mirror of
https://github.com/FFmpeg/FFmpeg.git
synced 2024-12-23 12:43:46 +02:00
f0ef11ea83
Simply taking the Zbb REV8 instruction into use in a simple loop gives some significant savings: bswap_buf_c: 1081.0 bswap_buf_rvb_b: 771.0 But we can also use the 64-bit REV8 as a pseudo-SIMD instruction with just one additional shift, and one fewer load, effectively doubling the bandwidth. Consequently, this patch is useful even if the compile-time target has Zbb enabled for C code: bswap_buf_c: 1081.0 bswap_buf_rvb_b: 341.0 (this patch) On the other hand, this approach fails miserably for bswap16_buf as the ratio of shifts and stores becomes unfavorable compared to naïve C: bswap16_buf_c: 1542.0 bswap16_buf_rvb_b: 1803.7 Unrolling to process 128 bits (4 samples) at a time actually worsens performance ever so slightly: bswap_buf_c: 1081.0 bswap_buf_rvb_b: 408.5
60 lines
1.7 KiB
C
60 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
|
|
*/
|
|
|
|
#include <stdint.h>
|
|
|
|
#include "libavutil/attributes.h"
|
|
#include "libavutil/bswap.h"
|
|
#include "bswapdsp.h"
|
|
|
|
static void bswap_buf(uint32_t *dst, const uint32_t *src, int w)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i + 8 <= w; i += 8) {
|
|
dst[i + 0] = av_bswap32(src[i + 0]);
|
|
dst[i + 1] = av_bswap32(src[i + 1]);
|
|
dst[i + 2] = av_bswap32(src[i + 2]);
|
|
dst[i + 3] = av_bswap32(src[i + 3]);
|
|
dst[i + 4] = av_bswap32(src[i + 4]);
|
|
dst[i + 5] = av_bswap32(src[i + 5]);
|
|
dst[i + 6] = av_bswap32(src[i + 6]);
|
|
dst[i + 7] = av_bswap32(src[i + 7]);
|
|
}
|
|
for (; i < w; i++)
|
|
dst[i + 0] = av_bswap32(src[i + 0]);
|
|
}
|
|
|
|
static void bswap16_buf(uint16_t *dst, const uint16_t *src, int len)
|
|
{
|
|
while (len--)
|
|
*dst++ = av_bswap16(*src++);
|
|
}
|
|
|
|
av_cold void ff_bswapdsp_init(BswapDSPContext *c)
|
|
{
|
|
c->bswap_buf = bswap_buf;
|
|
c->bswap16_buf = bswap16_buf;
|
|
|
|
#if ARCH_RISCV
|
|
ff_bswapdsp_init_riscv(c);
|
|
#elif ARCH_X86
|
|
ff_bswapdsp_init_x86(c);
|
|
#endif
|
|
}
|