comparison i386/snowdsp_mmx.c @ 3223:8f048c3295ff libavcodec

altivec support for snow

3222:38ee2f1d386d

 */

#include "../avcodec.h"
#include "../snow.h"
#include "mmx.h"

static void always_inline snow_interleave_line_header(int * i, int width, DWTELEM * low, DWTELEM * high){
    (*i) = (width) - 2;

    if (width & 1){
        low[(*i)+1] = low[((*i)+1)>>1];
        (*i)--;
    }
}

static void always_inline snow_horizontal_compose_lift_lead_out(int i, DWTELEM * dst, DWTELEM * src, DWTELEM * ref, int width, int w, int lift_high, int mul, int add, int shift){
    for(; i<w; i++){
        dst[i] = src[i] - ((mul * (ref[i] + ref[i + 1]) + add) >> shift);
    }

    if((width^lift_high)&1){
        dst[w] = src[w] - ((mul * 2 * ref[w] + add) >> shift);
    }
}

static void always_inline snow_horizontal_compose_liftS_lead_out(int i, DWTELEM * dst, DWTELEM * src, DWTELEM * ref, int width, int w){
        for(; i<w; i++){
            dst[i] = src[i] - (((-(ref[i] + ref[(i+1)])+W_BO) - 4 * src[i]) >> W_BS);
        }

        if(width&1){
            dst[w] = src[w] - (((-2 * ref[w] + W_BO) - 4 * src[w]) >> W_BS);
        }
}

void ff_snow_horizontal_compose97i_sse2(DWTELEM *b, int width){
    const int w2= (width+1)>>1;
    // SSE2 code runs faster with pointers aligned on a 32-byte boundary.
    DWTELEM temp_buf[(width>>1) + 4];

3223:8f048c3295ff

 */

#include "../avcodec.h"
#include "../snow.h"
#include "mmx.h"

void ff_snow_horizontal_compose97i_sse2(DWTELEM *b, int width){
    const int w2= (width+1)>>1;
    // SSE2 code runs faster with pointers aligned on a 32-byte boundary.
    DWTELEM temp_buf[(width>>1) + 4];