[all-commits] [llvm/llvm-project] d8ee28: [mlir][Linalg] Extend buffer allocation to support...

[Nicolas Vasilache via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: d8ee28b96ee77a466aea5e9ca9c6ed57b2194b4d
      https://github.com/llvm/llvm-project/commit/d8ee28b96ee77a466aea5e9ca9c6ed57b2194b4d
  Author: Nicolas Vasilache <nicolas.vasilache at gmail.com>
  Date:   2020-10-06 (Tue, 06 Oct 2020)

  Changed paths:
    M mlir/lib/Dialect/Linalg/IR/LinalgOps.cpp
    M mlir/lib/Dialect/Linalg/Transforms/TensorsToBuffers.cpp
    M mlir/test/Transforms/buffer-placement-preparation.mlir
    M mlir/test/lib/Transforms/TestBufferPlacement.cpp

  Log Message:
  -----------
  [mlir][Linalg] Extend buffer allocation to support Linalg init tensors

This revision adds init_tensors support to buffer allocation for Linalg on tensors.
Currently makes the assumption that the init_tensors fold onto the first output tensors.

This assumption is not currently enforced or cast in stone and requires experimenting with tiling linalg on tensors for ops **without reductions**.

Still this allows progress towards the end-to-end goal.