Chiebot-Mirror
/
FFmpeg
mirror of https://github.com/FFmpeg/FFmpeg.git
8
0
Fork 0
Code Issues Projects Releases Wiki Activity
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
113031 Commits
37 Branches
400 Tags
465 MiB
Tag: Branch: Tree: 7d7ba2175c
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '7d7ba2175c'
${ noResults }
FFmpeg/tests/checkasm/vf_bwdif.c

256 lines
11 KiB
Raw Normal View History Unescape

checkasm: add test for bwdif
2 years ago
/*
* This file is part of FFmpeg.
*
* FFmpeg is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* FFmpeg is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License along
* with FFmpeg; if not, write to the Free Software Foundation, Inc.,
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
*/
#include <string.h>
#include "checkasm.h"
avfilter/bwdif: Add proper BWDIFDSPContext This already avoids unnecessary indirectly included headers in the arch-specific vf_bwdif_init.c files; it is also in preparation for splitting the actual functions out of vf_bwdif.c. Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
1 year ago
#include "libavfilter/bwdifdsp.h"
tests/checkasm: Add test for vf_bwdif filter_intra Signed-off-by: John Cox <jc@kynesim.co.uk> Signed-off-by: Martin Storsjö <martin@martin.st>
1 year ago
#include "libavutil/mem_internal.h"
checkasm: add test for bwdif
2 years ago
#define WIDTH 256
#define randomize_buffers(buf0, buf1, mask, count) \
for (size_t i = 0; i < count; i++) \
buf0[i] = buf1[i] = rnd() & mask
avfilter/vf_bwdif: Add a filter_line3 method for optimisation Add an optional filter_line3 to the available optimisations. filter_line3 is equivalent to filter_line, memcpy, filter_line filter_line shares quite a number of loads and some calculations in common with its next iteration and testing shows that using aarch64 neon filter_line3s performance is 30% better than two filter_lines and a memcpy. Adds a test for vf_bwdif filter_line3 to checkasm Rounds job start lines down to a multiple of 4. This means that if filter_line3 exists then filter_line will not sometimes be called once at the end of a slice depending on thread count. The final slice may do up to 3 extra lines but filter_edge is faster than filter_line so it is unlikely to create any noticable thread load variation. Signed-off-by: John Cox <jc@kynesim.co.uk> Signed-off-by: Martin Storsjö <martin@martin.st>
1 year ago
#define randomize_overflow_check(buf0, buf1, mask, count) \
for (size_t i = 0; i < count; i++) \
buf0[i] = buf1[i] = (rnd() & 1) != 0 ? mask : 0;
checkasm: add test for bwdif
2 years ago
#define BODY(type, depth) \
do { \
type prev0[9*WIDTH], prev1[9*WIDTH]; \
type next0[9*WIDTH], next1[9*WIDTH]; \
type cur0[9*WIDTH], cur1[9*WIDTH]; \
type dst0[WIDTH], dst1[WIDTH]; \
const int stride = WIDTH; \
const int mask = (1<<depth)-1; \
\
declare_func(void, void *dst, void *prev, void *cur, void *next, \
int w, int prefs, int mrefs, int prefs2, int mrefs2, \
int prefs3, int mrefs3, int prefs4, int mrefs4, \
int parity, int clip_max); \
\
randomize_buffers(prev0, prev1, mask, 9*WIDTH); \
randomize_buffers(next0, next1, mask, 9*WIDTH); \
randomize_buffers( cur0, cur1, mask, 9*WIDTH); \
\
call_ref(dst0, prev0 + 4*WIDTH, cur0 + 4*WIDTH, next0 + 4*WIDTH, \
WIDTH, stride, -stride, 2*stride, -2*stride, \
3*stride, -3*stride, 4*stride, -4*stride, \
0, mask); \
call_new(dst1, prev1 + 4*WIDTH, cur1 + 4*WIDTH, next1 + 4*WIDTH, \
WIDTH, stride, -stride, 2*stride, -2*stride, \
3*stride, -3*stride, 4*stride, -4*stride, \
0, mask); \
\
if (memcmp(dst0, dst1, sizeof dst0) \
