+++ /dev/null
-/**
- * Author......: Jens Steube <jens.steube@gmail.com>
- * License.....: MIT
- */
-
-#define _SHA1_
-
-#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"
-
-// no unicode yet
-
-__kernel void m00134_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 void *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
- */
-
- u32 salt_buf0[4];
- u32 salt_buf1[4];
- u32 salt_buf2[4];
- u32 salt_buf3[4];
-
- salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
- salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
- salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
- salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
- salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
- salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
- salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
- salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
- salt_buf2[0] = salt_bufs[salt_pos].salt_buf[ 8];
- salt_buf2[1] = salt_bufs[salt_pos].salt_buf[ 9];
- salt_buf2[2] = salt_bufs[salt_pos].salt_buf[10];
- salt_buf2[3] = salt_bufs[salt_pos].salt_buf[11];
- salt_buf3[0] = salt_bufs[salt_pos].salt_buf[12];
- salt_buf3[1] = salt_bufs[salt_pos].salt_buf[13];
- salt_buf3[2] = salt_bufs[salt_pos].salt_buf[14];
- salt_buf3[3] = salt_bufs[salt_pos].salt_buf[15];
-
- const u32 salt_len = salt_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);
-
- make_unicode (w1, w2, w3);
- make_unicode (w0, w0, w1);
-
- const u32x out_len2 = out_len * 2;
-
- /**
- * prepend salt
- */
-
- const u32x out_salt_len = out_len2 + salt_len;
-
- switch_buffer_by_offset_le_VV (w0, w1, w2, w3, salt_len);
-
- w0[0] |= salt_buf0[0];
- w0[1] |= salt_buf0[1];
- w0[2] |= salt_buf0[2];
- w0[3] |= salt_buf0[3];
- w1[0] |= salt_buf1[0];
- w1[1] |= salt_buf1[1];
- w1[2] |= salt_buf1[2];
- w1[3] |= salt_buf1[3];
- w2[0] |= salt_buf2[0];
- w2[1] |= salt_buf2[1];
- w2[2] |= salt_buf2[2];
- w2[3] |= salt_buf2[3];
- w3[0] |= salt_buf3[0];
- w3[1] |= salt_buf3[1];
- w3[2] |= salt_buf3[2];
- w3[3] |= salt_buf3[3];
-
- append_0x80_4x4_VV (w0, w1, w2, w3, out_salt_len);
-
- /**
- * sha1
- */
-
- u32x w0_t = swap32 (w0[0]);
- u32x w1_t = swap32 (w0[1]);
- u32x w2_t = swap32 (w0[2]);
- u32x w3_t = swap32 (w0[3]);
- u32x w4_t = swap32 (w1[0]);
- u32x w5_t = swap32 (w1[1]);
- u32x w6_t = swap32 (w1[2]);
- u32x w7_t = swap32 (w1[3]);
- u32x w8_t = swap32 (w2[0]);
- u32x w9_t = swap32 (w2[1]);
- u32x wa_t = swap32 (w2[2]);
- u32x wb_t = swap32 (w2[3]);
- u32x wc_t = swap32 (w3[0]);
- u32x wd_t = swap32 (w3[1]);
- u32x we_t = 0;
- u32x wf_t = out_salt_len * 8;
-
- u32x a = SHA1M_A;
- u32x b = SHA1M_B;
- u32x c = SHA1M_C;
- u32x d = SHA1M_D;
- u32x e = SHA1M_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);
-
- COMPARE_M_SIMD (d, e, c, b);
- }
-}
-
-__kernel void m00134_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 void *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 m00134_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 void *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 m00134_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 void *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
- */
-
- u32 salt_buf0[4];
- u32 salt_buf1[4];
- u32 salt_buf2[4];
- u32 salt_buf3[4];
-
- salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
- salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
- salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
- salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
- salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
- salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
- salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
- salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
- salt_buf2[0] = salt_bufs[salt_pos].salt_buf[ 8];
- salt_buf2[1] = salt_bufs[salt_pos].salt_buf[ 9];
- salt_buf2[2] = salt_bufs[salt_pos].salt_buf[10];
- salt_buf2[3] = salt_bufs[salt_pos].salt_buf[11];
- salt_buf3[0] = salt_bufs[salt_pos].salt_buf[12];
- salt_buf3[1] = salt_bufs[salt_pos].salt_buf[13];
- salt_buf3[2] = salt_bufs[salt_pos].salt_buf[14];
- salt_buf3[3] = salt_bufs[salt_pos].salt_buf[15];
-
- const u32 salt_len = salt_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]
- };
-
- /**
- * reverse
- */
-
- const u32 e_rev = rotl32_S (search[1], 2u);
-
- /**
- * 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);
-
- make_unicode (w1, w2, w3);
- make_unicode (w0, w0, w1);
-
- const u32x out_len2 = out_len * 2;
-
- /**
- * prepend salt
- */
-
- const u32x out_salt_len = out_len2 + salt_len;
-
- switch_buffer_by_offset_le_VV (w0, w1, w2, w3, salt_len);
-
- w0[0] |= salt_buf0[0];
- w0[1] |= salt_buf0[1];
- w0[2] |= salt_buf0[2];
- w0[3] |= salt_buf0[3];
- w1[0] |= salt_buf1[0];
- w1[1] |= salt_buf1[1];
- w1[2] |= salt_buf1[2];
- w1[3] |= salt_buf1[3];
- w2[0] |= salt_buf2[0];
- w2[1] |= salt_buf2[1];
- w2[2] |= salt_buf2[2];
- w2[3] |= salt_buf2[3];
- w3[0] |= salt_buf3[0];
- w3[1] |= salt_buf3[1];
- w3[2] |= salt_buf3[2];
- w3[3] |= salt_buf3[3];
-
- append_0x80_4x4_VV (w0, w1, w2, w3, out_salt_len);
-
- /**
- * sha1
- */
-
- u32x w0_t = swap32 (w0[0]);
- u32x w1_t = swap32 (w0[1]);
- u32x w2_t = swap32 (w0[2]);
- u32x w3_t = swap32 (w0[3]);
- u32x w4_t = swap32 (w1[0]);
- u32x w5_t = swap32 (w1[1]);
- u32x w6_t = swap32 (w1[2]);
- u32x w7_t = swap32 (w1[3]);
- u32x w8_t = swap32 (w2[0]);
- u32x w9_t = swap32 (w2[1]);
- u32x wa_t = swap32 (w2[2]);
- u32x wb_t = swap32 (w2[3]);
- u32x wc_t = swap32 (w3[0]);
- u32x wd_t = swap32 (w3[1]);
- u32x we_t = 0;
- u32x wf_t = out_salt_len * 8;
-
- u32x a = SHA1M_A;
- u32x b = SHA1M_B;
- u32x c = SHA1M_C;
- u32x d = SHA1M_D;
- u32x e = SHA1M_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);
-
- if (MATCHES_NONE_VS (e, e_rev)) continue;
-
- 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);
-
