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

MSVC cvt intrinsics

Browse source
This commit is contained in:
anzz1 2023-03-22 04:36:29 +02:00
parent c43d45696f
commit 67ad7c445c
1 changed files with 5 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

5
ggml.c
View file

@ -182,8 +182,13 @@ typedef double ggml_float;
#ifdef __F16C__
#ifdef _MSC_VER
#define GGML_COMPUTE_FP16_TO_FP32(x) _mm_cvtss_f32(_mm_cvtph_ps(_mm_cvtsi32_si128(x)))
#define GGML_COMPUTE_FP32_TO_FP16(x) _mm_extract_epi16(_mm_cvtps_ph(_mm_set_ss(x), 0), 0)
#else
#define GGML_COMPUTE_FP16_TO_FP32(x) _cvtsh_ss(x)
#define GGML_COMPUTE_FP32_TO_FP16(x) _cvtss_sh(x, 0)
#endif
#elif defined(__POWER9_VECTOR__)