#if defined IS_AMD || defined IS_GENERIC
switch (offset)
{
- case 0:
- dst0[0] = src_r0[0];
- dst0[1] = src_r0[1];
- dst0[2] = src_r0[2];
- dst0[3] = src_r0[3];
- dst1[0] = src_r1[0];
- dst1[1] = src_r1[1];
- dst1[2] = src_r1[2];
- dst1[3] = src_r1[3];
- break;
-
- case 1:
- dst0[0] = src_l0[0]
- | src_r0[0] << 8;
- dst0[1] = amd_bytealign (src_r0[1], src_r0[0], 3);
- dst0[2] = amd_bytealign (src_r0[2], src_r0[1], 3);
- dst0[3] = amd_bytealign (src_r0[3], src_r0[2], 3);
- dst1[0] = amd_bytealign (src_r1[0], src_r0[3], 3);
- dst1[1] = amd_bytealign (src_r1[1], src_r1[0], 3);
- dst1[2] = amd_bytealign (src_r1[2], src_r1[1], 3);
- dst1[3] = amd_bytealign (src_r1[3], src_r1[2], 3);
+ case 31:
+ dst1[3] = src_l1[3] | src_r0[0] << 24;
break;
-
- case 2:
- dst0[0] = src_l0[0]
- | src_r0[0] << 16;
- dst0[1] = amd_bytealign (src_r0[1], src_r0[0], 2);
- dst0[2] = amd_bytealign (src_r0[2], src_r0[1], 2);
- dst0[3] = amd_bytealign (src_r0[3], src_r0[2], 2);
- dst1[0] = amd_bytealign (src_r1[0], src_r0[3], 2);
- dst1[1] = amd_bytealign (src_r1[1], src_r1[0], 2);
- dst1[2] = amd_bytealign (src_r1[2], src_r1[1], 2);
- dst1[3] = amd_bytealign (src_r1[3], src_r1[2], 2);
+ case 30:
+ dst1[3] = src_l1[3] | src_r0[0] << 16;
break;
-
- case 3:
- dst0[0] = src_l0[0]
- | src_r0[0] << 24;
- dst0[1] = amd_bytealign (src_r0[1], src_r0[0], 1);
- dst0[2] = amd_bytealign (src_r0[2], src_r0[1], 1);
- dst0[3] = amd_bytealign (src_r0[3], src_r0[2], 1);
- dst1[0] = amd_bytealign (src_r1[0], src_r0[3], 1);
- dst1[1] = amd_bytealign (src_r1[1], src_r1[0], 1);
- dst1[2] = amd_bytealign (src_r1[2], src_r1[1], 1);
- dst1[3] = amd_bytealign (src_r1[3], src_r1[2], 1);
+ case 29:
+ dst1[3] = src_l1[3] | src_r0[0] << 8;
break;
-
- case 4:
- dst0[1] = src_r0[0];
- dst0[2] = src_r0[1];
- dst0[3] = src_r0[2];
- dst1[0] = src_r0[3];
- dst1[1] = src_r1[0];
- dst1[2] = src_r1[1];
- dst1[3] = src_r1[2];
+ case 28:
+ dst1[3] = src_r0[0];
break;
-
- case 5:
- dst0[1] = src_l0[1]
- | src_r0[0] << 8;
- dst0[2] = amd_bytealign (src_r0[1], src_r0[0], 3);
- dst0[3] = amd_bytealign (src_r0[2], src_r0[1], 3);
- dst1[0] = amd_bytealign (src_r0[3], src_r0[2], 3);
- dst1[1] = amd_bytealign (src_r1[0], src_r0[3], 3);
- dst1[2] = amd_bytealign (src_r1[1], src_r1[0], 3);
- dst1[3] = amd_bytealign (src_r1[2], src_r1[1], 3);
+ case 27:
+ dst1[3] = amd_bytealign (src_r0[1], src_r0[0], 1);
+ dst1[2] = src_l1[2] | src_r0[0] << 24;
