bswap: use native types for av_bwap16().

This prevents a call to bytestream_get_be16() using a movzwl both before
and after the ror instruction, which is obviously inefficient. Arm uses
the same trick also.

Sintel decoding goes from (avg+SD) 9.856 +/- 0.003 to 9.797 +/- 0.003 sec.

Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
This commit is contained in:
Jason Garrett-Glaser 2011-04-22 17:59:55 -04:00 committed by Ronald S. Bultje
parent 6ffd7eddb8
commit 15919ee48f
1 changed files with 2 additions and 2 deletions

View File

@ -29,9 +29,9 @@
#include "libavutil/attributes.h" #include "libavutil/attributes.h"
#define av_bswap16 av_bswap16 #define av_bswap16 av_bswap16
static av_always_inline av_const uint16_t av_bswap16(uint16_t x) static av_always_inline av_const unsigned av_bswap16(unsigned x)
{ {
__asm__("rorw $8, %0" : "+r"(x)); __asm__("rorw $8, %w0" : "+r"(x));
return x; return x;
} }