Commits · f832eb7e9f4dc161e11cad7adada2f3de90a16b3 · Roger Ferrer / llvm-epi · GitLab

Jun 07, 2016
- [X86][SSE] Improved blend+zero target shuffle combining to use combined shuffle mask directly · ca1da1bf
  Simon Pilgrim authored Jun 07, 2016
  ca1da1bf
- [ARM] Shrink post-indexed LDR and STR to LDM/STM · 53298a18
  James Molloy authored Jun 07, 2016
  53298a18
- [ARM] Transform LDMs into writeback form to save code size · 75afc951
  James Molloy authored Jun 07, 2016
  75afc951
- [ARM] Incorrect relocation type for Thumb2 B<cond>.w · 353a2286
  Peter Smith authored Jun 07, 2016
  353a2286
- [InstCombine][AVX2] Add support for simplifying AVX2 per-element shifts to native shifts · db9893fb
  Simon Pilgrim authored Jun 07, 2016
  db9893fb
- [InstCombine][SSE] Add MOVMSK constant folding (PR27982) · 91e3ac82
  Simon Pilgrim authored Jun 07, 2016
  91e3ac82
- [AVX512] Allow avx2 and sse41 nontemporal load intrinsics to select EVEX... · 2f90c1fe
  Craig Topper authored Jun 07, 2016
  2f90c1fe
- [AVX512] Remove unnecessary mayLoad, mayStore, hasSidEffects flags from... · e1cac15f
  Craig Topper authored Jun 07, 2016
  e1cac15f
- [AVX512] Add NoVLX to a couple patterns that have VLX equivalents. Ordering of... · 0fcf9256
  Craig Topper authored Jun 07, 2016
  0fcf9256
- [pdb] Use MappedBlockStream to parse the PDB directory. · d8447990
  Zachary Turner authored Jun 07, 2016
  d8447990
- [LibFuzzer] s/dataflow sanitizer/DataflowSanitizer/ · d15c106c
  Dan Liew authored Jun 07, 2016
  d15c106c
- [LibFuzzer] Disable building and running LSan tests on Apple platforms because... · 0d09f145
  Dan Liew authored Jun 07, 2016
  0d09f145
- ARM: correct TLS access on WoA · 532dcbc2
  Saleem Abdulrasool authored Jun 07, 2016
  532dcbc2
- ARM: clang-format a couple of switches, add comments · ce4eee49
  Saleem Abdulrasool authored Jun 07, 2016
  ce4eee49
- ARM: normalise space in the patterns · 0cd0cb99
  Saleem Abdulrasool authored Jun 07, 2016
  0cd0cb99
- Add comments. · 4a1ebae5
  Rui Ueyama authored Jun 07, 2016
  4a1ebae5
- Re-land "[codeview] Emit information about global variables" · 6f3406df
  Reid Kleckner authored Jun 07, 2016
  6f3406df
- Try one more time to pacify -Wpessimizing-move, MSVC, libstdc++4.7, and the... · 4ece163c
  Reid Kleckner authored Jun 06, 2016
  4ece163c
- Revert "[codeview] Emit information about global variables" · e8a236fc
  Reid Kleckner authored Jun 06, 2016
  e8a236fc
- [InstCombine] scalarizePHI should not assume the code it sees has been CSE'd · a0c6ae02
  Michael Kuperstein authored Jun 06, 2016
  a0c6ae02
- Attempt to work around lack of std::map::emplace in libstdc++4.7 · 52a155fc
  Reid Kleckner authored Jun 06, 2016
  52a155fc
- [codeview] Emit information about global variables · 87eddf72
  Reid Kleckner authored Jun 06, 2016
  87eddf72
- Verifier: Simplify and fix issue where we were not verifying unmaterialized functions. · bb738170
  Peter Collingbourne authored Jun 06, 2016
  bb738170
- [pdbdump] Verify the size of TPI hash records. · ba0aab94
  Rui Ueyama authored Jun 06, 2016
  ba0aab94
- Verifier: Remove dead code. · 71bb7943
  Peter Collingbourne authored Jun 06, 2016
  71bb7943
Jun 06, 2016
- [LibFuzzer] Provide stub implementation of __sanitizer_cov_trace_pc_indir · 59144071
  Dan Liew authored Jun 06, 2016
  59144071
- AMDGPU: Add function for getting instruction size · 02458c2d
  Matt Arsenault authored Jun 06, 2016
  02458c2d
- AMDGPU: Fix constantexpr addrspacecasts · 3b2e2a59
  Matt Arsenault authored Jun 06, 2016
  3b2e2a59
- [PM] Preserve the correct set of analyses for GVN. · fea0a4c5
  Davide Italiano authored Jun 06, 2016
  fea0a4c5
- [GVN] Switch dump() definition over to LLVM_DUMP_METHOD. · 82c44782
  Davide Italiano authored Jun 06, 2016
  82c44782
- [LoopUnrollAnalyzer] Fix a crash in analyzeLoopUnrollCost. · 19edbadf
  Michael Zolotukhin authored Jun 06, 2016
  19edbadf
- Reapply [LSR] Create fewer redundant instructions. · 43e5160d
  Geoff Berry authored Jun 06, 2016
  43e5160d
- [pdbdump] Print out New FPO stream contents. · ef2b4884
  Rui Ueyama authored Jun 06, 2016
  ef2b4884
- [MBP] Reduce code size by running tail merging in MBP. · 77ea3447
  Haicheng Wu authored Jun 06, 2016
  77ea3447
- [BranchFolding] Replace MachineBlockFrequencyInfo with MBFIWrapper. NFC. · 664b561f
  Haicheng Wu authored Jun 06, 2016
  664b561f
- [cpu-detection] Substantial refactor of Host CPU detection code (x86) · 76c4a855
  Alina Sbirlea authored Jun 06, 2016
  76c4a855
- [InstCombine] limit icmp transform to ConstantInt (PR28011) · 6a333c3e
  Sanjay Patel authored Jun 06, 2016
  6a333c3e
- [AMDGPU][llvm-mc] v_cndmask_b32: src2 is mandatory; do not enforce VOP2 when src2 == VCC. · 13548776
  Artem Tamazov authored Jun 06, 2016
  13548776
- [LAA] Use load and store vectors (NFC) · e3e3b994
  Matthew Simpson authored Jun 06, 2016
  e3e3b994
- [KNL] Fix UMULO lowering. · edafb059
  Igor Breger authored Jun 06, 2016
  edafb059