break;
-
- case 6:
- dst0[1] = src_l0[1]
- | src_r0[0] << 16;
- dst0[2] = amd_bytealign (src_r0[1], src_r0[0], 2);
- dst0[3] = amd_bytealign (src_r0[2], src_r0[1], 2);
- dst1[0] = amd_bytealign (src_r0[3], src_r0[2], 2);
- dst1[1] = amd_bytealign (src_r1[0], src_r0[3], 2);
- dst1[2] = amd_bytealign (src_r1[1], src_r1[0], 2);
- dst1[3] = amd_bytealign (src_r1[2], src_r1[1], 2);
+ case 26:
+ dst1[3] = amd_bytealign (src_r0[1], src_r0[0], 2);
+ dst1[2] = src_l1[2] | src_r0[0] << 16;
break;
-
- case 7:
- dst0[1] = src_l0[1]
- | src_r0[0] << 24;
- dst0[2] = amd_bytealign (src_r0[1], src_r0[0], 1);
- dst0[3] = amd_bytealign (src_r0[2], src_r0[1], 1);
- dst1[0] = amd_bytealign (src_r0[3], src_r0[2], 1);
- dst1[1] = amd_bytealign (src_r1[0], src_r0[3], 1);
- dst1[2] = amd_bytealign (src_r1[1], src_r1[0], 1);
- dst1[3] = amd_bytealign (src_r1[2], src_r1[1], 1);
+ case 25:
+ dst1[3] = amd_bytealign (src_r0[1], src_r0[0], 3);
+ dst1[2] = src_l1[2] | src_r0[0] << 8;
break;
-
- case 8:
- dst0[2] = src_r0[0];
- dst0[3] = src_r0[1];
- dst1[0] = src_r0[2];
- dst1[1] = src_r0[3];
- dst1[2] = src_r1[0];
- dst1[3] = src_r1[1];
+ case 24:
+ dst1[3] = src_r0[1];
+ dst1[2] = src_r0[0];
break;
-
- case 9:
- dst0[2] = src_l0[2]
- | src_r0[0] << 8;
- dst0[3] = amd_bytealign (src_r0[1], src_r0[0], 3);
- dst1[0] = amd_bytealign (src_r0[2], src_r0[1], 3);
- dst1[1] = amd_bytealign (src_r0[3], src_r0[2], 3);
- dst1[2] = amd_bytealign (src_r1[0], src_r0[3], 3);
- dst1[3] = amd_bytealign (src_r1[1], src_r1[0], 3);
+ case 23:
+ dst1[3] = amd_bytealign (src_r0[2], src_r0[1], 1);
+ dst1[2] = amd_bytealign (src_r0[1], src_r0[0], 1);
+ dst1[1] = src_l1[1] | src_r0[0] << 24;
break;
-
- case 10:
- dst0[2] = src_l0[2]
- | src_r0[0] << 16;
- dst0[3] = amd_bytealign (src_r0[1], src_r0[0], 2);
- dst1[0] = amd_bytealign (src_r0[2], src_r0[1], 2);
- dst1[1] = amd_bytealign (src_r0[3], src_r0[2], 2);
- dst1[2] = amd_bytealign (src_r1[0], src_r0[3], 2);
- dst1[3] = amd_bytealign (src_r1[1], src_r1[0], 2);
+ case 22:
+ dst1[3] = amd_bytealign (src_r0[2], src_r0[1], 2);
+ dst1[2] = amd_bytealign (src_r0[1], src_r0[0], 2);
+ dst1[1] = src_l1[1] | src_r0[0] << 16;
break;
-
- case 11:
- dst0[2] = src_l0[2]
- | src_r0[0] << 24;
- dst0[3] = amd_bytealign (src_r0[1], src_r0[0], 1);
- dst1[0] = amd_bytealign (src_r0[2], src_r0[1], 1);
- dst1[1] = amd_bytealign (src_r0[3], src_r0[2], 1);
- dst1[2] = amd_bytealign (src_r1[0], src_r0[3], 1);
