mirror of
https://mirror.skon.top/https://github.com/FFmpeg/FFmpeg
synced 2026-04-21 05:11:59 +08:00
de18feb0f0
This adds a NEON-optimized function for computing 32x32 Sum of Absolute Differences (SAD) on AArch64, addressing a gap where x86 had SSE2/AVX2 implementations but AArch64 lacked equivalent coverage. The implementation mirrors the existing sad8 and sad16 NEON functions, employing a 4-row unrolled loop with UABAL and UABAL2 instructions for efficient load-compute interleaving, and four 8x16-bit accumulators to handle the wider 32-byte rows. Benchmarks on AWS Graviton3 (Neoverse V1, c7g.xlarge) using checkasm: sad_32x32_0: C 146.4 cycles -> NEON 98.1 cycles (1.49x speedup) sad_32x32_1: C 141.4 cycles -> NEON 98.9 cycles (1.43x speedup) sad_32x32_2: C 140.7 cycles -> NEON 95.0 cycles (1.48x speedup) Signed-off-by: Jeongkeun Kim <variety0724@gmail.com>
48 lines
1.7 KiB
C
48 lines
1.7 KiB
C
/*
|
|
* This file is part of FFmpeg.
|
|
*
|
|
* FFmpeg is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU Lesser General Public
|
|
* License as published by the Free Software Foundation; either
|
|
* version 2.1 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
|
|
* Lesser General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU Lesser 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
|
|
*/
|
|
|
|
#ifndef AVUTIL_AARCH64_PIXELUTILS_H
|
|
#define AVUTIL_AARCH64_PIXELUTILS_H
|
|
|
|
#include <stddef.h>
|
|
#include <stdint.h>
|
|
|
|
#include "cpu.h"
|
|
#include "libavutil/attributes.h"
|
|
#include "libavutil/cpu.h"
|
|
#include "libavutil/pixelutils.h"
|
|
|
|
int ff_pixelutils_sad8_neon (const uint8_t *src1, ptrdiff_t stride1,
|
|
const uint8_t *src2, ptrdiff_t stride2);
|
|
int ff_pixelutils_sad16_neon(const uint8_t *src1, ptrdiff_t stride1,
|
|
const uint8_t *src2, ptrdiff_t stride2);
|
|
int ff_pixelutils_sad32_neon(const uint8_t *src1, ptrdiff_t stride1,
|
|
const uint8_t *src2, ptrdiff_t stride2);
|
|
|
|
static inline av_cold void ff_pixelutils_sad_init_aarch64(av_pixelutils_sad_fn *sad, int aligned)
|
|
{
|
|
int cpu_flags = av_get_cpu_flags();
|
|
|
|
if (have_neon(cpu_flags)) {
|
|
sad[2] = ff_pixelutils_sad8_neon;
|
|
sad[3] = ff_pixelutils_sad16_neon;
|
|
sad[4] = ff_pixelutils_sad32_neon;
|
|
}
|
|
}
|
|
#endif
|