|| memcmp(prev0, prev1, sizeof prev0) \
|| memcmp(next0, next1, sizeof next0) \
|| memcmp( cur0, cur1, sizeof cur0)) \
fail(); \
bench_new(dst1, prev1 + 4*WIDTH, cur1 + 4*WIDTH, next1 + 4*WIDTH, \
WIDTH, stride, -stride, 2*stride, -2*stride, \
3*stride, -3*stride, 4*stride, -4*stride, \
0, mask); \
} while (0)
void checkasm_check_vf_bwdif(void)
{
avfilter/bwdif: Add proper BWDIFDSPContext This already avoids unnecessary indirectly included headers in the arch-specific vf_bwdif_init.c files; it is also in preparation for splitting the actual functions out of vf_bwdif.c. Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
1 year ago
BWDIFDSPContext ctx_8, ctx_10;
checkasm: add test for bwdif
2 years ago
ff_bwdif_init_filter_line(&ctx_8, 8);
ff_bwdif_init_filter_line(&ctx_10, 10);
if (check_func(ctx_8.filter_line, "bwdif8")) {
BODY(uint8_t, 8);
report("bwdif8");
}
if (check_func(ctx_10.filter_line, "bwdif10")) {
BODY(uint16_t, 10);
report("bwdif10");
}
tests/checkasm: Add test for vf_bwdif filter_intra Signed-off-by: John Cox <jc@kynesim.co.uk> Signed-off-by: Martin Storsjö <martin@martin.st>
1 year ago
avfilter/vf_bwdif: Add a filter_line3 method for optimisation Add an optional filter_line3 to the available optimisations. filter_line3 is equivalent to filter_line, memcpy, filter_line filter_line shares quite a number of loads and some calculations in common with its next iteration and testing shows that using aarch64 neon filter_line3s performance is 30% better than two filter_lines and a memcpy. Adds a test for vf_bwdif filter_line3 to checkasm Rounds job start lines down to a multiple of 4. This means that if filter_line3 exists then filter_line will not sometimes be called once at the end of a slice depending on thread count. The final slice may do up to 3 extra lines but filter_edge is faster than filter_line so it is unlikely to create any noticable thread load variation. Signed-off-by: John Cox <jc@kynesim.co.uk> Signed-off-by: Martin Storsjö <martin@martin.st>
1 year ago
if (!ctx_8.filter_line3)
ctx_8.filter_line3 = ff_bwdif_filter_line3_c;
{
LOCAL_ALIGNED_16(uint8_t, prev0, [11*WIDTH]);
LOCAL_ALIGNED_16(uint8_t, prev1, [11*WIDTH]);
LOCAL_ALIGNED_16(uint8_t, next0, [11*WIDTH]);
LOCAL_ALIGNED_16(uint8_t, next1, [11*WIDTH]);
LOCAL_ALIGNED_16(uint8_t, cur0, [11*WIDTH]);
LOCAL_ALIGNED_16(uint8_t, cur1, [11*WIDTH]);
LOCAL_ALIGNED_16(uint8_t, dst0, [WIDTH*3]);
LOCAL_ALIGNED_16(uint8_t, dst1, [WIDTH*3]);
const int stride = WIDTH;
const int mask = (1<<8)-1;
int parity;
for (parity = 0; parity != 2; ++parity) {
if (check_func(ctx_8.filter_line3, "bwdif8.line3.rnd.p%d", parity)) {
declare_func(void, void * dst1, int d_stride,
const void * prev1, const void * cur1, const void * next1, int prefs,
int w, int parity, int clip_max);
randomize_buffers(prev0, prev1, mask, 11*WIDTH);
randomize_buffers(next0, next1, mask, 11*WIDTH);
randomize_buffers( cur0, cur1, mask, 11*WIDTH);
call_ref(dst0, stride,
prev0 + stride * 4, cur0 + stride * 4, next0 + stride * 4, stride,
WIDTH, parity, mask);
call_new(dst1, stride,
prev1 + stride * 4, cur1 + stride * 4, next1 + stride * 4, stride,
WIDTH, parity, mask);
if (memcmp(dst0, dst1, WIDTH*3)
|| memcmp(prev0, prev1, WIDTH*11)
|| memcmp(next0, next1, WIDTH*11)
|| memcmp( cur0, cur1, WIDTH*11))
fail();
bench_new(dst1, stride,
prev1 + stride * 4, cur1 + stride * 4, next1 + stride * 4, stride,
WIDTH, parity, mask);
}
}
// Use just 0s and ~0s to try to provoke bad cropping or overflow
// Parity makes no difference to this test so just test 0
if (check_func(ctx_8.filter_line3, "bwdif8.line3.overflow")) {
