[all-commits] [llvm/llvm-project] 286a9d: [mlir][tosa] Add lowering for tosa.rescale to lina...

[rsuderman via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 286a9d467ea904490548a25e3c73ad0d50190b43
      https://github.com/llvm/llvm-project/commit/286a9d467ea904490548a25e3c73ad0d50190b43
  Author: Rob Suderman <rob.suderman at gmail.com>
  Date:   2021-03-18 (Thu, 18 Mar 2021)

  Changed paths:
    M mlir/include/mlir/Conversion/TosaToStandard/TosaToStandard.h
    M mlir/include/mlir/Dialect/Tosa/IR/TosaOps.td
    M mlir/include/mlir/Dialect/Tosa/IR/TosaTypesBase.td
    M mlir/lib/Conversion/TosaToLinalg/TosaToLinalg.cpp
    M mlir/lib/Conversion/TosaToLinalg/TosaToLinalgPass.cpp
    M mlir/lib/Conversion/TosaToStandard/TosaToStandard.cpp
    M mlir/lib/Conversion/TosaToStandard/TosaToStandardPass.cpp
    M mlir/test/Conversion/TosaToLinalg/tosa-to-linalg.mlir
    M mlir/test/Conversion/TosaToStandard/tosa-to-standard.mlir

  Log Message:
  -----------
  [mlir][tosa] Add lowering for tosa.rescale to linalg.generic

This adds a tosa.apply_scale operation that handles the scaling operation
common to quantized operatons. This scalar operation is lowered
in TosaToStandard.

We use a separate ApplyScale factorization as this is a replicable pattern
within TOSA. ApplyScale can be reused within pool/convolution/mul/matmul
for their quantized variants.

Tests are added to both tosa-to-standard and tosa-to-linalg-on-tensors
that verify each pass is correct.

Reviewed By: silvas

Differential Revision: https://reviews.llvm.org/D98753