ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

ggml : optimize and build warning fix for LoongArch (#11709)

Browse source 
* ggml : optimize convert f32<->f16 for loongarch_asx

* ggml : optimize loongarch_asx extend i16,i8,u8 to i32,i16

* ggml : Fix warnings when run cpu CI locally on LoongArch
This commit is contained in:
Jinyang He 2025-02-07 15:38:31 +08:00 • committed by GitHub
parent 855cd0734a
commit 225bbbfa39
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 22 additions and 57 deletions
Download patch file Download diff file Expand all files Collapse all files

18
ggml/src/ggml-cpu/ggml-cpu-impl.h
View file

@ -360,21 +360,15 @@ inline static int32x4_t ggml_vdotq_s32(int32x4_t acc, int8x16_t a, int8x16_t b)
#endif
#if defined(__loongarch_asx)
typedef union {
int32_t i;
float f;
} ft_union;
/* float type data load instructions */
static __m128 __lsx_vreplfr2vr_s(float val) {
ft_union fi_tmpval = {.f = val};
return (__m128)__lsx_vreplgr2vr_w(fi_tmpval.i);
static __m128 __lsx_vreplfr2vr_s(const float val) {
v4f32 res = {val, val, val, val};
return (__m128)res;
}
static __m256 __lasx_xvreplfr2vr_s(float val) {
ft_union fi_tmpval = {.f = val};
return (__m256)__lasx_xvreplgr2vr_w(fi_tmpval.i);
static __m256 __lasx_xvreplfr2vr_s(const float val) {
v8f32 res = {val, val, val, val, val, val, val, val};
return (__m256)res;
}
#endif