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

ggml : posixify madvise and pagesize (#3037)

Browse source 
* llama : use posix_madvise() instead of madvise() derived from BSD

sed -i 's,\<madvise\>,posix_&,g;s,\<MADV_,POSIX_&,g' llama.cpp

* ggml : use sysconf(_SC_PAGESIZE) instead of getpagesize() derived from BSD

sed -i 's,getpagesize(),sysconf(_SC_PAGESIZE),g' ggml.c

* metal : use sysconf(_SC_PAGESIZE) instead of getpagesize() derived from BSD

sed -i 's,getpagesize(),sysconf(_SC_PAGESIZE),g' ggml-metal.m
This commit is contained in:
Przemysław Pawełczyk 2023-09-07 10:15:06 +02:00 • committed by GitHub
parent 178b1850eb
commit fec2fb19e4
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 7 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml.c
View file

@ -194,7 +194,7 @@ typedef void * thread_ret_t;
inline static void * ggml_aligned_malloc(size_t size) {
void * aligned_memory = NULL;
#ifdef GGML_USE_METAL
int result = posix_memalign(&aligned_memory, getpagesize(), size);
int result = posix_memalign(&aligned_memory, sysconf(_SC_PAGESIZE), size);
#else
int result = posix_memalign(&aligned_memory, GGML_MEM_ALIGN, size);
#endif