Function npyv_divc_u8

numpy/core/src/common/simd/sse/arithmetic.h:93–109

* Integer Division ***************************/ See simd/intdiv.h for more clarification divide each unsigned 8-bit element by a precomputed divisor

// See simd/intdiv.h for more clarification
// divide each unsigned 8-bit element by a precomputed divisor
NPY_FINLINE npyv_u8 npyv_divc_u8(npyv_u8 a, const npyv_u8x3 divisor)
{
    const __m128i bmask = _mm_set1_epi32(0x00FF00FF);
    const __m128i shf1b = _mm_set1_epi8(0xFFU >> _mm_cvtsi128_si32(divisor.val[1]));
    const __m128i shf2b = _mm_set1_epi8(0xFFU >> _mm_cvtsi128_si32(divisor.val[2]));
    // high part of unsigned multiplication
    __m128i mulhi_even  = _mm_mullo_epi16(_mm_and_si128(a, bmask), divisor.val[0]);
    __m128i mulhi_odd   = _mm_mullo_epi16(_mm_srli_epi16(a, 8), divisor.val[0]);
            mulhi_even  = _mm_srli_epi16(mulhi_even, 8);
    __m128i mulhi       = npyv_select_u8(bmask, mulhi_even, mulhi_odd);
    // floor(a/d)       = (mulhi + ((a-mulhi) >> sh1)) >> sh2
    __m128i q           = _mm_sub_epi8(a, mulhi);
            q           = _mm_and_si128(_mm_srl_epi16(q, divisor.val[1]), shf1b);
            q           = _mm_add_epi8(mulhi, q);
            q           = _mm_and_si128(_mm_srl_epi16(q, divisor.val[2]), shf2b);
    return  q;
}
// divide each signed 8-bit element by a precomputed divisor (round towards zero)
NPY_FINLINE npyv_s16 npyv_divc_s16(npyv_s16 a, const npyv_s16x3 divisor);
NPY_FINLINE npyv_s8 npyv_divc_s8(npyv_s8 a, const npyv_s8x3 divisor)