Re: [FFmpeg-devel] [PATCH v5] libswscale/ppc: VSX-optimize 9-16 bit yuv2planeX
On Sat, Jan 12, 2019 at 06:25:57PM +0200, Lauri Kasanen wrote: > On Sat, 12 Jan 2019 14:52:07 +0100 > Michael Niedermayer wrote: > > > On Sat, Jan 12, 2019 at 10:47:50AM +0200, Lauri Kasanen wrote: > > > ./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. > > > > > > yuv420p9le > > > 12341 UNITS in planarX, 130976 runs, 96 skips > > > 73752 UNITS in planarX, 131066 runs, 6 skips > > > yuv420p9be > > > 12364 UNITS in planarX, 131025 runs, 47 skips > > > 73001 UNITS in planarX, 131055 runs, 17 skips > > > yuv420p10le > > > 12386 UNITS in planarX, 131042 runs, 30 skips > > > 72735 UNITS in planarX, 131062 runs, 10 skips > > > yuv420p10be > > > 12337 UNITS in planarX, 131045 runs, 27 skips > > > 72734 UNITS in planarX, 131057 runs, 15 skips > > > yuv420p12le > > > 12236 UNITS in planarX, 131058 runs, 14 skips > > > 73029 UNITS in planarX, 131062 runs, 10 skips > > > yuv420p12be > > > 12218 UNITS in planarX, 130973 runs, 99 skips > > > 72402 UNITS in planarX, 131069 runs, 3 skips > > > yuv420p14le > > > 12168 UNITS in planarX, 131067 runs, 5 skips > > > 72480 UNITS in planarX, 131069 runs, 3 skips > > > yuv420p14be > > > 12358 UNITS in planarX, 130948 runs,124 skips > > > 73772 UNITS in planarX, 131063 runs, 9 skips > > > yuv420p16le > > > 10439 UNITS in planarX, 130911 runs,161 skips > > > 157923 UNITS in planarX, 131068 runs, 4 skips > > > yuv420p16be > > > 10463 UNITS in planarX, 130874 runs,198 skips > > > 154405 UNITS in planarX, 131061 runs, 11 skips > > > > The number of skips in the benchmark is much larger on one > > side. That way the numbers become hard to compare as > > more cases aer skipped on one side > > > > please adjust the parameters so the skip counts are compareable > > or redo the tests until the numbers are more similar > > thanks > > How do I do that? It's a VM, so there are going to be pauses no matter > what, when other VMs run. Or should I take the largest run count with > about the same skips? I would try to adjust TIMER_REPORT so that either VM switches are skiped on both sides of the test reliably or that they are never skipped. The idea is to do the same to both so theres no asymetry from differntly successfull skips thx [...] -- Michael GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB Asymptotically faster algorithms should always be preferred if you have asymptotical amounts of data signature.asc Description: PGP signature ___ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
Re: [FFmpeg-devel] [PATCH v5] libswscale/ppc: VSX-optimize 9-16 bit yuv2planeX
On Sat, 12 Jan 2019 14:52:07 +0100 Michael Niedermayer wrote: > On Sat, Jan 12, 2019 at 10:47:50AM +0200, Lauri Kasanen wrote: > > ./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. > > > > yuv420p9le > > 12341 UNITS in planarX, 130976 runs, 96 skips > > 73752 UNITS in planarX, 131066 runs, 6 skips > > yuv420p9be > > 12364 UNITS in planarX, 131025 runs, 47 skips > > 73001 UNITS in planarX, 131055 runs, 17 skips > > yuv420p10le > > 12386 UNITS in planarX, 131042 runs, 30 skips > > 72735 UNITS in planarX, 131062 runs, 10 skips > > yuv420p10be > > 12337 UNITS in planarX, 131045 runs, 27 skips > > 72734 UNITS in planarX, 131057 runs, 15 skips > > yuv420p12le > > 12236 UNITS in planarX, 131058 runs, 14 skips > > 73029 UNITS in planarX, 131062 runs, 10 skips > > yuv420p12be > > 12218 UNITS in planarX, 130973 runs, 99 skips > > 72402 UNITS in planarX, 131069 runs, 3 skips > > yuv420p14le > > 12168 UNITS in planarX, 131067 runs, 5 skips > > 72480 UNITS in planarX, 131069 runs, 3 skips > > yuv420p14be > > 12358 UNITS in planarX, 130948 runs,124 skips > > 73772 UNITS in planarX, 131063 runs, 9 skips > > yuv420p16le > > 10439 UNITS in planarX, 130911 runs,161 skips > > 157923 UNITS in planarX, 131068 runs, 4 skips > > yuv420p16be > > 10463 UNITS in planarX, 130874 runs,198 skips > > 154405 UNITS in planarX, 131061 runs, 11 skips > > The number of skips in the benchmark is much larger on one > side. That way the numbers become hard to compare as > more cases aer skipped on one side > > please adjust the parameters so the skip counts are compareable > or redo the tests until the numbers are more similar > thanks How do I do that? It's a VM, so there are going to be pauses no matter what, when other VMs run. Or should I take the largest run count with about the same skips? - Lauri ___ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
