Re: [FFmpeg-devel] [PATCH] swscale/output: Altivec-optimize float yuv2plane1
On Sun, 16 Dec 2018 00:22:00 +0100
Michael Niedermayer wrote:
> On Sat, Dec 15, 2018 at 06:32:31PM +0200, Lauri Kasanen wrote:
> > Tested on POWER8 LE. Testing on earlier ppc and/or BE appreciated.
> >
> > libswscale/ppc/swscale_altivec.c | 139
> > ++-
> > 1 file changed, 137 insertions(+), 2 deletions(-)
>
> breaks build:
> src/libswscale/ppc/swscale_altivec.c: In function ‘yuv2plane1_float_altivec’:
> src/libswscale/ppc/swscale_altivec.c:158:80: error: expected declaration
> specifiers or ‘...’ before ‘(’ token
> const vector float vzero = (vector float) {0, 0, 0, 0};
Thanks for testing. I missed the vzero define at the top, I wonder why
my gcc did not break. Patch v2 coming.
- Lauri
___
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
Re: [FFmpeg-devel] [PATCH] swscale/output: Altivec-optimize float yuv2plane1
On Sat, Dec 15, 2018 at 06:32:31PM +0200, Lauri Kasanen wrote:
> This function wouldn't benefit from VSX instructions, and input
> and output share alignment, so I put it under altivec.
>
> ./ffmpeg_g -f rawvideo -pix_fmt rgb24 -s hd1080 -i /dev/zero -pix_fmt
> grayf32le \
> -f null -vframes 100 -v error -nostats -
>
> 3743 UNITS in planar1, 65495 runs, 41 skips
>
> -cpuflags 0
>
> 23511 UNITS in planar1, 65530 runs, 6 skips
>
> grayf32be
>
> 4647 UNITS in planar1, 65449 runs, 87 skips
>
> -cpuflags 0
>
> 28608 UNITS in planar1, 65530 runs, 6 skips
>
> The native speedup is 6.28133, and the bswapping one 6.15623.
> Fate passes, each format tested with an image to video conversion.
>
> Signed-off-by: Lauri Kasanen
> ---
>
> Tested on POWER8 LE. Testing on earlier ppc and/or BE appreciated.
>
> libswscale/ppc/swscale_altivec.c | 139
> ++-
> 1 file changed, 137 insertions(+), 2 deletions(-)
breaks build:
CC libswscale/ppc/swscale_altivec.o
In file included from src/libswscale/ppc/swscale_altivec.c:103:0:
src/libswscale/ppc/swscale_ppc_template.c: In function ‘yuv2planeX_16_altivec’:
src/libswscale/ppc/swscale_ppc_template.c:52:215: warning: ISO C90 forbids
mixed declarations and code [-Wdeclaration-after-statement]
yuv2planeX_8(vo1, vo2, l1, src[j], x, perm, vLumFilter);
^
In file included from src/libswscale/ppc/swscale_altivec.c:103:0:
src/libswscale/ppc/swscale_ppc_template.c:53:219: warning: ISO C90 forbids
mixed declarations and code [-Wdeclaration-after-statement]
yuv2planeX_8(vo3, vo4, l1, src[j], x + 8, perm, vLumFilter);
^
In file included from src/libswscale/ppc/swscale_altivec.c:103:0:
src/libswscale/ppc/swscale_ppc_template.c: In function ‘hScale_real_altivec’:
src/libswscale/ppc/swscale_ppc_template.c:189:21: warning: ISO C90 forbids
mixed declarations and code [-Wdeclaration-after-statement]
vector signed short src_vA = // vec_unpackh sign-extends...
