--- /dev/null
+/**
+ * Author......: Jens Steube <jens.steube@gmail.com>
+ * License.....: MIT
+ */
+
+#define _SHA1_
+
+//too much register pressure
+//#define NEW_SIMD_CODE
+
+#include "include/constants.h"
+#include "include/kernel_vendor.h"
+
+#define DGST_R0 3
+#define DGST_R1 4
+#define DGST_R2 2
+#define DGST_R3 1
+
+#include "include/kernel_functions.c"
+#include "OpenCL/types_ocl.c"
+#include "OpenCL/common.c"
+#include "include/rp_kernel.h"
+#include "OpenCL/rp.c"
+#include "OpenCL/simd.c"
+
+static void memcat64c_be (u32x block[16], const u32 offset, u32x carry[16])
+{
+ const u32 mod = offset & 3;
+ const u32 div = offset / 4;
+
+ u32 tmp00;
+ u32 tmp01;
+ u32 tmp02;
+ u32 tmp03;
+ u32 tmp04;
+ u32 tmp05;
+ u32 tmp06;
+ u32 tmp07;
+ u32 tmp08;
+ u32 tmp09;
+ u32 tmp10;
+ u32 tmp11;
+ u32 tmp12;
+ u32 tmp13;
+ u32 tmp14;
+ u32 tmp15;
+ u32 tmp16;
+
+ #ifdef IS_NV
+ const int selector = (0x76543210 >> ((offset & 3) * 4)) & 0xffff;
+
+ tmp00 = __byte_perm (carry[ 0], 0, selector);
+ tmp01 = __byte_perm (carry[ 1], carry[ 0], selector);
+ tmp02 = __byte_perm (carry[ 2], carry[ 1], selector);
+ tmp03 = __byte_perm (carry[ 3], carry[ 2], selector);
+ tmp04 = __byte_perm (carry[ 4], carry[ 3], selector);
+ tmp05 = __byte_perm (carry[ 5], carry[ 4], selector);
+ tmp06 = __byte_perm (carry[ 6], carry[ 5], selector);
+ tmp07 = __byte_perm (carry[ 7], carry[ 6], selector);
+ tmp08 = __byte_perm (carry[ 8], carry[ 7], selector);
+ tmp09 = __byte_perm (carry[ 9], carry[ 8], selector);
+ tmp10 = __byte_perm (carry[10], carry[ 9], selector);
+ tmp11 = __byte_perm (carry[11], carry[10], selector);
+ tmp12 = __byte_perm (carry[12], carry[11], selector);
+ tmp13 = __byte_perm (carry[13], carry[12], selector);
+ tmp14 = __byte_perm (carry[14], carry[13], selector);
+ tmp15 = __byte_perm (carry[15], carry[14], selector);
+ tmp17 = __byte_perm ( 0, carry[15], selector);
+ #endif
+
+ #if defined IS_AMD || defined IS_GENERIC
+ tmp00 = amd_bytealign ( 0, carry[ 0], offset);
+ tmp01 = amd_bytealign (carry[ 0], carry[ 1], offset);
+ tmp02 = amd_bytealign (carry[ 1], carry[ 2], offset);
+ tmp03 = amd_bytealign (carry[ 2], carry[ 3], offset);
+ tmp04 = amd_bytealign (carry[ 3], carry[ 4], offset);
+ tmp05 = amd_bytealign (carry[ 4], carry[ 5], offset);
+ tmp06 = amd_bytealign (carry[ 5], carry[ 6], offset);
+ tmp07 = amd_bytealign (carry[ 6], carry[ 7], offset);
+ tmp08 = amd_bytealign (carry[ 7], carry[ 8], offset);
+ tmp09 = amd_bytealign (carry[ 8], carry[ 9], offset);
+ tmp10 = amd_bytealign (carry[ 9], carry[10], offset);
+ tmp11 = amd_bytealign (carry[10], carry[11], offset);
+ tmp12 = amd_bytealign (carry[11], carry[12], offset);
+ tmp13 = amd_bytealign (carry[12], carry[13], offset);
+ tmp14 = amd_bytealign (carry[13], carry[14], offset);
+ tmp15 = amd_bytealign (carry[14], carry[15], offset);
+ tmp16 = amd_bytealign (carry[15], 0, offset);
+
