Skip to content

Fix aarch64 sbgemv_t compilation error for GCC < 13 #5176

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
Mar 12, 2025
Merged

Fix aarch64 sbgemv_t compilation error for GCC < 13 #5176

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
1 change: 1 addition & 0 deletions CONTRIBUTORS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -237,6 +237,7 @@ In chronological order:
* [2025-01-10] Add thread throttling profile for SGEMM on NEOVERSEV1
* [2025-01-21] Optimize gemv_t_sve_v1x3 kernel
* [2025-02-26] Add sbgemv_t_bfdot kernel
* [2025-03-12] Fix aarch64 sbgemv_t compilation error for GCC < 13

* Marek Michalowski <marek.michalowski@arm.com>
* [2025-01-21] Add thread throttling profile for SGEMV on `NEOVERSEV1`
Expand Down
17 changes: 6 additions & 11 deletions kernel/arm64/sbgemv_t_bfdot.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,11 +33,6 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
#include <arm_neon.h>
#include "common.h"

static inline float bf16_to_fp32(bfloat16 bf16) {
uint32_t fp32 = (uint32_t)bf16 << 16;
return *((float*)&fp32);
}

int CNAME(BLASLONG m, BLASLONG n, float alpha, bfloat16 *a, BLASLONG lda, bfloat16 *x, BLASLONG incx, float beta, float *y, BLASLONG incy)
{
if (m < 1 || n < 1) return(0);
Expand Down Expand Up @@ -132,10 +127,10 @@ int CNAME(BLASLONG m, BLASLONG n, float alpha, bfloat16 *a, BLASLONG lda, bfloat
}

for (; i < m; ++i) {
y0_ptr[iy] += alpha * a0_ptr[i] * x_ptr[i];
y1_ptr[iy] += alpha * a1_ptr[i] * x_ptr[i];
y2_ptr[iy] += alpha * a2_ptr[i] * x_ptr[i];
y3_ptr[iy] += alpha * a3_ptr[i] * x_ptr[i];
y0_ptr[iy] += alpha * vcvtah_f32_bf16(a0_ptr[i]) * vcvtah_f32_bf16(x_ptr[i]);
y1_ptr[iy] += alpha * vcvtah_f32_bf16(a1_ptr[i]) * vcvtah_f32_bf16(x_ptr[i]);
y2_ptr[iy] += alpha * vcvtah_f32_bf16(a2_ptr[i]) * vcvtah_f32_bf16(x_ptr[i]);
y3_ptr[iy] += alpha * vcvtah_f32_bf16(a3_ptr[i]) * vcvtah_f32_bf16(x_ptr[i]);
}

iy += incy;
Expand Down Expand Up @@ -177,7 +172,7 @@ int CNAME(BLASLONG m, BLASLONG n, float alpha, bfloat16 *a, BLASLONG lda, bfloat
}

for (; i < m; ++i) {
y_ptr[iy] += alpha * a_ptr[i] * x_ptr[i];
y_ptr[iy] += alpha * vcvtah_f32_bf16(a_ptr[i]) * vcvtah_f32_bf16(x_ptr[i]);
}

iy += incy;
Expand All @@ -191,7 +186,7 @@ int CNAME(BLASLONG m, BLASLONG n, float alpha, bfloat16 *a, BLASLONG lda, bfloat
temp = 0.0;
ix = 0;
for (i = 0; i < m; i++) {
temp += bf16_to_fp32(a[i]) * bf16_to_fp32(x[ix]);
temp += vcvtah_f32_bf16(a_ptr[i]) * vcvtah_f32_bf16(x_ptr[ix]);
ix += incx;
}
if (beta == 0.0f) {
Expand Down
Loading