10333     __m128i sh0, sh1;  variable
10341     sh1 = _mm_shuffle_epi8(val2, *(__m128i*)mask4_8);
10342     val0 = _mm_unpacklo_epi32(sh0,sh1); //0,4,8,12,16,20,24,28, 1,5,9,13,17,21,25,29
10344     val2 = _mm_unpackhi_epi32(sh0,sh1); //2,6,10,14,18,22,26,30, 3,7,11,15,19,23,27,31
10353     __m128i sh0, sh1;  variable
10359     sh1 = _mm_shuffle_epi8(val2, *(__m128i*)mask4_16);
10360     val0 = _mm_unpacklo_epi32(sh0,sh1); //0,4,8,12, 1,5,9,13
10362     val2 = _mm_unpackhi_epi32(sh0,sh1); //2,6,10,14, 3,7,11,15
11333     __m128i tmp, sh0, sh1, val0, val2;  variable
11341     sh1 =  _mm_shuffle_epi8(val2, *(__m128i*)mask0);
11342     val0 = _MM_BLENDV_EPI8(sh0, sh1, *(__m128i*)mask0_sel);
11345     sh1 =  _mm_shuffle_epi8(val2, *(__m128i*)mask1);
11346     val2 = _MM_BLENDV_EPI8(sh0, sh1, *(__m128i*)mask1_sel);
11534     __m128i sh0, sh1, val0, val2;  variable
11536 …sh1 = _mm_unpacklo_epi8(_pM128i(val.val[2]),_pM128i(val.val[3])); // c0,d0,c1,d1,c2,d2,c3,d3, c4,d…
11537     val0 = _mm_unpacklo_epi16(sh0,sh1); // a0,b0,c0,d0,a1,b1,c1,d1,a2,b2,c2,d2,a3,b3,c3,d3,
11538     val2 = _mm_unpackhi_epi16(sh0,sh1); //a4,b4,c4,d4,a5,b5,c5,d5, a6,b6,c6,d6,a7,b7,c7,d7
11546     __m128i sh0, sh1, val0, val2;  variable
11548     sh1 = _mm_unpacklo_epi16(_pM128i(val.val[2]),_pM128i(val.val[3])); //a2,a3,b2,b3,c2,c3,d2,d3
11549     val0 = _mm_unpacklo_epi32(sh0,sh1); // a0,a1,a2,a3,b0,b1,b2,b3
11550     val2 = _mm_unpackhi_epi32(sh0,sh1); // c0,c1,c2,c3,d0,d1,d2,d3
11559     __m128i sh0, sh1, val0, val1;  variable
11561     sh1 = _mm_unpacklo_epi32(_pM128i(val.val[2]), _pM128i(val.val[3])); //2,3,6,7
11562     val0 = _mm_unpacklo_epi64(sh0,sh1); //
11563     val1 = _mm_unpackhi_epi64(sh0,sh1); //
13141     __m128i c15, c23, maskgt23, bmask, maskgt15, sh0, sh1, a01, b128;  in vtbl3_u8()  local
13150     sh1 =  _mm_shuffle_epi8(_pM128i(a.val[2]), bmask); //for bi>15 bi is wrapped (bi-=15)  in vtbl3_u8()
13151     sh0 = _MM_BLENDV_EPI8(sh0, sh1, maskgt15); //SSE4.1  in vtbl3_u8()
13166     __m128i c15, c31, maskgt31, bmask, maskgt15, sh0, sh1, a01, a23, b128;  in vtbl4_u8()  local
13176     sh1 =  _mm_shuffle_epi8(a23, bmask); //for bi>15 bi is wrapped (bi-=15)  in vtbl4_u8()
13177     sh0 = _MM_BLENDV_EPI8 (sh0, sh1, maskgt15); //SSE4.1  in vtbl4_u8()
13240     __m128i c15, c23, maskgt15, maskgt23, sh0, sh1, b01, c128;  in vtbx3_u8()  local
13249     sh1 =  _mm_shuffle_epi8(_pM128i(b.val[2]), c128); //for bi>15 bi is wrapped (bi-=15)  in vtbx3_u8()
13250     sh0 = _MM_BLENDV_EPI8(sh0, sh1, maskgt15);  in vtbx3_u8()
13267     __m128i c15, c31, maskgt15, maskgt31, sh0, sh1, b01, b23, c128;  in vtbx4_u8()  local
13278     sh1 =  _mm_shuffle_epi8(b23, c128); //for bi>15 bi is wrapped (bi-=15)  in vtbx4_u8()
13279     sh0 = _MM_BLENDV_EPI8(sh0, sh1, maskgt15);  in vtbx4_u8()