These two patterns allow for more efficient codegen in VectorToSCF.
Depends On D101745
Differential D102222
[mlir] Support masks in TransferOpReduceRank and TransferReadPermutationLowering springerm on May 11 2021, 1:32 AM. Authored by
Details
Diff Detail
Event Timeline
Comment Actions Same as previous PRs, please add some minimal IR test.
Comment Actions Test case is included in mlir/test/Dialect/Vector/vector-transfer-lowering.mlir.
|
I don't fully understand what this is doing. If there's a better way to implement the mask handling below (maybe reusing some of these functions), please let me know.