^
src/libswscale/ppc/swscale_ppc_template.c:196:21: warning: ISO C90 forbids
mixed declarations and code [-Wdeclaration-after-statement]
vector signed int val_acc = vec_msums(src_vA, filter_v0,
val_v);
^
src/libswscale/ppc/swscale_altivec.c: In function ‘yuv2plane1_float_altivec’:
src/libswscale/ppc/swscale_altivec.c:158:80: error: expected declaration
specifiers or ‘...’ before ‘(’ token
const vector float vzero = (vector float) {0, 0, 0, 0};
^
src/libswscale/ppc/swscale_altivec.c:159:5: warning: ISO C90 forbids mixed
declarations and code [-Wdeclaration-after-statement]
vector uint32_t v;
^
src/libswscale/ppc/swscale_altivec.c:172:9: error: invalid parameter
combination for AltiVec intrinsic
vd = vec_madd(vd, vmul, vzero);
^
src/libswscale/ppc/swscale_altivec.c: In function
‘yuv2plane1_float_bswap_altivec’:
src/libswscale/ppc/swscale_altivec.c:191:80: error: expected declaration
specifiers or ‘...’ before ‘(’ token
const vector float vzero = (vector float) {0, 0, 0, 0};
^
src/libswscale/ppc/swscale_altivec.c:192:5: warning: ISO C90 forbids mixed
declarations and code [-Wdeclaration-after-statement]
const vector uint32_t vswapbig = (vector uint32_t) {16, 16, 16, 16};
^
src/libswscale/ppc/swscale_altivec.c:207:9: error: invalid parameter
combination for AltiVec intrinsic
vd = vec_madd(vd, vmul, vzero);
^
make: *** [libswscale/ppc/swscale_altivec.o] Error 1
[...]
--
Michael GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB
I have often repented speaking, but never of holding my tongue.
-- Xenocrates
signature.asc
Description: PGP signature
___
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
[FFmpeg-devel] [PATCH] swscale/output: Altivec-optimize float yuv2plane1
This function wouldn't benefit from VSX instructions, and input
and output share alignment, so I put it under altivec.
./ffmpeg_g -f rawvideo -pix_fmt rgb24 -s hd1080 -i /dev/zero -pix_fmt grayf32le
\
-f null -vframes 100 -v error -nostats -
3743 UNITS in planar1, 65495 runs, 41 skips
-cpuflags 0
23511 UNITS in planar1, 65530 runs, 6 skips
grayf32be
4647 UNITS in planar1, 65449 runs, 87 skips
-cpuflags 0
28608 UNITS in planar1, 65530 runs, 6 skips
The native speedup is 6.28133, and the bswapping one 6.15623.
Fate passes, each format tested with an image to video conversion.
Signed-off-by: Lauri Kasanen
---
Tested on POWER8 LE. Testing on earlier ppc and/or BE appreciated.
libswscale/ppc/swscale_altivec.c | 139 ++-
1 file changed, 137 insertions(+), 2 deletions(-)
diff --git a/libswscale/ppc/swscale_altivec.c b/libswscale/ppc/swscale_altivec.c
index 1d2b2fa..2ef5257 100644
--- a/libswscale/ppc/swscale_altivec.c
+++ b/libswscale/ppc/swscale_altivec.c
@@ -31,7 +31,8 @@
#include "yuv2rgb_altivec.h"
#include "libavutil/ppc/util_altivec.h"
-#if HAVE_ALTIVEC && HAVE_BIGENDIAN
+#if HAVE_ALTIVEC
+#if HAVE_BIGENDIAN
#define vzero vec_splat_s32(0)
#define GET_LS(a,b,c,s) {\
@@ -102,7 +103,135 @@
#include "swscale_ppc_template.c"
#undef FUNC
-#endif /* HAVE_ALTIVEC && HAVE_BIGENDIAN */
+#endif /* HAVE_BIGENDIAN */
+
+#define output_pixel(pos, val, bias, signedness) \
+if (big_endian) { \
