1/* 2 * Copyright (c) 2007 Luca Barbato <lu_zero@gentoo.org> 3 * 4 * This file is part of FFmpeg. 5 * 6 * FFmpeg is free software; you can redistribute it and/or 7 * modify it under the terms of the GNU Lesser General Public 8 * License as published by the Free Software Foundation; either 9 * version 2.1 of the License, or (at your option) any later version. 10 * 11 * FFmpeg is distributed in the hope that it will be useful, 12 * but WITHOUT ANY WARRANTY; without even the implied warranty of 13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 14 * Lesser General Public License for more details. 15 * 16 * You should have received a copy of the GNU Lesser General Public 17 * License along with FFmpeg; if not, write to the Free Software 18 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA 19 */ 20 21#include "config.h" 22 23#include <stdint.h> 24 25#include "libavutil/attributes.h" 26#include "libavutil/cpu.h" 27#include "libavutil/ppc/cpu.h" 28#include "libavutil/ppc/util_altivec.h" 29 30#include "libavcodec/svq1enc.h" 31 32#if HAVE_ALTIVEC 33static int ssd_int8_vs_int16_altivec(const int8_t *pix1, const int16_t *pix2, 34 intptr_t size) 35{ 36 int i, size16 = size >> 4; 37 vector signed char vpix1; 38 vector signed short vpix2, vdiff, vpix1l, vpix1h; 39 union { 40 vector signed int vscore; 41 int32_t score[4]; 42 } u = { .vscore = vec_splat_s32(0) }; 43 44 while (size16) { 45 // score += (pix1[i] - pix2[i]) * (pix1[i] - pix2[i]); 46 // load pix1 and the first batch of pix2 47 48 vpix1 = vec_unaligned_load(pix1); 49 vpix2 = vec_unaligned_load(pix2); 50 pix2 += 8; 51 // unpack 52 vpix1h = vec_unpackh(vpix1); 53 vdiff = vec_sub(vpix1h, vpix2); 54 vpix1l = vec_unpackl(vpix1); 55 // load another batch from pix2 56 vpix2 = vec_unaligned_load(pix2); 57 u.vscore = vec_msum(vdiff, vdiff, u.vscore); 58 vdiff = vec_sub(vpix1l, vpix2); 59 u.vscore = vec_msum(vdiff, vdiff, u.vscore); 60 pix1 += 16; 61 pix2 += 8; 62 size16--; 63 } 64 u.vscore = vec_sums(u.vscore, vec_splat_s32(0)); 65 66 size %= 16; 67 for (i = 0; i < size; i++) 68 u.score[3] += (pix1[i] - pix2[i]) * (pix1[i] - pix2[i]); 69 70 return u.score[3]; 71} 72#endif /* HAVE_ALTIVEC */ 73 74av_cold void ff_svq1enc_init_ppc(SVQ1EncContext *c) 75{ 76#if HAVE_ALTIVEC 77 if (!PPC_ALTIVEC(av_get_cpu_flags())) 78 return; 79 80 c->ssd_int8_vs_int16 = ssd_int8_vs_int16_altivec; 81#endif /* HAVE_ALTIVEC */ 82} 83