tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-15 12:42:40 -04:00
Code Issues Packages Projects Releases Wiki Activity

ggml : fixes for AVXVNNI instruction set with MSVC and Clang (#11027)

Browse Source 
* Fixes for clang AVX VNNI

* enable AVX VNNI and alder lake build for MSVC

* Apply suggestions from code review

---------

Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
Srihari-mcw
2024-12-31 19:53:33 +05:30
committed by GitHub
parent 45095a61bf
commit 0827b2c1da
5 changed files with 15 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-cpu/llamafile/sgemm.cpp
View File

@@ -1000,8 +1000,10 @@ class tinyBLAS_Q0_AVX {
inline __m256 updot(__m256i u, __m256i s) {
__m256i res;
#if defined(__AVXVNNI__) || (defined(__AVX512VNNI__) && defined(__AVX512VL__))
#if defined(__AVX512VNNI__) && defined(__AVX512VL__)
res = _mm256_dpbusd_epi32(_mm256_setzero_si256(), u, s);
#elif defined(__AVXVNNI__)
res = _mm256_dpbusd_avx_epi32(_mm256_setzero_si256(), u, s);
#else
res = _mm256_madd_epi16(_mm256_set1_epi16(1), _mm256_maddubs_epi16(u, s));
#endif