[all-commits] [llvm/llvm-project] 101d01: [mlir][Linalg] Revisit heuristic ordering of tenso...

[Nicolas Vasilache via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 101d017a643845b537687467e3f7c2a5d963df6e
      https://github.com/llvm/llvm-project/commit/101d017a643845b537687467e3f7c2a5d963df6e
  Author: Nicolas Vasilache <nicolas.vasilache at gmail.com>
  Date:   2021-09-21 (Tue, 21 Sep 2021)

  Changed paths:
    M mlir/lib/Dialect/Linalg/Transforms/ComprehensiveBufferize.cpp
    M mlir/test/Dialect/Linalg/comprehensive-module-bufferize-analysis.mlir
    M mlir/test/Dialect/Linalg/comprehensive-module-bufferize.mlir

  Log Message:
  -----------
  [mlir][Linalg] Revisit heuristic ordering of tensor.insert_slice in comprehensive bufferize.

It was previously assumed that tensor.insert_slice should be bufferized first in a greedy fashion to avoid out-of-place bufferization of the large tensor. This heuristic does not hold upon further inspection.

This CL removes the special handling of such ops and adds a test that exhibits better behavior and appears in real use cases.

The only test adversely affected is an artificial test which results in a returned memref: this pattern is not allowed by comprehensive bufferization in real scenarios anyway and the offending test is deleted.

Differential Revision: https://reviews.llvm.org/D110072