+ if (mod == 0)
+ {
+ tmp00 = tmp01;
+ tmp01 = tmp02;
+ tmp02 = tmp03;
+ tmp03 = tmp04;
+ tmp04 = tmp05;
+ tmp05 = tmp06;
+ tmp06 = tmp07;
+ tmp07 = tmp08;
+ tmp08 = tmp09;
+ tmp09 = tmp10;
+ tmp10 = tmp11;
+ tmp11 = tmp12;
+ tmp12 = tmp13;
+ tmp13 = tmp14;
+ tmp14 = tmp15;
+ tmp15 = tmp16;
+ tmp16 = 0;
+ }
+ #endif
+
+ carry[ 0] = 0;
+ carry[ 1] = 0;
+ carry[ 2] = 0;
+ carry[ 3] = 0;
+ carry[ 4] = 0;
+ carry[ 5] = 0;
+ carry[ 6] = 0;
+ carry[ 7] = 0;
+ carry[ 8] = 0;
+ carry[ 9] = 0;
+ carry[10] = 0;
+ carry[11] = 0;
+ carry[12] = 0;
+ carry[13] = 0;
+ carry[14] = 0;
+ carry[15] = 0;
+
+ switch (div)
+ {
+ case 0: block[ 0] |= tmp00;
+ block[ 1] = tmp01;
+ block[ 2] = tmp02;
+ block[ 3] = tmp03;
+ block[ 4] = tmp04;
+ block[ 5] = tmp05;
+ block[ 6] = tmp06;
+ block[ 7] = tmp07;
+ block[ 8] = tmp08;
+ block[ 9] = tmp09;
+ block[10] = tmp10;
+ block[11] = tmp11;
+ block[12] = tmp12;
+ block[13] = tmp13;
+ block[14] = tmp14;
+ block[15] = tmp15;
+ carry[ 0] = tmp16;
+ break;
+ case 1: block[ 1] |= tmp00;
+ block[ 2] = tmp01;
+ block[ 3] = tmp02;
+ block[ 4] = tmp03;
+ block[ 5] = tmp04;
+ block[ 6] = tmp05;
+ block[ 7] = tmp06;
+ block[ 8] = tmp07;
+ block[ 9] = tmp08;
+ block[10] = tmp09;
+ block[11] = tmp10;
+ block[12] = tmp11;
+ block[13] = tmp12;
+ block[14] = tmp13;
+ block[15] = tmp14;
+ carry[ 0] = tmp15;
+ carry[ 1] = tmp16;
+ break;
+ case 2: block[ 2] |= tmp00;
+ block[ 3] = tmp01;
+ block[ 4] = tmp02;
+ block[ 5] = tmp03;
+ block[ 6] = tmp04;
+ block[ 7] = tmp05;
+ block[ 8] = tmp06;
+ block[ 9] = tmp07;
+ block[10] = tmp08;
+ block[11] = tmp09;
+ block[12] = tmp10;
+ block[13] = tmp11;
+ block[14] = tmp12;
+ block[15] = tmp13;
+ carry[ 0] = tmp14;
+ carry[ 1] = tmp15;
+ carry[ 2] = tmp16;
+ break;
+ case 3: block[ 3] |= tmp00;
+ block[ 4] = tmp01;
+ block[ 5] = tmp02;
+ block[ 6] = tmp03;
+ block[ 7] = tmp04;
+ block[ 8] = tmp05;
+ block[ 9] = tmp06;
+ block[10] = tmp07;
+ block[11] = tmp08;
+ block[12] = tmp09;
+ block[13] = tmp10;
+ block[14] = tmp11;
+ block[15] = tmp12;
+ carry[ 0] = tmp13;
+ carry[ 1] = tmp14;
+ carry[ 2] = tmp15;
+ carry[ 3] = tmp16;
+ break;
+ case 4: block[ 4] |= tmp00;
+ block[ 5] = tmp01;
+ block[ 6] = tmp02;
+ block[ 7] = tmp03;
+ block[ 8] = tmp04;
+ block[ 9] = tmp05;
+ block[10] = tmp06;
+ block[11] = tmp07;
+ block[12] = tmp08;
+ block[13] = tmp09;
+ block[14] = tmp10;
+ block[15] = tmp11;
+ carry[ 0] = tmp12;
+ carry[ 1] = tmp13;
+ carry[ 2] = tmp14;
+ carry[ 3] = tmp15;
+ carry[ 4] = tmp16;
+ break;
+ case 5: block[ 5] |= tmp00;
+ block[ 6] = tmp01;
+ block[ 7] = tmp02;
+ block[ 8] = tmp03;
+ block[ 9] = tmp04;
+ block[10] = tmp05;
+ block[11] = tmp06;
+ block[12] = tmp07;
+ block[13] = tmp08;
+ block[14] = tmp09;
+ block[15] = tmp10;
+ carry[ 0] = tmp11;
+ carry[ 1] = tmp12;
+ carry[ 2] = tmp13;
+ carry[ 3] = tmp14;
+ carry[ 4] = tmp15;
+ carry[ 5] = tmp16;
+ break;
+ case 6: block[ 6] |= tmp00;
