1
0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-12-23 12:43:46 +02:00
FFmpeg/libavcodec/mips/h264dsp_mips.h
Shivraj Patil fb92f3ecb4 avcodec/mips: MSA (MIPS-SIMD-Arch) optimizations for AVC idct functions
This patch adds MSA (MIPS-SIMD-Arch) optimizations for AVC idct functions in new file h264idct_msa.c
Adds new generic macros (needed for this patch) in libavutil/mips/generic_macros_msa.h

Signed-off-by: Shivraj Patil <shivraj.patil@imgtec.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2015-06-11 17:10:45 +02:00

139 lines
7.7 KiB
C

/*
* Copyright (c) 2015 Parag Salasakar (Parag.Salasakar@imgtec.com)
*
* This file is part of FFmpeg.
*
* FFmpeg is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* FFmpeg is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with FFmpeg; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
#ifndef H264_DSP_MIPS_H
#define H264_DSP_MIPS_H
#include "libavcodec/h264.h"
void ff_h264_h_lpf_luma_inter_msa(uint8_t *src, int stride,
int alpha, int beta, int8_t *tc0);
void ff_h264_v_lpf_luma_inter_msa(uint8_t *src, int stride,
int alpha, int beta, int8_t *tc0);
void ff_h264_h_lpf_chroma_inter_msa(uint8_t *src, int stride,
int alpha, int beta, int8_t *tc0);
void ff_h264_v_lpf_chroma_inter_msa(uint8_t *src, int stride,
int alpha, int beta, int8_t *tc0);
void ff_h264_h_loop_filter_chroma422_msa(uint8_t *src, int32_t stride,
int32_t alpha, int32_t beta,
int8_t *tc0);
void ff_h264_h_loop_filter_chroma422_mbaff_msa(uint8_t *src, int32_t stride,
int32_t alpha, int32_t beta,
int8_t *tc0);
void ff_h264_h_loop_filter_luma_mbaff_msa(uint8_t *src, int32_t stride,
int32_t alpha, int32_t beta,
int8_t *tc0);
void ff_h264_idct_add_msa(uint8_t *dst, int16_t *src, int32_t dst_stride);
void ff_h264_idct4x4_addblk_dc_msa(uint8_t *dst, int16_t *src,
int32_t dst_stride);
void ff_h264_deq_idct_luma_dc_msa(int16_t *dst, int16_t *src,
int32_t de_q_val);
void ff_h264_idct_add16_msa(uint8_t *dst, const int32_t *blk_offset,
int16_t *block, int32_t stride,
const uint8_t nnzc[15 * 8]);
void ff_h264_idct_add16_intra_msa(uint8_t *dst, const int32_t *blk_offset,
int16_t *block, int32_t dst_stride,
const uint8_t nnzc[15 * 8]);
void ff_h264_idct_add8_msa(uint8_t **dst, const int32_t *blk_offset,
int16_t *block, int32_t dst_stride,
const uint8_t nnzc[15 * 8]);
void ff_h264_idct_add8_422_msa(uint8_t **dst, const int32_t *blk_offset,
int16_t *block, int32_t dst_stride,
const uint8_t nnzc[15 * 8]);
void ff_h264_idct8_addblk_msa(uint8_t *dst, int16_t *src, int32_t dst_stride);
void ff_h264_idct8_dc_addblk_msa(uint8_t *dst, int16_t *src,
int32_t dst_stride);
void ff_h264_idct8_add4_msa(uint8_t *dst, const int *blk_offset,
int16_t *blk, int dst_stride,
const uint8_t nnzc[15 * 8]);
void ff_h264_h_lpf_luma_intra_msa(uint8_t *src, int stride,
int alpha, int beta);
void ff_h264_v_lpf_luma_intra_msa(uint8_t *src, int stride,
int alpha, int beta);
void ff_h264_h_lpf_chroma_intra_msa(uint8_t *src, int stride,
int alpha, int beta);
void ff_h264_v_lpf_chroma_intra_msa(uint8_t *src, int stride,
int alpha, int beta);
void ff_h264_h_loop_filter_luma_mbaff_intra_msa(uint8_t *src, int stride,
int alpha, int beta);
