[all-commits] [llvm/llvm-project] 2d45e3: [MLIR][DISC] Revise ParallelLoopTilingPass with in...

[Stephan Herhut via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 2d45e332ba321a22996a1584af26d568b375b674
      https://github.com/llvm/llvm-project/commit/2d45e332ba321a22996a1584af26d568b375b674
  Author: tashuang.zk <tashuang.zk at alibaba-inc.com>
  Date:   2021-08-16 (Mon, 16 Aug 2021)

  Changed paths:
    M mlir/include/mlir/Dialect/SCF/Passes.h
    M mlir/include/mlir/Dialect/SCF/Passes.td
    M mlir/include/mlir/Dialect/SCF/Transforms.h
    M mlir/lib/Dialect/SCF/Transforms/ParallelLoopTiling.cpp
    A mlir/test/Dialect/SCF/parallel-loop-tiling-inbound-check.mlir

  Log Message:
  -----------
  [MLIR][DISC] Revise ParallelLoopTilingPass with inbound_check mode

Expand ParallelLoopTilingPass with an inbound_check mode.

In default mode, the upper bound of the inner loop is from the min op; in
inbound_check mode, the upper bound of the inner loop is the step of the outer
loop and an additional inbound check will be emitted inside of the inner loop.

This was 'FIXME' in the original codes and a typical usage is for GPU backends,
thus the outer loop and inner loop can be mapped to blocks/threads in seperate.

Differential Revision: https://reviews.llvm.org/D105455