This is an automated email from the git hooks/post-receive script.
unknown user pushed a change to branch master in repository llvm.
from 919946cec1b [MCA] Slightly refactor the bottleneck analysis view. NFCI new 6a59b736826 AMDGPU: Add ds_gws_init / ds_gws_barrier intrinsics
The 1 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 | 22 +++ lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp | 85 ++++++++++ lib/Target/AMDGPU/DSInstructions.td | 6 +- lib/Target/AMDGPU/SIISelLowering.cpp | 18 +++ lib/Target/AMDGPU/SIInsertWaitcnts.cpp | 28 ++-- lib/Target/AMDGPU/SIInstrInfo.cpp | 3 +- lib/Target/AMDGPU/SIMachineFunctionInfo.h | 37 ++++- test/CodeGen/AMDGPU/gws-hazards.mir | 103 ++++++++++++ ...rt-skips-flat-vmem.mir => insert-skips-gws.mir} | 19 +-- test/CodeGen/AMDGPU/llvm.amdgcn.ds.gws.barrier.ll | 179 +++++++++++++++++++++ test/CodeGen/AMDGPU/llvm.amdgcn.ds.gws.init.ll | 119 ++++++++++++++ test/CodeGen/AMDGPU/tail-duplication-convergent.ll | 48 ++++++ 12 files changed, 637 insertions(+), 30 deletions(-) create mode 100644 test/CodeGen/AMDGPU/gws-hazards.mir copy test/CodeGen/AMDGPU/{insert-skips-flat-vmem.mir => insert-skips-gws.mir} (61%) create mode 100644 test/CodeGen/AMDGPU/llvm.amdgcn.ds.gws.barrier.ll create mode 100644 test/CodeGen/AMDGPU/llvm.amdgcn.ds.gws.init.ll