Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ggml : LoongArch fixes (#16958)

Browse Source 
* Fix test-quantize-fns f16 and q4_0 failed when use LSX

* Fix LoongArch set float intrinsic when use LSX/LASX
This commit is contained in:
Jinyang He
2025-11-03 08:40:02 +02:00
committed by GitHub
parent ee3a5a10ad
commit fcfce040e8
3 changed files with 32 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cpu/simd-mappings.h
+25 -25
View File
@@ -956,7 +956,7 @@ do { \
#define GGML_F32Cx8 __m256
#define GGML_F32Cx8_ZERO (__m256)__lasx_xvldi(0)
#define GGML_F32Cx8_SET1(x) (__m256)__lasx_xvreplgr2vr_w((x))
#define GGML_F32Cx8_SET1(x) (__m256)__lasx_xvreplfr2vr_s((x))
static inline __m256 __lasx_f32cx8_load(const ggml_fp16_t * x) {
__m256i a;
@@ -999,34 +999,34 @@ static inline void __lasx_f32cx8_store(ggml_fp16_t * x, __m256 y) {
#define GGML_F32x4 __m128
#define GGML_F32x4_ZERO (__m128)__lsx_vldi(0)
#define GGML_F32x4_SET1(x) (__m128)__lsx_vinsgr2vr_w(__lsx_vldi(0),(x), 0)
#define GGML_F32x4_SET1(x) (__m128)__lsx_vreplfr2vr_s((x))
#define GGML_F32x4_LOAD(x) (__m128)__lsx_vld((x), 0)
#define GGML_F32x4_STORE(x, y) __lsx_vst(y, x, 0)
#define GGML_F32x4_FMA(a, b, c) __lsx_vfmadd_s(b, c, a)
#define GGML_F32x4_ADD __lsx_vfadd_s
#define GGML_F32x4_MUL __lsx_vfmul_s
#define GGML_F32x4_REDUCE(res, x) \
{ \
int offset = GGML_F32_ARR >> 1; \
for (int i = 0; i < offset; ++i) { \
x[i] = __lsx_vfadd_s(x[i], x[offset + i]); \
} \
offset >>= 1; \
for (int i = 0; i < offset; ++i) { \
x[i] = __lsx_vfadd_s(x[i], x[offset + i]); \
} \
offset >>= 1; \
for (int i = 0; i < offset; ++i) { \
x[i] = __lsx_vfadd_s(x[i], x[offset + i]); \
} \
__m128i tmp = __lsx_vsrli_d((__m128i) x[0], 32); \
tmp = (__m128i) __lsx_vfadd_s((__m128) tmp, x[0]); \
tmp = __lsx_vpickev_w(__lsx_vldi(0), tmp); \
const __m128 t0 = (__m128)__lsx_vshuf4i_w(tmp, 0x88); \
tmp = __lsx_vsrli_d((__m128i) t0, 32); \
tmp = (__m128i) __lsx_vfadd_s((__m128) tmp, t0); \
tmp = __lsx_vpickev_w(__lsx_vldi(0), tmp); \
res = (ggml_float) __lsx_vpickve2gr_w(__lsx_vshuf4i_w(tmp, 0x88), 0); \
#define GGML_F32x4_REDUCE(res, x) \
{ \
int offset = GGML_F32_ARR >> 1; \
for (int i = 0; i < offset; ++i) { \
x[i] = __lsx_vfadd_s(x[i], x[offset+i]); \
} \
offset >>= 1; \
for (int i = 0; i < offset; ++i) { \
x[i] = __lsx_vfadd_s(x[i], x[offset+i]); \
} \
offset >>= 1; \
for (int i = 0; i < offset; ++i) { \
x[i] = __lsx_vfadd_s(x[i], x[offset+i]); \
} \
__m128i t0 = __lsx_vpickev_w((__m128i)x[0], (__m128i)x[0]); \
__m128i t1 = __lsx_vpickod_w((__m128i)x[0], (__m128i)x[0]); \
__m128 t2 = __lsx_vfadd_s((__m128)t0, (__m128)t1); \
__m128i t3 = __lsx_vpickev_w((__m128i)t2, (__m128i)t2); \
__m128i t4 = __lsx_vpickod_w((__m128i)t2, (__m128i)t2); \
__m128 t5 = __lsx_vfadd_s((__m128)t3, (__m128)t4); \
res = (ggml_float) ((v4f32)t5)[0]; \
}
#define GGML_F32_VEC GGML_F32x4
@@ -1068,7 +1068,7 @@ static inline void __lsx_f16x4_store(ggml_fp16_t * x, __m128 y) {
#define GGML_F32Cx4 __m128
#define GGML_F32Cx4_ZERO (__m128)__lsx_vldi(0)
#define GGML_F32Cx4_SET1(x) (__m128)__lsx_vinsgr2vr_w(__lsx_vldi(0),(x), 0)
#define GGML_F32Cx4_SET1(x) (__m128)__lsx_vreplfr2vr_s((x))
#define GGML_F32Cx4_LOAD(x) (__m128)__lsx_f16x4_load(x)
#define GGML_F32Cx4_STORE(x, y) __lsx_f16x4_store(x, y)
#define GGML_F32Cx4_FMA GGML_F32x4_FMA