- COMPARE_S_SIMD (d, e, c, b);
- }
-}
-
-__kernel void m00134_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 void *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 m00134_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 void *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)
-{
-}
+++ /dev/null
-/**
- * Author......: Jens Steube <jens.steube@gmail.com>
- * License.....: MIT
- */
-
-#define _SHA1_
-
-#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 "OpenCL/simd.c"
-
-// no unicode yet
-
-__kernel void m00134_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 void *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_l_len = pws[gid].pw_len;
-
- /**
- * salt
- */
-
- u32 salt_buf0[4];
- u32 salt_buf1[4];
- u32 salt_buf2[4];
- u32 salt_buf3[4];
-
- salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
- salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
- salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
- salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
- salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
- salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
- salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
- salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
- salt_buf2[0] = salt_bufs[salt_pos].salt_buf[ 8];
- salt_buf2[1] = salt_bufs[salt_pos].salt_buf[ 9];
- salt_buf2[2] = salt_bufs[salt_pos].salt_buf[10];
- salt_buf2[3] = salt_bufs[salt_pos].salt_buf[11];
- salt_buf3[0] = salt_bufs[salt_pos].salt_buf[12];
- salt_buf3[1] = salt_bufs[salt_pos].salt_buf[13];
- salt_buf3[2] = salt_bufs[salt_pos].salt_buf[14];
- salt_buf3[3] = salt_bufs[salt_pos].salt_buf[15];
-
- const u32 salt_len = salt_bufs[salt_pos].salt_len;
-
- /**
- * loop
- */
-
- for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
- {
- const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos);
-
- const u32x pw_len = pw_l_len + pw_r_len;
-
- /**
- * concat password candidate
- */
-
- u32x wordl0[4] = { 0 };
- u32x wordl1[4] = { 0 };
- u32x wordl2[4] = { 0 };
- u32x wordl3[4] = { 0 };
-
- wordl0[0] = pw_buf0[0];
- wordl0[1] = pw_buf0[1];
- wordl0[2] = pw_buf0[2];
- wordl0[3] = pw_buf0[3];
- wordl1[0] = pw_buf1[0];
- wordl1[1] = pw_buf1[1];
- wordl1[2] = pw_buf1[2];
- wordl1[3] = pw_buf1[3];
-
- u32x wordr0[4] = { 0 };
- u32x wordr1[4] = { 0 };
- u32x wordr2[4] = { 0 };
- u32x wordr3[4] = { 0 };
-
- wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
- wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
- wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
- wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
- wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
- wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
- wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
- wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
-
- if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
- {
- switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
- }
- else
- {
- switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
- }
-
- u32x w0[4];
- u32x w1[4];
- u32x w2[4];
- u32x w3[4];
-
- w0[0] = wordl0[0] | wordr0[0];
- w0[1] = wordl0[1] | wordr0[1];
- w0[2] = wordl0[2] | wordr0[2];
- w0[3] = wordl0[3] | wordr0[3];
- w1[0] = wordl1[0] | wordr1[0];
- w1[1] = wordl1[1] | wordr1[1];
- w1[2] = wordl1[2] | wordr1[2];
- w1[3] = wordl1[3] | wordr1[3];
- w2[0] = wordl2[0] | wordr2[0];
- w2[1] = wordl2[1] | wordr2[1];
- w2[2] = wordl2[2] | wordr2[2];
- w2[3] = wordl2[3] | wordr2[3];
- w3[0] = wordl3[0] | wordr3[0];
- w3[1] = wordl3[1] | wordr3[1];
- w3[2] = wordl3[2] | wordr3[2];
- w3[3] = wordl3[3] | wordr3[3];
-
- make_unicode (w1, w2, w3);
- make_unicode (w0, w0, w1);
-
- const u32x pw_len2 = pw_len * 2;
-
- /**
- * prepend salt
- */
-
- switch_buffer_by_offset_le (w0, w1, w2, w3, salt_len);
-
- const u32x pw_salt_len = pw_len2 + salt_len;
-
- w0[0] |= salt_buf0[0];
- w0[1] |= salt_buf0[1];
- w0[2] |= salt_buf0[2];
- w0[3] |= salt_buf0[3];
- w1[0] |= salt_buf1[0];
- w1[1] |= salt_buf1[1];
- w1[2] |= salt_buf1[2];
- w1[3] |= salt_buf1[3];
- w2[0] |= salt_buf2[0];
- w2[1] |= salt_buf2[1];
- w2[2] |= salt_buf2[2];
- w2[3] |= salt_buf2[3];
- w3[0] |= salt_buf3[0];
- w3[1] |= salt_buf3[1];
- w3[2] |= salt_buf3[2];
- w3[3] |= salt_buf3[3];
-
- /**
- * sha1
- */
-
- u32x w0_t = swap32 (w0[0]);
- u32x w1_t = swap32 (w0[1]);
- u32x w2_t = swap32 (w0[2]);
- u32x w3_t = swap32 (w0[3]);
- u32x w4_t = swap32 (w1[0]);
- u32x w5_t = swap32 (w1[1]);
- u32x w6_t = swap32 (w1[2]);
- u32x w7_t = swap32 (w1[3]);
- u32x w8_t = swap32 (w2[0]);
- u32x w9_t = swap32 (w2[1]);
- u32x wa_t = swap32 (w2[2]);
- u32x wb_t = swap32 (w2[3]);
- u32x wc_t = swap32 (w3[0]);
- u32x wd_t = swap32 (w3[1]);
- u32x we_t = 0;
- u32x wf_t = pw_salt_len * 8;
-
- u32x a = SHA1M_A;
- u32x b = SHA1M_B;
- u32x c = SHA1M_C;
- u32x d = SHA1M_D;
- u32x e = SHA1M_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);
-
- COMPARE_M_SIMD (d, e, c, b);
- }
-}
-
-__kernel void m00134_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 void *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 m00134_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 void *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 m00134_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 void *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_l_len = pws[gid].pw_len;
-
- /**
- * salt
- */
-
- u32 salt_buf0[4];
- u32 salt_buf1[4];
- u32 salt_buf2[4];
- u32 salt_buf3[4];
-
- salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
- salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
- salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
- salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
- salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
- salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
- salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
- salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
- salt_buf2[0] = salt_bufs[salt_pos].salt_buf[ 8];
- salt_buf2[1] = salt_bufs[salt_pos].salt_buf[ 9];
- salt_buf2[2] = salt_bufs[salt_pos].salt_buf[10];
- salt_buf2[3] = salt_bufs[salt_pos].salt_buf[11];
- salt_buf3[0] = salt_bufs[salt_pos].salt_buf[12];
- salt_buf3[1] = salt_bufs[salt_pos].salt_buf[13];
- salt_buf3[2] = salt_bufs[salt_pos].salt_buf[14];
- salt_buf3[3] = salt_bufs[salt_pos].salt_buf[15];
-
- const u32 salt_len = salt_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]
- };
-
- /**
- * reverse
- */
-
- const u32 e_rev = rotl32_S (search[1], 2u);
-
- /**
- * loop
- */
-
- for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
- {
- const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos);
-
- const u32x pw_len = pw_l_len + pw_r_len;
-
- /**
- * concat password candidate
- */
-
- u32x wordl0[4] = { 0 };
- u32x wordl1[4] = { 0 };
- u32x wordl2[4] = { 0 };
- u32x wordl3[4] = { 0 };
-
- wordl0[0] = pw_buf0[0];
- wordl0[1] = pw_buf0[1];
- wordl0[2] = pw_buf0[2];
- wordl0[3] = pw_buf0[3];
- wordl1[0] = pw_buf1[0];
- wordl1[1] = pw_buf1[1];
- wordl1[2] = pw_buf1[2];
- wordl1[3] = pw_buf1[3];
-
- u32x wordr0[4] = { 0 };
- u32x wordr1[4] = { 0 };
- u32x wordr2[4] = { 0 };
- u32x wordr3[4] = { 0 };
-
- wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
- wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
- wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
- wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
- wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
- wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
- wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
- wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
-
- if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
- {
- switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
- }
- else
- {
- switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
- }
-
- u32x w0[4];
- u32x w1[4];
- u32x w2[4];
- u32x w3[4];
-
- w0[0] = wordl0[0] | wordr0[0];
- w0[1] = wordl0[1] | wordr0[1];
- w0[2] = wordl0[2] | wordr0[2];
- w0[3] = wordl0[3] | wordr0[3];
- w1[0] = wordl1[0] | wordr1[0];
- w1[1] = wordl1[1] | wordr1[1];
- w1[2] = wordl1[2] | wordr1[2];
- w1[3] = wordl1[3] | wordr1[3];
- w2[0] = wordl2[0] | wordr2[0];
- w2[1] = wordl2[1] | wordr2[1];
- w2[2] = wordl2[2] | wordr2[2];
- w2[3] = wordl2[3] | wordr2[3];
- w3[0] = wordl3[0] | wordr3[0];
- w3[1] = wordl3[1] | wordr3[1];
- w3[2] = wordl3[2] | wordr3[2];
- w3[3] = wordl3[3] | wordr3[3];
-
- make_unicode (w1, w2, w3);
- make_unicode (w0, w0, w1);
-
- const u32x pw_len2 = pw_len * 2;
-
- /**
- * prepend salt
- */
-
- switch_buffer_by_offset_le (w0, w1, w2, w3, salt_len);
-
- const u32x pw_salt_len = pw_len2 + salt_len;
-
- w0[0] |= salt_buf0[0];
- w0[1] |= salt_buf0[1];
- w0[2] |= salt_buf0[2];
- w0[3] |= salt_buf0[3];
- w1[0] |= salt_buf1[0];
- w1[1] |= salt_buf1[1];
- w1[2] |= salt_buf1[2];
- w1[3] |= salt_buf1[3];
- w2[0] |= salt_buf2[0];
- w2[1] |= salt_buf2[1];
- w2[2] |= salt_buf2[2];
- w2[3] |= salt_buf2[3];
- w3[0] |= salt_buf3[0];
- w3[1] |= salt_buf3[1];
- w3[2] |= salt_buf3[2];
- w3[3] |= salt_buf3[3];
-
- /**
- * sha1
- */
-
- u32x w0_t = swap32 (w0[0]);
- u32x w1_t = swap32 (w0[1]);
- u32x w2_t = swap32 (w0[2]);
- u32x w3_t = swap32 (w0[3]);
- u32x w4_t = swap32 (w1[0]);
- u32x w5_t = swap32 (w1[1]);
- u32x w6_t = swap32 (w1[2]);
- u32x w7_t = swap32 (w1[3]);
- u32x w8_t = swap32 (w2[0]);
- u32x w9_t = swap32 (w2[1]);
- u32x wa_t = swap32 (w2[2]);
- u32x wb_t = swap32 (w2[3]);
- u32x wc_t = swap32 (w3[0]);
- u32x wd_t = swap32 (w3[1]);
- u32x we_t = 0;
- u32x wf_t = pw_salt_len * 8;
-
- u32x a = SHA1M_A;
- u32x b = SHA1M_B;
- u32x c = SHA1M_C;
- u32x d = SHA1M_D;
- u32x e = SHA1M_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);
-
- if (MATCHES_NONE_VS (e, e_rev)) continue;
-
- 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);
-
- COMPARE_S_SIMD (d, e, c, b);
- }
-}
-
-__kernel void m00134_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 void *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 m00134_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 void *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)
-{
-}
+++ /dev/null
-/**
- * Author......: Jens Steube <jens.steube@gmail.com>
- * License.....: MIT
- */
-
-#define _SHA1_
-
-#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 "OpenCL/simd.c"
-
-static void m00134m (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_len, __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 void *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)
-{
- /**
- * modifier
- */
-
- const u32 gid = get_global_id (0);
- const u32 lid = get_local_id (0);
-
- /**
- * salt
- */
-
- u32 salt_buf0[4];
- u32 salt_buf1[4];
- u32 salt_buf2[4];
- u32 salt_buf3[4];
-
- salt_buf0[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
- salt_buf0[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
- salt_buf0[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
- salt_buf0[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
- salt_buf1[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
- salt_buf1[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
- salt_buf1[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
- salt_buf1[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
- salt_buf2[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
- salt_buf2[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
- salt_buf2[2] = swap32_S (salt_bufs[salt_pos].salt_buf[10]);
- salt_buf2[3] = swap32_S (salt_bufs[salt_pos].salt_buf[11]);
- salt_buf3[0] = swap32_S (salt_bufs[salt_pos].salt_buf[12]);
- salt_buf3[1] = swap32_S (salt_bufs[salt_pos].salt_buf[13]);
- salt_buf3[2] = swap32_S (salt_bufs[salt_pos].salt_buf[14]);
