This still satisfies the constraints required by the affine dialect and
gives more flexibility in what iteration bounds can be used when
loewring to the GPU dialect.
Details
Details
Diff Detail
Diff Detail
- Repository
- rG LLVM Github Monorepo
Differential D89782
[mlir] Use affine dim instead of symbol in SCFToGPU lowering. tpopp on Oct 20 2020, 2:35 AM. Authored by
Details This still satisfies the constraints required by the affine dialect and
Diff Detail
|