EngineX-Ascend/enginex-ascend-910-llama.cpp
10
0
Fork 0
Code Issues Pull Requests Actions 4 Projects Releases Wiki Activity

cpu : optimize the ggml NORM operation (#15953)

Browse Source 
* ggml-cpu: optimize norm operation to use intrinsics or Accelerate

          rename function

          add endif macro comment

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Aaron Teo <taronaeo@gmail.com>

* implement s390x SIMD suggested by @taronaeo

* add TODO comment

* tidy up spaces

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Aaron Teo <taronaeo@gmail.com>
This commit is contained in:
duduta
2025-10-09 22:11:15 +03:00
committed by GitHub
parent d00cbea63c
commit 1deee0f8d4
3 changed files with 77 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
ggml/src/ggml-cpu/ops.cpp
View File

@@ -3467,31 +3467,27 @@ static void ggml_compute_forward_norm_f32(
GGML_ASSERT(eps >= 0.0f);
// TODO: optimize
for (int64_t i03 = 0; i03 < ne03; i03++) {
for (int64_t i02 = 0; i02 < ne02; i02++) {
for (int64_t i01 = ith; i01 < ne01; i01 += nth) {
const float * x = (float *) ((char *) src0->data + i01*nb01 + i02*nb02 + i03*nb03);
ggml_float sum = 0.0;
for (int64_t i00 = 0; i00 < ne00; i00++) {
sum += (ggml_float)x[i00];
}
float sum = 0.0;
ggml_vec_sum_f32(ne00, &sum, x);
float mean = sum/ne00;
float * y = (float *) ((char *) dst->data + i01*nb1 + i02*nb2 + i03*nb3);
float variance = 0;
ggml_float sum2 = 0.0;
for (int64_t i00 = 0; i00 < ne00; i00++) {
float v = x[i00] - mean;
y[i00] = v;
sum2 += (ggml_float)(v*v);
}
#ifdef GGML_USE_ACCELERATE
mean = -mean;
vDSP_vsadd(x, 1, &mean, y, 1, ne00);
vDSP_measqv(y, 1, &variance, ne00);
#else
variance = ggml_vec_cvar_f32(ne00, y, x, mean);
#endif //GGML_USE_ACCELERATE
float variance = sum2/ne00;
const float scale = 1.0f/sqrtf(variance + eps);
ggml_vec_scale_f32(ne00, y, scale);
}
}