tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-02 13:55:43 +00:00
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

5
ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp
View File

@ -194,9 +194,12 @@ static inline __m256i sum_i16_pairs_int32x8(const __m256i x) {
}
static inline __m256i mul_sum_us8_pairs_int32x8(const __m256i ax, const __m256i sy) {
#if defined(__AVXVNNI__) || (defined(__AVX512VNNI__) && defined(__AVX512VL__))
#if defined(__AVX512VNNI__) && defined(__AVX512VL__)
const __m256i zero = _mm256_setzero_si256();
return _mm256_dpbusd_epi32(zero, ax, sy);
#elif defined(__AVXVNNI__)
const __m256i zero = _mm256_setzero_si256();
return _mm256_dpbusd_avx_epi32(zero, ax, sy);
#else
// Perform multiplication and create 16-bit values
const __m256i dot = _mm256_maddubs_epi16(ax, sy);