Commits · a9cd6aa895f7740cb7a125f3f45201c6402a6f4c · Roger Ferrer / llvm-epi-0.8 · GitLab

This is an archived project. Repository and other project resources are read-only.

Jul 05, 2016
- [AMDGPU] Assembler: Fix parsing error with floating-point literals passed to integer instructions · a9cd6aa8
  Sam Kolton authored Jul 05, 2016
  a9cd6aa8
- [mips][ias] Remove k_PhysReg since it's not possible to create an operand of this kind. · 976d938c
  Daniel Sanders authored Jul 05, 2016
  976d938c
- [Thumb] Reapply r272251 with a fix for PR28348 (mk 2) · ae5ff990
  James Molloy authored Jul 05, 2016
  ae5ff990
- Revert r274536: [mips][ias] Don't break apart and reconstruct StringRef's for k_Token. NFC. · 7b361a2c
  Daniel Sanders authored Jul 05, 2016
  7b361a2c
- [mips][ias] Don't break apart and reconstruct StringRef's for k_Token. NFC. · b2e0ca8e
  Daniel Sanders authored Jul 05, 2016
  b2e0ca8e
- [PowerPC] - Legalize vector types by widening instead of integer promotion · 44513e54
  Nemanja Ivanovic authored Jul 05, 2016
  44513e54
- AMDGPU/R600: Add PatFrags for selecting the correct vtx id for loads · 4a105d73
  Tom Stellard authored Jul 05, 2016
  4a105d73
Jul 04, 2016
- AMDGPU/SI: Remove hack for selecting < 32-bit loads to MUBUF instructions · 17a0ec54
  Tom Stellard authored Jul 04, 2016
  17a0ec54
- [X86][AVX512] Add support for lowering shuffles to VSHUFPD · 3ad04090
  Simon Pilgrim authored Jul 04, 2016
  3ad04090
- [AVX512] Remove masked VPERMD/VPERMQ/VPERMILPS/VPERMILPD intrinsics. They were... · 5d16cd9d
  Craig Topper authored Jul 04, 2016
  5d16cd9d
- AMDGPU/R600: Add indentation to VTX and TEX fetch asm strings · 991dfd7b
  Jan Vesely authored Jul 04, 2016
  991dfd7b
- Revert "[Thumb] Reapply r272251 with a fix for PR28348" · c3b4ed4a
  James Molloy authored Jul 04, 2016
  c3b4ed4a
- [Thumb] Reapply r272251 with a fix for PR28348 · 9f019835
  James Molloy authored Jul 04, 2016
  9f019835
Jul 03, 2016
- [X86] Add shuffle mask rescaling helper function. NFCI. · c804751a
  Simon Pilgrim authored Jul 03, 2016
  c804751a
- [X86][AVX2] Merge unary permute matching behind the same V2.isUndef() condition. NFCI. · 8e84fcf1
  Simon Pilgrim authored Jul 03, 2016
  8e84fcf1
- [X86][AVX512] Add support for 512-bit shuffle lowering to VPERMPD/VPERMQ · 7f096de0
  Simon Pilgrim authored Jul 03, 2016
  7f096de0
- [X86][AVX512] Add support for VPERMPD/VPERMQ masked shuffle comments · 68ea8064
  Simon Pilgrim authored Jul 03, 2016
  68ea8064
- [X86][AVX512] Add support for 512-bit shuffle decoding of VPERMPD/VPERMQ · a0d73835
  Simon Pilgrim authored Jul 03, 2016
  a0d73835
- [X86][AVX] Renamed VPERMILPI shuffle comment macros to be more specific · 5080e7f5
  Simon Pilgrim authored Jul 03, 2016
  5080e7f5
- [X86][AVX512] Add support for VPALIGNR/PSHUFD/PSHUFHW/PSHUFLW masked shuffle comments · dbd6db0d
  Simon Pilgrim authored Jul 03, 2016
  dbd6db0d
- [X86][AVX512] Add support for UNPCK masked shuffle comments · 598bdb6b
  Simon Pilgrim authored Jul 03, 2016
  598bdb6b
- [X86][AVX512] Add support for VPERM/VSHUF masked shuffle comments · 1f590761
  Simon Pilgrim authored Jul 03, 2016
  1f590761
- [X86][AVX512] Add support for PMOVZX masked shuffle comments · 68f438a0
  Simon Pilgrim authored Jul 03, 2016
  68f438a0
- [X86][AVX512] Add support for masked shuffle comments · 7c2fbdc1
  Simon Pilgrim authored Jul 03, 2016
  7c2fbdc1
- [X86][AVX512] Add support for lowering shuffles to VPERMILPS · 129b720c
  Simon Pilgrim authored Jul 03, 2016
  129b720c
Jul 02, 2016
- Fix spelling. · a7329dac
  Simon Pilgrim authored Jul 02, 2016
  a7329dac
- [X86][AVX512] Add support for lowering shuffles to VPERMILPD · 99e8a1aa
  Simon Pilgrim authored Jul 02, 2016
  99e8a1aa
- [X86][AVX512] Add support for 512-bit PSHUFB lowering · cde7c54b
  Simon Pilgrim authored Jul 02, 2016
  cde7c54b
- [X86][AVX512] Converted the MOVDDUP/MOVSLDUP/MOVSHDUP masked intrinsics to generic IR · 77dda7c2
  Simon Pilgrim authored Jul 02, 2016
  77dda7c2
- [Hexagon] Create global std::map lazily. · 4d9d2cc7
  Benjamin Kramer authored Jul 02, 2016
  4d9d2cc7
- [X86][AVX512] Add support for lowering shuffles to MOVDDUP/MOVSLDUP/MOVSHDUP · f040d8c0
  Simon Pilgrim authored Jul 02, 2016
  f040d8c0
- Use arrays or initializer lists to feed ArrayRefs instead of SmallVector where possible. · 3bc1edf9
  Benjamin Kramer authored Jul 02, 2016
  3bc1edf9
- [SystemZ] Move misplaced SystemZ::TDC to non-memory opcode range. · 32e8734e
  Marcin Koscielnicki authored Jul 02, 2016
  32e8734e
- AMDGPU: Add feature for unaligned access · 7f681ac7
  Matt Arsenault authored Jul 01, 2016
  7f681ac7
- AMDGPU: Expand unaligned accesses early · 8af47a09
  Matt Arsenault authored Jul 01, 2016
  8af47a09
- AMDGPU: Improve load/store of illegal types. · 327bb5ad
  Matt Arsenault authored Jul 01, 2016
  327bb5ad
Jul 01, 2016
- [Hexagon] Revert r274381: that was actually wrong · 1bba8961
  Krzysztof Parzyszek authored Jul 01, 2016
  1bba8961
- [Hexagon] Use MachineOperand::readsReg instead of isUse · a17250d8
  Krzysztof Parzyszek authored Jul 01, 2016
  a17250d8
- AMDGPU/SI: Enable testing several variants for si scheduler · 105c2a20
  Matt Arsenault authored Jul 01, 2016
  105c2a20
- Revert r274347 "[ARM] Refactor Thumb2 mul instruction descs" · a3bb5f15
  Hans Wennborg authored Jul 01, 2016
  a3bb5f15