1/* 2 * SIMD-optimized lossless video encoding functions 3 * Copyright (c) 2000, 2001 Fabrice Bellard 4 * Copyright (c) 2002-2004 Michael Niedermayer <michaelni@gmx.at> 5 * 6 * MMX optimization by Nick Kurshev <nickols_k@mail.ru> 7 * 8 * This file is part of FFmpeg. 9 * 10 * FFmpeg is free software; you can redistribute it and/or 11 * modify it under the terms of the GNU Lesser General Public 12 * License as published by the Free Software Foundation; either 13 * version 2.1 of the License, or (at your option) any later version. 14 * 15 * FFmpeg is distributed in the hope that it will be useful, 16 * but WITHOUT ANY WARRANTY; without even the implied warranty of 17 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 18 * Lesser General Public License for more details. 19 * 20 * You should have received a copy of the GNU Lesser General Public 21 * License along with FFmpeg; if not, write to the Free Software 22 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA 23 */ 24 25#include "libavutil/attributes.h" 26#include "libavutil/cpu.h" 27#include "libavutil/x86/asm.h" 28#include "libavutil/x86/cpu.h" 29#include "libavcodec/lossless_videoencdsp.h" 30#include "libavcodec/mathops.h" 31 32void ff_diff_bytes_sse2(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, 33 intptr_t w); 34void ff_diff_bytes_avx2(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, 35 intptr_t w); 36 37void ff_sub_left_predict_avx(uint8_t *dst, uint8_t *src, 38 ptrdiff_t stride, ptrdiff_t width, int height); 39 40#if HAVE_INLINE_ASM 41 42static void sub_median_pred_mmxext(uint8_t *dst, const uint8_t *src1, 43 const uint8_t *src2, intptr_t w, 44 int *left, int *left_top) 45{ 46 x86_reg i = 0; 47 uint8_t l, lt; 48 49 __asm__ volatile ( 50 "movq (%1, %0), %%mm0 \n\t" // LT 51 "psllq $8, %%mm0 \n\t" 52 "1: \n\t" 53 "movq (%1, %0), %%mm1 \n\t" // T 54 "movq -1(%2, %0), %%mm2 \n\t" // L 55 "movq (%2, %0), %%mm3 \n\t" // X 56 "movq %%mm2, %%mm4 \n\t" // L 57 "psubb %%mm0, %%mm2 \n\t" 58 "paddb %%mm1, %%mm2 \n\t" // L + T - LT 59 "movq %%mm4, %%mm5 \n\t" // L 60 "pmaxub %%mm1, %%mm4 \n\t" // max(T, L) 61 "pminub %%mm5, %%mm1 \n\t" // min(T, L) 62 "pminub %%mm2, %%mm4 \n\t" 63 "pmaxub %%mm1, %%mm4 \n\t" 64 "psubb %%mm4, %%mm3 \n\t" // dst - pred 65 "movq %%mm3, (%3, %0) \n\t" 66 "add $8, %0 \n\t" 67 "movq -1(%1, %0), %%mm0 \n\t" // LT 68 "cmp %4, %0 \n\t" 69 " jb 1b \n\t" 70 : "+r" (i) 71 : "r" (src1), "r" (src2), "r" (dst), "r" ((x86_reg) w)); 72 73 l = *left; 74 lt = *left_top; 75 76 dst[0] = src2[0] - mid_pred(l, src1[0], (l + src1[0] - lt) & 0xFF); 77 78 *left_top = src1[w - 1]; 79 *left = src2[w - 1]; 80} 81 82#endif /* HAVE_INLINE_ASM */ 83 84av_cold void ff_llvidencdsp_init_x86(LLVidEncDSPContext *c) 85{ 86 av_unused int cpu_flags = av_get_cpu_flags(); 87 88#if HAVE_INLINE_ASM 89 if (INLINE_MMXEXT(cpu_flags)) { 90 c->sub_median_pred = sub_median_pred_mmxext; 91 } 92#endif /* HAVE_INLINE_ASM */ 93 94 if (EXTERNAL_SSE2(cpu_flags)) { 95 c->diff_bytes = ff_diff_bytes_sse2; 96 } 97 98 if (EXTERNAL_AVX(cpu_flags)) { 99 c->sub_left_predict = ff_sub_left_predict_avx; 100 } 101 102 if (EXTERNAL_AVX2_FAST(cpu_flags)) { 103 c->diff_bytes = ff_diff_bytes_avx2; 104 } 105} 106