void ff_biweight_h264_pixels16_8_msa(uint8_t *dst, uint8_t *src,
int stride, int height, int log2_denom,
int weightd, int weights, int offset);
void ff_biweight_h264_pixels8_8_msa(uint8_t *dst, uint8_t *src,
int stride, int height, int log2_denom,
int weightd, int weights, int offset);
void ff_biweight_h264_pixels4_8_msa(uint8_t *dst, uint8_t *src,
int stride, int height, int log2_denom,
int weightd, int weights, int offset);
void ff_weight_h264_pixels16_8_msa(uint8_t *src, int stride, int height,
int log2_denom, int weight, int offset);
void ff_weight_h264_pixels8_8_msa(uint8_t *src, int stride, int height,
int log2_denom, int weight, int offset);
void ff_weight_h264_pixels4_8_msa(uint8_t *src, int stride, int height,
int log2_denom, int weight, int offset);
void ff_h264_intra_predict_plane_8x8_msa(uint8_t *src, ptrdiff_t stride);
void ff_h264_intra_predict_dc_4blk_8x8_msa(uint8_t *src, ptrdiff_t stride);
void ff_h264_intra_predict_hor_dc_8x8_msa(uint8_t *src, ptrdiff_t stride);
void ff_h264_intra_predict_vert_dc_8x8_msa(uint8_t *src, ptrdiff_t stride);
void ff_h264_intra_predict_mad_cow_dc_l0t_8x8_msa(uint8_t *src,
ptrdiff_t stride);
void ff_h264_intra_predict_mad_cow_dc_0lt_8x8_msa(uint8_t *src,
ptrdiff_t stride);
void ff_h264_intra_predict_mad_cow_dc_l00_8x8_msa(uint8_t *src,
ptrdiff_t stride);
void ff_h264_intra_predict_mad_cow_dc_0l0_8x8_msa(uint8_t *src,
ptrdiff_t stride);
void ff_h264_intra_predict_plane_16x16_msa(uint8_t *src, ptrdiff_t stride);
void ff_h264_intra_pred_vert_8x8_msa(uint8_t *src, ptrdiff_t stride);
void ff_h264_intra_pred_horiz_8x8_msa(uint8_t *src, ptrdiff_t stride);
void ff_h264_intra_pred_dc_16x16_msa(uint8_t *src, ptrdiff_t stride);
void ff_h264_intra_pred_vert_16x16_msa(uint8_t *src, ptrdiff_t stride);
void ff_h264_intra_pred_horiz_16x16_msa(uint8_t *src, ptrdiff_t stride);
void ff_h264_intra_pred_dc_left_16x16_msa(uint8_t *src, ptrdiff_t stride);
void ff_h264_intra_pred_dc_top_16x16_msa(uint8_t *src, ptrdiff_t stride);
void ff_h264_intra_pred_dc_128_8x8_msa(uint8_t *src, ptrdiff_t stride);
void ff_h264_intra_pred_dc_128_16x16_msa(uint8_t *src, ptrdiff_t stride);
void ff_vp8_pred8x8_127_dc_8_msa(uint8_t *src, ptrdiff_t stride);
void ff_vp8_pred8x8_129_dc_8_msa(uint8_t *src, ptrdiff_t stride);
void ff_vp8_pred16x16_127_dc_8_msa(uint8_t *src, ptrdiff_t stride);
void ff_vp8_pred16x16_129_dc_8_msa(uint8_t *src, ptrdiff_t stride);
void ff_h264_weight_pixels16_8_mmi(uint8_t *block, int stride, int height,
int log2_denom, int weight, int offset);
void ff_h264_biweight_pixels16_8_mmi(uint8_t *dst, uint8_t *src,
int stride, int height, int log2_denom, int weightd, int weights,
int offset);
void ff_h264_weight_pixels8_8_mmi(uint8_t *block, int stride, int height,
int log2_denom, int weight, int offset);
void ff_h264_biweight_pixels8_8_mmi(uint8_t *dst, uint8_t *src,
int stride, int height, int log2_denom, int weightd, int weights,
int offset);
void ff_h264_weight_pixels4_8_mmi(uint8_t *block, int stride, int height,
int log2_denom, int weight, int offset);
void ff_h264_biweight_pixels4_8_mmi(uint8_t *dst, uint8_t *src,
int stride, int height, int log2_denom, int weightd, int weights,
int offset);
#endif // #ifndef H264_DSP_MIPS_H