comparison dsputil.c @ 7564:7cf793954871 libavcodec

simd int->float 20% faster ac3 if downmixing, 15% if not

7563:8390efaa0c03

        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){
        tmp = (0x43c0ffff - tmp)>>31;
        // is this faster on some gcc/cpu combinations?

#endif
    c->vector_fmul = vector_fmul_c;
    c->vector_fmul_reverse = vector_fmul_reverse_c;
    c->vector_fmul_add_add = ff_vector_fmul_add_add_c;
    c->vector_fmul_window = ff_vector_fmul_window_c;
    c->float_to_int16 = ff_float_to_int16_c;
    c->float_to_int16_interleave = ff_float_to_int16_interleave_c;
    c->add_int16 = add_int16_c;
    c->sub_int16 = sub_int16_c;
    c->scalarproduct_int16 = scalarproduct_int16_c;

7564:7cf793954871

        dst[i] = s0*wj - s1*wi + add_bias;
        dst[j] = s0*wi + s1*wj + add_bias;
    }
}

static void int32_to_float_fmul_scalar_c(float *dst, const int *src, float mul, int len){
    int i;
    for(i=0; i<len; i++)
        dst[i] = src[i] * mul;
}

static av_always_inline int float_to_int16_one(const float *src){
    int_fast32_t tmp = *(const int32_t*)src;
    if(tmp & 0xf0000){
        tmp = (0x43c0ffff - tmp)>>31;
        // is this faster on some gcc/cpu combinations?

#endif
    c->vector_fmul = vector_fmul_c;
    c->vector_fmul_reverse = vector_fmul_reverse_c;
    c->vector_fmul_add_add = ff_vector_fmul_add_add_c;
    c->vector_fmul_window = ff_vector_fmul_window_c;
    c->int32_to_float_fmul_scalar = int32_to_float_fmul_scalar_c;
    c->float_to_int16 = ff_float_to_int16_c;
    c->float_to_int16_interleave = ff_float_to_int16_interleave_c;
    c->add_int16 = add_int16_c;
    c->sub_int16 = sub_int16_c;
    c->scalarproduct_int16 = scalarproduct_int16_c;