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

ggml : fix avx512 const correctness

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2024-04-19 17:45:08 +03:00
parent 52945429eb
commit 3badef1fe1
No known key found for this signature in database
GPG key ID: BF970631944C16B7
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml.c
View file

@ -1058,7 +1058,7 @@ do { \
// unlike _mm256_cvt intrinsics that require F16C, _mm512_cvt is defined in AVX512F // unlike _mm256_cvt intrinsics that require F16C, _mm512_cvt is defined in AVX512F
// so F16C guard isn't required // so F16C guard isn't required
#define GGML_F32Cx16_LOAD(x) _mm512_cvtph_ps(_mm256_loadu_si256((__m256i *)(x))) #define GGML_F32Cx16_LOAD(x) _mm512_cvtph_ps(_mm256_loadu_si256((const __m256i *)(x)))
#define GGML_F32Cx16_STORE(x, y) _mm256_storeu_si256((__m256i *)(x), _mm512_cvtps_ph(y, 0)) #define GGML_F32Cx16_STORE(x, y) _mm256_storeu_si256((__m256i *)(x), _mm512_cvtps_ph(y, 0))
#define GGML_F32Cx16_FMA(a, b, c) _mm512_fmadd_ps(b, c, a) #define GGML_F32Cx16_FMA(a, b, c) _mm512_fmadd_ps(b, c, a)