Skip to content

[Common] Reduced padding kernel compilation time #2827

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

Open
Oleg-Goncharov wants to merge 1 commit into
base: main
Choose a base branch
from
+2 −2
Open

[Common] Reduced padding kernel compilation time #2827

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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: 2 additions & 2 deletions transformer_engine/common/util/padding.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,7 +87,7 @@ __global__ void __launch_bounds__(threads_per_block) multi_padding_kernel(MultiP
// Note: Each thread loads n_iterations subtiles, casts to output
// type, and transposes in registers.
Type local_zero = static_cast<Type>(0.f);
#pragma unroll
#pragma unroll 4
for (int iter = 0; iter < n_iterations; ++iter) {
const int i1 = tidy + iter * bdimy;
const int j1 = tidx;
Expand Down Expand Up @@ -171,7 +171,7 @@ __global__ void __launch_bounds__(threads_per_block) multi_unpadding_kernel(Mult
// Note: Each thread loads n_iterations subtiles, casts to output
// type, and transposes in registers.
Type local_zero = static_cast<Type>(0.f);
#pragma unroll
#pragma unroll 4
for (int iter = 0; iter < n_iterations; ++iter) {
const int i1 = tidy + iter * bdimy;
const int j1 = tidx;
Expand Down
Loading