[all-commits] [llvm/llvm-project] b3ebe3: [mlir][bufferize] Bufferize after TensorCopyInsertion

[Matthias Springer via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: b3ebe3beeda64ab0072a2ef97a64520ed5d8d73f
      https://github.com/llvm/llvm-project/commit/b3ebe3beeda64ab0072a2ef97a64520ed5d8d73f
  Author: Matthias Springer <springerm at google.com>
  Date:   2022-06-17 (Fri, 17 Jun 2022)

  Changed paths:
    M mlir/include/mlir/Dialect/Bufferization/IR/BufferizableOpInterface.h
    M mlir/include/mlir/Dialect/Bufferization/IR/Bufferization.h
    M mlir/include/mlir/Dialect/Bufferization/Transforms/Bufferize.h
    M mlir/lib/Dialect/Arithmetic/Transforms/BufferizableOpInterfaceImpl.cpp
    M mlir/lib/Dialect/Bufferization/IR/BufferizableOpInterface.cpp
    M mlir/lib/Dialect/Bufferization/IR/BufferizationOps.cpp
    M mlir/lib/Dialect/Bufferization/Transforms/Bufferize.cpp
    M mlir/lib/Dialect/Bufferization/Transforms/FuncBufferizableOpInterfaceImpl.cpp
    M mlir/lib/Dialect/Bufferization/Transforms/OneShotAnalysis.cpp
    M mlir/lib/Dialect/Bufferization/Transforms/OneShotModuleBufferize.cpp
    M mlir/lib/Dialect/Linalg/Transforms/BufferizableOpInterfaceImpl.cpp
    M mlir/lib/Dialect/SCF/Transforms/BufferizableOpInterfaceImpl.cpp
    M mlir/lib/Dialect/Tensor/Transforms/BufferizableOpInterfaceImpl.cpp
    M mlir/lib/Dialect/Vector/Transforms/BufferizableOpInterfaceImpl.cpp
    M mlir/test/Dialect/Bufferization/Transforms/one-shot-bufferize-alloc-tensor-elimination.mlir
    M mlir/test/Dialect/Bufferization/Transforms/one-shot-bufferize-partial.mlir
    M mlir/test/Dialect/Bufferization/Transforms/one-shot-module-bufferize-allow-return-allocs.mlir
    M mlir/test/Dialect/Bufferization/Transforms/one-shot-module-bufferize.mlir
    M mlir/test/Dialect/Linalg/bufferize.mlir
    M mlir/test/Dialect/SCF/one-shot-bufferize.mlir
    M mlir/test/Dialect/Tensor/one-shot-bufferize.mlir

  Log Message:
  -----------
  [mlir][bufferize] Bufferize after TensorCopyInsertion

This change changes the bufferization so that it utilizes the new TensorCopyInsertion pass. One-Shot Bufferize no longer calls the One-Shot Analysis. Instead, it relies on the TensorCopyInsertion pass to make the entire IR fully inplacable. The `bufferize` implementations of all ops are simplified; they no longer have to account for out-of-place bufferization decisions. These were already materialized in the IR in the form of `bufferization.alloc_tensor` ops during the TensorCopyInsertion pass.

Differential Revision: https://reviews.llvm.org/D127652