libswscale/ppc: VSX-optimize 9-16 bit yuv2planeX

./ffmpeg_g -f rawvideo -pix_fmt rgb24 -s hd1080 -i /dev/zero -pix_fmt yuv420p16be \
-s 1920x1728 -f null -vframes 100 -v error -nostats -

9-14 bit funcs get about 6x speedup, 16-bit gets about 15x.
Fate passes, each format tested with an image to video conversion.

Only POWER8 includes 32-bit vector multiplies, so POWER7 is locked out
of the 16-bit function. This includes the vec_mulo/mule functions too,
not just vmuluwm.

With TIMER_REPORT skips disabled:
yuv420p9le
  12412 UNITS in planarX,  131072 runs,      0 skips
  73136 UNITS in planarX,  131072 runs,      0 skips
yuv420p9be
  12481 UNITS in planarX,  131072 runs,      0 skips
  73410 UNITS in planarX,  131072 runs,      0 skips
yuv420p10le
  12322 UNITS in planarX,  131072 runs,      0 skips
  72546 UNITS in planarX,  131072 runs,      0 skips
yuv420p10be
  12291 UNITS in planarX,  131072 runs,      0 skips
  72935 UNITS in planarX,  131072 runs,      0 skips
yuv420p12le
  12316 UNITS in planarX,  131072 runs,      0 skips
  72708 UNITS in planarX,  131072 runs,      0 skips
yuv420p12be
  12319 UNITS in planarX,  131072 runs,      0 skips
  72577 UNITS in planarX,  131072 runs,      0 skips
yuv420p14le
  12259 UNITS in planarX,  131072 runs,      0 skips
  72516 UNITS in planarX,  131072 runs,      0 skips
yuv420p14be
  12440 UNITS in planarX,  131072 runs,      0 skips
  72962 UNITS in planarX,  131072 runs,      0 skips
yuv420p16le
  10548 UNITS in planarX,  131072 runs,      0 skips
  73429 UNITS in planarX,  131072 runs,      0 skips
yuv420p16be
  10634 UNITS in planarX,  131072 runs,      0 skips
 150959 UNITS in planarX,  131072 runs,      0 skips

Signed-off-by: Lauri Kasanen <cand@gmx.com>

1 files changed, 2 insertions, 2 deletions

diff --git a/libswscale/ppc/swscale_ppc_template.c b/libswscale/ppc/swscale_ppc_template.c
index 00e4b99e00..11decab0b9 100644
--- a/libswscale/ppc/swscale_ppc_template.c
+++ b/libswscale/ppc/swscale_ppc_template.c
@@ -21,7 +21,7 @@
  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  */
 
-static void FUNC(yuv2planeX_16)(const int16_t *filter, int filterSize,
+static void FUNC(yuv2planeX_8_16)(const int16_t *filter, int filterSize,
                                   const int16_t **src, uint8_t *dest,
                                   const uint8_t *dither, int offset, int x)
 {
@@ -88,7 +88,7 @@ static void FUNC(yuv2planeX)(const int16_t *filter, int filterSize,
     yuv2planeX_u(filter, filterSize, src, dest, dst_u, dither, offset, 0);
 
     for (i = dst_u; i < dstW - 15; i += 16)
-        FUNC(yuv2planeX_16)(filter, filterSize, src, dest + i, dither,
+        FUNC(yuv2planeX_8_16)(filter, filterSize, src, dest + i, dither,
                               offset, i);
 
     yuv2planeX_u(filter, filterSize, src, dest, dstW, dither, offset, i);