Alan Li
Alan Li
Regarding: > Flatten the memory accesses in IREE, so that we don't have to worry about any n-d cases. Flattening Memref capabilities is in [upstream](https://github.com/llvm/llvm-project/blob/main/mlir/lib/Dialect/MemRef/Transforms/FlattenMemRefs.cpp). Just use it at a...
1. handled in https://github.com/iree-org/iree/pull/17601/files 3. after recent updates, don't have ukernels with size larger than 32.
Updated the patch to include masked load.
> Hi @lialan, thanks for the contribution! I think the goal of the PR is clear but, would you mind elaborating a bit more on the "how" in the description...
Design doc: https://gist.github.com/lialan/97900b4e3a54ec49b2a75bd27fa0bfe4