Welcome to ShenZhenJia Knowledge Sharing Community for programmer and developer-Open, Learning and Share
menu search
person
Welcome To Ask or Share your Answers For Others

Categories

I deal with image processing. I need to divide 16-bit integer SSE vector by 255.

I can't use shift operator like _mm_srli_epi16(), because 255 is not a multiple of power of 2.

I know of course that it is possible convert integer to float, perform division and then back conversion to integer.

But might somebody knows another solution...

See Question&Answers more detail:os

与恶龙缠斗过久,自身亦成为恶龙;凝视深渊过久,深渊将回以凝视…
thumb_up_alt 0 like thumb_down_alt 0 dislike
337 views
Welcome To Ask or Share your Answers For Others

1 Answer

There is an integer approximation of division by 255:

inline int DivideBy255(int value)
{
    return (value + 1 + (value >> 8)) >> 8;
}

So with using of SSE2 it will look like:

inline __m128i DivideI16By255(__m128i value)
{
    return _mm_srli_epi16(_mm_add_epi16(
        _mm_add_epi16(value, _mm_set1_epi16(1)), _mm_srli_epi16(value, 8)), 8);
}

For AVX2:

inline __m256i DivideI16By255(__m256i value)
{
    return _mm256_srli_epi16(_mm256_add_epi16(
        _mm256_add_epi16(value, _mm256_set1_epi16(1)), _mm256_srli_epi16(value, 8)), 8);
}

For Altivec (Power):

typedef __vector int16_t v128_s16;
const v128_s16 K16_0001 = {1, 1, 1, 1, 1, 1, 1, 1};
const v128_s16 K16_0008 = {8, 8, 8, 8, 8, 8, 8, 8};

inline v128_s16 DivideBy255(v128_s16 value)
{
    return vec_sr(vec_add(vec_add(value, K16_0001), vec_sr(value, K16_0008)), K16_0008);
}

For NEON (ARM):

inline int16x8_t DivideI16By255(int16x8_t value)
{
    return vshrq_n_s16(vaddq_s16(
        vaddq_s16(value, vdupq_n_s16(1)), vshrq_n_s16(value, 8)), 8);
}

与恶龙缠斗过久,自身亦成为恶龙;凝视深渊过久,深渊将回以凝视…
thumb_up_alt 0 like thumb_down_alt 0 dislike
Welcome to ShenZhenJia Knowledge Sharing Community for programmer and developer-Open, Learning and Share
...