[all-commits] [llvm/llvm-project] c92629: [MLIR][TOSA] Fix f16/bf16 support for MaxPool2D (#...

[Dhruv Chauhan via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: c92629150e361f7b2a06fc56200389b727616411
      https://github.com/llvm/llvm-project/commit/c92629150e361f7b2a06fc56200389b727616411
  Author: Dhruv Chauhan <dhruv.chauhan at arm.com>
  Date:   2023-10-18 (Wed, 18 Oct 2023)

  Changed paths:
    M mlir/lib/Conversion/TosaToLinalg/TosaToLinalgNamed.cpp
    M mlir/test/Dialect/Tosa/ops.mlir

  Log Message:
  -----------
  [MLIR][TOSA] Fix f16/bf16 support for MaxPool2D (#69332)

Currently, the MaxPool2D operation in the TOSA MLIR dialect does not
accept half-precision Fp16 and Bf16 tensors, converse to what is stated
in the [TOSA
Specification](https://www.mlplatform.org/tosa/tosa_spec.html#_max_pool2d).

This patch fixes the verifier to accept the two datatypes for
input/output tensors, and adds related LIT test cases in Tosa/ops.mlir