llvm-project/mlir
Krzysztof Drewniak 40aef79db0 [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
2022-01-20 20:52:12 +00:00
..
cmake/modules [mlir] Configure mlir so that it can be directly included in a parent cmakelists.txt 2022-01-19 12:02:22 -08:00
docs [mlir] Convert OpTrait::FunctionLike to FunctionOpInterface 2022-01-18 20:56:53 -08:00
examples [mlir][Pass] Deprecate FunctionPass in favor of OperationPass<FuncOp> 2022-01-18 19:52:44 -08:00
include [MLIR][GPU] Add debug output to enable dumping GPU assembly 2022-01-20 20:52:12 +00:00
lib [MLIR][GPU] Add debug output to enable dumping GPU assembly 2022-01-20 20:52:12 +00:00
python [mlir] Rework subclass construction in PybindAdaptors.h 2022-01-19 18:09:05 +01:00
test [mlir][pdl] Make `pdl` the default dialect when parsing/printing 2022-01-20 20:22:53 +00:00
tools [mlir:Analysis] Move the LoopAnalysis library to Dialect/Affine/Analysis 2022-01-18 10:28:22 -08:00
unittests [mlir][Pass] Deprecate FunctionPass in favor of OperationPass<FuncOp> 2022-01-18 19:52:44 -08:00
utils [mlir][textmate] Add support for function visibility 2022-01-18 18:48:43 -08:00
.clang-format
.clang-tidy Enable readability-redundant-smartptr-get in MLIR local clang-tidy config 2022-01-08 20:07:11 +00:00
CMakeLists.txt [cmake] Make include(GNUInstallDirs) always below project(..) 2022-01-20 18:59:17 +00:00
LICENSE.TXT
README.md

README.md

Multi-Level Intermediate Representation

See https://mlir.llvm.org/ for more information.