- salt_buf3[3] = swap32_S (salt_bufs[salt_pos].salt_buf[15]);
-
- const u32 salt_len = salt_bufs[salt_pos].salt_len;
-
- const u32 pw_salt_len = pw_len + salt_len;
-
- /**
- * prepend salt
- */
-
- const u32 w0l = w0[0];
-
- switch_buffer_by_offset_be_S (w0, w1, w2, w3, salt_len);
-
- w0[0] |= salt_buf0[0];
- w0[1] |= salt_buf0[1];
- w0[2] |= salt_buf0[2];
- w0[3] |= salt_buf0[3];
- w1[0] |= salt_buf1[0];
- w1[1] |= salt_buf1[1];
- w1[2] |= salt_buf1[2];
- w1[3] |= salt_buf1[3];
- w2[0] |= salt_buf2[0];
- w2[1] |= salt_buf2[1];
- w2[2] |= salt_buf2[2];
- w2[3] |= salt_buf2[3];
- w3[0] |= salt_buf3[0];
- w3[1] |= salt_buf3[1];
- w3[2] |= salt_buf3[2];
- w3[3] |= salt_buf3[3];
-
- u32x t0[4];
- u32x t1[4];
- u32x t2[4];
- u32x t3[4];
-
- t0[0] = w0[0];
- t0[1] = w0[1];
- t0[2] = w0[2];
- t0[3] = w0[3];
- t1[0] = w1[0];
- t1[1] = w1[1];
- t1[2] = w1[2];
- t1[3] = w1[3];
- t2[0] = w2[0];
- t2[1] = w2[1];
- t2[2] = w2[2];
- t2[3] = w2[3];
- t3[0] = w3[0];
- t3[1] = w3[1];
- t3[2] = w3[2];
- t3[3] = w3[3];
-
- /**
- * loop
- */
-
- for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
- {
- const u32x w0r = ix_create_bft (bfs_buf, il_pos);
-
- const u32x w0lr = w0l | w0r;
-
- overwrite_at_be_4x4 (t0, t1, t2, t3, w0lr, salt_len);
-
- /**
- * sha1
- */
-
- u32x w0_t = t0[0];
- u32x w1_t = t0[1];
- u32x w2_t = t0[2];
- u32x w3_t = t0[3];
- u32x w4_t = t1[0];
- u32x w5_t = t1[1];
- u32x w6_t = t1[2];
- u32x w7_t = t1[3];
- u32x w8_t = t2[0];
- u32x w9_t = t2[1];
- u32x wa_t = t2[2];
- u32x wb_t = t2[3];
- u32x wc_t = t3[0];
- u32x wd_t = t3[1];
- u32x we_t = 0;
- u32x wf_t = pw_salt_len * 8;
-
- u32x a = SHA1M_A;
- u32x b = SHA1M_B;
- u32x c = SHA1M_C;
- u32x d = SHA1M_D;
- u32x e = SHA1M_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);
-
- COMPARE_M_SIMD (d, e, c, b);
- }
-}
-
-static void m00134s (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_len, __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 void *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)
-{
- /**
- * modifier
- */
-
- const u32 gid = get_global_id (0);
- const u32 lid = get_local_id (0);
-
- /**
- * 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]
- };
-
- /**
- * reverse
- */
-
- const u32 e_rev = rotl32_S (search[1], 2u);
-
- /**
- * salt
- */
-
- u32 salt_buf0[4];
- u32 salt_buf1[4];
- u32 salt_buf2[4];
- u32 salt_buf3[4];
-
- salt_buf0[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
- salt_buf0[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
- salt_buf0[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
- salt_buf0[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
- salt_buf1[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
- salt_buf1[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
- salt_buf1[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
- salt_buf1[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
- salt_buf2[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
- salt_buf2[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
- salt_buf2[2] = swap32_S (salt_bufs[salt_pos].salt_buf[10]);
- salt_buf2[3] = swap32_S (salt_bufs[salt_pos].salt_buf[11]);
- salt_buf3[0] = swap32_S (salt_bufs[salt_pos].salt_buf[12]);
- salt_buf3[1] = swap32_S (salt_bufs[salt_pos].salt_buf[13]);
- salt_buf3[2] = swap32_S (salt_bufs[salt_pos].salt_buf[14]);
- salt_buf3[3] = swap32_S (salt_bufs[salt_pos].salt_buf[15]);
-
- const u32 salt_len = salt_bufs[salt_pos].salt_len;
-
- const u32 pw_salt_len = pw_len + salt_len;
-
- /**
- * prepend salt
- */
-
- const u32 w0l = w0[0];
-
- switch_buffer_by_offset_be_S (w0, w1, w2, w3, salt_len);
-
- w0[0] |= salt_buf0[0];
- w0[1] |= salt_buf0[1];
- w0[2] |= salt_buf0[2];
- w0[3] |= salt_buf0[3];
- w1[0] |= salt_buf1[0];
- w1[1] |= salt_buf1[1];
- w1[2] |= salt_buf1[2];
- w1[3] |= salt_buf1[3];
- w2[0] |= salt_buf2[0];
- w2[1] |= salt_buf2[1];
- w2[2] |= salt_buf2[2];
- w2[3] |= salt_buf2[3];
- w3[0] |= salt_buf3[0];
- w3[1] |= salt_buf3[1];
- w3[2] |= salt_buf3[2];
- w3[3] |= salt_buf3[3];
-
- u32x t0[4];
- u32x t1[4];
- u32x t2[4];
- u32x t3[4];
-
- t0[0] = w0[0];
- t0[1] = w0[1];
- t0[2] = w0[2];
- t0[3] = w0[3];
- t1[0] = w1[0];
- t1[1] = w1[1];
- t1[2] = w1[2];
- t1[3] = w1[3];
- t2[0] = w2[0];
- t2[1] = w2[1];
- t2[2] = w2[2];
- t2[3] = w2[3];
- t3[0] = w3[0];
- t3[1] = w3[1];
- t3[2] = w3[2];
- t3[3] = w3[3];
-
- /**
- * loop
- */
-
- for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
- {
- const u32x w0r = ix_create_bft (bfs_buf, il_pos);
-
- const u32x w0lr = w0l | w0r;
-
- overwrite_at_be_4x4 (t0, t1, t2, t3, w0lr, salt_len);
-
- /**
- * sha1
- */
-
- u32x w0_t = t0[0];
- u32x w1_t = t0[1];
- u32x w2_t = t0[2];
- u32x w3_t = t0[3];
- u32x w4_t = t1[0];
- u32x w5_t = t1[1];
- u32x w6_t = t1[2];
- u32x w7_t = t1[3];
- u32x w8_t = t2[0];
- u32x w9_t = t2[1];
- u32x wa_t = t2[2];
- u32x wb_t = t2[3];
- u32x wc_t = t3[0];
- u32x wd_t = t3[1];
- u32x we_t = 0;
- u32x wf_t = pw_salt_len * 8;
-
- u32x a = SHA1M_A;
- u32x b = SHA1M_B;
- u32x c = SHA1M_C;
- u32x d = SHA1M_D;
- u32x e = SHA1M_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);
-
- if (MATCHES_NONE_VS (e, e_rev)) continue;
-
- 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);
-
- COMPARE_S_SIMD (d, e, c, b);
- }
-}
-
-__kernel void m00134_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 void *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)
-{
- /**
- * base
- */
-
- const u32 gid = get_global_id (0);
-
- if (gid >= gid_max) return;
-
- u32 w0[4];
-
- w0[0] = pws[gid].i[ 0];
- w0[1] = pws[gid].i[ 1];
- w0[2] = pws[gid].i[ 2];
- w0[3] = pws[gid].i[ 3];
-
- u32 w1[4];
-
- w1[0] = 0;
- w1[1] = 0;
- w1[2] = 0;
- w1[3] = 0;
-
- u32 w2[4];
-
- w2[0] = 0;
- w2[1] = 0;
- w2[2] = 0;
- w2[3] = 0;
-
- u32 w3[4];
-
- w3[0] = 0;
- w3[1] = 0;
- w3[2] = 0;
