Commits · c61ade1ca08dde0a05645ba58f9b826a7a15e3f9 · Raul Torres / llvm-target-spread · GitLab

Nov 13, 2017
- [SCEV] Handling for ICmp occuring in the evolution chain. · c61ade1c
  Jatin Bhateja authored Nov 13, 2017
  c61ade1c
- Revert "[CodeGenPrepare] Check that erased sunken address are not reused" · 8222160e
  Simon Dardis authored Nov 13, 2017
  8222160e
- [ARM GlobalISel] Update legalizer test · 69aa20e3
  Diana Picus authored Nov 13, 2017
  69aa20e3
- [PowerPC][msan] Update msan to handle changed memory layouts in newer kernels · 44156a0e
  Bill Seurer authored Nov 13, 2017
  44156a0e
- Inserting a base test for X86 performance nops · 4c679e14
  Omer Paparo Bivas authored Nov 13, 2017
  4c679e14
- [X86] test/testn intrinsics lowering to IR. llvm part. · 2aa707bd
  Uriel Korach authored Nov 13, 2017
  2aa707bd
- Move the setting of LLVM_BUILD_MODE to a macro so that we can re-use it in compiler-rt · 99e183cd
  Greg Bedwell authored Nov 13, 2017
  99e183cd
- [ARM] Place jump table as the first operand in additions · 842aa901
  Momchil Velikov authored Nov 13, 2017
  842aa901
- [CodeGenPrepare] Check that erased sunken address are not reused · 8e2a5bd2
  Simon Dardis authored Nov 13, 2017
  8e2a5bd2
- [CodeExtractor] Add missing AllowVarArgs initialization. · 71147559
  Florian Hahn authored Nov 13, 2017
  71147559
- [PartialInliner] Inline vararg functions that forward varargs. · 0e9dec67
  Florian Hahn authored Nov 13, 2017
  0e9dec67
- Test commit · 070a7ff1
  Sander de Smalen authored Nov 13, 2017
  070a7ff1
- [x86][AVX512] Lowering shuffle i/f intrinsics to LLVM IR · 9a7f9f12
  Jina Nahias authored Nov 13, 2017
  9a7f9f12
- [X86][SKX] Adding scheduling info of non-intrinsic + commutable SKX opcodes. · c9f23006
  Gadi Haber authored Nov 13, 2017
  c9f23006
- [X86] Limit NOPs to 7 bytes when 'slm' is spelled 'silvermont'. · 1af2adb9
  Craig Topper authored Nov 13, 2017
  1af2adb9
- [X86] Use sse_load_f32/f64 to improve load folding of scalar vfscalefss/sd,... · 75d71540
  Craig Topper authored Nov 13, 2017
  75d71540
- [X86] Regenerate test. NFC · c748455e
  Craig Topper authored Nov 13, 2017
  c748455e
- MI: Print ranges on MMO · 88efb9ff
  Matt Arsenault authored Nov 13, 2017
  88efb9ff
- [X86] Use sse_load_f32/f64 to improve load folding for scalar VFPCLASS intrinsics. · ca8abedb
  Craig Topper authored Nov 13, 2017
  ca8abedb
- [X86] Add tests for missed opportunities to fold a 128-bit vector load into... · bf328f26
  Craig Topper authored Nov 13, 2017
  bf328f26
- AMDGPU: Preserve nuw in shl add ptr combine · e5e0c742
  Matt Arsenault authored Nov 13, 2017
  e5e0c742
- [X86] Fix SQRTSS/SQRTSD/RCPSS/RCPSD intrinsics to use... · d4f60940
  Craig Topper authored Nov 13, 2017
  d4f60940
- [X86] Add tests for full vector loads to fold-load-unops.ll. · 24389c67
  Craig Topper authored Nov 13, 2017
  24389c67
- [X86] Regenerate fold-load-unops.ll and add and avx512f command line. · a95a1fd4
  Craig Topper authored Nov 13, 2017
  a95a1fd4
- AMDGPU: Fix multi-use shl/add combine · fbe95335
  Matt Arsenault authored Nov 13, 2017
  fbe95335
- [X86] Attempt to fix signed and unsigned comparison warning. · 23493f37
  Craig Topper authored Nov 13, 2017
  23493f37
- [X86] Use sse_load_f32/f64 in patterns for the memory forms of VRNDSCALESS/SD. · deee24b8
  Craig Topper authored Nov 13, 2017
  deee24b8
- [X86] Use EVEX encoded VRNDSCALE instructions to implement the legacy round intrinsics. · 63157c47
  Craig Topper authored Nov 13, 2017
  63157c47
- [X86] Split VRNDSCALE/VREDUCE/VGETMANT/VRANGE ISD nodes into versions with and... · 0af48f1a
  Craig Topper authored Nov 13, 2017
  0af48f1a
- Fix some misc. -enable-var-scope violations · 90e4f719
  Matt Arsenault authored Nov 13, 2017
  90e4f719
- AMDGPU: Select d16 loads into low component of register · e1cd482f
  Matt Arsenault authored Nov 13, 2017
  e1cd482f
- AMDGPU: Fix -enable-var-scope violations · 70b92820
  Matt Arsenault authored Nov 12, 2017
  70b92820
- AMDGPU: Fix missing gfx9 atomic inc/dec tests · cf9b6d8d
  Matt Arsenault authored Nov 12, 2017
  cf9b6d8d
Nov 12, 2017
- [X86] Add an X86ISD::RANGES opcode to use for the scalar intrinsics. · b42a23ff
  Craig Topper authored Nov 12, 2017
  b42a23ff
- [X86] Add test cases and command lines demonstrating how we accidentally... · 6b53c4a9
  Craig Topper authored Nov 12, 2017
  6b53c4a9
- [X86] Remove some no longer needed intrinsic lowering code. · 1382932c
  Craig Topper authored Nov 12, 2017
  1382932c
- [llvm] Remove redundant return [NFC] · d1046732
  Mandeep Singh Grang authored Nov 12, 2017
  d1046732
- [InstCombine] Teach visitICmpInst to not break integer absolute value idioms · d3e5781e
  Craig Topper authored Nov 12, 2017
  d3e5781e
Nov 11, 2017
- [X86] Use vrndscaleps/pd for 128/256 ffloor/ftrunc/fceil/fnearbyint/frint when avx512vl is enabled. · ac250825
  Craig Topper authored Nov 11, 2017
  ac250825
- [X86] Remove avx512-round.ll. The 512-bit rounding tests are now in... · ae9ffa1f
  Craig Topper authored Nov 11, 2017
  ae9ffa1f