This is an automated email from the git hooks/post-receive script.
unknown user pushed a change to branch master in repository llvm.
from 3b0297768d9 [MachineOperand] Add ChangeToTargetIndex method. NFC new 7af89e579da [AMDGPU] Add an llvm.amdgcn.wqm intrinsic for WQM new 6ba48659282 [AMDGPU] refactor WQM pass in preparation for WWM (NFCI) new ecf573917ab [AMDGPU] Add support for Whole Wavefront Mode new c300b1a6d37 [AMDGPU] Implement llvm.amdgcn.set.inactive intrinsic
The 4 revisions listed above as "new" are entirely new to this repository and will be described in separate emails. The revisions listed as "adds" were already present in the repository and have only been added to this reference.
Summary of changes: include/llvm/IR/IntrinsicsAMDGPU.td | 26 +++ lib/Target/AMDGPU/AMDGPU.h | 4 + lib/Target/AMDGPU/AMDGPUTargetMachine.cpp | 9 + lib/Target/AMDGPU/CMakeLists.txt | 1 + lib/Target/AMDGPU/SIFixSGPRCopies.cpp | 7 +- lib/Target/AMDGPU/SIFixWWMLiveness.cpp | 202 +++++++++++++++++ lib/Target/AMDGPU/SIISelLowering.cpp | 10 + lib/Target/AMDGPU/SIInstrInfo.cpp | 32 +++ lib/Target/AMDGPU/SIInstructions.td | 33 +++ lib/Target/AMDGPU/SIWholeQuadMode.cpp | 290 +++++++++++++++++++----- test/CodeGen/AMDGPU/fix-wwm-liveness.mir | 73 ++++++ test/CodeGen/AMDGPU/llvm.amdgcn.set.inactive.ll | 29 +++ test/CodeGen/AMDGPU/wqm.ll | 235 ++++++++++++++++++- test/CodeGen/AMDGPU/wqm.mir | 50 ++++ 14 files changed, 936 insertions(+), 65 deletions(-) create mode 100644 lib/Target/AMDGPU/SIFixWWMLiveness.cpp create mode 100644 test/CodeGen/AMDGPU/fix-wwm-liveness.mir create mode 100644 test/CodeGen/AMDGPU/llvm.amdgcn.set.inactive.ll create mode 100644 test/CodeGen/AMDGPU/wqm.mir