- w3[3] = 0;
-
- const u32 pw_len = pws[gid].pw_len;
-
- /**
- * main
- */
-
- m00134m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
-}
-
-__kernel void m00134_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 void *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)
-{
- /**
- * base
- */
-
- const u32 gid = get_global_id (0);
-
- if (gid >= gid_max) return;
-
- u32 w0[4];
-
- w0[0] = pws[gid].i[ 0];
- w0[1] = pws[gid].i[ 1];
- w0[2] = pws[gid].i[ 2];
- w0[3] = pws[gid].i[ 3];
-
- u32 w1[4];
-
- w1[0] = pws[gid].i[ 4];
- w1[1] = pws[gid].i[ 5];
- w1[2] = pws[gid].i[ 6];
- w1[3] = pws[gid].i[ 7];
-
- u32 w2[4];
-
- w2[0] = 0;
- w2[1] = 0;
- w2[2] = 0;
- w2[3] = 0;
-
- u32 w3[4];
-
- w3[0] = 0;
- w3[1] = 0;
- w3[2] = 0;
- w3[3] = 0;
-
- const u32 pw_len = pws[gid].pw_len;
-
- /**
- * main
- */
-
- m00134m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
-}
-
-__kernel void m00134_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 void *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)
-{
- /**
- * base
- */
-
- const u32 gid = get_global_id (0);
-
- if (gid >= gid_max) return;
-
- u32 w0[4];
-
- w0[0] = pws[gid].i[ 0];
- w0[1] = pws[gid].i[ 1];
- w0[2] = pws[gid].i[ 2];
- w0[3] = pws[gid].i[ 3];
-
- u32 w1[4];
-
- w1[0] = pws[gid].i[ 4];
- w1[1] = pws[gid].i[ 5];
- w1[2] = pws[gid].i[ 6];
- w1[3] = pws[gid].i[ 7];
-
- u32 w2[4];
-
- w2[0] = pws[gid].i[ 8];
- w2[1] = pws[gid].i[ 9];
- w2[2] = pws[gid].i[10];
- w2[3] = pws[gid].i[11];
-
- u32 w3[4];
-
- w3[0] = pws[gid].i[12];
- w3[1] = pws[gid].i[13];
- w3[2] = 0;
- w3[3] = 0;
-
- const u32 pw_len = pws[gid].pw_len;
-
- /**
- * main
- */
-
- m00134m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
-}
-
-__kernel void m00134_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 void *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)
-{
- /**
- * base
- */
-
- const u32 gid = get_global_id (0);
-
- if (gid >= gid_max) return;
-
- u32 w0[4];
-
- w0[0] = pws[gid].i[ 0];
- w0[1] = pws[gid].i[ 1];
- w0[2] = pws[gid].i[ 2];
- w0[3] = pws[gid].i[ 3];
-
- u32 w1[4];
-
- w1[0] = 0;
- w1[1] = 0;
- w1[2] = 0;
- w1[3] = 0;
-
- u32 w2[4];
-
- w2[0] = 0;
- w2[1] = 0;
- w2[2] = 0;
- w2[3] = 0;
-
- u32 w3[4];
-
- w3[0] = 0;
- w3[1] = 0;
- w3[2] = 0;
- w3[3] = 0;
-
- const u32 pw_len = pws[gid].pw_len;
-
- /**
- * main
- */
-
- m00134s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
-}
-
-__kernel void m00134_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 void *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)
-{
- /**
- * base
- */
-
- const u32 gid = get_global_id (0);
-
- if (gid >= gid_max) return;
-
- u32 w0[4];
-
- w0[0] = pws[gid].i[ 0];
- w0[1] = pws[gid].i[ 1];
- w0[2] = pws[gid].i[ 2];
- w0[3] = pws[gid].i[ 3];
-
- u32 w1[4];
-
- w1[0] = pws[gid].i[ 4];
- w1[1] = pws[gid].i[ 5];
- w1[2] = pws[gid].i[ 6];
- w1[3] = pws[gid].i[ 7];
-
- u32 w2[4];
-
- w2[0] = 0;
- w2[1] = 0;
- w2[2] = 0;
- w2[3] = 0;
-
- u32 w3[4];
-
- w3[0] = 0;
- w3[1] = 0;
- w3[2] = 0;
- w3[3] = 0;
-
- const u32 pw_len = pws[gid].pw_len;
-
- /**
- * main
- */
-
- m00134s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
-}
-
-__kernel void m00134_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 void *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)
-{
- /**
- * base
- */
-
- const u32 gid = get_global_id (0);
-
- if (gid >= gid_max) return;
-
- u32 w0[4];
-
- w0[0] = pws[gid].i[ 0];
- w0[1] = pws[gid].i[ 1];
- w0[2] = pws[gid].i[ 2];
- w0[3] = pws[gid].i[ 3];
-
- u32 w1[4];
-
- w1[0] = pws[gid].i[ 4];
- w1[1] = pws[gid].i[ 5];
- w1[2] = pws[gid].i[ 6];
- w1[3] = pws[gid].i[ 7];
-
- u32 w2[4];
-
- w2[0] = pws[gid].i[ 8];
- w2[1] = pws[gid].i[ 9];
- w2[2] = pws[gid].i[10];
- w2[3] = pws[gid].i[11];
-
- u32 w3[4];
-
- w3[0] = pws[gid].i[12];
- w3[1] = pws[gid].i[13];
- w3[2] = 0;
- w3[3] = 0;
-
- const u32 pw_len = pws[gid].pw_len;
-
- /**
- * main
- */
-
- m00134s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
-}
--- /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)
+{
+}
--- /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 "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_l_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)
+ {
+ const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos);
+
+ const u32x pw_len = pw_l_len + pw_r_len;
+
+ /**
+ * concat password candidate
+ */
+
+ u32x wordl0[4] = { 0 };
+ u32x wordl1[4] = { 0 };
+ u32x wordl2[4] = { 0 };
+ u32x wordl3[4] = { 0 };
+
+ wordl0[0] = pw_buf0[0];
+ wordl0[1] = pw_buf0[1];
+ wordl0[2] = pw_buf0[2];
+ wordl0[3] = pw_buf0[3];
+ wordl1[0] = pw_buf1[0];
+ wordl1[1] = pw_buf1[1];
+ wordl1[2] = pw_buf1[2];
+ wordl1[3] = pw_buf1[3];
+
+ u32x wordr0[4] = { 0 };
+ u32x wordr1[4] = { 0 };
+ u32x wordr2[4] = { 0 };
+ u32x wordr3[4] = { 0 };
+
+ wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+ wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+ wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+ wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+ wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+ wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+ wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+ wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+ if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+ {
+ switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+ }
+ else
+ {
+ switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+ }
+
+ u32x w0[4];
+ u32x w1[4];
+ u32x w2[4];
+ u32x w3[4];
+
+ w0[0] = wordl0[0] | wordr0[0];
+ w0[1] = wordl0[1] | wordr0[1];
+ w0[2] = wordl0[2] | wordr0[2];
+ w0[3] = wordl0[3] | wordr0[3];
+ w1[0] = wordl1[0] | wordr1[0];
+ w1[1] = wordl1[1] | wordr1[1];
+ w1[2] = wordl1[2] | wordr1[2];
+ w1[3] = wordl1[3] | wordr1[3];
+
+ append_0x80_2x4_VV (w0, w1, pw_len);
+
+ make_unicode (w1, w2, w3);
