Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Skip FP8 dot/gemm for MLIR and offload them to rocBLAS #2924

Merged
merged 3 commits into from
Mar 25, 2024
Merged

Skip FP8 dot/gemm for MLIR and offload them to rocBLAS #2924

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
9d9364c
add skip for FP8 dot/gemm inside MLIR
umangyadav Mar 25, 2024
33cd9c6
formatting
umangyadav Mar 25, 2024
c0fc875
formatting
umangyadav Mar 25, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions src/targets/gpu/fuse_mlir.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -277,6 +277,10 @@ auto is_mlir_dot(mlir_mode mode)
return false;
if(mode != mlir_mode::fast)
return true;
// dot operation where (FP8 * FP8 = FP8) is not available in MLIR. rocBLAS has the support
// for it.
if(ins->get_shape().type() == migraphx::shape::fp8e4m3fnuz_type)
return false;
auto a = ins->inputs().front()->get_shape();
auto b = ins->inputs().back()->get_shape();
// auto m = a.lens()[a.lens().size() - 2];
Expand Down
Loading