X-Git-Url: https://git.sesse.net/?a=blobdiff_plain;f=common%2Fmc.h;h=582c0ab437f616f227b6a2ee937de99076626342;hb=30140b34b879605cf70cab0634a4a8faef5b6e60;hp=08331b81eac11965d127120d6b56f3e9357e0fde;hpb=04dc25367d218c92ba85c4cae34cc8b36bab05a3;p=x264 diff --git a/common/mc.h b/common/mc.h index 08331b81..582c0ab4 100644 --- a/common/mc.h +++ b/common/mc.h @@ -1,10 +1,9 @@ /***************************************************************************** - * mc.h: h264 encoder library (Motion Compensation) + * mc.h: motion compensation ***************************************************************************** - * Copyright (C) 2003 Laurent Aimar - * $Id: mc.h,v 1.1 2004/06/03 19:27:07 fenrir Exp $ + * Copyright (C) 2004-2014 x264 project * - * Authors: Laurent Aimar + * Authors: Loren Merritt * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -18,12 +17,44 @@ * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111, USA. + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA. + * + * This program is also available under a commercial proprietary license. + * For more information, contact us at licensing@x264.com. *****************************************************************************/ #ifndef X264_MC_H #define X264_MC_H +struct x264_weight_t; +typedef void (* weight_fn_t)( pixel *, intptr_t, pixel *,intptr_t, const struct x264_weight_t *, int ); +typedef struct x264_weight_t +{ + /* aligning the first member is a gcc hack to force the struct to be + * 16 byte aligned, as well as force sizeof(struct) to be a multiple of 16 */ + ALIGNED_16( int16_t cachea[8] ); + int16_t cacheb[8]; + int32_t i_denom; + int32_t i_scale; + int32_t i_offset; + weight_fn_t *weightfn; +} ALIGNED_16( x264_weight_t ); + +extern const x264_weight_t x264_weight_none[3]; +extern const uint8_t x264_hpel_ref0[16]; +extern const uint8_t x264_hpel_ref1[16]; + +#define SET_WEIGHT( w, b, s, d, o )\ +{\ + (w).i_scale = (s);\ + (w).i_denom = (d);\ + (w).i_offset = (o);\ + if( b )\ + h->mc.weight_cache( h, &w );\ + else\ + w.weightfn = NULL;\ +} + /* Do the MC * XXX: Only width = 4, 8 or 16 are valid * width == 4 -> height == 4 or 8 @@ -33,46 +64,74 @@ typedef struct { - void (*mc_luma)(uint8_t *dst, int i_dst, uint8_t **src, int i_src, - int mvx, int mvy, - int i_width, int i_height ); + void (*mc_luma)( pixel *dst, intptr_t i_dst, pixel **src, intptr_t i_src, + int mvx, int mvy, int i_width, int i_height, const x264_weight_t *weight ); /* may round up the dimensions if they're not a power of 2 */ - uint8_t* (*get_ref)(uint8_t *dst, int *i_dst, uint8_t **src, int i_src, - int mvx, int mvy, - int i_width, int i_height ); + pixel* (*get_ref)( pixel *dst, intptr_t *i_dst, pixel **src, intptr_t i_src, + int mvx, int mvy, int i_width, int i_height, const x264_weight_t *weight ); /* mc_chroma may write up to 2 bytes of garbage to the right of dst, * so it must be run from left to right. */ - void (*mc_chroma)(uint8_t *dst, int i_dst, uint8_t *src, int i_src, - int mvx, int mvy, - int i_width, int i_height ); + void (*mc_chroma)( pixel *dstu, pixel *dstv, intptr_t i_dst, pixel *src, intptr_t i_src, + int mvx, int mvy, int i_width, int i_height ); - void (*avg[10])( uint8_t *dst, int, uint8_t *src, int ); - void (*avg_weight[10])( uint8_t *dst, int, uint8_t *src, int, int i_weight ); + void (*avg[12])( pixel *dst, intptr_t dst_stride, pixel *src1, intptr_t src1_stride, + pixel *src2, intptr_t src2_stride, int i_weight ); /* only 16x16, 8x8, and 4x4 defined */ - void (*copy[7])( uint8_t *dst, int, uint8_t *src, int, int i_height ); + void (*copy[7])( pixel *dst, intptr_t dst_stride, pixel *src, intptr_t src_stride, int i_height ); + void (*copy_16x16_unaligned)( pixel *dst, intptr_t dst_stride, pixel *src, intptr_t src_stride, int i_height ); - void (*plane_copy)( uint8_t *dst, int i_dst, - uint8_t *src, int i_src, int w, int h); + void (*store_interleave_chroma)( pixel *dst, intptr_t i_dst, pixel *srcu, pixel *srcv, int height ); + void (*load_deinterleave_chroma_fenc)( pixel *dst, pixel *src, intptr_t i_src, int height ); + void (*load_deinterleave_chroma_fdec)( pixel *dst, pixel *src, intptr_t i_src, int height ); - void (*hpel_filter)( uint8_t *dsth, uint8_t *dstv, uint8_t *dstc, uint8_t *src, - int i_stride, int i_width, int i_height ); + void (*plane_copy)( pixel *dst, intptr_t i_dst, pixel *src, intptr_t i_src, int w, int h ); + void (*plane_copy_interleave)( pixel *dst, intptr_t i_dst, pixel *srcu, intptr_t i_srcu, + pixel *srcv, intptr_t i_srcv, int w, int h ); + /* may write up to 15 pixels off the end of each plane */ + void (*plane_copy_deinterleave)( pixel *dstu, intptr_t i_dstu, pixel *dstv, intptr_t i_dstv, + pixel *src, intptr_t i_src, int w, int h ); + void (*plane_copy_deinterleave_rgb)( pixel *dsta, intptr_t i_dsta, pixel *dstb, intptr_t i_dstb, + pixel *dstc, intptr_t i_dstc, pixel *src, intptr_t i_src, int pw, int w, int h ); + void (*plane_copy_deinterleave_v210)( pixel *dsty, intptr_t i_dsty, + pixel *dstc, intptr_t i_dstc, + uint32_t *src, intptr_t i_src, int w, int h ); + void (*hpel_filter)( pixel *dsth, pixel *dstv, pixel *dstc, pixel *src, + intptr_t i_stride, int i_width, int i_height, int16_t *buf ); /* prefetch the next few macroblocks of fenc or fdec */ - void (*prefetch_fenc)( uint8_t *pix_y, int stride_y, - uint8_t *pix_uv, int stride_uv, int mb_x ); + void (*prefetch_fenc) ( pixel *pix_y, intptr_t stride_y, pixel *pix_uv, intptr_t stride_uv, int mb_x ); + void (*prefetch_fenc_420)( pixel *pix_y, intptr_t stride_y, pixel *pix_uv, intptr_t stride_uv, int mb_x ); + void (*prefetch_fenc_422)( pixel *pix_y, intptr_t stride_y, pixel *pix_uv, intptr_t stride_uv, int mb_x ); /* prefetch the next few macroblocks of a hpel reference frame */ - void (*prefetch_ref)( uint8_t *pix, int stride, int parity ); - + void (*prefetch_ref)( pixel *pix, intptr_t stride, int parity ); + void *(*memcpy_aligned)( void *dst, const void *src, size_t n ); - void (*memzero_aligned)( void *dst, int n ); + void (*memzero_aligned)( void *dst, size_t n ); + + /* successive elimination prefilter */ + void (*integral_init4h)( uint16_t *sum, pixel *pix, intptr_t stride ); + void (*integral_init8h)( uint16_t *sum, pixel *pix, intptr_t stride ); + void (*integral_init4v)( uint16_t *sum8, uint16_t *sum4, intptr_t stride ); + void (*integral_init8v)( uint16_t *sum8, intptr_t stride ); + + void (*frame_init_lowres_core)( pixel *src0, pixel *dst0, pixel *dsth, pixel *dstv, pixel *dstc, + intptr_t src_stride, intptr_t dst_stride, int width, int height ); + weight_fn_t *weight; + weight_fn_t *offsetadd; + weight_fn_t *offsetsub; + void (*weight_cache)( x264_t *, x264_weight_t * ); + + void (*mbtree_propagate_cost)( int16_t *dst, uint16_t *propagate_in, uint16_t *intra_costs, + uint16_t *inter_costs, uint16_t *inv_qscales, float *fps_factor, int len ); - void (*frame_init_lowres_core)( uint8_t *src0, uint8_t *dst0, uint8_t *dsth, uint8_t *dstv, uint8_t *dstc, - int src_stride, int dst_stride, int width, int height ); + void (*mbtree_propagate_list)( x264_t *h, uint16_t *ref_costs, int16_t (*mvs)[2], + int16_t *propagate_amount, uint16_t *lowres_costs, + int bipred_weight, int mb_y, int len, int list ); } x264_mc_functions_t; -void x264_mc_init( int cpu, x264_mc_functions_t *pf ); +void x264_mc_init( int cpu, x264_mc_functions_t *pf, int cpu_independent ); #endif