+ make_unicode (w0, w0, w1);
+
+ const u32x pw_len2 = pw_len * 2;
+
+ const u32x pw_salt_len = pw_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) + pw_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 = pw_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_l_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)
+ {
+ const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos);
+
+ const u32x pw_len = pw_l_len + pw_r_len;
+
+ /**
+ * concat password candidate
+ */
+
+ u32x wordl0[4] = { 0 };
+ u32x wordl1[4] = { 0 };
+ u32x wordl2[4] = { 0 };
+ u32x wordl3[4] = { 0 };
+
+ wordl0[0] = pw_buf0[0];
+ wordl0[1] = pw_buf0[1];
+ wordl0[2] = pw_buf0[2];
+ wordl0[3] = pw_buf0[3];
+ wordl1[0] = pw_buf1[0];
+ wordl1[1] = pw_buf1[1];
+ wordl1[2] = pw_buf1[2];
+ wordl1[3] = pw_buf1[3];
+
+ u32x wordr0[4] = { 0 };
+ u32x wordr1[4] = { 0 };
+ u32x wordr2[4] = { 0 };
+ u32x wordr3[4] = { 0 };
+
+ wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+ wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+ wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+ wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+ wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+ wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+ wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+ wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+ if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+ {
+ switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+ }
+ else
+ {
+ switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+ }
+
+ u32x w0[4];
+ u32x w1[4];
+ u32x w2[4];
+ u32x w3[4];
+
+ w0[0] = wordl0[0] | wordr0[0];
+ w0[1] = wordl0[1] | wordr0[1];
+ w0[2] = wordl0[2] | wordr0[2];
+ w0[3] = wordl0[3] | wordr0[3];
+ w1[0] = wordl1[0] | wordr1[0];
+ w1[1] = wordl1[1] | wordr1[1];
+ w1[2] = wordl1[2] | wordr1[2];
+ w1[3] = wordl1[3] | wordr1[3];
+
+ append_0x80_2x4_VV (w0, w1, pw_len);
+
+ make_unicode (w1, w2, w3);
+ make_unicode (w0, w0, w1);
+
+ const u32x pw_len2 = pw_len * 2;
+
+ const u32x pw_salt_len = pw_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) + pw_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 = pw_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)
+{
+}
--- /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 "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;
+ }
+}
+
+static void m13500m (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_len, __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)
+{
+ /**
+ * modifier
+ */
+
+ const u32 gid = get_global_id (0);
+ const u32 lid = get_local_id (0);
+
+ /**
+ * 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;
+
+ const u32 pw_salt_len = pw_len + salt_len;
+
+ /**
+ * loop
+ */
+
+ u32 w0l = w0[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = ix_create_bft (bfs_buf, il_pos);
+
+ const u32x w0lr = w0l | w0r;
+
+ /**
+ * prepend salt -- can't stay outside the loop this time
+ */
+
+ u32x carry[16];
+
+ carry[ 0] = w0lr;
+ carry[ 1] = w0[1];
+ carry[ 2] = w0[2];
+ carry[ 3] = w0[3];
+ carry[ 4] = w1[0];
+ carry[ 5] = w1[1];
+ carry[ 6] = w1[2];
+ carry[ 7] = w1[3];
+ carry[ 8] = w2[0];
+ carry[ 9] = w2[1];
+ carry[10] = w2[2];
+ carry[11] = w2[3];
+ carry[12] = w3[0];
+ carry[13] = w3[1];
+ carry[14] = w3[2];
+ carry[15] = 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) + pw_len) >= 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 = pw_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);
+ }
+}
+
+static void m13500s (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_len, __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)
+{
+ /**
+ * modifier
+ */
+
+ const u32 gid = get_global_id (0);
+ const u32 lid = get_local_id (0);
+
+ /**
+ * 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;
+
+ const u32 pw_salt_len = pw_len + 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
+ */
+
+ u32 w0l = w0[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = ix_create_bft (bfs_buf, il_pos);
+
+ const u32x w0lr = w0l | w0r;
+
+ /**
+ * prepend salt -- can't stay outside the loop this time
+ */
+
+ u32x carry[16];
+
+ carry[ 0] = w0lr;
+ carry[ 1] = w0[1];
+ carry[ 2] = w0[2];
+ carry[ 3] = w0[3];
+ carry[ 4] = w1[0];
+ carry[ 5] = w1[1];
+ carry[ 6] = w1[2];
+ carry[ 7] = w1[3];
+ carry[ 8] = w2[0];
+ carry[ 9] = w2[1];
+ carry[10] = w2[2];
+ carry[11] = w2[3];
+ carry[12] = w3[0];
+ carry[13] = w3[1];
+ carry[14] = w3[2];
+ carry[15] = 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) + pw_len) >= 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 = pw_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_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)
+{
+ /**
+ * base
+ */
+
+ const u32 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = 0;
+ w1[1] = 0;
+ w1[2] = 0;
+ w1[3] = 0;
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ /**
+ * main
+ */
+
+ m13500m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
+}
+
+__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)
+{
+ /**
+ * base
+ */
+
+ const u32 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ /**
+ * main
+ */
+
+ m13500m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
+}
+
+__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)
+{
+ /**
+ * base
+ */
+
+ const u32 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = pws[gid].i[ 8];
+ w2[1] = pws[gid].i[ 9];
+ w2[2] = pws[gid].i[10];
+ w2[3] = pws[gid].i[11];
+
+ u32 w3[4];
+
+ w3[0] = pws[gid].i[12];
+ w3[1] = pws[gid].i[13];
+ w3[2] = 0;
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ /**
+ * main
+ */
+
+ m13500m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
+}
+
+__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)
+{
+ /**
+ * base
+ */
+
+ const u32 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = 0;
+ w1[1] = 0;
+ w1[2] = 0;
