[PATCH] D59990: AMDGPU. Divergence driven ISel. Assign register class for cross block values according to the divergence.

[Alexander via Phabricator via llvm-commits]

alex-t updated this revision to Diff 199406.
alex-t added a comment.

Added fixes after extended testing. Also GFX10 related update.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D59990/new/

https://reviews.llvm.org/D59990

Files:
  include/llvm/CodeGen/FunctionLoweringInfo.h
  include/llvm/CodeGen/SelectionDAG.h
  include/llvm/CodeGen/TargetLowering.h
  include/llvm/CodeGen/TargetRegisterInfo.h
  lib/CodeGen/SelectionDAG/DAGCombiner.cpp
  lib/CodeGen/SelectionDAG/FunctionLoweringInfo.cpp
  lib/CodeGen/SelectionDAG/InstrEmitter.cpp
  lib/CodeGen/SelectionDAG/InstrEmitter.h
  lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
  lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp
  lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp
  lib/Target/AMDGPU/SIFixSGPRCopies.cpp
  lib/Target/AMDGPU/SIISelLowering.cpp
  lib/Target/AMDGPU/SIISelLowering.h
  lib/Target/AMDGPU/SIInstrInfo.cpp
  lib/Target/AMDGPU/SIRegisterInfo.h
  lib/Target/ARM/ARMISelLowering.cpp
  lib/Target/ARM/ARMISelLowering.h
  test/CodeGen/AMDGPU/atomicrmw-nand.ll
  test/CodeGen/AMDGPU/branch-relaxation.ll
  test/CodeGen/AMDGPU/branch-uniformity.ll
  test/CodeGen/AMDGPU/control-flow-fastregalloc.ll
  test/CodeGen/AMDGPU/divergent-branch-uniform-condition.ll
  test/CodeGen/AMDGPU/fabs.ll
  test/CodeGen/AMDGPU/fdiv32-to-rcp-folding.ll
  test/CodeGen/AMDGPU/fmin_legacy.ll
  test/CodeGen/AMDGPU/fneg-fabs.ll
  test/CodeGen/AMDGPU/fsub.ll
  test/CodeGen/AMDGPU/i1-copy-from-loop.ll
  test/CodeGen/AMDGPU/i1-copy-phi-uniform-branch.ll
  test/CodeGen/AMDGPU/insert_vector_elt.ll
  test/CodeGen/AMDGPU/llvm.amdgcn.div.scale.ll
  test/CodeGen/AMDGPU/llvm.amdgcn.fmed3.ll
  test/CodeGen/AMDGPU/llvm.amdgcn.mov.dpp.ll
  test/CodeGen/AMDGPU/llvm.amdgcn.mqsad.pk.u16.u8.ll
  test/CodeGen/AMDGPU/llvm.amdgcn.qsad.pk.u16.u8.ll
  test/CodeGen/AMDGPU/loop_break.ll
  test/CodeGen/AMDGPU/madak.ll
  test/CodeGen/AMDGPU/mubuf-legalize-operands.ll
  test/CodeGen/AMDGPU/multilevel-break.ll
  test/CodeGen/AMDGPU/select-opt.ll
  test/CodeGen/AMDGPU/sgpr-control-flow.ll
  test/CodeGen/AMDGPU/si-fix-sgpr-copies.mir
  test/CodeGen/AMDGPU/smrd.ll
  test/CodeGen/AMDGPU/subreg-coalescer-undef-use.ll
  test/CodeGen/AMDGPU/uniform-loop-inside-nonuniform.ll
  test/CodeGen/AMDGPU/use-sgpr-multiple-times.ll
  test/CodeGen/AMDGPU/valu-i1.ll
  test/CodeGen/AMDGPU/vgpr-spill-emergency-stack-slot-compute.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D59990.199406.patch
Type: text/x-patch
Size: 69990 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190514/dccff8f6/attachment.bin>