HomePhabricator

[mlir] Use affine dim instead of symbol in SCFToGPU lowering.

Authored by Tres Popp <tpopp@google.com> on Oct 20 2020, 2:32 AM.

Description

[mlir] Use affine dim instead of symbol in SCFToGPU lowering.

This still satisfies the constraints required by the affine dialect and
gives more flexibility in what iteration bounds can be used when
loewring to the GPU dialect.

Differential Revision: https://reviews.llvm.org/D89782