Commits · 16f963ba0dde224471450203ed8976ee955d64a5 · Raul Torres / llvm-target-spread · GitLab

Jun 08, 2018
- [AMDGPU] Simplify memory legalizer (add missing virtual descructor) · 6db1f5da
  Tony Tye authored Jun 08, 2018
  6db1f5da
- [AMDGPU] Simplify memory legalizer · a5a7c331
  Tony Tye authored Jun 07, 2018
  a5a7c331
Jun 07, 2018
- AMDGPU: Fix not including v2f64 in SReg_128 · f1c868ef
  Matt Arsenault authored Jun 07, 2018
  f1c868ef
- AMDGPU: Use scalar operations for f16 fabs/fneg patterns · 697300bd
  Matt Arsenault authored Jun 07, 2018
  697300bd
- AMDGPU: Try a lot harder to emit scalar loads · 90083d30
  Matt Arsenault authored Jun 07, 2018
  90083d30
- [AMDGPU] Improve reciprocal handling · df61be70
  Stanislav Mekhanoshin authored Jun 06, 2018
  df61be70
Jun 06, 2018
- AMDGPU: Custom lower v2f16 fneg/fabs with illegal f16 · e9524f1f
  Matt Arsenault authored Jun 06, 2018
  e9524f1f
- [MC] Pass MCSubtargetInfo to fixupNeedsRelaxation and applyFixup · 57f661bd
  Peter Smith authored Jun 06, 2018
  57f661bd
Jun 05, 2018
- AMDGPU: Preserve metadata when widening loads · 57e541e8
  Matt Arsenault authored Jun 05, 2018
  57e541e8
- AMDGPU: Use more custom insert/extract_vector_elt lowering · 9224c00d
  Matt Arsenault authored Jun 05, 2018
  9224c00d
Jun 04, 2018
- Move Analysis/Utils/Local.h back to Transforms · 31b98d2e
  David Blaikie authored Jun 04, 2018
  31b98d2e
- [AMDGPU] Small refactoring in the scheduler · 838c07c5
  Stanislav Mekhanoshin authored Jun 04, 2018
  838c07c5
- [AMDGPU] Factored out common part of GCNRPTracker::reset() · 28624f94
  Stanislav Mekhanoshin authored Jun 04, 2018
  28624f94
- [AMDGPU][Waitcnt] Fix handling of flat instrs · f0b93f1e
  Mark Searles authored Jun 04, 2018
  f0b93f1e
- AMDGPU: Make various NamedOperands upper case · 59198ed0
  Nicolai Haehnle authored Jun 04, 2018
  59198ed0
- TableGen: Streamline the semantics of NAME · 01d261f1
  Nicolai Haehnle authored Jun 04, 2018
  01d261f1
Jun 01, 2018
- Set ADDE/ADDC/SUBE/SUBC to expand by default · 8467411d
  Amaury Sechet authored Jun 01, 2018
  8467411d
- AMDGPU/R600: Move intrinsics to IntrinsicsAMDGPU.td · e4377889
  Tom Stellard authored Jun 01, 2018
  e4377889
May 31, 2018
- [AMDGPU] Construct memory clauses before RA · 739174c4
  Stanislav Mekhanoshin authored May 31, 2018
  739174c4
- [GlobalISel][AMDGPU] LegalizerInfo verifier: Adding LegalizerInfo::verify(...) call for AMDGPU · 76c29c68
  Roman Tereshin authored May 31, 2018
  76c29c68
- [AMDGPU] Track occupancy in MFI · d4b500cb
  Stanislav Mekhanoshin authored May 31, 2018
  d4b500cb
- AMDGPU/R600: Make sure functions are cacheline aligned · f5016b79
  Jan Vesely authored May 31, 2018
  f5016b79
- AMDGPU: Split AMDGPUTTI into GCNTTI and R600TTI · c7624317
  Tom Stellard authored May 30, 2018
  c7624317
May 30, 2018
- [AMDGPU][Waitcnt] Fix build error: unused variable 'SWaitInst' · ed54ff1d
  Mark Searles authored May 30, 2018
  ed54ff1d
- AMDGPU: Use better alignment for kernarg lowering · 7b4826e6
  Matt Arsenault authored May 30, 2018
  7b4826e6
- [AMDGPU][Waitcnt] Fix handling of loops with many bottom blocks · 10545414
  Mark Searles authored May 30, 2018
  10545414
May 29, 2018
- AMDGPU: Fix typo in option description · 2e4d338d
  Matt Arsenault authored May 29, 2018
  2e4d338d
- AMDGPU: Round up kernel argument allocation size · 1ea0402e
  Matt Arsenault authored May 29, 2018
  1ea0402e
- AMDGPU: Always set COMPUTE_PGM_RSRC2.ENABLE_TRAP_HANDLER to zero for AMDHSA as · 2ca6b1f2
  Konstantin Zhuravlyov authored May 29, 2018
  2ca6b1f2
- AMDGPU: Pass function directly instead of MachineFunction · ceafc55e
  Matt Arsenault authored May 29, 2018
  ceafc55e
- AMDGPU: Add nuw to add off of kernarg ptr · 2fb9ccf7
  Matt Arsenault authored May 29, 2018
  2fb9ccf7
- AMDGPU: Split R600 MCInst lowering into its own class · 57b9342c
  Tom Stellard authored May 29, 2018
  57b9342c
- [AMDGPU] Fixed build warning · fa213f79
  Tim Renouf authored May 29, 2018
  fa213f79
May 28, 2018
- [AMDGPU] Re-enabled 128bit wide-vector generation for local addr space by default. · eacb1020
  Farhana Aleen authored May 28, 2018
  eacb1020
May 27, 2018
- [AMDGPU] Fixed WWM bug in block otherwise entirely in WQM · 364edcd2
  Tim Renouf authored May 27, 2018
  364edcd2
May 25, 2018
- [AMDGPU][Waitcnt] Remove obsolete waitcnt option · 32efedcf
  Mark Searles authored May 25, 2018
  32efedcf
- [AMDGPU] Fixed test failure with AMDGPUPerfHint · 7fc1cee0
  Stanislav Mekhanoshin authored May 25, 2018
  7fc1cee0
- Fix -Winconsistent-missing-overrides in AMDGPU code · cb48efd5
  Reid Kleckner authored May 25, 2018
  cb48efd5
- [AMDGPU] Add perf hints to functions · 1c538423
  Stanislav Mekhanoshin authored May 25, 2018
  1c538423
- [AMDGPU] Fixed incorrect break from loop · ad8b7c11
  Tim Renouf authored May 25, 2018
  ad8b7c11