[mlir][gpu] Add basic support to do elementwise ops on mma matrix type
authorthomasraoux <thomasraoux@google.com>
Mon, 1 Nov 2021 18:43:54 +0000 (11:43 -0700)
committerthomasraoux <thomasraoux@google.com>
Mon, 1 Nov 2021 18:51:19 +0000 (11:51 -0700)
commit8a992b20dba54a061717a14eab86ccbe097da4c0
tree3082ef878db6ef25b4b0f03c807dcbea50d5a015
parentdfa098140716cc41cfc8b83f3f083008e7219bf9
[mlir][gpu] Add basic support to do elementwise ops on mma matrix type

In order to support fusion with mma matrix type we need to be able to
execute elementwise operations on them. This add an op to be able to
support some basic elementwise operations. This is a is not a full
solution as it only supports a limited scope or operations. Ideally we would
want to be able to fuse with more kind of operations.

Differential Revision: https://reviews.llvm.org/D112857
mlir/include/mlir/Dialect/GPU/CMakeLists.txt
mlir/include/mlir/Dialect/GPU/GPUBase.td
mlir/include/mlir/Dialect/GPU/GPUDialect.h
mlir/include/mlir/Dialect/GPU/GPUOps.td
mlir/include/mlir/IR/OpBase.td
mlir/lib/Conversion/GPUToNVVM/WmmaOpsToNvvm.cpp
mlir/lib/Dialect/GPU/CMakeLists.txt
mlir/lib/Dialect/GPU/IR/GPUDialect.cpp
mlir/test/Conversion/GPUToNVVM/wmma-ops-to-nvvm.mlir
mlir/test/Dialect/GPU/ops.mlir
utils/bazel/llvm-project-overlay/mlir/BUILD.bazel