ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-06-16 13:58:09 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

whisper : PPC64 big-endian support (#398)

Browse Source 
* ggml : set cache line size to 128 on POWER9

* whisper : add PPC64 big endian support
This commit is contained in:
fitzsim
2023-01-23 18:48:10 +00:00
committed by GitHub
parent 2c3f50a021
commit ae16c21e9c
3 changed files with 80 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
ggml.c
View File

@ -339,8 +339,12 @@ int64_t ggml_cycles_per_ms(void) {
#if defined(__cpp_lib_hardware_interference_size)
#define CACHE_LINE_SIZE hardware_destructive_interference_size
#else
#if defined(__POWER9_VECTOR__)
#define CACHE_LINE_SIZE 128
#else
#define CACHE_LINE_SIZE 64
#endif
#endif
static const size_t CACHE_LINE_SIZE_F32 = CACHE_LINE_SIZE/sizeof(float);
@ -609,9 +613,12 @@ static const size_t CACHE_LINE_SIZE_F32 = CACHE_LINE_SIZE/sizeof(float);
#define GGML_F16_VEC_LOAD(p, i) (i & 0x1) ? \
vec_extract_fp32_from_shorth(vec_xl(0, p - GGML_F16_EPR)) : \
vec_extract_fp32_from_shortl(vec_xl(0, p))
#define GGML_F16_VEC_STORE(p, r, i) \
if (i & 0x1) \
vec_xst(vec_pack_to_short_fp32(r[i], r[i - 1]), 0, p - GGML_F16_EPR)
#define GGML_ENDIAN_BYTE(i) ((unsigned char *)&(uint16_t){1})[i]
#define GGML_F16_VEC_STORE(p, r, i) \
if (i & 0x1) \
vec_xst(vec_pack_to_short_fp32(r[i - GGML_ENDIAN_BYTE(1)], \
r[i - GGML_ENDIAN_BYTE(0)]), \
0, p - GGML_F16_EPR)
#elif defined(__wasm_simd128__)