./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
---
libswscale/ppc/swscale_ppc_template.c | 4 +-
libswscale/ppc/swscale_vsx.c | 186 +-
2 files changed, 184 insertions(+), 6 deletions(-)
v6: No patch changes, updated bench numbers without skips.
diff --git a/libswscale/ppc/swscale_ppc_template.c
b/libswscale/ppc/swscale_ppc_template.c
index 00e4b99..11decab 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);
diff --git a/libswscale/ppc/swscale_vsx.c b/libswscale/ppc/swscale_vsx.c
index 70da6ae..f6c7f1d 100644
--- a/libswscale/ppc/swscale_vsx.c
+++ b/libswscale/ppc/swscale_vsx.c
@@ -83,6 +83,8 @@
#include "swscale_ppc_template.c"
#undef FUNC
+#undef vzero
+
#endif /* !HAVE_BIGENDIAN */
static void yuv2plane1_8_u(const int16_t *src, uint8_t *dest, int dstW,
@@ -180,6 +182,76 @@ static void yuv2plane1_nbps_vsx(const int16_t *src,
uint16_t *dest, int dstW,
yuv2plane1_nbps_u(src, dest, dstW, big_endian, output_bits, i);
}
+static void yuv2planeX_nbps_u(const int16_t *filter, int filterSize,
+ const int16_t **src, uint16_t *dest, int dstW,
+ int big_endian, int output_bits, int start)
+{
+int i;
+int shift = 11 + 16 - output_bits;
+
+for (i = start; i < dstW; i++) {
+int val = 1 << (shift - 1);
+int j;
+
+for (j = 0; j < filterSize; j++)
+val += src[j][i] * filter[j];
+
+output_pixel([i], val);
+}
+}
+
+static void yuv2planeX_nbps_vsx(const int16_t *filter, int filterSize,
+const int16_t **src, uint16_t *dest, int dstW,
+int big_endian, int output_bits)
+{
+const int dst_u = -(uintptr_t)dest & 7;
+const int shift = 11 + 16 - output_bits;
+const int add = (1 << (shift - 1));
+const int clip = (1 << output_bits) - 1;
+const uint16_t swap = big_endian ? 8 : 0;
+const vector uint32_t vadd = (vector uint32_t) {add, add, add, add};
+const vector uint32_t vshift = (vector uint32_t) {shift, shift, shift,
shift};
+const vector uint16_t vswap = (vector uint16_t) {swap, swap, swap, swap,
swap, swap, swap, swap};
+const vector uint16_t vlargest = (vector uint16_t) {clip, clip, clip,
clip, clip, clip, clip, clip};
+const vector int16_t vzero = vec_splat_s16(0);
+const vector uint8_t vperm = (vector uint8_t) {0, 1, 8, 9, 2, 3, 10, 11,
4,
