[all-commits] [llvm/llvm-project] 13593d: [mlir][tensor][bufferize] Fix tensor.insert_slice ...

[Matthias Springer via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 13593dc9dc5a8f587402bf1e5f180f2c0fc750ee
      https://github.com/llvm/llvm-project/commit/13593dc9dc5a8f587402bf1e5f180f2c0fc750ee
  Author: Matthias Springer <springerm at google.com>
  Date:   2022-11-26 (Sat, 26 Nov 2022)

  Changed paths:
    M mlir/lib/Dialect/Tensor/Transforms/BufferizableOpInterfaceImpl.cpp
    M mlir/test/Dialect/Tensor/one-shot-bufferize.mlir

  Log Message:
  -----------
  [mlir][tensor][bufferize] Fix tensor.insert_slice regression

This reverts D132662 (apart from overall cleanups), which introduced a too aggressive optimization for tensor.insert_slice bufferization. Instead, bufferizesToMemoryRead is improved to handle some of these cases. The remaining cases can still bufferize efficiently when running the canonicalizer before the bufferization.

Differential Revision: https://reviews.llvm.org/D138745