declare_func(void, void * dst1, int d_stride,
const void * prev1, const void * cur1, const void * next1, int prefs,
int w, int parity, int clip_max);
randomize_overflow_check(prev0, prev1, mask, 11*WIDTH);
randomize_overflow_check(next0, next1, mask, 11*WIDTH);
randomize_overflow_check( cur0, cur1, mask, 11*WIDTH);
call_ref(dst0, stride,
prev0 + stride * 4, cur0 + stride * 4, next0 + stride * 4, stride,
WIDTH, 0, mask);
call_new(dst1, stride,
prev1 + stride * 4, cur1 + stride * 4, next1 + stride * 4, stride,
WIDTH, 0, mask);
if (memcmp(dst0, dst1, WIDTH*3)
|| memcmp(prev0, prev1, WIDTH*11)
|| memcmp(next0, next1, WIDTH*11)
|| memcmp( cur0, cur1, WIDTH*11))
fail();
// No point to benching
}
report("bwdif8.line3");
}
tests/checkasm: Add test for vf_bwdif filter_edge Signed-off-by: John Cox <jc@kynesim.co.uk> Signed-off-by: Martin Storsjö <martin@martin.st>
1 year ago
{
LOCAL_ALIGNED_16(uint8_t, prev0, [11*WIDTH]);
LOCAL_ALIGNED_16(uint8_t, prev1, [11*WIDTH]);
LOCAL_ALIGNED_16(uint8_t, next0, [11*WIDTH]);
LOCAL_ALIGNED_16(uint8_t, next1, [11*WIDTH]);
LOCAL_ALIGNED_16(uint8_t, cur0, [11*WIDTH]);
LOCAL_ALIGNED_16(uint8_t, cur1, [11*WIDTH]);
LOCAL_ALIGNED_16(uint8_t, dst0, [WIDTH*3]);
LOCAL_ALIGNED_16(uint8_t, dst1, [WIDTH*3]);
const int stride = WIDTH;
const int mask = (1<<8)-1;
int spat;
int parity;
for (spat = 0; spat != 2; ++spat) {
for (parity = 0; parity != 2; ++parity) {
if (check_func(ctx_8.filter_edge, "bwdif8.edge.s%d.p%d", spat, parity)) {
declare_func(void, void *dst1, void *prev1, void *cur1, void *next1,
int w, int prefs, int mrefs, int prefs2, int mrefs2,
int parity, int clip_max, int spat);
randomize_buffers(prev0, prev1, mask, 11*WIDTH);
randomize_buffers(next0, next1, mask, 11*WIDTH);
randomize_buffers( cur0, cur1, mask, 11*WIDTH);
memset(dst0, 0xba, WIDTH * 3);
memset(dst1, 0xba, WIDTH * 3);
call_ref(dst0 + stride,
prev0 + stride * 4, cur0 + stride * 4, next0 + stride * 4, WIDTH,
stride, -stride, stride * 2, -stride * 2,
parity, mask, spat);
call_new(dst1 + stride,
prev1 + stride * 4, cur1 + stride * 4, next1 + stride * 4, WIDTH,
stride, -stride, stride * 2, -stride * 2,
parity, mask, spat);
if (memcmp(dst0, dst1, WIDTH*3)
|| memcmp(prev0, prev1, WIDTH*11)
|| memcmp(next0, next1, WIDTH*11)
|| memcmp( cur0, cur1, WIDTH*11))
fail();
bench_new(dst1 + stride,
prev1 + stride * 4, cur1 + stride * 4, next1 + stride * 4, WIDTH,
stride, -stride, stride * 2, -stride * 2,
parity, mask, spat);
}
}
}
report("bwdif8.edge");
}
tests/checkasm: Add test for vf_bwdif filter_intra Signed-off-by: John Cox <jc@kynesim.co.uk> Signed-off-by: Martin Storsjö <martin@martin.st>
1 year ago
if (check_func(ctx_8.filter_intra, "bwdif8.intra")) {
LOCAL_ALIGNED_16(uint8_t, cur0, [11*WIDTH]);
LOCAL_ALIGNED_16(uint8_t, cur1, [11*WIDTH]);
LOCAL_ALIGNED_16(uint8_t, dst0, [WIDTH*3]);
LOCAL_ALIGNED_16(uint8_t, dst1, [WIDTH*3]);
const int stride = WIDTH;
const int mask = (1<<8)-1;
declare_func(void, void *dst1, void *cur1, int w, int prefs, int mrefs,
int prefs3, int mrefs3, int parity, int clip_max);
randomize_buffers( cur0, cur1, mask, 11*WIDTH);
memset(dst0, 0xba, WIDTH * 3);
memset(dst1, 0xba, WIDTH * 3);
call_ref(dst0 + stride,
cur0 + stride * 4, WIDTH,
stride, -stride, stride * 3, -stride * 3,
0, mask);
call_new(dst1 + stride,
cur0 + stride * 4, WIDTH,
stride, -stride, stride * 3, -stride * 3,
0, mask);
if (memcmp(dst0, dst1, WIDTH*3)
|| memcmp( cur0, cur1, WIDTH*11))
fail();
bench_new(dst1 + stride,
cur0 + stride * 4, WIDTH,
stride, -stride, stride * 3, -stride * 3,
0, mask);
report("bwdif8.intra");
}
checkasm: add test for bwdif
2 years ago
}