Re: [FFmpeg-devel] [PATCH v5] libswscale/ppc: VSX-optimize 9-16 bit yuv2planeX
On Sat, Jan 12, 2019 at 10:47:50AM +0200, Lauri Kasanen wrote: > ./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. > > yuv420p9le > 12341 UNITS in planarX, 130976 runs, 96 skips > 73752 UNITS in planarX, 131066 runs, 6 skips > yuv420p9be > 12364 UNITS in planarX, 131025 runs, 47 skips > 73001 UNITS in planarX, 131055 runs, 17 skips > yuv420p10le > 12386 UNITS in planarX, 131042 runs, 30 skips > 72735 UNITS in planarX, 131062 runs, 10 skips > yuv420p10be > 12337 UNITS in planarX, 131045 runs, 27 skips > 72734 UNITS in planarX, 131057 runs, 15 skips > yuv420p12le > 12236 UNITS in planarX, 131058 runs, 14 skips > 73029 UNITS in planarX, 131062 runs, 10 skips > yuv420p12be > 12218 UNITS in planarX, 130973 runs, 99 skips > 72402 UNITS in planarX, 131069 runs, 3 skips > yuv420p14le > 12168 UNITS in planarX, 131067 runs, 5 skips > 72480 UNITS in planarX, 131069 runs, 3 skips > yuv420p14be > 12358 UNITS in planarX, 130948 runs,124 skips > 73772 UNITS in planarX, 131063 runs, 9 skips > yuv420p16le > 10439 UNITS in planarX, 130911 runs,161 skips > 157923 UNITS in planarX, 131068 runs, 4 skips > yuv420p16be > 10463 UNITS in planarX, 130874 runs,198 skips > 154405 UNITS in planarX, 131061 runs, 11 skips The number of skips in the benchmark is much larger on one side. That way the numbers become hard to compare as more cases aer skipped on one side please adjust the parameters so the skip counts are compareable or redo the tests until the numbers are more similar thanks [...] -- Michael GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB Modern terrorism, a quick summary: Need oil, start war with country that has oil, kill hundread thousand in war. Let country fall into chaos, be surprised about raise of fundamantalists. Drop more bombs, kill more people, be surprised about them taking revenge and drop even more bombs and strip your own citizens of their rights and freedoms. to be continued signature.asc Description: PGP signature ___ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
[FFmpeg-devel] [PATCH v5] 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.
yuv420p9le
12341 UNITS in planarX, 130976 runs, 96 skips
73752 UNITS in planarX, 131066 runs, 6 skips
yuv420p9be
12364 UNITS in planarX, 131025 runs, 47 skips
73001 UNITS in planarX, 131055 runs, 17 skips
yuv420p10le
12386 UNITS in planarX, 131042 runs, 30 skips
72735 UNITS in planarX, 131062 runs, 10 skips
yuv420p10be
12337 UNITS in planarX, 131045 runs, 27 skips
72734 UNITS in planarX, 131057 runs, 15 skips
yuv420p12le
12236 UNITS in planarX, 131058 runs, 14 skips
73029 UNITS in planarX, 131062 runs, 10 skips
yuv420p12be
12218 UNITS in planarX, 130973 runs, 99 skips
72402 UNITS in planarX, 131069 runs, 3 skips
yuv420p14le
12168 UNITS in planarX, 131067 runs, 5 skips
72480 UNITS in planarX, 131069 runs, 3 skips
yuv420p14be
12358 UNITS in planarX, 130948 runs,124 skips
73772 UNITS in planarX, 131063 runs, 9 skips
yuv420p16le
10439 UNITS in planarX, 130911 runs,161 skips
157923 UNITS in planarX, 131068 runs, 4 skips
yuv420p16be
10463 UNITS in planarX, 130874 runs,198 skips
154405 UNITS in planarX, 131061 runs, 11 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(-)
v2: Separate macros so that yuv2plane1_16_vsx remains available for power7
v3: Remove accidental tabs, switch to HAVE_POWER8 from configure + runtime check
v4: #if HAVE_POWER8
v5: Get rid of the mul #if, turns out gcc vec_mul works
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,
