Function npyv_divc_s8

numpy/core/src/common/simd/avx2/arithmetic.h:95–103

// 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)
{
    const __m256i bmask = _mm256_set1_epi32(0x00FF00FF);
    // instead of _mm256_cvtepi8_epi16/_mm256_packs_epi16 to wrap around overflow
    __m256i divc_even = npyv_divc_s16(_mm256_srai_epi16(_mm256_slli_epi16(a, 8), 8), divisor);
    __m256i divc_odd  = npyv_divc_s16(_mm256_srai_epi16(a, 8), divisor);
            divc_odd  = _mm256_slli_epi16(divc_odd, 8);
    return _mm256_blendv_epi8(divc_odd, divc_even, bmask);
}
// divide each unsigned 16-bit element by a precomputed divisor
NPY_FINLINE npyv_u16 npyv_divc_u16(npyv_u16 a, const npyv_u16x3 divisor)
{