frederik
/
libxcb
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

xcb_popcount: Use __builtin_popcount if compiler supports it 

If the compiler knows of a better implementation for counting the number
of bits set in a word for the target CPU, let it use that, instead of the
classic algorithm optimized for PDP-6.

Signed-off-by: Alan Coopersmith <alan.coopersmith@oracle.com>
This commit is contained in:
Alan Coopersmith 2024-03-02 12:01:54 -08:00
parent c268499c30
commit 86a478032b
1 changed files with 13 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
src/xcb_util.c
View File

@ -62,12 +62,25 @@
#include <sys/stat.h> #include <sys/stat.h>
#ifndef __has_builtin
# define __has_builtin(x) 0
#endif
int xcb_popcount(uint32_t mask) int xcb_popcount(uint32_t mask)
{ {
#if __has_builtin(__builtin_popcount)
return __builtin_popcount(mask);
#else
/*
* Count the number of bits set to 1 in a 32-bit word.
* Algorithm from MIT AI Lab Memo 239: "HAKMEM", ITEM 169.
* https://dspace.mit.edu/handle/1721.1/6086
*/
uint32_t y; uint32_t y;
y = (mask >> 1) & 033333333333; y = (mask >> 1) & 033333333333;
y = mask - y - ((y >> 1) & 033333333333); y = mask - y - ((y >> 1) & 033333333333);
return ((y + (y >> 3)) & 030707070707) % 077; return ((y + (y >> 3)) & 030707070707) % 077;
#endif
} }
int xcb_sumof(uint8_t *list, int len) int xcb_sumof(uint8_t *list, int len)