mirror of
https://git.ffmpeg.org/ffmpeg.git
synced 2024-12-24 08:12:44 +00:00
f6b9e365cd
Silences a gcc warning: src/libavcodec/ppc/svq1enc_altivec.c: In function 'ff_svq1enc_init_ppc': src/libavcodec/ppc/svq1enc_altivec.c:80:26: warning: assignment from incompatible pointer type
83 lines
2.5 KiB
C
83 lines
2.5 KiB
C
/*
|
|
* Copyright (c) 2007 Luca Barbato <lu_zero@gentoo.org>
|
|
*
|
|
* 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 "config.h"
|
|
|
|
#include <stdint.h>
|
|
|
|
#include "libavutil/attributes.h"
|
|
#include "libavutil/cpu.h"
|
|
#include "libavutil/ppc/cpu.h"
|
|
#include "libavutil/ppc/util_altivec.h"
|
|
|
|
#include "libavcodec/svq1enc.h"
|
|
|
|
#if HAVE_ALTIVEC
|
|
static int ssd_int8_vs_int16_altivec(const int8_t *pix1, const int16_t *pix2,
|
|
intptr_t size)
|
|
{
|
|
int i, size16 = size >> 4;
|
|
vector signed char vpix1;
|
|
vector signed short vpix2, vdiff, vpix1l, vpix1h;
|
|
union {
|
|
vector signed int vscore;
|
|
int32_t score[4];
|
|
} u = { .vscore = vec_splat_s32(0) };
|
|
|
|
while (size16) {
|
|
// score += (pix1[i] - pix2[i]) * (pix1[i] - pix2[i]);
|
|
// load pix1 and the first batch of pix2
|
|
|
|
vpix1 = vec_unaligned_load(pix1);
|
|
vpix2 = vec_unaligned_load(pix2);
|
|
pix2 += 8;
|
|
// unpack
|
|
vpix1h = vec_unpackh(vpix1);
|
|
vdiff = vec_sub(vpix1h, vpix2);
|
|
vpix1l = vec_unpackl(vpix1);
|
|
// load another batch from pix2
|
|
vpix2 = vec_unaligned_load(pix2);
|
|
u.vscore = vec_msum(vdiff, vdiff, u.vscore);
|
|
vdiff = vec_sub(vpix1l, vpix2);
|
|
u.vscore = vec_msum(vdiff, vdiff, u.vscore);
|
|
pix1 += 16;
|
|
pix2 += 8;
|
|
size16--;
|
|
}
|
|
u.vscore = vec_sums(u.vscore, vec_splat_s32(0));
|
|
|
|
size %= 16;
|
|
for (i = 0; i < size; i++)
|
|
u.score[3] += (pix1[i] - pix2[i]) * (pix1[i] - pix2[i]);
|
|
|
|
return u.score[3];
|
|
}
|
|
#endif /* HAVE_ALTIVEC */
|
|
|
|
av_cold void ff_svq1enc_init_ppc(SVQ1EncContext *c)
|
|
{
|
|
#if HAVE_ALTIVEC
|
|
if (!PPC_ALTIVEC(av_get_cpu_flags()))
|
|
return;
|
|
|
|
c->ssd_int8_vs_int16 = ssd_int8_vs_int16_altivec;
|
|
#endif /* HAVE_ALTIVEC */
|
|
}
|