+AV_WB16(pos, bias + av_clip_ ## signedness ## 16(val >> shift)); \
+} else { \
+AV_WL16(pos, bias + av_clip_ ## signedness ## 16(val >> shift)); \
+}
+
+static void
+yuv2plane1_float_u(const int32_t *src, float *dest, int dstW, int start)
+{
+static const int big_endian = HAVE_BIGENDIAN;
+static const int shift = 3;
+static const float float_mult = 1.0f / 65535.0f;
+int i, val;
+uint16_t val_uint;
+
+for (i = start; i < dstW; ++i){
+val = src[i] + (1 << (shift - 1));
+output_pixel(_uint, val, 0, uint);
+dest[i] = float_mult * (float)val_uint;
+}
+}
+
+static void
+yuv2plane1_float_bswap_u(const int32_t *src, uint32_t *dest, int dstW, int
start)
+{
+static const int big_endian = HAVE_BIGENDIAN;
+static const int shift = 3;
+static const float float_mult = 1.0f / 65535.0f;
+int i, val;
+uint16_t val_uint;
+
+for (i = start; i < dstW; ++i){
+val = src[i] + (1 << (shift - 1));
+output_pixel(_uint, val, 0, uint);
+dest[i] = av_bswap32(av_float2int(float_mult * (float)val_uint));
+}
+}
+
+static void yuv2plane1_float_altivec(const int32_t *src, float *dest, int dstW)
+{
+const int dst_u = -(uintptr_t)dest & 3;
+const int shift = 3;
+const int add = (1 << (shift - 1));
+const int clip = (1 << 16) - 1;
+const float fmult = 1.0f / 65535.0f;
+const vector uint32_t vadd = (vector uint32_t) {add, add, add, add};
+const vector uint32_t vshift = (vector uint32_t) vec_splat_u32(shift);
+const vector uint32_t vlargest = (vector uint32_t) {clip, clip, clip,
clip};
+const vector float vmul = (vector float) {fmult, fmult, fmult, fmult};
+const vector float vzero = (vector float) {0, 0, 0, 0};
+vector uint32_t v;
+vector float vd;
+int i;
+
+yuv2plane1_float_u(src, dest, dst_u, 0);
+
+for (i = dst_u; i < dstW - 3; i += 4) {
+v = vec_ld(0, (const uint32_t *) [i]);
+v = vec_add(v, vadd);
+v = vec_sr(v, vshift);
+v = vec_min(v, vlargest);
+
+vd = vec_ctf(v, 0);
+vd = vec_madd(vd, vmul, vzero);
+
+vec_st(vd, 0, [i]);
+}
+
+yuv2plane1_float_u(src, dest, dstW, i);
+}
+
+static void yuv2plane1_float_bswap_altivec(const int32_t *src, uint32_t *dest,
int dstW)
+{
+const int dst_u = -(uintptr_t)dest & 3;
+const int shift = 3;
+const int add = (1 << (shift - 1));
+const int clip = (1 << 16) - 1;
+const float fmult = 1.0f / 65535.0f;
+const vector uint32_t vadd = (vector uint32_t) {add, add, add, add};
+const vector uint32_t vshift = (vector uint32_t) vec_splat_u32(shift);
+const vector uint32_t vlargest = (vector uint32_t) {clip, clip, clip,
clip};
+const vector float vmul = (vector float) {fmult, fmult, fmult, fmult};
+const vector float vzero = (vector float) {0, 0, 0, 0};
+const vector uint32_t vswapbig = (vector uint32_t) {16, 16, 16, 16};
+const vector uint16_t vswapsmall = vec_splat_u16(8);
+vector uint32_t v;
+vector float vd;
+int i;
+
+yuv2plane1_float_bswap_u(src, dest, dst_u, 0);
+
+for (i = dst_u; i < dstW - 3; i += 4) {
+v = vec_ld(0, (const uint32_t *) [i]);
+v = vec_add(v, vadd);
+v = vec_sr(v, vshift);
+v = vec_min(v, vlargest);
+
+vd = vec_ctf(v, 0);
+vd = vec_madd(vd, vmul, vzero);
+
+vd = (vector float) vec_rl((vector uint32_t) vd, vswapbig);
+vd = (vector float)
