Skip to content

Small gemm kernel improvements for AArch64 #5091

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

Merged
martin-frbg merged 1 commit into from
Jan 24, 2025
Merged

Small gemm kernel improvements for AArch64 #5091

Show file tree
Hide file tree
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
2 changes: 1 addition & 1 deletion kernel/arm64/dgemm_small_kernel_tn_sve.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -213,7 +213,7 @@ CNAME(BLASLONG M,
const BLASLONG n2 = N & -2;
const BLASLONG n8 = N & -8;

const int pack_a = M >= v_size2 && N >= 8 && K >= 8 ? 1 : 0;
const int pack_a = M >= v_size2 && N >= 8 ? 1 : 0;
FLOAT* packed_a =
(pack_a) ? packed_a = (FLOAT*)malloc(K * v_size2 * sizeof(FLOAT)) : NULL;

Expand Down
2 changes: 1 addition & 1 deletion kernel/arm64/dgemm_small_kernel_tt_sve.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -219,7 +219,7 @@ CNAME(BLASLONG M,
const BLASLONG n4 = N & -4;
const BLASLONG n2 = N & -2;

const int pack_a = M >= v_size2 && N >= 8 && K >= 8 ? 1 : 0;
const int pack_a = M >= v_size2 && N >= 8 ? 1 : 0;
FLOAT* packed_a =
(pack_a) ? packed_a = (FLOAT*)malloc(K * v_size2 * sizeof(FLOAT)) : NULL;

Expand Down
2 changes: 1 addition & 1 deletion kernel/arm64/sgemm_small_kernel_tn_sve.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -222,7 +222,7 @@ CNAME(BLASLONG M,
const BLASLONG n8 = N & -8;
const BLASLONG n4 = N & -4;

const int pack_a = M >= v_size2 && N >= 8 && K >= 8 ? 1 : 0;
const int pack_a = M >= v_size2 && N >= 8 ? 1 : 0;
FLOAT* packed_a =
(pack_a) ? packed_a = (FLOAT*)malloc(K * v_size2 * sizeof(FLOAT)) : NULL;

Expand Down
2 changes: 1 addition & 1 deletion kernel/arm64/sgemm_small_kernel_tt_sve.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -223,7 +223,7 @@ CNAME(BLASLONG M,
const BLASLONG n8 = N & -8;
const BLASLONG n4 = N & -4;

const int pack_a = M >= v_size2 && N >= 8 && K >= 8 ? 1 : 0;
const int pack_a = M >= v_size2 && N >= 8 ? 1 : 0;
FLOAT* packed_a =
(pack_a) ? packed_a = (FLOAT*)malloc(K * v_size2 * sizeof(FLOAT)) : NULL;

Expand Down
Loading