Support IR that is generated by the vector-to-scf lowering of N-D vector transfers with a mask. (Until now only 1-D and 2-D transfers were supported.) Only transfers that were fully unrolled are supported.
Details
Details
Diff Detail
Diff Detail
- Repository
- rG LLVM Github Monorepo
Event Timeline
mlir/test/Dialect/NVGPU/transform-create-async-groups.mlir | ||
---|---|---|
168–171 | These values are dead (have no uses). No need to match them. |
Comment Actions
Looks good to me.
Just a quick suggestion – what do we think about adding an end-to-end integration test for this Op? Recently, @nicolasvasilache introduced the test-lower-to-nvvm pass which could be really helpful.
Comment Actions
Good idea. I'm going to add copy_async to D156371 and also add an integration test to that.
These values are dead (have no uses). No need to match them.