Re: une solution

et pour les plus assidus l'implémentation

#define SIMD_CHAR_AS_LONGLONG(a) (((long long)a) & 0xFF)
#define SIMD_LL_SETR_EPI8(a, b, c, d, e, f, g, h) \
 SIMD_CHAR_AS_LONGLONG(a) | (SIMD_CHAR_AS_LONGLONG(b) << 8) | \
 (SIMD_CHAR_AS_LONGLONG(c) << 16) | (SIMD_CHAR_AS_LONGLONG(d) << 24) | \
 (SIMD_CHAR_AS_LONGLONG(e) << 32) | (SIMD_CHAR_AS_LONGLONG(f) << 40) | \
 (SIMD_CHAR_AS_LONGLONG(g) << 48) | (SIMD_CHAR_AS_LONGLONG(h) << 56)
#define SIMD_MM_SETR_EPI8(a0, a1, a2, a3, a4, a5, a6, a7, a8, a9, aa, ab, ac, ad, ae, af) \
{SIMD_LL_SETR_EPI8(a0, a1, a2, a3, a4, a5, a6, a7), SIMD_LL_SETR_EPI8(a8, a9, aa, ab, ac, ad, ae, af)}
const __m128i FIRST_MASK = SIMD_MM_SETR_EPI8(0x0,0x2,0x4,0x6,0x8,0xA,0xC,0xE,-1,-1,-1,-1,-1,-1,-1,-1);
const __m128i SECOND_MASK = SIMD_MM_SETR_EPI8(-1,-1,-1,-1,-1,-1,-1,-1,0x0,0x2,0x4,0x6,0x8,0xA,0xC,0xE);
struct U122U8
{
 void operator()(const unsigned char* src, unsigned char* dst, int pixelsCount) const
 {
 const quint16 *pIn = reinterpret_cast<const quint16 *>(src);
#pragma omp parallel for schedule(static)
 for (int i=0; i< pixelsCount; i+=16) {
 // charge 8 pixels allignés
 // désature en shiftant à droite
 // réarrange les octets
 const __m128i first = _mm_shuffle_epi8 (
 _mm_srli_epi16(
 _mm_load_si128((const __m128i *)(pIn + i)), 4),
 FIRST_MASK);
 // même chose pour les 8 octets suivants
 const __m128i second = _mm_shuffle_epi8 (
 _mm_srli_epi16(
 _mm_load_si128((const __m128i *)(pIn + i + 8)), 4),
 SECOND_MASK);
 // bitwise OR
 _mm_storeu_si128((__m128i *)(dst + i), _mm_or_si128(first, second));
 }
 }
};