- dst1[3] = amd_bytealign (src_r1[1], src_r1[0], 1);
+ case 21:
+ dst1[3] = amd_bytealign (src_r0[2], src_r0[1], 3);
+ dst1[2] = amd_bytealign (src_r0[1], src_r0[0], 3);
+ dst1[1] = src_l1[1] | src_r0[0] << 8;
break;
-
- case 12:
- dst0[3] = src_r0[0];
- dst1[0] = src_r0[1];
- dst1[1] = src_r0[2];
- dst1[2] = src_r0[3];
- dst1[3] = src_r1[0];
+ case 20:
+ dst1[3] = src_r0[2];
+ dst1[2] = src_r0[1];
+ dst1[1] = src_r0[0];
break;
-
- case 13:
- dst0[3] = src_l0[3]
- | src_r0[0] << 8;
- dst1[0] = amd_bytealign (src_r0[1], src_r0[0], 3);
- dst1[1] = amd_bytealign (src_r0[2], src_r0[1], 3);
- dst1[2] = amd_bytealign (src_r0[3], src_r0[2], 3);
- dst1[3] = amd_bytealign (src_r1[0], src_r0[3], 3);
+ case 19:
+ dst1[3] = amd_bytealign (src_r0[3], src_r0[2], 1);
+ dst1[2] = amd_bytealign (src_r0[2], src_r0[1], 1);
+ dst1[1] = amd_bytealign (src_r0[1], src_r0[0], 1);
+ dst1[0] = src_l1[0] | src_r0[0] << 24;
break;
-
- case 14:
- dst0[3] = src_l0[3]
- | src_r0[0] << 16;
- dst1[0] = amd_bytealign (src_r0[1], src_r0[0], 2);
- dst1[1] = amd_bytealign (src_r0[2], src_r0[1], 2);
- dst1[2] = amd_bytealign (src_r0[3], src_r0[2], 2);
- dst1[3] = amd_bytealign (src_r1[0], src_r0[3], 2);
+ case 18:
+ dst1[3] = amd_bytealign (src_r0[3], src_r0[2], 2);
+ dst1[2] = amd_bytealign (src_r0[2], src_r0[1], 2);
+ dst1[1] = amd_bytealign (src_r0[1], src_r0[0], 2);
+ dst1[0] = src_l1[0] | src_r0[0] << 16;
break;
-
- case 15:
- dst0[3] = src_l0[3]
- | src_r0[0] << 24;
- dst1[0] = amd_bytealign (src_r0[1], src_r0[0], 1);
- dst1[1] = amd_bytealign (src_r0[2], src_r0[1], 1);
- dst1[2] = amd_bytealign (src_r0[3], src_r0[2], 1);
- dst1[3] = amd_bytealign (src_r1[0], src_r0[3], 1);
+ case 17:
+ dst1[3] = amd_bytealign (src_r0[3], src_r0[2], 3);
+ dst1[2] = amd_bytealign (src_r0[2], src_r0[1], 3);
+ dst1[1] = amd_bytealign (src_r0[1], src_r0[0], 3);
+ dst1[0] = src_l1[0] | src_r0[0] << 8;
break;
-
case 16:
- dst1[0] = src_r0[0];
- dst1[1] = src_r0[1];
- dst1[2] = src_r0[2];
dst1[3] = src_r0[3];
+ dst1[2] = src_r0[2];
+ dst1[1] = src_r0[1];
+ dst1[0] = src_r0[0];
break;
-
- case 17:
- dst1[0] = src_l1[0]
- | src_r0[0] << 8;
- dst1[1] = amd_bytealign (src_r0[1], src_r0[0], 3);
- dst1[2] = amd_bytealign (src_r0[2], src_r0[1], 3);
- dst1[3] = amd_bytealign (src_r0[3], src_r0[2], 3);
+ case 15:
+ dst1[3] = amd_bytealign (src_r1[0], src_r0[3], 1);
+ dst1[2] = amd_bytealign (src_r0[3], src_r0[2], 1);
