Commits · c0bba1a96dd40b02ae3eff265664276d4033ee8b · Roger Ferrer / llvm-epi · GitLab

Nov 21, 2016
- [LoopReroll] Make root-finding more aggressive. · c0bba1a9
  Eli Friedman authored Nov 21, 2016
  c0bba1a9
- [InstCombine] canonicalize min/max constant to select's false value · 3b0bafee
  Sanjay Patel authored Nov 21, 2016
  3b0bafee
- reassociate-deadinst.ll: avoid accidental match on path · 1e567764
  Hubert Tong authored Nov 21, 2016
  1e567764
- [asan] Make ASan compatible with linker dead stripping on Windows · 01660a3d
  Reid Kleckner authored Nov 21, 2016
  01660a3d
- [MemorySSA] Fix unit tests broken by D26704 · 17e3f9b7
  Mandeep Singh Grang authored Nov 21, 2016
  17e3f9b7
- [mips] Add tests for half precision floating point support. · 40a5040c
  Simon Dardis authored Nov 21, 2016
  40a5040c
- [mips] seq macro support · 43115a1c
  Simon Dardis authored Nov 21, 2016
  43115a1c
- [AsmPrinter] Enable codeview for windows-itanium · 106e05a0
  Shoaib Meenai authored Nov 21, 2016
  106e05a0
- [MemorySSA] Fix for non-determinism in codegen · 73f0095d
  Mandeep Singh Grang authored Nov 21, 2016
  73f0095d
- [CodeGenPrep] Skip merging empty case blocks · 82f55c54
  Jun Bum Lim authored Nov 21, 2016
  82f55c54
- small fixup which enables the issuing of the aforementioned instruction (w/o... · 94ddbb4a
  Coby Tayree authored Nov 21, 2016
  94ddbb4a
- Fix known zero bits for addrspacecast. · 02f75f31
  Yaxun Liu authored Nov 21, 2016
  02f75f31
- [X86][SSE] Add SSE reciprocal estimate tests · 6704059a
  Simon Pilgrim authored Nov 21, 2016
  6704059a
- [SelectionDAG] Add ComputeNumSignBits support for CONCAT_VECTORS opcode · 49d7eda9
  Simon Pilgrim authored Nov 21, 2016
  49d7eda9
- [llvm-cov] Avoid 0% when reporting something that's 0/0 · 35369c1e
  Alex Lorenz authored Nov 21, 2016
  35369c1e
- Adjust arm64-irtranslator.ll test to changes from r287368 · 68dd8816
  Benjamin Kramer authored Nov 21, 2016
  68dd8816
- [X86][SSE] Allow PACKSS to be used to truncate any type of all/none sign bits input · b7bbaa66
  Simon Pilgrim authored Nov 21, 2016
  b7bbaa66
- [InstrProfiling] Mark __llvm_profile_instrument_target last parameter as i32... · 1c2bd1e9
  Marcin Koscielnicki authored Nov 21, 2016
  1c2bd1e9
- [AVX-512] Add EVEX form of VMOVZPQILo2PQIZrm to load folding tables to match SSE and AVX. · 9f2d632e
  Craig Topper authored Nov 21, 2016
  9f2d632e
- [bpf] attempt to fix big-endian bots · 2bb523f5
  Alexei Starovoitov authored Nov 21, 2016
  2bb523f5
- [bpf] fix dwarf elf relocs and line numbers · 7ab125db
  Alexei Starovoitov authored Nov 21, 2016
  7ab125db
- [XRay][AArch64] Implemented a test for the compile-time sleds emitted, and... · 31761f30
  Dean Michael Berris authored Nov 21, 2016
  31761f30
- [GlobalSplit] Port to the new pass manager. · 2ae76dd2
  Davide Italiano authored Nov 21, 2016
  2ae76dd2
Nov 20, 2016
- [mips] Restrict tail call optimization · 1dcb9110
  Simon Dardis authored Nov 20, 2016
  1dcb9110
- [X86][SSE] Add some initial combine tests that could (should?) use PACKSS · 0878d464
  Simon Pilgrim authored Nov 20, 2016
  0878d464
- [AVX-512] Add tests for masked palignr/valignd/valignq shuffles, many of which... · 85a1f5c2
  Craig Topper authored Nov 20, 2016
  85a1f5c2
- The 'vpmultishiftqb' instruction was implemented falsely, this patch amend it. · 99a66390
  Coby Tayree authored Nov 20, 2016
  99a66390
- Some instructions were missing, other implemented falsely. this patch aims at... · 97e9cf62
  Coby Tayree authored Nov 20, 2016
  97e9cf62
- [X86][AVX512] Combine unary + zero target shuffles to VPERMV3 with a zero vector where possible · 5fadce4a
  Simon Pilgrim authored Nov 20, 2016
  5fadce4a
- [X86][AVX512] Add support for VBMI VPERMV3 target shuffle combines · 5401bae5
  Simon Pilgrim authored Nov 20, 2016
  5401bae5
- [X86][AVX512] Add support for VBMI VPERMV target shuffle combines · 3f40412e
  Simon Pilgrim authored Nov 20, 2016
  3f40412e
- [X86][AVX512] Add some initial VBMI target shuffle combine tests · 9e3f5cc0
  Simon Pilgrim authored Nov 20, 2016
  9e3f5cc0
- [X86][AVX512F] Add support for uint_to_fp v2i32 to v2f64 on AVX512F-only targets · 096b6d4f
  Simon Pilgrim authored Nov 20, 2016
  096b6d4f
- [X86] RegCall - Handling long double arguments · c0f073b6
  Oren Ben Simhon authored Nov 20, 2016
  c0f073b6
- [bpf] add BPF disassembler · e6ddac0d
  Alexei Starovoitov authored Nov 20, 2016
  e6ddac0d
Nov 19, 2016
- [X86][SSE] Improve PSHUFB lowering from either input · a14e0cb8
  Simon Pilgrim authored Nov 19, 2016
  a14e0cb8
- [X86][AVX512] Add VPERMV/VPERMV3 v64i8 byte shuffles on avx512vbmi targets · 623a7c57
  Simon Pilgrim authored Nov 19, 2016
  623a7c57
- [ThinLTO] Fix crash when importing an opaque type · fec21582
  Mehdi Amini authored Nov 19, 2016
  fec21582
- [ThinLTO] Implement -pass-remarks-output in ThinLTOCodeGenerator · 19f176b9
  Mehdi Amini authored Nov 19, 2016
  19f176b9
- [X86][AVX512] Add avx512vbmi tests · f011f7e1
  Simon Pilgrim authored Nov 19, 2016
  f011f7e1