ea0931fb96
* commit '65d5d5865845f057cc6530a8d0f34db952d9009c': dsputil: Move SVQ1 encoding specific bits into svq1enc Conflicts: libavcodec/x86/Makefile Merged-by: Michael Niedermayer <michaelni@gmx.at>
105 lines
3.1 KiB
C
105 lines
3.1 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
|
|
*/
|
|
|
|
/**
|
|
* @file
|
|
* miscellaneous integer operations
|
|
*/
|
|
|
|
#include "config.h"
|
|
#if HAVE_ALTIVEC_H
|
|
#include <altivec.h>
|
|
#endif
|
|
|
|
#include "libavutil/attributes.h"
|
|
#include "libavutil/ppc/types_altivec.h"
|
|
#include "libavutil/ppc/util_altivec.h"
|
|
#include "libavcodec/dsputil.h"
|
|
#include "dsputil_altivec.h"
|
|
|
|
static int32_t scalarproduct_int16_altivec(const int16_t *v1, const int16_t *v2,
|
|
int order)
|
|
{
|
|
int i;
|
|
LOAD_ZERO;
|
|
register vec_s16 vec1;
|
|
register vec_s32 res = vec_splat_s32(0), t;
|
|
int32_t ires;
|
|
|
|
for (i = 0; i < order; i += 8) {
|
|
vec1 = vec_unaligned_load(v1);
|
|
t = vec_msum(vec1, vec_ld(0, v2), zero_s32v);
|
|
res = vec_sums(t, res);
|
|
v1 += 8;
|
|
v2 += 8;
|
|
}
|
|
res = vec_splat(res, 3);
|
|
vec_ste(res, 0, &ires);
|
|
|
|
return ires;
|
|
}
|
|
|
|
static int32_t scalarproduct_and_madd_int16_altivec(int16_t *v1,
|
|
const int16_t *v2,
|
|
const int16_t *v3,
|
|
int order, int mul)
|
|
{
|
|
LOAD_ZERO;
|
|
vec_s16 *pv1 = (vec_s16 *) v1;
|
|
register vec_s16 muls = { mul, mul, mul, mul, mul, mul, mul, mul };
|
|
register vec_s16 t0, t1, i0, i1, i4;
|
|
register vec_s16 i2 = vec_ld(0, v2), i3 = vec_ld(0, v3);
|
|
register vec_s32 res = zero_s32v;
|
|
register vec_u8 align = vec_lvsl(0, v2);
|
|
int32_t ires;
|
|
|
|
order >>= 4;
|
|
do {
|
|
i1 = vec_ld(16, v2);
|
|
t0 = vec_perm(i2, i1, align);
|
|
i2 = vec_ld(32, v2);
|
|
t1 = vec_perm(i1, i2, align);
|
|
i0 = pv1[0];
|
|
i1 = pv1[1];
|
|
res = vec_msum(t0, i0, res);
|
|
res = vec_msum(t1, i1, res);
|
|
i4 = vec_ld(16, v3);
|
|
t0 = vec_perm(i3, i4, align);
|
|
i3 = vec_ld(32, v3);
|
|
t1 = vec_perm(i4, i3, align);
|
|
pv1[0] = vec_mladd(t0, muls, i0);
|
|
pv1[1] = vec_mladd(t1, muls, i1);
|
|
pv1 += 2;
|
|
v2 += 16;
|
|
v3 += 16;
|
|
} while (--order);
|
|
res = vec_splat(vec_sums(res, zero_s32v), 3);
|
|
vec_ste(res, 0, &ires);
|
|
|
|
return ires;
|
|
}
|
|
|
|
av_cold void ff_int_init_altivec(DSPContext *c, AVCodecContext *avctx)
|
|
{
|
|
c->scalarproduct_int16 = scalarproduct_int16_altivec;
|
|
|
|
c->scalarproduct_and_madd_int16 = scalarproduct_and_madd_int16_altivec;
|
|
}
|