History

swscale/x86/rgb2rgb: disable rgb24toyv12_mmxext for x86_64

The mmxext implementation is slower than the C version in x86_64. m32 m64 rgb24toyv12_16_200_c: 24942.7 14812.6 rgb24toyv12_16_200_mmxext: 17857.2 ( 1.40x) 17400.4 ( 0.85x) rgb24toyv12_128_60_c: 56892.9 35616.9 rgb24toyv12_128_60_mmxext: 40730.9 ( 1.40x) 39610.4 ( 0.90x) rgb24toyv12_512_16_c: 58402.7 37209.4 rgb24toyv12_512_16_mmxext: 44842.4 ( 1.30x) 41136.2 ( 0.90x) rgb24toyv12_1920_4_c: 54827.4 34737.4 rgb24toyv12_1920_4_mmxext: 51169.9 ( 1.07x) 34818.9 ( 1.00x)

Ramiro Polla committed 2 years ago

Commit caaec2e1 parent e0cc0611 file · +3 −3Browse files

Unified · Split

libswscale/x86/rgb2rgb.c+3−3
@@ -1480,7 +1480,7 @@ static inline void planar2x_mmxext(const uint8_t *src, uint8_t *dst, int srcWidt · 1479 unmodified lines
14801480 * others are ignored in the C version.
14811481 * FIXME: Write HQ version.
14821482 */
1483−#if HAVE_7REGS
1483+#if ARCH_X86_32 && HAVE_7REGS
14841484 static inline void rgb24toyv12_mmxext(const uint8_t *src, uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
14851485 int width, int height,
14861486 int lumStride, int chromStride, int srcStride,
@@ -2257,9 +2257,9 @@ static av_cold void rgb2rgb_init_mmxext(void) · 770 unmodified lines
22572257 yuyvtoyuv422 = yuyvtoyuv422_mmxext;
22582258
22592259 planar2x = planar2x_mmxext;
2260−#if HAVE_7REGS
2260+#if ARCH_X86_32 && HAVE_7REGS
22612261 ff_rgb24toyv12 = rgb24toyv12_mmxext;
2262−#endif /* HAVE_7REGS */
2262+#endif /* ARCH_X86_32 && HAVE_7REGS */
22632263
22642264 yuyvtoyuv420 = yuyvtoyuv420_mmxext;
22652265 uyvytoyuv420 = uyvytoyuv420_mmxext;

Keyboard shortcuts

General

Show keyboard shortcuts
?
Focus the current search
/

Issues and pull requests

Open filters
f

Issues, pull requests and Inbox

Select next item
j↓
Select previous item
k↑
Open selected item
Enter
Dismiss filters or clear selection
Esc

Repository code

Go to file
t