+ dst1[1] = amd_bytealign (src_r0[2], src_r0[1], 1);
+ dst1[0] = amd_bytealign (src_r0[1], src_r0[0], 1);
+ dst0[3] = src_l0[3] | src_r0[0] << 24;
break;
-
- case 18:
- dst1[0] = src_l1[0]
- | src_r0[0] << 16;
- dst1[1] = amd_bytealign (src_r0[1], src_r0[0], 2);
- dst1[2] = amd_bytealign (src_r0[2], src_r0[1], 2);
- dst1[3] = amd_bytealign (src_r0[3], src_r0[2], 2);
+ case 14:
+ dst1[3] = amd_bytealign (src_r1[0], src_r0[3], 2);
+ dst1[2] = amd_bytealign (src_r0[3], src_r0[2], 2);
+ dst1[1] = amd_bytealign (src_r0[2], src_r0[1], 2);
+ dst1[0] = amd_bytealign (src_r0[1], src_r0[0], 2);
+ dst0[3] = src_l0[3] | src_r0[0] << 16;
break;
-
- case 19:
- dst1[0] = src_l1[0]
- | src_r0[0] << 24;
- dst1[1] = amd_bytealign (src_r0[1], src_r0[0], 1);
- dst1[2] = amd_bytealign (src_r0[2], src_r0[1], 1);
- dst1[3] = amd_bytealign (src_r0[3], src_r0[2], 1);
+ case 13:
+ dst1[3] = amd_bytealign (src_r1[0], src_r0[3], 3);
+ dst1[2] = amd_bytealign (src_r0[3], src_r0[2], 3);
+ dst1[1] = amd_bytealign (src_r0[2], src_r0[1], 3);
+ dst1[0] = amd_bytealign (src_r0[1], src_r0[0], 3);
+ dst0[3] = src_l0[3] | src_r0[0] << 8;
break;
-
- case 20:
- dst1[1] = src_r0[0];
- dst1[2] = src_r0[1];
- dst1[3] = src_r0[2];
+ case 12:
+ dst1[3] = src_r1[0];
+ dst1[2] = src_r0[3];
+ dst1[1] = src_r0[2];
+ dst1[0] = src_r0[1];
+ dst0[3] = src_r0[0];
break;
-
- case 21:
- dst1[1] = src_l1[1]
- | src_r0[0] << 8;
- dst1[2] = amd_bytealign (src_r0[1], src_r0[0], 3);
- dst1[3] = amd_bytealign (src_r0[2], src_r0[1], 3);
+ case 11:
+ dst1[3] = amd_bytealign (src_r1[1], src_r1[0], 1);
+ dst1[2] = amd_bytealign (src_r1[0], src_r0[3], 1);
+ dst1[1] = amd_bytealign (src_r0[3], src_r0[2], 1);
+ dst1[0] = amd_bytealign (src_r0[2], src_r0[1], 1);
+ dst0[3] = amd_bytealign (src_r0[1], src_r0[0], 1);
+ dst0[2] = src_l0[2] | src_r0[0] << 24;
break;
-
- case 22:
- dst1[1] = src_l1[1]
- | src_r0[0] << 16;
- dst1[2] = amd_bytealign (src_r0[1], src_r0[0], 2);
- dst1[3] = amd_bytealign (src_r0[2], src_r0[1], 2);
+ case 10:
+ dst1[3] = amd_bytealign (src_r1[1], src_r1[0], 2);
+ dst1[2] = amd_bytealign (src_r1[0], src_r0[3], 2);
+ dst1[1] = amd_bytealign (src_r0[3], src_r0[2], 2);
+ dst1[0] = amd_bytealign (src_r0[2], src_r0[1], 2);
+ dst0[3] = amd_bytealign (src_r0[1], src_r0[0], 2);
+ dst0[2] = src_l0[2] | src_r0[0] << 16;
break;
-
- case 23:
- dst1[1] = src_l1[1]
- | src_r0[0] << 24;
