Commits · e7bdf227f66eb66fa2a34534bff7443aa1a7eead · Roger Ferrer / llvm-epi · GitLab

Jan 30, 2017
- [Inliner] Fold analysis remarks into missed remarks · e7bdf227
  Adam Nemet authored Jan 30, 2017
  e7bdf227
- [InstCombine] enable lshr(shl X, C1), C2 folds for vectors with splat constants · 1196d7cd
  Sanjay Patel authored Jan 30, 2017
  1196d7cd
- [InstCombine] add tests for shift-shift patterns; NFC · 127d6406
  Sanjay Patel authored Jan 30, 2017
  127d6406
Jan 29, 2017
- [InstCombine] enable (X >>?,exact C1) << C2 --> X << (C2 - C1) for vectors with splats · 062adaab
  Sanjay Patel authored Jan 29, 2017
  062adaab
- [InstCombine] add tests for shl(shr X, C1), C2 transforms; NFC · c0057483
  Sanjay Patel authored Jan 29, 2017
  c0057483
Jan 28, 2017
- [SLP] Vectorize loads of consecutive memory accesses, accessed in non-consecutive (jumbled) way. · 3121334d
  Mohammad Shahid authored Jan 28, 2017
  3121334d
- [InstCombine] Merge DebugLoc when speculatively hoisting store instruction · 505a25ae
  Taewook Oh authored Jan 28, 2017
  505a25ae
- [InstCombine] move icmp transforms that might be recognized as min/max and inf-loop (PR31751) · febcb9ce
  Sanjay Patel authored Jan 27, 2017
  febcb9ce
Jan 27, 2017
- [ARM/AArch64] Relocate and update InterleavedAccessPass tests (NFC) · 3650df13
  Matthew Simpson authored Jan 27, 2017
  3650df13
- [LICM] When we are recomputing the alias sets for a subloop, we cannot · fd2d7c72
  Chandler Carruth authored Jan 27, 2017
  fd2d7c72
- NewGVN: Add basic dead and redundant store elimination · c479686a
  Daniel Berlin authored Jan 27, 2017
  c479686a
- Constant fold switch inst when looking for trivial conditions to unswitch on. · e5f8d643
  Xin Tong authored Jan 27, 2017
  e5f8d643
- [PM] Port LoopLoadElimination to the new pass manager and wire it into · baabda93
  Chandler Carruth authored Jan 27, 2017
  baabda93
- [NVPTX] Upgrade NVVM intrinsics in InstCombineCalls. · 698c31b8
  Justin Lebar authored Jan 27, 2017
  698c31b8
- Revert a couple of InstCombine/Guard checkins · 7516192a
  Sanjoy Das authored Jan 26, 2017
  7516192a
Jan 26, 2017
- NewGVN: Fix bug exposed by PR31761 · 1ea5f324
  Daniel Berlin authored Jan 26, 2017
  1ea5f324
- [InstCombine] fold (X >>u C) << C --> X & (-1 << C) · 50753f02
  Sanjay Patel authored Jan 26, 2017
  50753f02
- [InstCombine] use m_APInt to allow (X << C) >>u C --> X & (-1 >>u C) with splat vectors · b0d96d32
  Sanjay Patel authored Jan 26, 2017
  b0d96d32
- [InstCombine] add tests for shift-shift folds; NFC · 0ca3f64c
  Sanjay Patel authored Jan 26, 2017
  0ca3f64c
- NewGVN: Fix output of pr31578 testcase now that we mark unreachable blocks as unreachable · 66e3a3d0
  Daniel Berlin authored Jan 26, 2017
  66e3a3d0
- NewGVN: Make unreachable blocks be marked with unreachable · 2b83492e
  Daniel Berlin authored Jan 26, 2017
  2b83492e
- [LV] Fix an issue where forming LCSSA in the place that we did would · 6f4ed077
  Chandler Carruth authored Jan 26, 2017
  6f4ed077
- [SLP] Add one more reduction operation for extra argument test to make · 7a7510ea
  Alexey Bataev authored Jan 26, 2017
  7a7510ea
- [SLP] Fixed test for extra arguments in horizontal reductions. · 7046a852
  Alexey Bataev authored Jan 26, 2017
  7046a852
- [PM] Simplify the new PM interface to the loop unroller and expose two · eab3b90a
  Chandler Carruth authored Jan 26, 2017
  eab3b90a
- [LoopUnroll] Properly update loopinfo for runtime unrolling by 2 · 5dd55e84
  Michael Kuperstein authored Jan 26, 2017
  5dd55e84
- [NewGVN] Skip uses in unreachable blocks. · ccbbc831
  Davide Italiano authored Jan 26, 2017
  ccbbc831
- LowerTypeTests: Ignore external globals with type metadata. · 1df6e858
  Peter Collingbourne authored Jan 26, 2017
  1df6e858
- [ValueTracking] Implement SignBitMustBeZero correctly for sqrt. · 7e3184c4
  Justin Lebar authored Jan 26, 2017
  7e3184c4
Jan 25, 2017
- [SLP] Extra test for functionality with extra args. · 1da8ba2a
  Alexey Bataev authored Jan 25, 2017
  1da8ba2a
- [Guards] Introduce loop-predication pass · 8fb3d57e
  Artur Pilipenko authored Jan 25, 2017
  8fb3d57e
- [InstCombine] Canonicalize guards for NOT OR condition · b85f7a5d
  Artur Pilipenko authored Jan 25, 2017
  b85f7a5d
- [InstCombine][SSE] Add support for PACKSS/PACKUS constant folding · 6f6b2791
  Simon Pilgrim authored Jan 25, 2017
  6f6b2791
- [InstCombine] Canonicalize guards for AND condition · 4df4c4a4
  Artur Pilipenko authored Jan 25, 2017
  4df4c4a4
- [InstCombine] Allow InstrCombine to remove one of adjacent guards if they are equivalent · e812ca00
  Artur Pilipenko authored Jan 25, 2017
  e812ca00
- [SLP] Improve horizontal vectorization for non-power-of-2 number of · d28ab559
  Alexey Bataev authored Jan 25, 2017
  d28ab559
- Mark @llvm.powi.* as safe to speculatively execute. · 16f1e5f1
  whitequark authored Jan 25, 2017
  16f1e5f1
- [X86] enable memory interleaving for X86\SLM arch. · 20caee95
  Mohammed Agabaria authored Jan 25, 2017
  20caee95
- [SimplifyCFG] Do not sink and merge inline-asm instructions. · 4ec7b20e
  Akira Hatanaka authored Jan 25, 2017
  4ec7b20e
- [InstCombine] Added regression test to narrow-swich.ll · 22921338
  Gerolf Hoflehner authored Jan 25, 2017
  22921338