CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-10 10:27:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : add ggml_scale_bias (#14417)

Browse Source 
* ggml : add ggml_scale_bias

* ggml_vec_mad1_f32

* add more simd

* add CUDA

* sycl

* vulkan

* cann (placeholder)

* opencl

* will this fix cpu?

* fix cuda

* suggestions from coderabbit

* fix cann compile error

* vDSP_vsmsa

* rm __ARM_FEATURE_SVE

* use memcpy for op params

* make code looks more consistent

* use scalar for __ARM_FEATURE_SVE

* add x param to ggml_vec_mad1_f32
This commit is contained in:
Xuan-Son Nguyen
2025-07-09 18:16:12 +02:00
committed by GitHub
parent 26a48ad699
commit 98bab638fb
14 changed files with 139 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
ggml/src/ggml-cpu/ops.cpp
View File

@@ -4643,9 +4643,11 @@ static void ggml_compute_forward_scale_f32(
GGML_ASSERT(ggml_is_contiguous(dst));
GGML_ASSERT(ggml_are_same_shape(src0, dst));
// scale factor
float v;
memcpy(&v, dst->op_params, sizeof(float));
float s; // scale factor
float b; // bias
memcpy(&s, (float *) dst->op_params + 0, sizeof(float));
memcpy(&b, (float *) dst->op_params + 1, sizeof(float));
const int ith = params->ith;
const int nth = params->nth;
@@ -4664,12 +4666,22 @@ static void ggml_compute_forward_scale_f32(
const size_t nb1 = dst->nb[1];
for (int i1 = ir0; i1 < ir1; i1++) {
if (dst->data != src0->data) {
// src0 is same shape as dst => same indices
memcpy((char *)dst->data + i1*nb1, (char *)src0->data + i1*nb01, nc * sizeof(float));
if (b == 0.0f) {
for (int i1 = ir0; i1 < ir1; i1++) {
if (dst->data != src0->data) {
// src0 is same shape as dst => same indices
// TODO: add x parameter to ggml_vec_scale_f32 and remove this memcpy
memcpy((char *)dst->data + i1*nb1, (char *)src0->data + i1*nb01, nc * sizeof(float));
}
ggml_vec_scale_f32(nc, (float *) ((char *) dst->data + i1*nb1), s);
}
} else {
for (int i1 = ir0; i1 < ir1; i1++) {
ggml_vec_mad1_f32(nc,
(float *) ((char *) dst->data + i1*nb1),
(float *) ((char *) src0->data + i1*nb1),
s, b);
}
ggml_vec_scale_f32(nc, (float *) ((char *) dst->data + i1*nb1), v);
}
}

39
ggml/src/ggml-cpu/vec.h
View File

@@ -351,6 +351,45 @@ inline static void ggml_vec_mad_f32_unroll(const int n, const int xs, const int
#endif
}
inline static void ggml_vec_mad1_f32(const int n, float * y, const float * x, const float s, const float b) {
#if defined(GGML_USE_ACCELERATE)
vDSP_vsmsa(x, 1, &s, &b, y, 1, n);
#elif defined(GGML_SIMD)
#if defined(__ARM_FEATURE_SVE)
// scalar ; TODO: Write SVE code
for (int i = 0; i < n; ++i) {
y[i] = x[i]*s + b;
}
#else
const int np = (n & ~(GGML_F32_STEP - 1));
GGML_F32_VEC vs = GGML_F32_VEC_SET1(s);
GGML_F32_VEC vb = GGML_F32_VEC_SET1(b);
GGML_F32_VEC ay[GGML_F32_ARR];
for (int i = 0; i < np; i += GGML_F32_STEP) {
for (int j = 0; j < GGML_F32_ARR; j++) {
ay[j] = GGML_F32_VEC_LOAD(x + i + j*GGML_F32_EPR);
ay[j] = GGML_F32_VEC_FMA(ay[j], vs, vb);
GGML_F32_VEC_STORE(y + i + j*GGML_F32_EPR, ay[j]);
}
}
// leftovers
for (int i = np; i < n; ++i) {
y[i] = x[i]*s + b;
}
#endif
#else
// scalar
for (int i = 0; i < n; ++i) {
y[i] = x[i]*s + b;
}
#endif
}
//inline static void ggml_vec_scale_f32(const int n, float * y, const float v) { for (int i = 0; i < n; ++i) y[i] *= v; }
inline static void ggml_vec_scale_f32(const int n, float * y, const float v) {
#if defined(GGML_USE_ACCELERATE)