1/* 2 * SIMD-optimized IDCT functions for HEVC decoding 3 * Copyright (c) Alexandra Hajkova 4 * 5 * This file is part of FFmpeg. 6 * 7 * FFmpeg is free software; you can redistribute it and/or 8 * modify it under the terms of the GNU Lesser General Public 9 * License as published by the Free Software Foundation; either 10 * version 2.1 of the License, or (at your option) any later version. 11 * 12 * FFmpeg is distributed in the hope that it will be useful, 13 * but WITHOUT ANY WARRANTY; without even the implied warranty of 14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 15 * Lesser General Public License for more details. 16 * 17 * You should have received a copy of the GNU Lesser General Public 18 * License along with FFmpeg; if not, write to the Free Software 19 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA 20 */ 21 22#include "config.h" 23 24#include "libavutil/attributes.h" 25#include "libavutil/cpu.h" 26#include "libavutil/ppc/cpu.h" 27#include "libavutil/ppc/util_altivec.h" 28 29#include "libavcodec/hevcdsp.h" 30 31#if HAVE_ALTIVEC 32static const vec_s16 trans4[4] = { 33 { 64, 64, 64, 64, 64, 64, 64, 64 }, 34 { 83, 36, 83, 36, 83, 36, 83, 36 }, 35 { 64, -64, 64, -64, 64, -64, 64, -64 }, 36 { 36, -83, 36, -83, 36, -83, 36, -83 }, 37}; 38 39static const vec_u8 mask[2] = { 40 { 0x00, 0x01, 0x08, 0x09, 0x10, 0x11, 0x18, 0x19, 0x02, 0x03, 0x0A, 0x0B, 0x12, 0x13, 0x1A, 0x1B }, 41 { 0x04, 0x05, 0x0C, 0x0D, 0x14, 0x15, 0x1C, 0x1D, 0x06, 0x07, 0x0E, 0x0F, 0x16, 0x17, 0x1E, 0x1F }, 42}; 43 44static av_always_inline void transform4x4(vec_s16 src_01, vec_s16 src_23, 45 vec_s32 res[4], const int shift, 46 int16_t *coeffs) 47{ 48 vec_s16 src_02, src_13; 49 vec_s32 zero = vec_splat_s32(0); 50 vec_s32 e0, o0, e1, o1; 51 vec_s32 add; 52 53 src_13 = vec_mergel(src_01, src_23); 54 src_02 = vec_mergeh(src_01, src_23); 55 56 e0 = vec_msums(src_02, trans4[0], zero); 57 o0 = vec_msums(src_13, trans4[1], zero); 58 e1 = vec_msums(src_02, trans4[2], zero); 59 o1 = vec_msums(src_13, trans4[3], zero); 60 61 switch(shift) { 62 case 7: add = vec_sl(vec_splat_s32(1), vec_splat_u32( 7 - 1)); break; 63 case 10: add = vec_sl(vec_splat_s32(1), vec_splat_u32(10 - 1)); break; 64 case 12: add = vec_sl(vec_splat_s32(1), vec_splat_u32(12 - 1)); break; 65 default: abort(); 66 } 67 68 e0 = vec_add(e0, add); 69 e1 = vec_add(e1, add); 70 71 res[0] = vec_add(e0, o0); 72 res[1] = vec_add(e1, o1); 73 res[2] = vec_sub(e1, o1); 74 res[3] = vec_sub(e0, o0); 75} 76 77static av_always_inline void scale(vec_s32 res[4], vec_s16 res_packed[2], 78 const int shift) 79{ 80 int i; 81 vec_u32 v_shift; 82 83 switch(shift) { 84 case 7: v_shift = vec_splat_u32(7) ; break; 85 case 10: v_shift = vec_splat_u32(10); break; 86 case 12: v_shift = vec_splat_u32(12); break; 87 default: abort(); 88 } 89 90 for (i = 0; i < 4; i++) 91 res[i] = vec_sra(res[i], v_shift); 92 93 // clip16 94 res_packed[0] = vec_packs(res[0], res[1]); 95 res_packed[1] = vec_packs(res[2], res[3]); 96} 97 98#define FUNCDECL(a, depth) a ## _ ## depth ## _altivec 99#define FUNC(a, b) FUNCDECL(a, b) 100 101#define BIT_DEPTH 8 102#include "hevcdsp_template.c" 103#undef BIT_DEPTH 104 105#define BIT_DEPTH 10 106#include "hevcdsp_template.c" 107#undef BIT_DEPTH 108#endif /* HAVE_ALTIVEC */ 109 110av_cold void ff_hevc_dsp_init_ppc(HEVCDSPContext *c, const int bit_depth) 111{ 112#if HAVE_ALTIVEC 113 if (!PPC_ALTIVEC(av_get_cpu_flags())) 114 return; 115 116 if (bit_depth == 8) 117 c->idct[0] = ff_hevc_idct_4x4_8_altivec; 118 if (bit_depth == 10) 119 c->idct[0] = ff_hevc_idct_4x4_10_altivec; 120#endif /* HAVE_ALTIVEC */ 121} 122