deblock.c

从服务器上下的x264编码器源码……希望对大家有帮助……这个是09年4月11日的

/*****************************************************************************
* deblock.c: Altivec-accelerated deblocking for h264 encoder
*****************************************************************************
* Copyright (C) 2007-2008 Guillaume Poirier <[e-mail]>
*
* 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
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program 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 General Public License for more details.
*
* 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., 51 Franklin Street, Fifth Floor, Boston, MA  02111, USA.
*****************************************************************************/

#include "common/common.h"
#include "ppccommon.h"

#define transpose4x16(r0, r1, r2, r3) {      \
    register vec_u8_t r4;                    \
    register vec_u8_t r5;                    \
    register vec_u8_t r6;                    \
    register vec_u8_t r7;                    \
                                             \
    r4 = vec_mergeh(r0, r2);  /*0, 2 set 0*/ \
    r5 = vec_mergel(r0, r2);  /*0, 2 set 1*/ \
    r6 = vec_mergeh(r1, r3);  /*1, 3 set 0*/ \
    r7 = vec_mergel(r1, r3);  /*1, 3 set 1*/ \
                                             \
    r0 = vec_mergeh(r4, r6);  /*all set 0*/  \
    r1 = vec_mergel(r4, r6);  /*all set 1*/  \
    r2 = vec_mergeh(r5, r7);  /*all set 2*/  \
    r3 = vec_mergel(r5, r7);  /*all set 3*/  \
}

static inline void write16x4(uint8_t *dst, int dst_stride,
                             register vec_u8_t r0, register vec_u8_t r1,
                             register vec_u8_t r2, register vec_u8_t r3) {
    DECLARE_ALIGNED_16(unsigned char result[64]);
    uint32_t *src_int = (uint32_t *)result, *dst_int = (uint32_t *)dst;
    int int_dst_stride = dst_stride/4;

    vec_st(r0, 0, result);
    vec_st(r1, 16, result);
    vec_st(r2, 32, result);
    vec_st(r3, 48, result);
    /* FIXME: there has to be a better way!!!! */
    *dst_int = *src_int;
    *(dst_int+   int_dst_stride) = *(src_int + 1);
    *(dst_int+ 2*int_dst_stride) = *(src_int + 2);
    *(dst_int+ 3*int_dst_stride) = *(src_int + 3);
    *(dst_int+ 4*int_dst_stride) = *(src_int + 4);
    *(dst_int+ 5*int_dst_stride) = *(src_int + 5);
    *(dst_int+ 6*int_dst_stride) = *(src_int + 6);
    *(dst_int+ 7*int_dst_stride) = *(src_int + 7);
    *(dst_int+ 8*int_dst_stride) = *(src_int + 8);
    *(dst_int+ 9*int_dst_stride) = *(src_int + 9);
    *(dst_int+10*int_dst_stride) = *(src_int + 10);
    *(dst_int+11*int_dst_stride) = *(src_int + 11);
    *(dst_int+12*int_dst_stride) = *(src_int + 12);
    *(dst_int+13*int_dst_stride) = *(src_int + 13);
    *(dst_int+14*int_dst_stride) = *(src_int + 14);
    *(dst_int+15*int_dst_stride) = *(src_int + 15);
}

