diff options
| author | Srinivasa Ravi <srinivasar@nvidia.com> | 2025-01-30 11:05:12 +0530 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-01-30 11:05:12 +0530 |
| commit | ab9e447fb17029573a517ac14c4c0f8c0733c3aa (patch) | |
| tree | 36ef805f1a012ce9c559150b227f9e4f331d59b4 /clang/lib/CodeGen/BackendUtil.cpp | |
| parent | 1f38d38d544b090fd7b9b63454d8310eff0bb7d9 (diff) | |
| download | llvm-ab9e447fb17029573a517ac14c4c0f8c0733c3aa.zip llvm-ab9e447fb17029573a517ac14c4c0f8c0733c3aa.tar.gz llvm-ab9e447fb17029573a517ac14c4c0f8c0733c3aa.tar.bz2 | |
[MLIR][NVVM] Add support for mapa MLIR Ops (#124514)
Adds `mapa` and `mapa.shared.cluster` MLIR Ops to generate mapa
instructions.
`mapa` - Map the address of the shared variable in the target CTA.
- `mapa` - source is a register containing generic address pointing to
shared memory.
- `mapa.shared.cluster` - source is a shared memory variable or a
register containing a valid shared memory address.
PTX Spec Reference:
https://docs.nvidia.com/cuda/parallel-thread-execution/#data-movement-and-conversion-instructions-mapa
Diffstat (limited to 'clang/lib/CodeGen/BackendUtil.cpp')
0 files changed, 0 insertions, 0 deletions