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

ggml : Fix warnings when run cpu CI locally on LoongArch

Browse source
This commit is contained in:
Jinyang He 2025-02-06 16:31:40 +08:00
parent 45aa1db6cf
commit 99bbe263f6
2 changed files with 10 additions and 24 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

16
ggml/src/ggml-cpu/ggml-cpu-quants.c
View file

@ -577,12 +577,10 @@ static inline __m128i mul_sum_i8_pairs(const __m128i x, const __m128i y) {
// horizontally add 8 floats
static inline float hsum_float_8(const __m256 x) {
__m128 res = lasx_extractf128(x, 1);
ft_union tmp;
res = __lsx_vfadd_s(res, lasx_extractf128(x, 0));
res = __lsx_vfadd_s(res, (__m128)__lsx_vpickod_d((__m128i)res, (__m128i)res));
res = __lsx_vfadd_s(res, (__m128)__lsx_vinsgr2vr_w(__lsx_vldi(0), __lsx_vpickve2gr_w(res, 1), 0));
tmp.i = __lsx_vpickve2gr_w(res, 0);
return tmp.f;
return ((v4f32)res)[0];
}
// horizontally add 8 int32_t
@ -924,7 +922,6 @@ void quantize_row_q8_0(const float * restrict x, void * restrict vy, int64_t k)
#elif defined(__loongarch_asx)
for (int i = 0; i < nb; i++) {
ft_union fi;
__m256 v0 = (__m256)__lasx_xvld( x , 0);
__m256 v1 = (__m256)__lasx_xvld( x , 32);
__m256 v2 = (__m256)__lasx_xvld( x , 64);
@ -942,8 +939,7 @@ void quantize_row_q8_0(const float * restrict x, void * restrict vy, int64_t k)
max4 = __lsx_vfmax_s( max4, (__m128)__lsx_vpickod_d((__m128i) max4, (__m128i)max4 ) );
__m128 tmp = max4;
max4 = __lsx_vfmax_s( max4, (__m128)__lsx_vinsgr2vr_w(tmp, __lsx_vpickve2gr_w( max4, 1 ), 0 ));
fi.i = __lsx_vpickve2gr_w( (__m128i)max4, 0 );
const float max_scalar = fi.f;
const float max_scalar = ((v4f32)max4)[0];
// Quantize these floats
const float d = max_scalar / 127.f;
@ -1248,7 +1244,6 @@ void quantize_row_q8_1(const float * restrict x, void * restrict vy, int64_t k)
#elif defined(__loongarch_asx)
for (int i = 0; i < nb; i++) {
ft_union ft;
__m256 v0 = (__m256)__lasx_xvld( x , 0 );
__m256 v1 = (__m256)__lasx_xvld( x , 32 );
__m256 v2 = (__m256)__lasx_xvld( x , 64 );
@ -1266,8 +1261,7 @@ void quantize_row_q8_1(const float * restrict x, void * restrict vy, int64_t k)
max4 = __lsx_vfmax_s( max4, (__m128)__lsx_vpickod_d((__m128i) max4, (__m128i)max4 ) );
__m128 tmp = max4;
max4 = __lsx_vfmax_s( max4, (__m128)__lsx_vextrins_w((__m128i)tmp, (__m128i)max4, 0x10 ));
ft.i = __lsx_vpickve2gr_w( (__m128i)max4, 0 );
const float max_scalar = ft.f;
const float max_scalar = ((v4f32)max4)[0];
// Quantize these floats
const float d = max_scalar / 127.f;
@ -6139,9 +6133,7 @@ void ggml_vec_dot_q4_K_q8_K(int n, float * restrict s, size_t bs, const void * r
acc_m = __lsx_vfadd_s(acc_m, (__m128)tmp1);
ft_union fi;
fi.i = __lsx_vpickve2gr_w(acc_m, 0);
*s = hsum_float_8(acc) + fi.f ;
*s = hsum_float_8(acc) + ((v4f32)acc_m)[0];
#else
const uint8_t * scales = (const uint8_t*)&utmp[0];