32i16/v64i8 bitcasts when AVX512F is available, but BWI is not. · 11704dcc
  Craig Topper authored Feb 23, 2018
  11704dcc
- [X86] Regenerate i128 multiply tests · 43e8e400
  Simon Pilgrim authored Feb 23, 2018
  43e8e400
- Support for the mno-stack-arg-probe flag · 89c35fc4
  Hans Wennborg authored Feb 23, 2018
  89c35fc4
- [X86][F16C] Regenerate half conversion tests · 17f01c39
  Simon Pilgrim authored Feb 23, 2018
  17f01c39
- [DAGCOmbine] Ensure that (brcond (setcc ...)) is handled in a canonical manner. · 893a6b89
  Amaury Sechet authored Feb 23, 2018
  893a6b89
- Remove file missed by r325852 due to merge conflict. · 1a9a404f
  Richard Smith authored Feb 23, 2018
  1a9a404f
- Revert r325128 ("[X86] Reduce Store Forward Block issues in HW"). · ade53736
  Richard Smith authored Feb 23, 2018
  ade53736
- [X86] Turn setne X, signedmax into setgt signedmax, X in LowerVSETCC to avoid an invert · 0dcc88a5
  Craig Topper authored Feb 23, 2018
  0dcc88a5
- [X86] Turn setne X, signedmin into setgt X, signedmin in LowerVSETCC to avoid an invert · d2fab308
  Craig Topper authored Feb 22, 2018
  d2fab308
Feb 22, 2018
- [X86][AVX512] Add DQ+VLX scalar int<->fp tests cases for D43441 · b8237d2e
  Simon Pilgrim authored Feb 22, 2018
  b8237d2e
- [X86][MMX] Generlize MMX_MOVD64rr combines to accept v4i16/v8i8 build vectors as well as v2i32 · 55b7e011
  Simon Pilgrim authored Feb 21, 2018
  55b7e011
Feb 21, 2018
- [X86][MMX] Add MMX_MOVD64rr build vector tests showing undef elements in the lower half · 664582b7
  Simon Pilgrim authored Feb 21, 2018
  664582b7
- [X86][MMX] Run MMX bitcast test on 32 and 64-bit targets · 7f078eab
  Simon Pilgrim authored Feb 21, 2018
  7f078eab
- [X86][MMX] Regenerate MMX MASKMOV test · 01da1191
  Simon Pilgrim authored Feb 21, 2018
  01da1191