#define NEW_SIMD_CODE
-#include "include/constants.h"
-#include "include/kernel_vendor.h"
+#include "inc_hash_constants.h"
+#include "inc_vendor.cl"
#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"
+#include "inc_hash_functions.cl"
+#include "inc_types.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
#if VECT_SIZE == 1
#define uint_to_hex_lower8(i) (u32x) (l_bin2asc[(i)])
#define uint_to_hex_lower8(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-static void m07600m (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, __local u32 *l_bin2asc)
+void m07600m (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, __local u32 *l_bin2asc)
{
/**
* modifier
*/
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];
-
- u32 salt_buf1[4];
-
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];
- u32 salt_buf2[4];
-
- salt_buf2[0] = 0;
- salt_buf2[1] = 0;
- salt_buf2[2] = 0;
- salt_buf2[3] = 0;
-
- u32 salt_buf3[4];
-
- salt_buf3[0] = 0;
- salt_buf3[1] = 0;
- salt_buf3[2] = 0;
- salt_buf3[3] = 0;
-
- const u32 total_len = (32 + 40) * 8;
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
/**
* loop
* Prepend salt
*/
- u32x w0t[4];
-
- w0t[0] = uint_to_hex_lower8 ((a >> 24) & 255) << 0
- | uint_to_hex_lower8 ((a >> 16) & 255) << 16;
- w0t[1] = uint_to_hex_lower8 ((a >> 8) & 255) << 0
- | uint_to_hex_lower8 ((a >> 0) & 255) << 16;
- w0t[2] = uint_to_hex_lower8 ((b >> 24) & 255) << 0
- | uint_to_hex_lower8 ((b >> 16) & 255) << 16;
- w0t[3] = uint_to_hex_lower8 ((b >> 8) & 255) << 0
- | uint_to_hex_lower8 ((b >> 0) & 255) << 16;
-
- u32x w1t[4];
-
- w1t[0] = uint_to_hex_lower8 ((c >> 24) & 255) << 0
- | uint_to_hex_lower8 ((c >> 16) & 255) << 16;
- w1t[1] = uint_to_hex_lower8 ((c >> 8) & 255) << 0
- | uint_to_hex_lower8 ((c >> 0) & 255) << 16;
- w1t[2] = uint_to_hex_lower8 ((d >> 24) & 255) << 0
- | uint_to_hex_lower8 ((d >> 16) & 255) << 16;
- w1t[3] = uint_to_hex_lower8 ((d >> 8) & 255) << 0
- | uint_to_hex_lower8 ((d >> 0) & 255) << 16;
-
- u32x w2t[2];
-
- w2t[0] = uint_to_hex_lower8 ((e >> 24) & 255) << 0
- | uint_to_hex_lower8 ((e >> 16) & 255) << 16;
- w2t[1] = uint_to_hex_lower8 ((e >> 8) & 255) << 0
- | uint_to_hex_lower8 ((e >> 0) & 255) << 16;
-
w0_t = salt_buf0[0];
w1_t = salt_buf0[1];
w2_t = salt_buf0[2];
w5_t = salt_buf1[1];
w6_t = salt_buf1[2];
w7_t = salt_buf1[3];
- w8_t = w0t[0];
- w9_t = w0t[1];
- wa_t = w0t[2];
- wb_t = w0t[3];
- wc_t = w1t[0];
- wd_t = w1t[1];
- we_t = w1t[2];
- wf_t = w1t[3];
+ w8_t = uint_to_hex_lower8 ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a >> 16) & 255) << 16;
+ w9_t = uint_to_hex_lower8 ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a >> 0) & 255) << 16;
+ wa_t = uint_to_hex_lower8 ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b >> 16) & 255) << 16;
+ wb_t = uint_to_hex_lower8 ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b >> 0) & 255) << 16;
+ wc_t = uint_to_hex_lower8 ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c >> 16) & 255) << 16;
+ wd_t = uint_to_hex_lower8 ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c >> 0) & 255) << 16;
+ we_t = uint_to_hex_lower8 ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d >> 16) & 255) << 16;
+ wf_t = uint_to_hex_lower8 ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d >> 0) & 255) << 16;
+
+ const u32x e_sav = e;
/**
* 2nd SHA1
// 2nd transform
- w0_t = swap32 (w2t[0]);
- w1_t = swap32 (w2t[1]);
+ w0_t = uint_to_hex_lower8 ((e_sav >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e_sav >> 16) & 255) << 16;
+ w1_t = uint_to_hex_lower8 ((e_sav >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e_sav >> 0) & 255) << 16;