+ block[ 7] = tmp01;
+ block[ 8] = tmp02;
+ block[ 9] = tmp03;
+ block[10] = tmp04;
+ block[11] = tmp05;
+ block[12] = tmp06;
+ block[13] = tmp07;
+ block[14] = tmp08;
+ block[15] = tmp09;
+ carry[ 0] = tmp10;
+ carry[ 1] = tmp11;
+ carry[ 2] = tmp12;
+ carry[ 3] = tmp13;
+ carry[ 4] = tmp14;
+ carry[ 5] = tmp15;
+ carry[ 6] = tmp16;
+ break;
+ case 7: block[ 7] |= tmp00;
+ block[ 8] = tmp01;
+ block[ 9] = tmp02;
+ block[10] = tmp03;
+ block[11] = tmp04;
+ block[12] = tmp05;
+ block[13] = tmp06;
+ block[14] = tmp07;
+ block[15] = tmp08;
+ carry[ 0] = tmp09;
+ carry[ 1] = tmp10;
+ carry[ 2] = tmp11;
+ carry[ 3] = tmp12;
+ carry[ 4] = tmp13;
+ carry[ 5] = tmp14;
+ carry[ 6] = tmp15;
+ carry[ 7] = tmp16;
+ break;
+ case 8: block[ 8] |= tmp00;
+ block[ 9] = tmp01;
+ block[10] = tmp02;
+ block[11] = tmp03;
+ block[12] = tmp04;
+ block[13] = tmp05;
+ block[14] = tmp06;
+ block[15] = tmp07;
+ carry[ 0] = tmp08;
+ carry[ 1] = tmp09;
+ carry[ 2] = tmp10;
+ carry[ 3] = tmp11;
+ carry[ 4] = tmp12;
+ carry[ 5] = tmp13;
+ carry[ 6] = tmp14;
+ carry[ 7] = tmp15;
+ carry[ 8] = tmp16;
+ break;
+ case 9: block[ 9] |= tmp00;
+ block[10] = tmp01;
+ block[11] = tmp02;
+ block[12] = tmp03;
+ block[13] = tmp04;
+ block[14] = tmp05;
+ block[15] = tmp06;
+ carry[ 0] = tmp07;
+ carry[ 1] = tmp08;
+ carry[ 2] = tmp09;
+ carry[ 3] = tmp10;
+ carry[ 4] = tmp11;
+ carry[ 5] = tmp12;
+ carry[ 6] = tmp13;
+ carry[ 7] = tmp14;
+ carry[ 8] = tmp15;
+ carry[ 9] = tmp16;
+ break;
+ case 10: block[10] |= tmp00;
+ block[11] = tmp01;
+ block[12] = tmp02;
+ block[13] = tmp03;
+ block[14] = tmp04;
+ block[15] = tmp05;
+ carry[ 0] = tmp06;
+ carry[ 1] = tmp07;
+ carry[ 2] = tmp08;
+ carry[ 3] = tmp09;
+ carry[ 4] = tmp10;
+ carry[ 5] = tmp11;
+ carry[ 6] = tmp12;
+ carry[ 7] = tmp13;
+ carry[ 8] = tmp14;
+ carry[ 9] = tmp15;
+ carry[10] = tmp16;
+ break;
+ case 11: block[11] |= tmp00;
+ block[12] = tmp01;
+ block[13] = tmp02;
+ block[14] = tmp03;
+ block[15] = tmp04;
+ carry[ 0] = tmp05;
+ carry[ 1] = tmp06;
+ carry[ 2] = tmp07;
+ carry[ 3] = tmp08;
+ carry[ 4] = tmp09;
+ carry[ 5] = tmp10;
+ carry[ 6] = tmp11;
+ carry[ 7] = tmp12;
+ carry[ 8] = tmp13;
+ carry[ 9] = tmp14;
+ carry[10] = tmp15;
+ carry[11] = tmp16;
+ break;
+ case 12: block[12] |= tmp00;
+ block[13] = tmp01;
+ block[14] = tmp02;
+ block[15] = tmp03;
+ carry[ 0] = tmp04;
+ carry[ 1] = tmp05;
+ carry[ 2] = tmp06;
+ carry[ 3] = tmp07;
+ carry[ 4] = tmp08;
+ carry[ 5] = tmp09;
+ carry[ 6] = tmp10;
+ carry[ 7] = tmp11;
+ carry[ 8] = tmp12;
+ carry[ 9] = tmp13;
+ carry[10] = tmp14;
+ carry[11] = tmp15;
+ carry[12] = tmp16;
+ break;
+ case 13: block[13] |= tmp00;
+ block[14] = tmp01;
+ block[15] = tmp02;
+ carry[ 0] = tmp03;
+ carry[ 1] = tmp04;
+ carry[ 2] = tmp05;
+ carry[ 3] = tmp06;
+ carry[ 4] = tmp07;
+ carry[ 5] = tmp08;
+ carry[ 6] = tmp09;
+ carry[ 7] = tmp10;
+ carry[ 8] = tmp11;
+ carry[ 9] = tmp12;
