| 1 | /* |
| 2 | * Copyright (C) 2013 Xiaolei Yu <dreifachstein@gmail.com> |
| 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 | #include "libswscale/swscale.h" |
| 23 | #include "libswscale/swscale_internal.h" |
| 24 | #include "libavutil/arm/cpu.h" |
| 25 | |
| 26 | extern void rgbx_to_nv12_neon_32(const uint8_t *src, uint8_t *y, uint8_t *chroma, |
| 27 | int width, int height, |
| 28 | int y_stride, int c_stride, int src_stride, |
| 29 | int32_t coeff_tbl[9]); |
| 30 | |
| 31 | extern void rgbx_to_nv12_neon_16(const uint8_t *src, uint8_t *y, uint8_t *chroma, |
| 32 | int width, int height, |
| 33 | int y_stride, int c_stride, int src_stride, |
| 34 | int32_t coeff_tbl[9]); |
| 35 | |
| 36 | static int rgbx_to_nv12_neon_32_wrapper(SwsContext *context, const uint8_t *src[], |
| 37 | int srcStride[], int srcSliceY, int srcSliceH, |
| 38 | uint8_t *dst[], int dstStride[]) { |
| 39 | |
| 40 | rgbx_to_nv12_neon_32(src[0] + srcSliceY * srcStride[0], |
| 41 | dst[0] + srcSliceY * dstStride[0], |
| 42 | dst[1] + (srcSliceY / 2) * dstStride[1], |
| 43 | context->srcW, srcSliceH, |
| 44 | dstStride[0], dstStride[1], srcStride[0], |
| 45 | context->input_rgb2yuv_table); |
| 46 | |
| 47 | return 0; |
| 48 | } |
| 49 | |
| 50 | static int rgbx_to_nv12_neon_16_wrapper(SwsContext *context, const uint8_t *src[], |
| 51 | int srcStride[], int srcSliceY, int srcSliceH, |
| 52 | uint8_t *dst[], int dstStride[]) { |
| 53 | |
| 54 | rgbx_to_nv12_neon_16(src[0] + srcSliceY * srcStride[0], |
| 55 | dst[0] + srcSliceY * dstStride[0], |
| 56 | dst[1] + (srcSliceY / 2) * dstStride[1], |
| 57 | context->srcW, srcSliceH, |
| 58 | dstStride[0], dstStride[1], srcStride[0], |
| 59 | context->input_rgb2yuv_table); |
| 60 | |
| 61 | return 0; |
| 62 | } |
| 63 | |
| 64 | static void get_unscaled_swscale_neon(SwsContext *c) { |
| 65 | int accurate_rnd = c->flags & SWS_ACCURATE_RND; |
| 66 | if (c->srcFormat == AV_PIX_FMT_RGBA |
| 67 | && c->dstFormat == AV_PIX_FMT_NV12 |
| 68 | && (c->srcW >= 16)) { |
| 69 | c->swscale = accurate_rnd ? rgbx_to_nv12_neon_32_wrapper |
| 70 | : rgbx_to_nv12_neon_16_wrapper; |
| 71 | } |
| 72 | } |
| 73 | |
| 74 | void ff_get_unscaled_swscale_arm(SwsContext *c) |
| 75 | { |
| 76 | int cpu_flags = av_get_cpu_flags(); |
| 77 | if (have_neon(cpu_flags)) |
| 78 | get_unscaled_swscale_neon(c); |
| 79 | } |