[all-commits] [llvm/llvm-project] 40aef7: [MLIR][GPU] Add debug output to enable dumping GPU...

[Krzysztof Drewniak via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 40aef79db0b02b171a65b3a13053ae963a3e8753
      https://github.com/llvm/llvm-project/commit/40aef79db0b02b171a65b3a13053ae963a3e8753
  Author: Krzysztof Drewniak <Krzysztof.Drewniak at amd.com>
  Date:   2022-01-20 (Thu, 20 Jan 2022)

  Changed paths:
    M mlir/include/mlir/Dialect/GPU/Passes.h
    M mlir/lib/Dialect/GPU/Transforms/SerializeToBlob.cpp
    M mlir/lib/Dialect/GPU/Transforms/SerializeToHsaco.cpp

  Log Message:
  -----------
  [MLIR][GPU] Add debug output to enable dumping GPU assembly

- Set the DEBUG_TYPE of SerializeToBlob to serialize-to-blob
- Add debug output to print the assembly or PTX for GPU modules before
  they are assembled and linked

Note that, as SerializeToBlob is a superclass of SerializeToCubin and
SerializeToHsaco, --debug-only=serialize-to-blom will dump the
intermediate compiler result for both of these passes.

In addition, if LLVM options such as --stop-after are used to control
the GPU kernel compilation process, the debug output will contain the
appropriate intermediate IR.

Reviewed By: herhut

Differential Revision: https://reviews.llvm.org/D117519