+ w1[3] = 0;
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ /**
+ * main
+ */
+
+ m13500s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
+}
+
+__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)
+{
+ /**
+ * base
+ */
+
+ const u32 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ /**
+ * main
+ */
+
+ m13500s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
+}
+
+__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)
+{
+ /**
+ * base
+ */
+
+ const u32 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = pws[gid].i[ 8];
+ w2[1] = pws[gid].i[ 9];
+ w2[2] = pws[gid].i[10];
+ w2[3] = pws[gid].i[11];
+
+ u32 w3[4];
+
+ w3[0] = pws[gid].i[12];
+ w3[1] = pws[gid].i[13];
+ w3[2] = 0;
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ /**
+ * main
+ */
+
+ m13500s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
+}
} oldoffice34_t;
+typedef struct
+{
+ u32 salt_buf[128];
+ u32 salt_len;
+
+ u32 pc_digest[5];
+ u32 pc_offset;
+
+} pstoken_t;
+
typedef struct
{
u32 version;
--- /dev/null
+/**
+ * Author......: Jens Steube <jens.steube@gmail.com>
+ * License.....: MIT
+ */
+
+void sha1_64 (uint block[16], uint digest[5])
+{
+ u32 A = digest[0];
+ u32 B = digest[1];
+ u32 C = digest[2];
+ u32 D = digest[3];
+ u32 E = digest[4];
+
+ u32 w0_t = block[ 0];
+ u32 w1_t = block[ 1];
+ u32 w2_t = block[ 2];
+ u32 w3_t = block[ 3];
+ u32 w4_t = block[ 4];
+ u32 w5_t = block[ 5];
+ u32 w6_t = block[ 6];
+ u32 w7_t = block[ 7];
+ u32 w8_t = block[ 8];
+ u32 w9_t = block[ 9];
+ u32 wa_t = block[10];
+ u32 wb_t = block[11];
+ u32 wc_t = block[12];
+ u32 wd_t = block[13];
+ u32 we_t = block[14];
+ u32 wf_t = block[15];
+
+ #define SHA1_F0(x,y,z) ((z) ^ ((x) & ((y) ^ (z))))
+ #define SHA1_F1(x,y,z) ((x) ^ (y) ^ (z))
+ #define SHA1_F2(x,y,z) (((x) & (y)) | ((z) & ((x) ^ (y))))
+
+ #define SHA1_STEP(f,a,b,c,d,e,x) \
+ { \
+ e += K; \
+ e += x; \
+ e += f (b, c, d); \
+ e += rotl32 (a, 5u); \
+ b = rotl32 (b, 30u); \
+ }
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0 , A, B, C, D, E, w0_t);
+ SHA1_STEP (SHA1_F0 , E, A, B, C, D, w1_t);
+ SHA1_STEP (SHA1_F0 , D, E, A, B, C, w2_t);
+ SHA1_STEP (SHA1_F0 , C, D, E, A, B, w3_t);
+ SHA1_STEP (SHA1_F0 , B, C, D, E, A, w4_t);
+ SHA1_STEP (SHA1_F0 , A, B, C, D, E, w5_t);
+ SHA1_STEP (SHA1_F0 , E, A, B, C, D, w6_t);
+ SHA1_STEP (SHA1_F0 , D, E, A, B, C, w7_t);
+ SHA1_STEP (SHA1_F0 , C, D, E, A, B, w8_t);
+ SHA1_STEP (SHA1_F0 , B, C, D, E, A, w9_t);
+ SHA1_STEP (SHA1_F0 , A, B, C, D, E, wa_t);
+ SHA1_STEP (SHA1_F0 , E, A, B, C, D, wb_t);
+ SHA1_STEP (SHA1_F0 , D, E, A, B, C, wc_t);
+ SHA1_STEP (SHA1_F0 , C, D, E, A, B, wd_t);
+ SHA1_STEP (SHA1_F0 , B, C, D, E, A, we_t);
+ SHA1_STEP (SHA1_F0 , A, B, C, D, E, wf_t);
+ w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0 , E, A, B, C, D, w0_t);
+ w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0 , D, E, A, B, C, w1_t);
+ w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0 , C, D, E, A, B, w2_t);
+ w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0 , 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_F2 , A, B, C, D, E, w8_t);
+ w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2 , E, A, B, C, D, w9_t);
+ wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2 , D, E, A, B, C, wa_t);
+ wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2 , C, D, E, A, B, wb_t);
+ wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2 , B, C, D, E, A, wc_t);
+ wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2 , A, B, C, D, E, wd_t);
+ we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2 , E, A, B, C, D, we_t);
+ wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2 , D, E, A, B, C, wf_t);
+ w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2 , C, D, E, A, B, w0_t);
+ w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2 , B, C, D, E, A, w1_t);
+ w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2 , A, B, C, D, E, w2_t);
+ w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2 , E, A, B, C, D, w3_t);
+ w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2 , D, E, A, B, C, w4_t);
+ w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2 , C, D, E, A, B, w5_t);
+ w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2 , B, C, D, E, A, w6_t);
+ w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2 , A, B, C, D, E, w7_t);
+ w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2 , E, A, B, C, D, w8_t);
+ w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2 , D, E, A, B, C, w9_t);
+ wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2 , C, D, E, A, B, wa_t);
+ wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2 , 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);
+
+ digest[0] += A;
+ digest[1] += B;
+ digest[2] += C;
+ digest[3] += D;
+ digest[4] += E;
+}
#define KERN_TYPE_AXCRYPT 13200
#define KERN_TYPE_SHA1_AXCRYPT 13300
#define KERN_TYPE_KEEPASS 13400
+#define KERN_TYPE_PSTOKEN 13500
/**
* signatures
} oldoffice34_t;
+typedef struct
+{
+ u32 salt_buf[128];
+ u32 salt_len;
+
+ u32 pc_digest[5];
+ u32 pc_offset;
+
+} pstoken_t;
+
typedef struct
{
uint P[256];
} psafe3_t;
-typedef struct
-{
- u32 salt_buf[128];
- u32 salt_len;
-
-} pstoken_t;
-
typedef struct
{
char plain_buf[256];
attack_exec = ATTACK_EXEC_INSIDE_KERNEL;
opts_type = OPTS_TYPE_PT_GENERATE_BE
| OPTS_TYPE_PT_UNICODE
- | OPTS_TYPE_PT_ADD80;
- kern_type = KERN_TYPE_SHA1_SLTPWU;
+ | OPTS_TYPE_PT_ADD80;
+ kern_type = KERN_TYPE_PSTOKEN;
dgst_size = DGST_SIZE_4_5;
parse_func = pstoken_parse_hash;
sort_by_digest = sort_by_digest_4_5;
break;
case 13400: ((keepass_t *) hashes_buf[0].esalt)->version = 2;
break;
+ case 13500: ((pstoken_t *) hashes_buf[0].esalt)->salt_len = 113;
+ break;
}
}
*/
#include "cpu-md5.c"
+#include "cpu-sha1.c"
#include "cpu-sha256.c"
/**
else if (hash_mode == 13500)
{
