Commits · eb4a55e066b6c6af99573d6ae6f9c41abfa0c110 · Roger Ferrer / llvm-epi-0.8 · GitLab

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

Dec 09, 2016
- AMDGPU: Clean up instruction bits · eb4a55e0
  Matt Arsenault authored Dec 09, 2016
  eb4a55e0
- Revert "In visitSTORE, always use FindBetterChain, rather than only when UseAA is enabled." · bedb5d90
  Nirav Dave authored Dec 09, 2016
  bedb5d90
- In visitSTORE, always use FindBetterChain, rather than only when UseAA is enabled. · fd51ff4f
  Nirav Dave authored Dec 09, 2016
  fd51ff4f
- AMDGPU/SI: Don't mark VINTRP instructions as mayLoad · 2a48433f
  Tom Stellard authored Dec 09, 2016
  2a48433f
- AMDGPU: Select i16 instructions to VOP3 forms · 27c06293
  Matt Arsenault authored Dec 09, 2016
  27c06293
Dec 08, 2016
- AMDGPU: Make f16 ConstantFP legal · e96d0374
  Matt Arsenault authored Dec 08, 2016
  e96d0374
- [AMDGPU] Fix number of reserved SGPRs on CI to reflect flat scratch use · 73b54f41
  Stanislav Mekhanoshin authored Dec 08, 2016
  73b54f41
- AMDGPU: Fix commuting v_sub_u16 · 6c06a6f4
  Matt Arsenault authored Dec 08, 2016
  6c06a6f4
- [AMDGPU] Add amdgpu-unify-metadata pass · 50ea93a2
  Stanislav Mekhanoshin authored Dec 08, 2016
  50ea93a2
- [AMDGPU] Scalarization of global uniform loads. · 18009560
  Alexander Timofeev authored Dec 08, 2016
  18009560
- AMDGPU: Properly implement SIRegisterInfo::isFrameOffsetLegal and needsFrameBaseReg · 2857dc38
  Nicolai Haehnle authored Dec 08, 2016
  2857dc38
Dec 07, 2016
- AMDGPU : Add S_SETREG instructions to fix fdiv precision issues. · 8485fa09
  Tom Stellard authored Dec 07, 2016
  8485fa09
- AMDGPU: Add llvm.amdgcn.interp.mov intrinsic · 2187bb8a
  Tom Stellard authored Dec 06, 2016
  2187bb8a
- AMDGPU: Fix crash on i16 constant expression · 269ffdac
  Matt Arsenault authored Dec 06, 2016
  269ffdac
Dec 06, 2016
- AMDGPU: Fix operand name for v_interp_* · ac066f35
  Matt Arsenault authored Dec 06, 2016
  ac066f35
- AMDGPU/SI: Set correct value for amd_kernel_code_t::kernarg_segment_alignment · 175959e3
  Tom Stellard authored Dec 06, 2016
  175959e3
- AMDGPU/SI: Don't move copies of immediates to the VALU · 00cfa747
  Tom Stellard authored Dec 06, 2016
  00cfa747
- AMDGPU: Don't required structured CFG · ad55ee58
  Matt Arsenault authored Dec 06, 2016
  ad55ee58
Dec 05, 2016
- AMDGPU: Consolidate inline immediate predicate functions · 26faed39
  Matt Arsenault authored Dec 05, 2016
  26faed39
- AMDGPU: Minor assembler refactoring · c7f28a5d
  Matt Arsenault authored Dec 05, 2016
  c7f28a5d
- AMDGPU: Assembler support for exp · bf6bdac1
  Matt Arsenault authored Dec 05, 2016
  bf6bdac1
- AMDGPU: Change how exp is printed · 8a63cb90
  Matt Arsenault authored Dec 05, 2016
  8a63cb90
- AMDGPU: Refactor exp instructions · 7bee6ac7
  Matt Arsenault authored Dec 05, 2016
  7bee6ac7
- [AMDGPU] Disassembler: fix s_buffer_store_dword instructions · 83102d99
  Sam Kolton authored Dec 05, 2016
  83102d99
Dec 03, 2016
- AMDGPU: remove a couple of unused variables · 9c89ba7f
  Saleem Abdulrasool authored Dec 03, 2016
  9c89ba7f
- AMDGPU: Clean up struct initializers · b55f620e
  Matt Arsenault authored Dec 03, 2016
  b55f620e
Dec 02, 2016
- AMDGPU: Implement isCheapAddrSpaceCast · d4da0edd
  Matt Arsenault authored Dec 02, 2016
  d4da0edd
- AMDGPU: Use wider scalar spills for SGPR spilling · c47701c0
  Matt Arsenault authored Dec 02, 2016
  c47701c0
Nov 29, 2016
- AMDGPU: Disallow exec as SMEM instruction operand · 640c44b8
  Matt Arsenault authored Nov 29, 2016
  640c44b8
- AMDGPU: Use SGPR_64 for argument lowerings · cdad316c
  Matt Arsenault authored Nov 29, 2016
  cdad316c
- AMDGPU: Rename flat operands to match mubuf · 97279a8c
  Matt Arsenault authored Nov 29, 2016
  97279a8c
- AMDGPU: Use else if · 437fd71f
  Matt Arsenault authored Nov 29, 2016
  437fd71f
- AMDGPU: Materialize frame index before add · f96eeec0
  Matt Arsenault authored Nov 29, 2016
  f96eeec0
- AMDGPU: Refactor immediate folding logic · ff8bb49b
  Matt Arsenault authored Nov 29, 2016
  ff8bb49b
- AMDGPU/SI: Avoid moving PHIs to VALU when phi values are defined in scalar branches · 0bc68811
  Tom Stellard authored Nov 29, 2016
  0bc68811
Nov 28, 2016
- MachineScheduler: Export function to construct "default" scheduler. · 115efcd3
  Matthias Braun authored Nov 28, 2016
  115efcd3
- [AMDGPU] Allow hoisting of comparisons out of a loop and eliminate condition copies · 0ee250ee
  Stanislav Mekhanoshin authored Nov 28, 2016
  0ee250ee
Nov 26, 2016
- AMDGPU/SI: Use float as the operand type for amdgcn.interp intrinsics · 1473f07c
  Tom Stellard authored Nov 26, 2016
  1473f07c
Nov 25, 2016
- AMDGPU/SI: Add back reverted SGPR spilling code, but disable it · 79c05871
  Marek Olsak authored Nov 25, 2016
  79c05871
- Revert "AMDGPU: Implement SGPR spilling with scalar stores" · e3895bfb
  Marek Olsak authored Nov 25, 2016
  e3895bfb