- dst1[2] = amd_bytealign (src_r0[1], src_r0[0], 1);
- dst1[3] = amd_bytealign (src_r0[2], src_r0[1], 1);
+ case 9:
+ dst1[3] = amd_bytealign (src_r1[1], src_r1[0], 3);
+ dst1[2] = amd_bytealign (src_r1[0], src_r0[3], 3);
+ dst1[1] = amd_bytealign (src_r0[3], src_r0[2], 3);
+ dst1[0] = amd_bytealign (src_r0[2], src_r0[1], 3);
+ dst0[3] = amd_bytealign (src_r0[1], src_r0[0], 3);
+ dst0[2] = src_l0[2] | src_r0[0] << 8;
break;
-
- case 24:
- dst1[2] = src_r0[0];
- dst1[3] = src_r0[1];
+ case 8:
+ dst1[3] = src_r1[1];
+ dst1[2] = src_r1[0];
+ dst1[1] = src_r0[3];
+ dst1[0] = src_r0[2];
+ dst0[3] = src_r0[1];
+ dst0[2] = src_r0[0];
break;
-
- case 25:
- dst1[2] = src_l1[2]
- | src_r0[0] << 8;
- dst1[3] = amd_bytealign (src_r0[1], src_r0[0], 3);
+ case 7:
+ dst1[3] = amd_bytealign (src_r1[2], src_r1[1], 1);
+ dst1[2] = amd_bytealign (src_r1[1], src_r1[0], 1);
+ dst1[1] = amd_bytealign (src_r1[0], src_r0[3], 1);
+ dst1[0] = amd_bytealign (src_r0[3], src_r0[2], 1);
+ dst0[3] = amd_bytealign (src_r0[2], src_r0[1], 1);
+ dst0[2] = amd_bytealign (src_r0[1], src_r0[0], 1);
+ dst0[1] = src_l0[1] | src_r0[0] << 24;
break;
-
- case 26:
- dst1[2] = src_l1[2]
- | src_r0[0] << 16;
- dst1[3] = amd_bytealign (src_r0[1], src_r0[0], 2);
+ case 6:
+ dst1[3] = amd_bytealign (src_r1[2], src_r1[1], 2);
+ dst1[2] = amd_bytealign (src_r1[1], src_r1[0], 2);
+ dst1[1] = amd_bytealign (src_r1[0], src_r0[3], 2);
+ dst1[0] = amd_bytealign (src_r0[3], src_r0[2], 2);
+ dst0[3] = amd_bytealign (src_r0[2], src_r0[1], 2);
+ dst0[2] = amd_bytealign (src_r0[1], src_r0[0], 2);
+ dst0[1] = src_l0[1] | src_r0[0] << 16;
break;
-
- case 27:
- dst1[2] = src_l1[2]
- | src_r0[0] << 24;
- dst1[3] = amd_bytealign (src_r0[1], src_r0[0], 1);
+ case 5:
+ dst1[3] = amd_bytealign (src_r1[2], src_r1[1], 3);
+ dst1[2] = amd_bytealign (src_r1[1], src_r1[0], 3);
+ dst1[1] = amd_bytealign (src_r1[0], src_r0[3], 3);
+ dst1[0] = amd_bytealign (src_r0[3], src_r0[2], 3);
+ dst0[3] = amd_bytealign (src_r0[2], src_r0[1], 3);
+ dst0[2] = amd_bytealign (src_r0[1], src_r0[0], 3);
+ dst0[1] = src_l0[1] | src_r0[0] << 8;
break;
-
- case 28:
- dst1[3] = src_r0[0];
+ case 4:
+ dst1[3] = src_r1[2];
+ dst1[2] = src_r1[1];
+ dst1[1] = src_r1[0];
+ dst1[0] = src_r0[3];
+ dst0[3] = src_r0[2];
+ dst0[2] = src_r0[1];
+ dst0[1] = src_r0[0];
break;
-
- case 29:
- dst1[3] = src_l1[3]
- | src_r0[0] << 8;
+ case 3:
+ dst1[3] = amd_bytealign (src_r1[3], src_r1[2], 1);