+ carry[10] = tmp13;
+ carry[11] = tmp14;
+ carry[12] = tmp15;
+ carry[13] = tmp16;
+ break;
+ case 14: block[14] |= tmp00;
+ block[15] = tmp01;
+ carry[ 0] = tmp02;
+ carry[ 1] = tmp03;
+ carry[ 2] = tmp04;
+ carry[ 3] = tmp05;
+ carry[ 4] = tmp06;
+ carry[ 5] = tmp07;
+ carry[ 6] = tmp08;
+ carry[ 7] = tmp09;
+ carry[ 8] = tmp10;
+ carry[ 9] = tmp11;
+ carry[10] = tmp12;
+ carry[11] = tmp13;
+ carry[12] = tmp14;
+ carry[13] = tmp15;
+ carry[14] = tmp16;
+ break;
+ case 15: block[15] |= tmp00;
+ carry[ 0] = tmp01;
+ carry[ 1] = tmp02;
+ carry[ 2] = tmp03;
+ carry[ 3] = tmp04;
+ carry[ 4] = tmp05;
+ carry[ 5] = tmp06;
+ carry[ 6] = tmp07;
+ carry[ 7] = tmp08;
+ carry[ 8] = tmp09;
+ carry[ 9] = tmp10;
+ carry[10] = tmp11;
+ carry[11] = tmp12;
+ carry[12] = tmp13;
+ carry[13] = tmp14;
+ carry[14] = tmp15;
+ carry[15] = tmp16;
+ break;
+ }
+}
+
+__kernel void m13500_m04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global pstoken_t *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+{
+ /**
+ * modifier
+ */
+
+ const u32 lid = get_local_id (0);
+
+ /**
+ * base
+ */
+
+ const u32 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ /**
+ * salt
+ */
+
+ const u32 pc_offset = esalt_bufs[salt_pos].pc_offset;
+
+ u32 pc_digest[5];
+
+ pc_digest[0] = esalt_bufs[salt_pos].pc_digest[0];
+ pc_digest[1] = esalt_bufs[salt_pos].pc_digest[1];
+ pc_digest[2] = esalt_bufs[salt_pos].pc_digest[2];
+ pc_digest[3] = esalt_bufs[salt_pos].pc_digest[3];
+ pc_digest[4] = esalt_bufs[salt_pos].pc_digest[4];
+
+ u32 salt_buf0[4];
+ u32 salt_buf1[4];
+ u32 salt_buf2[4];
+ u32 salt_buf3[4];
+
+ salt_buf0[0] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 0]);
+ salt_buf0[1] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 1]);
+ salt_buf0[2] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 2]);
+ salt_buf0[3] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 3]);
+ salt_buf1[0] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 4]);
+ salt_buf1[1] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 5]);
+ salt_buf1[2] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 6]);
+ salt_buf1[3] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 7]);
+ salt_buf2[0] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 8]);
+ salt_buf2[1] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 9]);
+ salt_buf2[2] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 10]);
+ salt_buf2[3] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 11]);
+ salt_buf3[0] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 12]);
+ salt_buf3[1] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 13]);
+ salt_buf3[2] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 14]);
+ salt_buf3[3] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 15]);
+
+ const u32 salt_len = esalt_bufs[salt_pos].salt_len;
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ u32x w0[4] = { 0 };