pstoken_t *pstokens = (pstoken_t *) data.esalts_buf;
- pstoken_t *pstoken = &pstokens[salt_pos];
- uint mysalt = pstoken->salt_len > 512 ? 512 : pstoken->salt_len;
+ pstoken_t *pstoken = &pstokens[salt_pos];
- char pstoken_tmp[1024 + 1];
- u8 *salt_buf_ptr = (u8 *) pstoken->salt_buf;
+ const u32 salt_len = (pstoken->salt_len > 512) ? 512 : pstoken->salt_len;
- memset(pstoken_tmp, 0, sizeof (pstoken_tmp));
+ char pstoken_tmp[1024 + 1] = { 0 };
- for (uint i = 0; i < mysalt; i++)
+ for (uint i = 0, j = 0; i < salt_len; i += 1, j += 2)
{
- snprintf(&pstoken_tmp[i*2], 2, "%02x", salt_buf_ptr[i]);
+ const u8 *ptr = (const u8 *) pstoken->salt_buf;
+
+ sprintf (pstoken_tmp + j, "%02x", ptr[i]);
}
snprintf (out_buf, len-1, "%08x%08x%08x%08x%08x:%s",
- digest_buf[0],
- digest_buf[1],
- digest_buf[2],
- digest_buf[3],
- digest_buf[4],
- pstoken_tmp);
+ digest_buf[0],
+ digest_buf[1],
+ digest_buf[2],
+ digest_buf[3],
+ digest_buf[4],
+ pstoken_tmp);
}
else
{
int pstoken_parse_hash (char *input_buf, uint input_len, hash_t *hash_buf)
{
- if (data.opts_type & OPTS_TYPE_ST_HEX)
- {
- if ((input_len < DISPLAY_LEN_MIN_13500) || (input_len > DISPLAY_LEN_MAX_13500)) return (PARSER_GLOBAL_LENGTH);
- }
- else
- {
- if ((input_len < DISPLAY_LEN_MIN_13500) || (input_len > DISPLAY_LEN_MAX_13500)) return (PARSER_GLOBAL_LENGTH);
- }
+ if ((input_len < DISPLAY_LEN_MIN_13500) || (input_len > DISPLAY_LEN_MAX_13500)) return (PARSER_GLOBAL_LENGTH);
u32 *digest = (u32 *) hash_buf->digest;
+
salt_t *salt = hash_buf->salt;
- pstoken_t *pstoken = (pstoken_t *) hash_buf->esalt;
- u8 pstoken_tmp[DISPLAY_LEN_MAX_13500 - 40 - 1];
- memset(pstoken_tmp, 0, DISPLAY_LEN_MAX_13500 - 40 - 1);
+ pstoken_t *pstoken = (pstoken_t *) hash_buf->esalt;
digest[0] = hex_to_u32 ((const u8 *) &input_buf[ 0]);
digest[1] = hex_to_u32 ((const u8 *) &input_buf[ 8]);
if (salt_len == UINT_MAX || salt_len % 2 != 0) return (PARSER_SALT_LENGTH);
- for (uint i = 0; i < salt_len / 2; i++)
- {
- pstoken_tmp[i] = hex_to_u8 ((const u8 *) &salt_buf[i * 2]);
+ u8 *pstoken_ptr = (u8 *) pstoken->salt_buf;
+
+ for (uint i = 0, j = 0; i < salt_len; i += 2, j += 1)
+ {
+ pstoken_ptr[j] = hex_to_u8 ((const u8 *) &salt_buf[i]);
}
- salt_len /= 2;
- salt->salt_len = salt_len;
- pstoken->salt_len = salt_len;
+ pstoken->salt_len = salt_len / 2;
- memcpy(salt->salt_buf, pstoken_tmp, 16);
- memcpy(pstoken->salt_buf, pstoken_tmp, salt_len);
+ salt->salt_len = 32;
+
+ /* some fake salt for the sorting mechanisms */
+
+ salt->salt_buf[0] = pstoken->salt_buf[0];
+ salt->salt_buf[1] = pstoken->salt_buf[1];
+ salt->salt_buf[2] = pstoken->salt_buf[2];
+ salt->salt_buf[3] = pstoken->salt_buf[3];
+ salt->salt_buf[4] = pstoken->salt_buf[4];
+ salt->salt_buf[5] = pstoken->salt_buf[5];
+ salt->salt_buf[6] = pstoken->salt_buf[6];
+ salt->salt_buf[7] = pstoken->salt_buf[7];
+
+ salt->salt_len = 32;
+
+ /* we need to check if we can precompute some of the data --
+ this is possible since the scheme is badly designed */
+
+ pstoken->pc_digest[0] = SHA1M_A;
+ pstoken->pc_digest[1] = SHA1M_B;
+ pstoken->pc_digest[2] = SHA1M_C;
+ pstoken->pc_digest[3] = SHA1M_D;
+ pstoken->pc_digest[4] = SHA1M_E;
+
+ pstoken->pc_offset = 0;
+
+ for (uint i = 0; i < pstoken->salt_len - 64; i += 64)
+ {
+ uint w[16];
+
+ w[ 0] = byte_swap_32 (pstoken->salt_buf[i + 0]);
+ w[ 1] = byte_swap_32 (pstoken->salt_buf[i + 1]);
+ w[ 2] = byte_swap_32 (pstoken->salt_buf[i + 2]);
+ w[ 3] = byte_swap_32 (pstoken->salt_buf[i + 3]);
+ w[ 4] = byte_swap_32 (pstoken->salt_buf[i + 4]);
+ w[ 5] = byte_swap_32 (pstoken->salt_buf[i + 5]);
+ w[ 6] = byte_swap_32 (pstoken->salt_buf[i + 6]);
+ w[ 7] = byte_swap_32 (pstoken->salt_buf[i + 7]);
+ w[ 8] = byte_swap_32 (pstoken->salt_buf[i + 8]);
+ w[ 9] = byte_swap_32 (pstoken->salt_buf[i + 9]);
+ w[10] = byte_swap_32 (pstoken->salt_buf[i + 10]);
+ w[11] = byte_swap_32 (pstoken->salt_buf[i + 11]);
+ w[12] = byte_swap_32 (pstoken->salt_buf[i + 12]);
+ w[13] = byte_swap_32 (pstoken->salt_buf[i + 13]);
+ w[14] = byte_swap_32 (pstoken->salt_buf[i + 14]);
+ w[15] = byte_swap_32 (pstoken->salt_buf[i + 15]);
+
+ sha1_64 (w, pstoken->pc_digest);
+
+ pstoken->pc_offset += 16;
+ }
return (PARSER_OK);
}
use Digest::CRC qw (crc32);
use Crypt::PBKDF2;
use Crypt::DES;
-use Crypt::ECB 2.00, qw (encrypt);
+use Crypt::ECB qw (encrypt);
use Crypt::CBC;
use Crypt::Eksblowfish::Bcrypt qw (bcrypt en_base64);
use Crypt::Digest::RIPEMD160 qw (ripemd160_hex);
sub get_pstoken_salt
{
- # Cannot be fully random because of the salt structure, will use a constant salt.
- my $pstoken_const =
- "\x71\x00\x00\x00\x04\x03\x02\x01\x01\x00\x00\x00\xbc\x02" .
- "\x00\x00\x00\x00\x00\x00\x10\x50\x00\x50\x00\x57\x00\x45" .
- "\x00\x42\x00\x45\x00\x58\x00\x54\x00\x06\x45\x00\x4e\x00" .
- "\x47\x00\x0e\x50\x00\x53\x00\x46\x00\x54\x00\x5f\x00\x48" .
- "\x00\x52\x00\x34\x32\x00\x30\x00\x31\x00\x36\x00\x2d\x00" .
- "\x30\x00\x34\x00\x2d\x00\x30\x00\x38\x00\x2d\x00\x31\x00" .
- "\x39\x00\x2e\x00\x32\x00\x37\x00\x2e\x00\x30\x00\x35\x00" .
- "\x2e\x00\x30\x00\x30\x00\x30\x00\x30\x00\x30\x00\x32\x00" .
- "\x00";
-
- return unpack ("H*", $pstoken_const);
+ # Cannot be fully random because of the salt structure, will use a constant salt.
+ my $pstoken_const =
+ "\x71\x00\x00\x00\x04\x03\x02\x01\x01\x00\x00\x00\xbc\x02" .
+ "\x00\x00\x00\x00\x00\x00\x10\x50\x00\x50\x00\x57\x00\x45" .
+ "\x00\x42\x00\x45\x00\x58\x00\x54\x00\x06\x45\x00\x4e\x00" .
+ "\x47\x00\x0e\x50\x00\x53\x00\x46\x00\x54\x00\x5f\x00\x48" .
+ "\x00\x52\x00\x34\x32\x00\x30\x00\x31\x00\x36\x00\x2d\x00" .
+ "\x30\x00\x34\x00\x2d\x00\x30\x00\x38\x00\x2d\x00\x31\x00" .
+ "\x39\x00\x2e\x00\x32\x00\x37\x00\x2e\x00\x30\x00\x35\x00" .
+ "\x2e\x00\x30\x00\x30\x00\x30\x00\x30\x00\x30\x00\x32\x00" .
+ "\x00";
+
+ return unpack ("H*", $pstoken_const);
}
sub get_random_md5chap_salt
projects / hashcat.git / commitdiff