llvm-capstone/mlir
Jakub Kuderski ed4daeaa13
[mlir][spirv][gpu] Add conversion for load/store/mad coop matrix ops (#66311)
This is plugged in as an alternative lowering path in the gpu to spirv
dialect conversion. Add custom op builders for coop matrix ops to make
the create functions nicer to work with and less error-prone. The latter
is accomplished by following the op syntax and also requiring stride to
be a constant op to avoid confusion around the order of arguments.

The remaining lowering patterns will be added in a future patch.
2023-09-14 22:16:27 -04:00
..
benchmark/python [NFC][Py Reformat] Reformat python files in mlir subdir 2023-05-26 08:05:40 +02:00
cmake/modules [mlir][python bindings] generate all the enums 2023-08-23 15:03:55 -05:00
docs [mlir][bufferization] Add an ownership based buffer deallocation pass (#66337) 2023-09-14 12:13:37 +02:00
examples [mlir] Move FunctionInterfaces to Interfaces directory and inherit from CallableOpInterface 2023-08-31 11:28:23 +00:00
include [mlir][spirv][gpu] Add conversion for load/store/mad coop matrix ops (#66311) 2023-09-14 22:16:27 -04:00
lib [mlir][spirv][gpu] Add conversion for load/store/mad coop matrix ops (#66311) 2023-09-14 22:16:27 -04:00
python [mlir][linalg][transform][python] Drop _get_op_result... from mix-ins. (#65726) 2023-09-14 17:24:16 +02:00
test [mlir][spirv][gpu] Add conversion for load/store/mad coop matrix ops (#66311) 2023-09-14 22:16:27 -04:00
tools [mlir] Split up VectorToLLVM pass 2023-09-13 16:09:56 +00:00
unittests [mlir][gpu][NVPTX] Enable NVIDIA GPU JIT compilation path (#66220) 2023-09-14 18:00:27 -04:00
utils [mlir][arith] Rename operations: maxfmaximumf, minfminimumf (#65800) 2023-09-11 22:02:19 -07:00
.clang-format
.clang-tidy
CMakeLists.txt [mlir][gpu] Deprecate gpu::Serialization* passes. (#65857) 2023-09-11 16:32:15 -04:00
LICENSE.TXT
README.md

Multi-Level Intermediate Representation

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