/** \brief performs a 6x16 transpose of data in src, and stores it to dst */
#define readAndTranspose16x6(src, src_stride, r8, r9, r10, r11, r12, r13) {\
    register vec_u8_t r0, r1, r2, r3, r4, r5, r6, r7, r14, r15;\
    VEC_LOAD(src,                  r0, 16, vec_u8_t, pix );    \
    VEC_LOAD(src +    src_stride,  r1, 16, vec_u8_t, pix );    \
    VEC_LOAD(src +  2*src_stride,  r2, 16, vec_u8_t, pix );    \
    VEC_LOAD(src +  3*src_stride,  r3, 16, vec_u8_t, pix );    \
    VEC_LOAD(src +  4*src_stride,  r4, 16, vec_u8_t, pix );    \
    VEC_LOAD(src +  5*src_stride,  r5, 16, vec_u8_t, pix );    \
    VEC_LOAD(src +  6*src_stride,  r6, 16, vec_u8_t, pix );    \
    VEC_LOAD(src +  7*src_stride,  r7, 16, vec_u8_t, pix );    \
    VEC_LOAD(src + 14*src_stride, r14, 16, vec_u8_t, pix );    \
    VEC_LOAD(src + 15*src_stride, r15, 16, vec_u8_t, pix );    \
                                                               \
    VEC_LOAD(src + 8*src_stride,   r8, 16, vec_u8_t, pix );    \
    VEC_LOAD(src + 9*src_stride,   r9, 16, vec_u8_t, pix );    \
    VEC_LOAD(src + 10*src_stride, r10, 16, vec_u8_t, pix );    \
    VEC_LOAD(src + 11*src_stride, r11, 16, vec_u8_t, pix );    \
    VEC_LOAD(src + 12*src_stride, r12, 16, vec_u8_t, pix );    \
    VEC_LOAD(src + 13*src_stride, r13, 16, vec_u8_t, pix );    \
                                                               \
    /*Merge first pairs*/                                      \
    r0 = vec_mergeh(r0, r8);    /*0, 8*/                       \
    r1 = vec_mergeh(r1, r9);    /*1, 9*/                       \
    r2 = vec_mergeh(r2, r10);   /*2,10*/                       \
    r3 = vec_mergeh(r3, r11);   /*3,11*/                       \
    r4 = vec_mergeh(r4, r12);   /*4,12*/                       \
    r5 = vec_mergeh(r5, r13);   /*5,13*/                       \
    r6 = vec_mergeh(r6, r14);   /*6,14*/                       \
    r7 = vec_mergeh(r7, r15);   /*7,15*/                       \
                                                               \
    /*Merge second pairs*/                                     \
    r8  = vec_mergeh(r0, r4);   /*0,4, 8,12 set 0*/            \
    r9  = vec_mergel(r0, r4);   /*0,4, 8,12 set 1*/            \
    r10 = vec_mergeh(r1, r5);   /*1,5, 9,13 set 0*/            \
    r11 = vec_mergel(r1, r5);   /*1,5, 9,13 set 1*/            \
    r12 = vec_mergeh(r2, r6);   /*2,6,10,14 set 0*/            \
    r13 = vec_mergel(r2, r6);   /*2,6,10,14 set 1*/            \
    r14 = vec_mergeh(r3, r7);   /*3,7,11,15 set 0*/            \
    r15 = vec_mergel(r3, r7);   /*3,7,11,15 set 1*/            \
                                                               \
    /*Third merge*/                                            \
    r0 = vec_mergeh(r8, r12);   /*0,2,4,6,8,10,12,14 set 0*/   \
    r1 = vec_mergel(r8, r12);   /*0,2,4,6,8,10,12,14 set 1*/   \
    r2 = vec_mergeh(r9, r13);   /*0,2,4,6,8,10,12,14 set 2*/   \
    r4 = vec_mergeh(r10, r14);  /*1,3,5,7,9,11,13,15 set 0*/   \
    r5 = vec_mergel(r10, r14);  /*1,3,5,7,9,11,13,15 set 1*/   \
    r6 = vec_mergeh(r11, r15);  /*1,3,5,7,9,11,13,15 set 2*/   \
    /* Don't need to compute 3 and 7*/                         \
                                                               \
    /*Final merge*/                                            \
    r8  = vec_mergeh(r0, r4);   /*all set 0*/                  \
    r9  = vec_mergel(r0, r4);   /*all set 1*/                  \
    r10 = vec_mergeh(r1, r5);   /*all set 2*/                  \
    r11 = vec_mergel(r1, r5);   /*all set 3*/                  \
    r12 = vec_mergeh(r2, r6);   /*all set 4*/                  \
    r13 = vec_mergel(r2, r6);   /*all set 5*/                  \
    /* Don't need to compute 14 and 15*/                       \
                                                               \
}

// out: o = |x-y| < a
static inline vec_u8_t diff_lt_altivec ( register vec_u8_t x,
                                         register vec_u8_t y,
                                         register vec_u8_t a) {

    register vec_u8_t diff = vec_subs(x, y);
    register vec_u8_t diffneg = vec_subs(y, x);
    register vec_u8_t o = vec_or(diff, diffneg); /* |x-y| */
    o = (vec_u8_t)vec_cmplt(o, a);
    return o;
}

static inline vec_u8_t h264_deblock_mask ( register vec_u8_t p0,
                                           register vec_u8_t p1,
                                           register vec_u8_t q0,
                                           register vec_u8_t q1,
                                           register vec_u8_t alpha,
                                           register vec_u8_t beta) {