Re: [FFmpeg-devel] [PATCH v4] libswscale/ppc: VSX-optimize 9-16 bit yuv2planeX
On Sat, 12 Jan 2019 01:03:09 +0100 Michael Niedermayer wrote: > On Fri, Jan 11, 2019 at 11:16:20AM +0200, Lauri Kasanen wrote: > > On Fri, 11 Jan 2019 09:56:15 +0100 > > Michael Niedermayer wrote: > > > > > > +#ifdef __GNUC__ > > > > +// GCC does not support vmuluwm yet. Bug open. > > > > > > this should probably be tested by configure similar to how other > > > compiler limitations are tested > > > > We can't really test for it, because there is no standard name for it. I > > don't know what name the gcc devs will pick for it, it could be vec_mul, > > vec_vmuluwm or something different. > > the code contains a #if and a #else case > so i thought there was something else than the __GNUC__ case and gcc > would follow that It's second-hand info from libsimdpp. I don't know where they got it. However, I found out yesterday that gcc docs are wrong, and vec_mul for gcc does use the correct instruction on power8. Respinning. - Lauri ___ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
Re: [FFmpeg-devel] [PATCH v4] libswscale/ppc: VSX-optimize 9-16 bit yuv2planeX
On Fri, Jan 11, 2019 at 11:16:20AM +0200, Lauri Kasanen wrote: > On Fri, 11 Jan 2019 09:56:15 +0100 > Michael Niedermayer wrote: > > > > +#ifdef __GNUC__ > > > +// GCC does not support vmuluwm yet. Bug open. > > > > this should probably be tested by configure similar to how other > > compiler limitations are tested > > We can't really test for it, because there is no standard name for it. I > don't know what name the gcc devs will pick for it, it could be vec_mul, > vec_vmuluwm or something different. the code contains a #if and a #else case so i thought there was something else than the __GNUC__ case and gcc would follow that [...] -- Michael GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB Concerning the gods, I have no means of knowing whether they exist or not or of what sort they may be, because of the obscurity of the subject, and the brevity of human life -- Protagoras signature.asc Description: PGP signature ___ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
Re: [FFmpeg-devel] [PATCH v4] libswscale/ppc: VSX-optimize 9-16 bit yuv2planeX
On Fri, 11 Jan 2019 09:56:15 +0100 Michael Niedermayer wrote: > > +#ifdef __GNUC__ > > +// GCC does not support vmuluwm yet. Bug open. > > this should probably be tested by configure similar to how other > compiler limitations are tested We can't really test for it, because there is no standard name for it. I don't know what name the gcc devs will pick for it, it could be vec_mul, vec_vmuluwm or something different. - Lauri ___ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
Re: [FFmpeg-devel] [PATCH v4] libswscale/ppc: VSX-optimize 9-16 bit yuv2planeX
On Thu, Jan 10, 2019 at 11:55:34AM +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
>
> Signed-off-by: Lauri Kasanen
> ---
>
> 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
>
> libswscale/ppc/swscale_ppc_template.c | 4 +-
> libswscale/ppc/swscale_vsx.c | 195
> +-
> 2 files changed, 193 insertions(+), 6 deletions(-)
[...]
> +static void yuv2planeX_16_vsx(const int16_t *filter, int filterSize,
> + const int32_t **src, uint16_t *dest, int dstW,
> + int big_endian, int output_bits)
> +{
> +const int dst_u = -(uintptr_t)dest & 7;
> +const int shift = 15;
> +const int bias = 0x8000;
> +const int add = (1 << (shift - 1)) - 0x4000;
> +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 vbias = (vector uint16_t) {bias, bias, bias, bias,
> bias, bias, bias, bias};
> +vector int32_t vfilter[MAX_FILTER_SIZE];
> +vector uint16_t v;
> +vector uint32_t vleft, vright, vtmp;
> +vector int32_t vin32l, vin32r;
> +int i, j;
> +
> +for (i = 0; i < filterSize; i++) {
> +vfilter[i] = (vector int32_t) {filter[i], filter[i], filter[i],
> filter[i]};
> +}
> +
> +yuv2planeX_16_u(filter, filterSize, src, dest, dst_u, big_endian,
> output_bits, 0);
> +
> +for (i = dst_u; i < dstW - 7; i += 8) {
> +vleft = vright = vadd;
> +
> +for (j = 0; j < filterSize; j++) {
> +vin32l = vec_vsx_ld(0, [j][i]);
> +vin32r = vec_vsx_ld(0, [j][i + 4]);
> +
> +#ifdef __GNUC__
> +// GCC does not support vmuluwm yet. Bug open.
this should probably be tested by configure similar to how other
compiler limitations are tested
[...]
--
Michael GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB
Old school: Use the lowest level language in which you can solve the problem
conveniently.
New school: Use the highest level language in which the latest supercomputer
can solve the problem without the user falling asleep waiting.
signature.asc
Description: PGP signature
___
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
[FFmpeg-devel] [PATCH v4] 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
---
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
libswscale/ppc/swscale_ppc_template.c | 4 +-
libswscale/ppc/swscale_vsx.c | 195 +-
2 files changed, 193 insertions(+), 6 deletions(-)
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..12effe2 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);
