[all-commits] [llvm/llvm-project] 293c21: [mlir][tosa] Improve lowering of tosa.conv2d (#74143)

[Spenser Bauman via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 293c21db9381fde27cda46e5c3ff8bf8578e5399
      https://github.com/llvm/llvm-project/commit/293c21db9381fde27cda46e5c3ff8bf8578e5399
  Author: Spenser Bauman <sbauman at mathworks.com>
  Date:   2023-12-02 (Sat, 02 Dec 2023)

  Changed paths:
    M mlir/lib/Conversion/TosaToLinalg/TosaToLinalgNamed.cpp
    M mlir/test/Conversion/TosaToLinalg/tosa-to-linalg-named.mlir

  Log Message:
  -----------
  [mlir][tosa] Improve lowering of tosa.conv2d (#74143)

The existing lowering of tosa.conv2d emits a separate linalg.generic
operator to add the bias after computing the computation.

This change eliminates that additional step by using the generated
linalg.conv_2d_* operator by using the bias value as the input to the
linalg.conv_2d operation.

Rather than:

    %init = tensor.empty()
    %conv = linalg.conv_2d ins(%A, %B) %outs(%init)

    %init = tensor.empty()
    %bias = linalg.generic ins(%conv, %bias) outs(%init2) {
      // perform add operation
    }

The lowering now produces:

    %init = tensor.empty()
    %bias_expanded = linalg.broadcast ins(%bias) outs(%init)
    %conv = linalg.conv_2d ins(%A, %B) %outs(%bias)

This is the same strategy as
https://github.com/llvm/llvm-project/pull/73049 applied to convolutions.