comparison dsputil.c @ 7263:fc843d00867c libavcodec

exploit mdct symmetry 2% faster vorbis on conroe, k8. 7% on celeron.

7262:e3822c61f2e4

    for(i=0; i<len; i++)
        dst[i*step] = src0[i] * src1[i] + src2[i] + src3;
}

void ff_vector_fmul_window_c(float *dst, const float *src0, const float *src1, const float *win, float add_bias, int len){
    int i;
    for(i=0; i<len; i++)
        dst[i] = src0[i]*win[len-i-1] + src1[i]*win[i] + add_bias;
}

static av_always_inline int float_to_int16_one(const float *src){
    int_fast32_t tmp = *(const int32_t*)src;
    if(tmp & 0xf0000){

7263:fc843d00867c

    for(i=0; i<len; i++)
        dst[i*step] = src0[i] * src1[i] + src2[i] + src3;
}

void ff_vector_fmul_window_c(float *dst, const float *src0, const float *src1, const float *win, float add_bias, int len){
    int i,j;
    dst += len;
    win += len;
    src0+= len;
    for(i=-len, j=len-1; i<0; i++, j--) {
        float s0 = src0[i];
        float s1 = src1[j];
        float wi = win[i];
        float wj = win[j];
        dst[i] = s0*wj - s1*wi + add_bias;
        dst[j] = s0*wi + s1*wj + add_bias;
    }
}

static av_always_inline int float_to_int16_one(const float *src){
    int_fast32_t tmp = *(const int32_t*)src;
    if(tmp & 0xf0000){