w2_t = 0x80000000;
w3_t = 0;
w4_t = 0;
wc_t = 0;
wd_t = 0;
we_t = 0;
- wf_t = total_len;
+ wf_t = (salt_len + 40) * 8;
+
+ w0_t = swap32 (w0_t);
+ w1_t = swap32 (w1_t);
#undef K
#define K SHA1C00
}
}
-static void m07600s (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, __local u32 *l_bin2asc)
+void m07600s (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, __local u32 *l_bin2asc)
{
/**
* modifier
*/
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];
-
- u32 salt_buf1[4];
-
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];
- u32 salt_buf2[4];
-
- salt_buf2[0] = 0;
- salt_buf2[1] = 0;
- salt_buf2[2] = 0;
- salt_buf2[3] = 0;
-
- u32 salt_buf3[4];
-
- salt_buf3[0] = 0;
- salt_buf3[1] = 0;
- salt_buf3[2] = 0;
- salt_buf3[3] = 0;
-
- const u32 total_len = (32 + 40) * 8;
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
/**
* digest
* Prepend salt
*/
- u32x w0t[4];
-
- w0t[0] = uint_to_hex_lower8 ((a >> 24) & 255) << 0
- | uint_to_hex_lower8 ((a >> 16) & 255) << 16;
- w0t[1] = uint_to_hex_lower8 ((a >> 8) & 255) << 0
- | uint_to_hex_lower8 ((a >> 0) & 255) << 16;
- w0t[2] = uint_to_hex_lower8 ((b >> 24) & 255) << 0
- | uint_to_hex_lower8 ((b >> 16) & 255) << 16;
- w0t[3] = uint_to_hex_lower8 ((b >> 8) & 255) << 0
- | uint_to_hex_lower8 ((b >> 0) & 255) << 16;
-
- u32x w1t[4];
-
- w1t[0] = uint_to_hex_lower8 ((c >> 24) & 255) << 0
- | uint_to_hex_lower8 ((c >> 16) & 255) << 16;
- w1t[1] = uint_to_hex_lower8 ((c >> 8) & 255) << 0
- | uint_to_hex_lower8 ((c >> 0) & 255) << 16;
- w1t[2] = uint_to_hex_lower8 ((d >> 24) & 255) << 0
- | uint_to_hex_lower8 ((d >> 16) & 255) << 16;
- w1t[3] = uint_to_hex_lower8 ((d >> 8) & 255) << 0
- | uint_to_hex_lower8 ((d >> 0) & 255) << 16;
-
- u32x w2t[2];
-
- w2t[0] = uint_to_hex_lower8 ((e >> 24) & 255) << 0
- | uint_to_hex_lower8 ((e >> 16) & 255) << 16;
- w2t[1] = uint_to_hex_lower8 ((e >> 8) & 255) << 0
- | uint_to_hex_lower8 ((e >> 0) & 255) << 16;
-
w0_t = salt_buf0[0];
w1_t = salt_buf0[1];
w2_t = salt_buf0[2];
w5_t = salt_buf1[1];
w6_t = salt_buf1[2];
w7_t = salt_buf1[3];
- w8_t = w0t[0];
- w9_t = w0t[1];
- wa_t = w0t[2];
- wb_t = w0t[3];
- wc_t = w1t[0];
- wd_t = w1t[1];
- we_t = w1t[2];
- wf_t = w1t[3];
+ w8_t = uint_to_hex_lower8 ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a >> 16) & 255) << 16;
+ w9_t = uint_to_hex_lower8 ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a >> 0) & 255) << 16;
+ wa_t = uint_to_hex_lower8 ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b >> 16) & 255) << 16;
+ wb_t = uint_to_hex_lower8 ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b >> 0) & 255) << 16;
+ wc_t = uint_to_hex_lower8 ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c >> 16) & 255) << 16;
+ wd_t = uint_to_hex_lower8 ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c >> 0) & 255) << 16;
+ we_t = uint_to_hex_lower8 ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d >> 16) & 255) << 16;
+ wf_t = uint_to_hex_lower8 ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d >> 0) & 255) << 16;
+
+ const u32x e_sav = e;
/**
* 2nd SHA1
// 2nd transform
- w0_t = swap32 (w2t[0]);
- w1_t = swap32 (w2t[1]);
+ w0_t = uint_to_hex_lower8 ((e_sav >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e_sav >> 16) & 255) << 16;
+ w1_t = uint_to_hex_lower8 ((e_sav >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e_sav >> 0) & 255) << 16;
w2_t = 0x80000000;
w3_t = 0;
w4_t = 0;
wc_t = 0;
wd_t = 0;
we_t = 0;
- wf_t = total_len;
+ wf_t = (salt_len + 40) * 8;
+
+ w0_t = swap32 (w0_t);
+ w1_t = swap32 (w1_t);
#undef K
#define K SHA1C00