diff options
| author | Guray Ozen <guray.ozen@gmail.com> | 2023-11-22 16:08:09 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-11-22 16:08:09 +0100 |
| commit | 9ceea088592ebaafed8eaccfc236a0ec284655ce (patch) | |
| tree | 3fd752e7752c017c7a9be52020dccce960575961 /llvm/lib/CodeGen/MachineCopyPropagation.cpp | |
| parent | ed5404cd6b20ef6b54ef713399f03857990861a8 (diff) | |
| download | llvm-9ceea088592ebaafed8eaccfc236a0ec284655ce.zip llvm-9ceea088592ebaafed8eaccfc236a0ec284655ce.tar.gz llvm-9ceea088592ebaafed8eaccfc236a0ec284655ce.tar.bz2 | |
[mlir] `im2col` & `l2cache` on cp.async.bulk.tensor.shared.cluster.global` (#72967)
PR adds support of `im2col` and `l2cache` to
`cp.async.bulk.tensor.shared.cluster.global`. The Op is now supports all
the traits of the corresponding PTX instruction.
The current structure of this operation looks somewhat like below. The
PR also simplifies types so we don't need to write obvious types after
`:` anymore.
```
nvvm.cp.async.bulk.tensor.shared.cluster.global
%dest, %tmaDescriptor, %barrier,
box[%crd0,%crd1,%crd2,%crd3,%crd4]
im2col[%off0,%off1,%off2] <-- PR introduces
multicast_mask = %ctamask
l2_cache_hint = %cacheHint <-- PR introduces
: !llvm.ptr<3>, !llvm.ptr
```
Diffstat (limited to 'llvm/lib/CodeGen/MachineCopyPropagation.cpp')
0 files changed, 0 insertions, 0 deletions