diff options
| author | Jay Foad <jay.foad@amd.com> | 2023-11-02 10:35:15 +0000 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-11-02 10:35:15 +0000 |
| commit | b90cfe46015d9d12317146251e633d2ca07dccd7 (patch) | |
| tree | 754b6cab15d6e76267fb839a785d09996d81f07b /llvm/lib/IR/Module.cpp | |
| parent | 3a223f4414444c3ecc65abb6482df3df87e26b86 (diff) | |
| download | llvm-b90cfe46015d9d12317146251e633d2ca07dccd7.zip llvm-b90cfe46015d9d12317146251e633d2ca07dccd7.tar.gz llvm-b90cfe46015d9d12317146251e633d2ca07dccd7.tar.bz2 | |
[AMDGPU] New ttracedata intrinsics (#70235)
Add llvm.amdgcn.s.ttracedata and llvm.amdgcn.s.ttracedata.imm which map
directly to the corresponding instructions s_ttracedata and
s_ttracedata_imm. These are inherently whole-wave operations so any
non-uniform inputs are readfirstlaned.
Diffstat (limited to 'llvm/lib/IR/Module.cpp')
0 files changed, 0 insertions, 0 deletions