+ u32x w1[4] = { 0 };
+ u32x w2[4] = { 0 };
+ u32x w3[4] = { 0 };
+
+ const u32x out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+ append_0x80_2x4_VV (w0, w1, out_len);
+
+ make_unicode (w1, w2, w3);
+ make_unicode (w0, w0, w1);
+
+ const u32x out_len2 = out_len * 2;
+
+ const u32x out_salt_len = out_len2 + salt_len;
+
+ /**
+ * prepend salt -- can't stay outside the loop this time
+ */
+
+ u32x carry[16];
+
+ carry[ 0] = swap32 (w0[0]);
+ carry[ 1] = swap32 (w0[1]);
+ carry[ 2] = swap32 (w0[2]);
+ carry[ 3] = swap32 (w0[3]);
+ carry[ 4] = swap32 (w1[0]);
+ carry[ 5] = swap32 (w1[1]);
+ carry[ 6] = swap32 (w1[2]);
+ carry[ 7] = swap32 (w1[3]);
+ carry[ 8] = swap32 (w2[0]);
+ carry[ 9] = swap32 (w2[1]);
+ carry[10] = swap32 (w2[2]);
+ carry[11] = swap32 (w2[3]);
+ carry[12] = swap32 (w3[0]);
+ carry[13] = swap32 (w3[1]);
+ carry[14] = swap32 (w3[2]);
+ carry[15] = swap32 (w3[3]);
+
+ u32x w[16];
+
+ w[ 0] = salt_buf0[0];
+ w[ 1] = salt_buf0[1];
+ w[ 2] = salt_buf0[2];
+ w[ 3] = salt_buf0[3];
+ w[ 4] = salt_buf1[0];
+ w[ 5] = salt_buf1[1];
+ w[ 6] = salt_buf1[2];
+ w[ 7] = salt_buf1[3];
+ w[ 8] = salt_buf2[0];
+ w[ 9] = salt_buf2[1];
+ w[10] = salt_buf2[2];
+ w[11] = salt_buf2[3];
+ w[12] = salt_buf3[0];
+ w[13] = salt_buf3[1];
+ w[14] = salt_buf3[2];
+ w[15] = salt_buf3[3];
+
+ memcat64c_be (w, salt_len & 0x3f, carry);
+
+ u32x a = pc_digest[0];
+ u32x b = pc_digest[1];
+ u32x c = pc_digest[2];
+ u32x d = pc_digest[3];
+ u32x e = pc_digest[4];
+
+ if (((salt_len & 0x3f) + out_len2) >= 56)
+ {
+ u32x w0_t = w[ 0];
+ u32x w1_t = w[ 1];
+ u32x w2_t = w[ 2];
+ u32x w3_t = w[ 3];
+ u32x w4_t = w[ 4];
+ u32x w5_t = w[ 5];
+ u32x w6_t = w[ 6];
+ u32x w7_t = w[ 7];
+ u32x w8_t = w[ 8];
+ u32x w9_t = w[ 9];
+ u32x wa_t = w[10];
+ u32x wb_t = w[11];
+ u32x wc_t = w[12];
+ u32x wd_t = w[13];
+ u32x we_t = w[14];
+ u32x wf_t = w[15];
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ a += pc_digest[0];
+ b += pc_digest[1];
+ c += pc_digest[2];
+ d += pc_digest[3];
+ e += pc_digest[4];
+
+ w[ 0] = carry[ 0];
+ w[ 1] = carry[ 1];
+ w[ 2] = carry[ 2];
+ w[ 3] = carry[ 3];
+ w[ 4] = carry[ 4];
+ w[ 5] = carry[ 5];
+ w[ 6] = carry[ 6];
+ w[ 7] = carry[ 7];
+ w[ 8] = carry[ 8];
+ w[ 9] = carry[ 9];
+ w[10] = carry[10];
+ w[11] = carry[11];
+ w[12] = carry[12];
+ w[13] = carry[13];
+ w[14] = carry[14];
+ w[15] = carry[15];
+ }
+
+ /**
+ * final sha1
+ */
+
+ u32x w0_t = w[ 0];
+ u32x w1_t = w[ 1];
+ u32x w2_t = w[ 2];
+ u32x w3_t = w[ 3];
+ u32x w4_t = w[ 4];
+ u32x w5_t = w[ 5];
+ u32x w6_t = w[ 6];
+ u32x w7_t = w[ 7];
+ u32x w8_t = w[ 8];
+ u32x w9_t = w[ 9];
+ u32x wa_t = w[10];
+ u32x wb_t = w[11];
+ u32x wc_t = w[12];
+ u32x wd_t = w[13];
+ u32x we_t = 0;
+ u32x wf_t = out_salt_len * 8;
+
+ u32x r_a = a;
+ u32x r_b = b;
+ u32x r_c = c;
+ u32x r_d = d;
+ u32x r_e = e;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ a += r_a;
