diff options
| author | Srinivasa Ravi <srinivasar@nvidia.com> | 2025-06-04 13:29:46 +0530 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-06-04 13:29:46 +0530 |
| commit | 4e4273c9409dfbbfb42ca74468eaf9bd843bc376 (patch) | |
| tree | 2f70f9e940241961a2c1425edb2cefc933a4f9ea /clang/lib/CodeGen/CodeGenModule.cpp | |
| parent | 11a9dad1a5d1e83338425f595c7685d1a0564121 (diff) | |
| download | llvm-4e4273c9409dfbbfb42ca74468eaf9bd843bc376.zip llvm-4e4273c9409dfbbfb42ca74468eaf9bd843bc376.tar.gz llvm-4e4273c9409dfbbfb42ca74468eaf9bd843bc376.tar.bz2 | |
[MLIR][NVVM] Add dot.accumulate.2way Op (#140518)
This change adds the `dot.accumulate.2way` Op to the NVVM dialect for
16-bit to 8-bit dot-product accumulate operation.
PTX Spec Reference:
https://docs.nvidia.com/cuda/parallel-thread-execution/#integer-arithmetic-instructions-dp2a
Diffstat (limited to 'clang/lib/CodeGen/CodeGenModule.cpp')
0 files changed, 0 insertions, 0 deletions