Even though tensor.cast is not part of the sparse tensor dialect,
it may be used to cast static dimension sizes to dynamic dimension
sizes for sparse tensors without changing the actual sparse tensor
itself. Those cases should be lowered properly when replacing sparse
tensor types with their opaque pointers. Likewise, no op sparse
conversions are handled by this revision in a similar manner.
Details
Details
Diff Detail
Diff Detail
- Repository
- rG LLVM Github Monorepo
Event Timeline
Comment Actions
This PR also fixes sparse_tensor.convert to handle the no-op conversion case.
It would be nice to mention this in the PR description.
Rather than this, everything looks good to me.