+ b += r_b;
+ c += r_c;
+ d += r_d;
+ e += r_e;
+
+ COMPARE_M_SIMD (d, e, c, b);
+ }
+}
+
+__kernel void m13500_m08 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global pstoken_t *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+{
+}
+
+__kernel void m13500_m16 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global pstoken_t *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+{
+}
+
+__kernel void m13500_s04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global pstoken_t *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+{
+ /**
+ * modifier
+ */
+
+ const u32 lid = get_local_id (0);
+
+ /**
+ * base
+ */
+
+ const u32 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ /**
+ * salt
+ */
+
+ const u32 pc_offset = esalt_bufs[salt_pos].pc_offset;
+
+ u32 pc_digest[5];
+
+ pc_digest[0] = esalt_bufs[salt_pos].pc_digest[0];
+ pc_digest[1] = esalt_bufs[salt_pos].pc_digest[1];
+ pc_digest[2] = esalt_bufs[salt_pos].pc_digest[2];
+ pc_digest[3] = esalt_bufs[salt_pos].pc_digest[3];
+ pc_digest[4] = esalt_bufs[salt_pos].pc_digest[4];
+
+ u32 salt_buf0[4];
+ u32 salt_buf1[4];
+ u32 salt_buf2[4];
+ u32 salt_buf3[4];
+
+ salt_buf0[0] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 0]);
+ salt_buf0[1] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 1]);
+ salt_buf0[2] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 2]);
+ salt_buf0[3] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 3]);
+ salt_buf1[0] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 4]);
+ salt_buf1[1] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 5]);
+ salt_buf1[2] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 6]);
+ salt_buf1[3] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 7]);
+ salt_buf2[0] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 8]);
+ salt_buf2[1] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 9]);
+ salt_buf2[2] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 10]);
+ salt_buf2[3] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 11]);
+ salt_buf3[0] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 12]);
+ salt_buf3[1] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 13]);
+ salt_buf3[2] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 14]);
+ salt_buf3[3] = swap32_S (esalt_bufs[salt_pos].salt_buf[pc_offset + 15]);
+
+ const u32 salt_len = esalt_bufs[salt_pos].salt_len;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ u32x w0[4] = { 0 };
+ u32x w1[4] = { 0 };
+ u32x w2[4] = { 0 };
+ u32x w3[4] = { 0 };
+
+ const u32x out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+ append_0x80_2x4_VV (w0, w1, out_len);
+
+ make_unicode (w1, w2, w3);
+ make_unicode (w0, w0, w1);
+
+ const u32x out_len2 = out_len * 2;
+
+ const u32x out_salt_len = out_len2 + salt_len;
+
+ /**
+ * prepend salt -- can't stay outside the loop this time
+ */
+
+ u32x carry[16];
+
