diff options
| author | Navdeep Kumar <navdeep.navdeep37@gmail.com> | 2021-05-06 12:05:07 +0530 |
|---|---|---|
| committer | Uday Bondhugula <uday@polymagelabs.com> | 2021-05-06 12:06:25 +0530 |
| commit | 875eb523c13249114507cb8facd797773e278d9e (patch) | |
| tree | 8076679a1df69ec424de7f8d78914dcbdeb5f5a0 /llvm/tools/llvm-objdump/llvm-objdump.cpp | |
| parent | 16c7829784f071d9fd4ae9da4cc8b3786a58018e (diff) | |
| download | llvm-875eb523c13249114507cb8facd797773e278d9e.zip llvm-875eb523c13249114507cb8facd797773e278d9e.tar.gz llvm-875eb523c13249114507cb8facd797773e278d9e.tar.bz2 | |
[MLIR][GPU][NVVM] Add warp synchronous matrix-multiply accumulate ops
Add warp synchronous matrix-multiply accumulate ops in GPU and NVVM
dialect. Add following three ops to GPU dialect :-
1.) subgroup_mma_load_matrix
2.) subgroup_mma_store_matrix
3.) subgroup_mma_compute
Add following three ops to NVVM dialect :-
1.) wmma.m16n16k16.load.[a,b,c].[f16,f32].row.stride
2.) wmma.m16n16k16.store.d.[f16,f32].row.stride
3.) wmma.m16n16k16.mma.row.row.[f16,f32].[f16,f32]
Reviewed By: bondhugula, ftynse, ThomasRaoux
Differential Revision: https://reviews.llvm.org/D95330
Diffstat (limited to 'llvm/tools/llvm-objdump/llvm-objdump.cpp')
0 files changed, 0 insertions, 0 deletions