- __m512i permute_idx = _mm512_set_epi8(7, 6, 5, 4, 7, 6, 5, 4,
- 6, 5, 4, 3, 6, 5, 4, 3,
- 5, 4, 3, 2, 5, 4, 3, 2,
- 4, 3, 2, 1, 4, 3, 2, 1,
- 3, 2, 1, 0, 3, 2, 1, 0,
- 2, 1, 0, -1, 2, 1, 0, -1,
- 1, 0, -1, -2, 1, 0, -1, -2,
- 0, -1, -2, -3, 0, -1, -2, -3);
-
- const __m512i rewind_idx = _mm512_set_epi8(0, 0, 0, 0, 0, 0, 0, 0,
- 0, 0, 0, 0, 0, 0, 0, 0,
- 0, 0, 0, 0, 0, 0, 0, 0,
- 0, 0, 0, 0, 0, 0, 0, 0,
- 0, 0, 0, 0, 0, 0, 0, 0,
- 0, 0, 0, 59, 0, 0, 0, 59,
- 0, 0, 59, 58, 0, 0, 59, 58,
- 0, 59, 58, 57, 0, 59, 58, 57);
+ __m512i permute_idx = _mm512_set_epi32(0x07060504, 0x07060504,
+ 0x06050403, 0x06050403,
+ 0x05040302, 0x05040302,
+ 0x04030201, 0x04030201,
+ 0x03020100, 0x03020100,
+ 0x020100FF, 0x020100FF,
+ 0x0100FFFE, 0x0100FFFE,
+ 0x00FFFEFD, 0x00FFFEFD);
+ const __m512i rewind_idx = _mm512_set_epi32(0x00000000, 0x00000000,
+ 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000,
+ 0x00000000, 0x00000000,
+ 0x0000003B, 0x0000003B,
+ 0x00003B3A, 0x00003B3A,
+ 0x003B3A39, 0x003B3A39);