This is an archive of the discontinued LLVM Phabricator instance.

[mlir][Linalg] Refactor and improve vectorization to add support for reduction into 0-d tensors.
ClosedPublic

Authored by nicolasvasilache on Oct 12 2021, 3:22 AM.

Details

Summary

This revision takes advantage of the recently added support for 0-d transfers and vector.multi_reduction that return a scalar.

Diff Detail

Event Timeline

nicolasvasilache requested review of this revision.Oct 12 2021, 3:22 AM
pifon2a accepted this revision.Oct 12 2021, 3:57 AM
pifon2a added inline comments.
mlir/lib/Dialect/Linalg/Transforms/Vectorization.cpp
251

nit: update this to use the new macro

mlir/test/Dialect/Linalg/vectorization.mlir
877

nit: wrap the lines with CHECK-SAME?

This revision is now accepted and ready to land.Oct 12 2021, 3:57 AM
nicolasvasilache marked an inline comment as done.

Address review.

nicolasvasilache marked an inline comment as done.Oct 12 2021, 5:47 AM
This revision was landed with ongoing or failed builds.Oct 12 2021, 5:47 AM
This revision was automatically updated to reflect the committed changes.