diff options
| author | Krzysztof Drewniak <Krzysztof.Drewniak@amd.com> | 2022-10-17 17:47:56 +0000 |
|---|---|---|
| committer | Krzysztof Drewniak <Krzysztof.Drewniak@amd.com> | 2022-10-18 15:37:20 +0000 |
| commit | 44027f390854f3088bf85c5c4d8cf1405dd4bb4c (patch) | |
| tree | 6423a88871c3108182e4f56b207974a936dec39d /llvm/tools/llvm-reduce/llvm-reduce.cpp | |
| parent | 44b7da89d774019dc52342712a0edd73f90ad90a (diff) | |
| download | llvm-44027f390854f3088bf85c5c4d8cf1405dd4bb4c.zip llvm-44027f390854f3088bf85c5c4d8cf1405dd4bb4c.tar.gz llvm-44027f390854f3088bf85c5c4d8cf1405dd4bb4c.tar.bz2 | |
[mlir][GPU] Prevent adding duplicate async tokens
If, in the GPU async transformation, the operation being given an
async dependency already depended on the token in question, we
would add duplicate tokens, creating issues in GPU to LLVM lowering.
To resolve this issue, add a check to addAsyncDependency() to ensure
that duplicate tokens are not present in the token list.
(I'm open to a different approach here, this is just what I went with
initially)
Reviewed By: Mogball
Differential Revision: https://reviews.llvm.org/D136105
Diffstat (limited to 'llvm/tools/llvm-reduce/llvm-reduce.cpp')
0 files changed, 0 insertions, 0 deletions