1/* 2 * Copyright (c) 2021 Loongson Technology Corporation Limited 3 * Contributed by Hao Chen <chenhao@loongson.cn> 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 "idctdsp_loongarch.h" 23#include "libavutil/loongarch/loongson_intrinsics.h" 24 25void ff_put_pixels_clamped_lasx(const int16_t *block, 26 uint8_t *av_restrict pixels, 27 ptrdiff_t stride) 28{ 29 __m256i b0, b1, b2, b3; 30 __m256i temp0, temp1; 31 ptrdiff_t stride_2x = stride << 1; 32 ptrdiff_t stride_4x = stride << 2; 33 ptrdiff_t stride_3x = stride_2x + stride; 34 35 DUP4_ARG2(__lasx_xvld, block, 0, block, 32, block, 64, block, 96, 36 b0, b1, b2, b3); 37 DUP4_ARG1(__lasx_xvclip255_h, b0, b1, b2, b3, b0, b1, b2, b3); 38 DUP2_ARG2(__lasx_xvpickev_b, b1, b0, b3, b2, temp0, temp1); 39 __lasx_xvstelm_d(temp0, pixels, 0, 0); 40 __lasx_xvstelm_d(temp0, pixels + stride, 0, 2); 41 __lasx_xvstelm_d(temp0, pixels + stride_2x, 0, 1); 42 __lasx_xvstelm_d(temp0, pixels + stride_3x, 0, 3); 43 pixels += stride_4x; 44 __lasx_xvstelm_d(temp1, pixels, 0, 0); 45 __lasx_xvstelm_d(temp1, pixels + stride, 0, 2); 46 __lasx_xvstelm_d(temp1, pixels + stride_2x, 0, 1); 47 __lasx_xvstelm_d(temp1, pixels + stride_3x, 0, 3); 48} 49 50void ff_put_signed_pixels_clamped_lasx(const int16_t *block, 51 uint8_t *av_restrict pixels, 52 ptrdiff_t stride) 53{ 54 __m256i b0, b1, b2, b3; 55 __m256i temp0, temp1; 56 __m256i const_128 = {0x0080008000800080, 0x0080008000800080, 57 0x0080008000800080, 0x0080008000800080}; 58 ptrdiff_t stride_2x = stride << 1; 59 ptrdiff_t stride_4x = stride << 2; 60 ptrdiff_t stride_3x = stride_2x + stride; 61 62 DUP4_ARG2(__lasx_xvld, block, 0, block, 32, block, 64, block, 96, 63 b0, b1, b2, b3); 64 DUP4_ARG2(__lasx_xvadd_h, b0, const_128, b1, const_128, b2, const_128, 65 b3, const_128, b0, b1, b2, b3); 66 DUP4_ARG1(__lasx_xvclip255_h, b0, b1, b2, b3, b0, b1, b2, b3); 67 DUP2_ARG2(__lasx_xvpickev_b, b1, b0, b3, b2, temp0, temp1); 68 __lasx_xvstelm_d(temp0, pixels, 0, 0); 69 __lasx_xvstelm_d(temp0, pixels + stride, 0, 2); 70 __lasx_xvstelm_d(temp0, pixels + stride_2x, 0, 1); 71 __lasx_xvstelm_d(temp0, pixels + stride_3x, 0, 3); 72 pixels += stride_4x; 73 __lasx_xvstelm_d(temp1, pixels, 0, 0); 74 __lasx_xvstelm_d(temp1, pixels + stride, 0, 2); 75 __lasx_xvstelm_d(temp1, pixels + stride_2x, 0, 1); 76 __lasx_xvstelm_d(temp1, pixels + stride_3x, 0, 3); 77} 78 79void ff_add_pixels_clamped_lasx(const int16_t *block, 80 uint8_t *av_restrict pixels, 81 ptrdiff_t stride) 82{ 83 __m256i b0, b1, b2, b3; 84 __m256i p0, p1, p2, p3, p4, p5, p6, p7; 85 __m256i temp0, temp1, temp2, temp3; 86 uint8_t *pix = pixels; 87 ptrdiff_t stride_2x = stride << 1; 88 ptrdiff_t stride_4x = stride << 2; 89 ptrdiff_t stride_3x = stride_2x + stride; 90 91 DUP4_ARG2(__lasx_xvld, block, 0, block, 32, block, 64, block, 96, 92 b0, b1, b2, b3); 93 p0 = __lasx_xvldrepl_d(pix, 0); 94 pix += stride; 95 p1 = __lasx_xvldrepl_d(pix, 0); 96 pix += stride; 97 p2 = __lasx_xvldrepl_d(pix, 0); 98 pix += stride; 99 p3 = __lasx_xvldrepl_d(pix, 0); 100 pix += stride; 101 p4 = __lasx_xvldrepl_d(pix, 0); 102 pix += stride; 103 p5 = __lasx_xvldrepl_d(pix, 0); 104 pix += stride; 105 p6 = __lasx_xvldrepl_d(pix, 0); 106 pix += stride; 107 p7 = __lasx_xvldrepl_d(pix, 0); 108 DUP4_ARG3(__lasx_xvpermi_q, p1, p0, 0x20, p3, p2, 0x20, p5, p4, 0x20, 109 p7, p6, 0x20, temp0, temp1, temp2, temp3); 110 DUP4_ARG2(__lasx_xvaddw_h_h_bu, b0, temp0, b1, temp1, b2, temp2, b3, temp3, 111 temp0, temp1, temp2, temp3); 112 DUP4_ARG1(__lasx_xvclip255_h, temp0, temp1, temp2, temp3, 113 temp0, temp1, temp2, temp3); 114 DUP2_ARG2(__lasx_xvpickev_b, temp1, temp0, temp3, temp2, temp0, temp1); 115 __lasx_xvstelm_d(temp0, pixels, 0, 0); 116 __lasx_xvstelm_d(temp0, pixels + stride, 0, 2); 117 __lasx_xvstelm_d(temp0, pixels + stride_2x, 0, 1); 118 __lasx_xvstelm_d(temp0, pixels + stride_3x, 0, 3); 119 pixels += stride_4x; 120 __lasx_xvstelm_d(temp1, pixels, 0, 0); 121 __lasx_xvstelm_d(temp1, pixels + stride, 0, 2); 122 __lasx_xvstelm_d(temp1, pixels + stride_2x, 0, 1); 123 __lasx_xvstelm_d(temp1, pixels + stride_3x, 0, 3); 124} 125