[all-commits] [llvm/llvm-project] 121aab: [MLIR][Affine] Simplify nested modulo operations w...

[Krzysztof Drewniak via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 121aab84d16f659cea539becff2cc2fef82ec152
      https://github.com/llvm/llvm-project/commit/121aab84d16f659cea539becff2cc2fef82ec152
  Author: Krzysztof Drewniak <Krzysztof.Drewniak at amd.com>
  Date:   2021-09-17 (Fri, 17 Sep 2021)

  Changed paths:
    M mlir/lib/IR/AffineExpr.cpp
    M mlir/test/IR/affine-map.mlir
    M mlir/test/Transforms/loop-fusion-2.mlir
    M mlir/test/Transforms/loop-fusion.mlir

  Log Message:
  -----------
  [MLIR][Affine] Simplify nested modulo operations when able

It is the case that, for all positive a and b such that b divides a
(e mod (a * b)) mod b = e mod b. For example, ((d0 mod 35) mod 5) can
be simplified to (d0 mod 5), but ((d0 mod 35) mod 4) cannot be simplified
further (x = 36 is a counterexample).

This change enables more complex simplifications. For example,
((d0 * 72 + d1) mod 144) mod 9 can now simplify to (d0 * 72 + d1) mod 9
and thus to d1 mod 9. Expressions with chained modulus operators are
reasonably common in tensor applications, and this change _should_
improve code generation for such expressions.

Reviewed By: nicolasvasilache

Differential Revision: https://reviews.llvm.org/D109930