+ dst1[2] = amd_bytealign (src_r1[2], src_r1[1], 1);
+ dst1[1] = amd_bytealign (src_r1[1], src_r1[0], 1);
+ dst1[0] = amd_bytealign (src_r1[0], src_r0[3], 1);
+ dst0[3] = amd_bytealign (src_r0[3], src_r0[2], 1);
+ dst0[2] = amd_bytealign (src_r0[2], src_r0[1], 1);
+ dst0[1] = amd_bytealign (src_r0[1], src_r0[0], 1);
+ dst0[0] = src_l0[0] | src_r0[0] << 24;
break;
-
- case 30:
- dst1[3] = src_l1[3]
- | src_r0[0] << 16;
+ case 2:
+ dst1[3] = amd_bytealign (src_r1[3], src_r1[2], 2);
+ dst1[2] = amd_bytealign (src_r1[2], src_r1[1], 2);
+ dst1[1] = amd_bytealign (src_r1[1], src_r1[0], 2);
+ dst1[0] = amd_bytealign (src_r1[0], src_r0[3], 2);
+ dst0[3] = amd_bytealign (src_r0[3], src_r0[2], 2);
+ dst0[2] = amd_bytealign (src_r0[2], src_r0[1], 2);
+ dst0[1] = amd_bytealign (src_r0[1], src_r0[0], 2);
+ dst0[0] = src_l0[0] | src_r0[0] << 16;
break;
-
- case 31:
- dst1[3] = src_l1[3]
- | src_r0[0] << 24;
+ case 1:
+ dst1[3] = amd_bytealign (src_r1[3], src_r1[2], 3);
+ dst1[2] = amd_bytealign (src_r1[2], src_r1[1], 3);
+ dst1[1] = amd_bytealign (src_r1[1], src_r1[0], 3);
+ dst1[0] = amd_bytealign (src_r1[0], src_r0[3], 3);
+ dst0[3] = amd_bytealign (src_r0[3], src_r0[2], 3);
+ dst0[2] = amd_bytealign (src_r0[2], src_r0[1], 3);
+ dst0[1] = amd_bytealign (src_r0[1], src_r0[0], 3);
+ dst0[0] = src_l0[0] | src_r0[0] << 8;
+ break;
+ case 0:
+ dst1[3] = src_r1[3];
+ dst1[2] = src_r1[2];
+ dst1[1] = src_r1[1];
+ dst1[0] = src_r1[0];
+ dst0[3] = src_r0[3];
+ dst0[2] = src_r0[2];
+ dst0[1] = src_r0[1];
+ dst0[0] = src_r0[0];
break;
}
#endif
u32 out_len = in_len;
- u32 tib40[4];
- u32 tib41[4];
-
- tib40[0] = buf0[0];
- tib40[1] = buf0[1];
- tib40[2] = buf0[2];
- tib40[3] = buf0[3];
- tib41[0] = buf1[0];
- tib41[1] = buf1[1];
- tib41[2] = buf1[2];
- tib41[3] = buf1[3];
-
- append_block8 (out_len, buf0, buf1, buf0, buf1, tib40, tib41);
+ append_block8 (out_len, buf0, buf1, buf0, buf1, buf0, buf1);
out_len += in_len;
return out_len;
}
-u32 apply_rules (__global u32 *cmds, u32 buf0[4], u32 buf1[4], const u32 len)
+u32 apply_rules (const __global u32 *cmds, u32 buf0[4], u32 buf1[4], const u32 len)
{
u32 out_len = len;
return out_len;
}
+
+u32 apply_rules_vect (const u32 pw_buf0[4], const u32 pw_buf1[4], const u32 pw_len, const __global kernel_rule_t *rules_buf, const u32 il_pos, u32x w0[4], u32x w1[4])
+{
+ #if VECT_SIZE == 1
+
+ w0[0] = pw_buf0[0];
+ w0[1] = pw_buf0[1];
+ w0[2] = pw_buf0[2];
