mirror of
https://github.com/ggerganov/whisper.cpp.git
synced 2025-06-23 11:11:26 +02:00
ggml-cpu: reduce asm calls for hsum (llama/14037)
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
This commit is contained in:
parent
34940abe53
commit
203451bcba
@ -944,10 +944,8 @@ static inline void __lsx_f16x4_store(ggml_fp16_t * x, __m128 y) {
|
||||
for (int i = 0; i < offset; ++i) { \
|
||||
x[i] = vec_add(x[i], x[offset + i]); \
|
||||
} \
|
||||
res = vec_extract(x[0], 0) + \
|
||||
vec_extract(x[0], 1) + \
|
||||
vec_extract(x[0], 2) + \
|
||||
vec_extract(x[0], 3); \
|
||||
float32x4_t tmp = x[0] + vec_reve(x[0]); \
|
||||
res = tmp[0] + tmp[1]; \
|
||||
}
|
||||
|
||||
#define GGML_F32_VEC GGML_F32x4
|
||||
|
Loading…
x
Reference in New Issue
Block a user