CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-17 11:37:10 +00:00
Code Issues Packages 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

66
ggml/src/ggml-cpu/vec.cpp
View File

@@ -404,6 +404,72 @@ void ggml_vec_swiglu_f32(const int n, float * y, const float * x, const float *
}
}
ggml_float ggml_vec_cvar_f32(const int n, float * y, const float * x, const float mean) {
int i = 0;
ggml_float sum = 0;
// TODO: optimize to process the remaining elements in groups using the smaller vector sizes from AVX2 and SSE
// ref: https://github.com/ggml-org/llama.cpp/pull/15953#pullrequestreview-3310928344
#if defined(__AVX512F__) && defined(__AVX512DQ__)
for (; i + 15 < n; i += 16) {
__m512 val = _mm512_sub_ps(_mm512_loadu_ps(x + i),
_mm512_set1_ps(mean));
_mm512_storeu_ps(y + i, val);
sum += (ggml_float)_mm512_reduce_add_ps(_mm512_mul_ps(val, val));
}
#elif defined(__AVX2__) && defined(__FMA__)
for (; i + 7 < n; i += 8) {
__m256 val = _mm256_sub_ps(_mm256_loadu_ps(x + i),
_mm256_set1_ps(mean));
_mm256_storeu_ps(y + i, val);
val = _mm256_mul_ps(val,val);
__m128 val2 = _mm_add_ps(_mm256_extractf128_ps(val, 1),
_mm256_castps256_ps128(val));
val2 = _mm_add_ps(val2, _mm_movehl_ps(val2, val2));
val2 = _mm_add_ss(val2, _mm_movehdup_ps(val2));
sum += (ggml_float)_mm_cvtss_f32(val2);
}
#elif defined(__SSE2__)
for (; i + 3 < n; i += 4) {
__m128 val = _mm_sub_ps(_mm_loadu_ps(x + i),
_mm_set1_ps(mean));
_mm_storeu_ps(y + i, val);
val = _mm_mul_ps(val, val);
#if defined(__AVX__) || defined(__AVX2__) || defined(__AVX512F__)
val = _mm_add_ps(val, _mm_movehl_ps(val, val));
val = _mm_add_ss(val, _mm_movehdup_ps(val));
#else
__m128 tmp = _mm_shuffle_ps(val, val, _MM_SHUFFLE(2, 3, 0, 1));
val = _mm_add_ps(val, tmp);
tmp = _mm_movehl_ps(tmp, val);
val = _mm_add_ss(val, tmp);
#endif // __AVX__ || __AVX2__ || __AVX512F__
sum += (ggml_float)_mm_cvtss_f32(val);
}
#elif defined(__ARM_NEON) && defined(__aarch64__)
for (; i + 3 < n; i += 4) {
float32x4_t val = vsubq_f32(vld1q_f32(x + i),
vdupq_n_f32(mean));
vst1q_f32(y + i, val);
val = vmulq_f32(val, val);
sum += (ggml_float)vaddvq_f32(val);
}
#elif defined(__VXE__) || defined(__VXE2__)
for (; i + 3 < n; i += 4) {
float32x4_t val = vec_sub(vec_xl(0, x + i), vec_splats(mean));
vec_xst(val, 0, y + i);
val = vec_mul(val, val);
sum += (ggml_float)vec_hsum_f32x4(val);
}
#endif
for (; i < n; ++i) {
float val = x[i] - mean;
val *= val;
sum += (ggml_float)val;
y[i] = val;
}
return sum/n;
}
ggml_float ggml_vec_soft_max_f32(const int n, float * y, const float * x, float max) {
int i = 0;
ggml_float sum = 0;