+ w0[3] = pw_buf0[3];
+ w1[0] = pw_buf1[0];
+ w1[1] = pw_buf1[1];
+ w1[2] = pw_buf1[2];
+ w1[3] = pw_buf1[3];
+
+ return apply_rules (rules_buf[il_pos].cmds, w0, w1, pw_len);
+
+ #else
+
+ u32 out_len = 0;
+
+ #pragma unroll
+ for (int i = 0; i < VECT_SIZE; i++)
+ {
+ u32 tmp0[4];
+ u32 tmp1[4];
+
+ tmp0[0] = pw_buf0[0];
+ tmp0[1] = pw_buf0[1];
+ tmp0[2] = pw_buf0[2];
+ tmp0[3] = pw_buf0[3];
+ tmp1[0] = pw_buf1[0];
+ tmp1[1] = pw_buf1[1];
+ tmp1[2] = pw_buf1[2];
+ tmp1[3] = pw_buf1[3];
+
+ out_len = apply_rules (rules_buf[il_pos + i].cmds, tmp0, tmp1, pw_len);
+
+ // it's guaranteed to have out_len always the same for each call in the loop
+
+ switch (i)
+ {
+ #if VECT_SIZE >= 2
+ case 0:
+ w0[0].s0 = tmp0[0];
+ w0[1].s0 = tmp0[1];
+ w0[2].s0 = tmp0[2];
+ w0[3].s0 = tmp0[3];
+ w1[0].s0 = tmp1[0];
+ w1[1].s0 = tmp1[1];
+ w1[2].s0 = tmp1[2];
+ w1[3].s0 = tmp1[3];
+ break;
+
+ case 1:
+ w0[0].s1 = tmp0[0];
+ w0[1].s1 = tmp0[1];
+ w0[2].s1 = tmp0[2];
+ w0[3].s1 = tmp0[3];
+ w1[0].s1 = tmp1[0];
+ w1[1].s1 = tmp1[1];
+ w1[2].s1 = tmp1[2];
+ w1[3].s1 = tmp1[3];
+ break;
+ #endif
+
+ #if VECT_SIZE >= 4
+ case 2:
+ w0[0].s2 = tmp0[0];
+ w0[1].s2 = tmp0[1];
+ w0[2].s2 = tmp0[2];
+ w0[3].s2 = tmp0[3];
+ w1[0].s2 = tmp1[0];
+ w1[1].s2 = tmp1[1];
+ w1[2].s2 = tmp1[2];
+ w1[3].s2 = tmp1[3];
+ break;
+
+ case 3:
+ w0[0].s3 = tmp0[0];
+ w0[1].s3 = tmp0[1];
+ w0[2].s3 = tmp0[2];
+ w0[3].s3 = tmp0[3];
+ w1[0].s3 = tmp1[0];
+ w1[1].s3 = tmp1[1];
+ w1[2].s3 = tmp1[2];
+ w1[3].s3 = tmp1[3];
+ break;
+ #endif
+
+ #if VECT_SIZE >= 8
+ case 4:
+ w0[0].s4 = tmp0[0];
+ w0[1].s4 = tmp0[1];
+ w0[2].s4 = tmp0[2];
+ w0[3].s4 = tmp0[3];
+ w1[0].s4 = tmp1[0];
+ w1[1].s4 = tmp1[1];
+ w1[2].s4 = tmp1[2];
+ w1[3].s4 = tmp1[3];
+ break;
+
+ case 5:
+ w0[0].s5 = tmp0[0];
+ w0[1].s5 = tmp0[1];
+ w0[2].s5 = tmp0[2];
+ w0[3].s5 = tmp0[3];
+ w1[0].s5 = tmp1[0];
+ w1[1].s5 = tmp1[1];
+ w1[2].s5 = tmp1[2];
+ w1[3].s5 = tmp1[3];
+ break;
+
+ case 6:
+ w0[0].s6 = tmp0[0];
+ w0[1].s6 = tmp0[1];
+ w0[2].s6 = tmp0[2];
+ w0[3].s6 = tmp0[3];
+ w1[0].s6 = tmp1[0];
+ w1[1].s6 = tmp1[1];
+ w1[2].s6 = tmp1[2];
+ w1[3].s6 = tmp1[3];
+ break;
+
+ case 7:
+ w0[0].s7 = tmp0[0];
+ w0[1].s7 = tmp0[1];
+ w0[2].s7 = tmp0[2];
+ w0[3].s7 = tmp0[3];
+ w1[0].s7 = tmp1[0];
+ w1[1].s7 = tmp1[1];
+ w1[2].s7 = tmp1[2];
+ w1[3].s7 = tmp1[3];
+ break;
+ #endif
+ }
+ }
+
+ return out_len;
+
+ #endif
+}
projects / hashcat.git / blobdiff