+ carry[ 0] = swap32 (w0[0]);
+ carry[ 1] = swap32 (w0[1]);
+ carry[ 2] = swap32 (w0[2]);
+ carry[ 3] = swap32 (w0[3]);
+ carry[ 4] = swap32 (w1[0]);
+ carry[ 5] = swap32 (w1[1]);
+ carry[ 6] = swap32 (w1[2]);
+ carry[ 7] = swap32 (w1[3]);
+ carry[ 8] = swap32 (w2[0]);
+ carry[ 9] = swap32 (w2[1]);
+ carry[10] = swap32 (w2[2]);
+ carry[11] = swap32 (w2[3]);
+ carry[12] = swap32 (w3[0]);
+ carry[13] = swap32 (w3[1]);
+ carry[14] = swap32 (w3[2]);
+ carry[15] = swap32 (w3[3]);
+
+ u32x w[16];
+
+ w[ 0] = salt_buf0[0];
+ w[ 1] = salt_buf0[1];
+ w[ 2] = salt_buf0[2];
+ w[ 3] = salt_buf0[3];
+ w[ 4] = salt_buf1[0];
+ w[ 5] = salt_buf1[1];
+ w[ 6] = salt_buf1[2];
+ w[ 7] = salt_buf1[3];
+ w[ 8] = salt_buf2[0];
+ w[ 9] = salt_buf2[1];
+ w[10] = salt_buf2[2];
+ w[11] = salt_buf2[3];
+ w[12] = salt_buf3[0];
+ w[13] = salt_buf3[1];
+ w[14] = salt_buf3[2];
+ w[15] = salt_buf3[3];
+
+ memcat64c_be (w, salt_len & 0x3f, carry);
+
+ u32x a = pc_digest[0];
+ u32x b = pc_digest[1];
+ u32x c = pc_digest[2];
+ u32x d = pc_digest[3];
+ u32x e = pc_digest[4];
+
+ if (((salt_len & 0x3f) + out_len2) >= 56)
+ {
+ u32x w0_t = w[ 0];
+ u32x w1_t = w[ 1];
+ u32x w2_t = w[ 2];
+ u32x w3_t = w[ 3];
+ u32x w4_t = w[ 4];
+ u32x w5_t = w[ 5];
+ u32x w6_t = w[ 6];
+ u32x w7_t = w[ 7];
+ u32x w8_t = w[ 8];
+ u32x w9_t = w[ 9];
+ u32x wa_t = w[10];
+ u32x wb_t = w[11];
+ u32x wc_t = w[12];
+ u32x wd_t = w[13];
+ u32x we_t = w[14];
+ u32x wf_t = w[15];
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ a += pc_digest[0];
+ b += pc_digest[1];
+ c += pc_digest[2];
+ d += pc_digest[3];
+ e += pc_digest[4];
+
+ w[ 0] = carry[ 0];
+ w[ 1] = carry[ 1];
+ w[ 2] = carry[ 2];
+ w[ 3] = carry[ 3];
+ w[ 4] = carry[ 4];
+ w[ 5] = carry[ 5];
+ w[ 6] = carry[ 6];
+ w[ 7] = carry[ 7];
+ w[ 8] = carry[ 8];
+ w[ 9] = carry[ 9];
+ w[10] = carry[10];
+ w[11] = carry[11];
+ w[12] = carry[12];
+ w[13] = carry[13];
+ w[14] = carry[14];
+ w[15] = carry[15];
+ }
+
+ /**
+ * final sha1
+ */
+
+ u32x w0_t = w[ 0];
+ u32x w1_t = w[ 1];
+ u32x w2_t = w[ 2];
+ u32x w3_t = w[ 3];
+ u32x w4_t = w[ 4];
+ u32x w5_t = w[ 5];
+ u32x w6_t = w[ 6];
+ u32x w7_t = w[ 7];
+ u32x w8_t = w[ 8];
+ u32x w9_t = w[ 9];
+ u32x wa_t = w[10];
+ u32x wb_t = w[11];
+ u32x wc_t = w[12];
+ u32x wd_t = w[13];
+ u32x we_t = 0;
+ u32x wf_t = out_salt_len * 8;
+
+ u32x r_a = a;
+ u32x r_b = b;
+ u32x r_c = c;
+ u32x r_d = d;
+ u32x r_e = e;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ a += r_a;
+ b += r_b;
+ c += r_c;
+ d += r_d;
+ e += r_e;
+
+ COMPARE_S_SIMD (d, e, c, b);
+ }
+}
+
+__kernel void m13500_s08 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global pstoken_t *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+{
+}
+
+__kernel void m13500_s16 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global pstoken_t *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+{
+}
projects / hashcat.git / blobdiff