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 "libavutil/attributes.h" 24#include "libavutil/cpu.h" 25#include "libavutil/ppc/cpu.h" 26#include "libavutil/ppc/util_altivec.h" 27 28#include "libavcodec/lossless_audiodsp.h" 29 30#if HAVE_BIGENDIAN 31#define GET_T(tt0,tt1,src,a,b){ \ 32 a = vec_ld(16, src); \ 33 tt0 = vec_perm(b, a, align); \ 34 b = vec_ld(32, src); \ 35 tt1 = vec_perm(a, b, align); \ 36 } 37#else 38#define GET_T(tt0,tt1,src,a,b){ \ 39 tt0 = vec_vsx_ld(0, src); \ 40 tt1 = vec_vsx_ld(16, src); \ 41 } 42#endif 43 44#if HAVE_ALTIVEC 45static int32_t scalarproduct_and_madd_int16_altivec(int16_t *v1, 46 const int16_t *v2, 47 const int16_t *v3, 48 int order, int mul) 49{ 50 LOAD_ZERO; 51 vec_s16 *pv1 = (vec_s16 *) v1; 52 register vec_s16 muls = { mul, mul, mul, mul, mul, mul, mul, mul }; 53 register vec_s16 t0, t1, i0, i1, i4, i2, i3; 54 register vec_s32 res = zero_s32v; 55#if HAVE_BIGENDIAN 56 register vec_u8 align = vec_lvsl(0, v2); 57 i2 = vec_ld(0, v2); 58 i3 = vec_ld(0, v3); 59#endif 60 int32_t ires; 61 62 order >>= 4; 63 do { 64 GET_T(t0,t1,v2,i1,i2); 65 i0 = pv1[0]; 66 i1 = pv1[1]; 67 res = vec_msum(t0, i0, res); 68 res = vec_msum(t1, i1, res); 69 GET_T(t0,t1,v3,i4,i3); 70 pv1[0] = vec_mladd(t0, muls, i0); 71 pv1[1] = vec_mladd(t1, muls, i1); 72 pv1 += 2; 73 v2 += 16; 74 v3 += 16; 75 } while (--order); 76 res = vec_splat(vec_sums(res, zero_s32v), 3); 77 vec_ste(res, 0, &ires); 78 79 return ires; 80} 81#endif /* HAVE_ALTIVEC */ 82 83av_cold void ff_llauddsp_init_ppc(LLAudDSPContext *c) 84{ 85#if HAVE_ALTIVEC 86 if (!PPC_ALTIVEC(av_get_cpu_flags())) 87 return; 88 89 c->scalarproduct_and_madd_int16 = scalarproduct_and_madd_int16_altivec; 90#endif /* HAVE_ALTIVEC */ 91} 92