llvm-project/mlir
Navdeep Kumar eaaf7a6a09 [MLIR][GPU][NVVM] Add conversion of warp synchronous matrix-multiply accumulate GPU ops
Add conversion of warp synchronous matrix-multiply
accumulate GPU ops
Add conversion of warp synchronous matrix-multiply accumulate GPU ops to
NVVM ops. The following conversions are added :-
  1.) subgroup_mma_load_matrix -> wmma.m16n16k16.load.[a,b,c]..row.stride
  2.) subgroup_mma_store_matrix -> wmma.m16n16k16.store.d.[f16,f32].row.stride
  3.) subgroup_mma_compute -> wmma.m16n16k16.mma.row.row.[f16,f32].[f16,f32]

Reviewed By: bondhugula, ftynse

Differential Revision: https://reviews.llvm.org/D95331
2021-05-21 21:20:33 +05:30
..
cmake/modules [cmake] Add support for multiple distributions 2021-05-12 11:13:18 -07:00
docs [mlir][Standard] NFC - Drop remaining EDSC usage 2021-05-21 10:40:39 +00:00
examples Add a helper function to convert LogicalResult to int for return from main 2021-05-19 00:12:39 +00:00
include [MLIR][GPU][NVVM] Add conversion of warp synchronous matrix-multiply accumulate GPU ops 2021-05-21 21:20:33 +05:30
lib [MLIR][GPU][NVVM] Add conversion of warp synchronous matrix-multiply accumulate GPU ops 2021-05-21 21:20:33 +05:30
python [mlir] Add Python bindings for vector dialect 2021-05-20 17:53:08 +09:00
test [MLIR][GPU][NVVM] Add conversion of warp synchronous matrix-multiply accumulate GPU ops 2021-05-21 21:20:33 +05:30
tools [mlir][Standard] NFC - Drop remaining EDSC usage 2021-05-21 10:40:39 +00:00
unittests [mlir][spirv] NFC: Replace OwningSPIRVModuleRef with OwningOpRef 2021-05-06 17:17:44 -04:00
utils [mlir] Add a vscode language extension for MLIR 2021-04-21 14:44:37 -07:00
.clang-format
.clang-tidy Fix MLIR clang-tidy: when tweaking it does not inherit from the parent 2020-03-07 17:44:21 +00:00
CMakeLists.txt Move MLIR python sources to mlir/python. 2021-05-03 18:36:48 +00:00
LICENSE.TXT Add the Apache2 with LLVM exceptions license to MLIR 2019-12-24 00:58:06 -08:00
README.md mlir README.md: Fix the syntax 2019-12-24 13:31:07 +01:00

README.md

Multi-Level Intermediate Representation

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