#define DGST_R3 3
#include "include/kernel_functions.c"
-#include "types_ocl.c"
-#include "common.c"
+#include "OpenCL/types_ocl.c"
+#include "OpenCL/common.c"
-#ifdef VECT_SIZE1
-#define COMPARE_M "check_multi_vect1_comp4.c"
-#endif
+#define COMPARE_S "OpenCL/check_single_comp4.c"
+#define COMPARE_M "OpenCL/check_multi_comp4.c"
-#ifdef VECT_SIZE2
-#define COMPARE_M "check_multi_vect2_comp4.c"
-#endif
-
-#ifdef VECT_SIZE4
-#define COMPARE_M "check_multi_vect4_comp4.c"
-#endif
-
-static void md5_transform (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[4])
+void md5_transform (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[4])
{
u32 a = digest[0];
u32 b = digest[1];
u32 we_t = w3[2];
u32 wf_t = w3[3];
- u32 tmp2;
-
MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
- MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+ MD5_STEP (MD5_H , a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H , d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H , c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H , b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H , a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H , d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H , c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H , b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H , a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H , d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H , c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H , b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H , a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H , d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H , c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H , b, c, d, a, w2_t, MD5C2f, MD5S23);
MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
digest[3] += d;
}
-static void hmac_md5_pad (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[4], u32 opad[4])
+void hmac_md5_pad (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[4], u32 opad[4])
{
w0[0] = w0[0] ^ 0x36363636;
w0[1] = w0[1] ^ 0x36363636;
md5_transform (w0, w1, w2, w3, opad);
}
-static void hmac_md5_run (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[4], u32 opad[4], u32 digest[4])
+void hmac_md5_run (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[4], u32 opad[4], u32 digest[4])
{
digest[0] = ipad[0];
digest[1] = ipad[1];
md5_transform (w0, w1, w2, w3, digest);
}
-static void sha1_transform (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[5])
+void sha1_transform (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[5])
{
u32 A = digest[0];
u32 B = digest[1];
digest[4] += E;
}
-static void hmac_sha1_pad (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5])
+void hmac_sha1_pad (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5])
{
w0[0] = w0[0] ^ 0x36363636;
w0[1] = w0[1] ^ 0x36363636;
sha1_transform (w0, w1, w2, w3, opad);
}
-static void hmac_sha1_run (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5], u32 digest[5])
+void hmac_sha1_run (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5], u32 digest[5])
{
digest[0] = ipad[0];
digest[1] = ipad[1];
sha1_transform (w0, w1, w2, w3, digest);
}
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m02500_init (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global wpa_tmp_t *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 wpa_t *wpa_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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m02500_init (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global wpa_tmp_t *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 wpa_t *wpa_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
* pads
*/
- w0[0] = swap_workaround (w0[0]);
- w0[1] = swap_workaround (w0[1]);
- w0[2] = swap_workaround (w0[2]);
- w0[3] = swap_workaround (w0[3]);
- w1[0] = swap_workaround (w1[0]);
- w1[1] = swap_workaround (w1[1]);
- w1[2] = swap_workaround (w1[2]);
- w1[3] = swap_workaround (w1[3]);
- w2[0] = swap_workaround (w2[0]);
- w2[1] = swap_workaround (w2[1]);
- w2[2] = swap_workaround (w2[2]);
- w2[3] = swap_workaround (w2[3]);
- w3[0] = swap_workaround (w3[0]);
- w3[1] = swap_workaround (w3[1]);
- w3[2] = swap_workaround (w3[2]);
- w3[3] = swap_workaround (w3[3]);
+ w0[0] = swap32 (w0[0]);
+ w0[1] = swap32 (w0[1]);
+ w0[2] = swap32 (w0[2]);
+ w0[3] = swap32 (w0[3]);
+ w1[0] = swap32 (w1[0]);
+ w1[1] = swap32 (w1[1]);
+ w1[2] = swap32 (w1[2]);
+ w1[3] = swap32 (w1[3]);
+ w2[0] = swap32 (w2[0]);
+ w2[1] = swap32 (w2[1]);
+ w2[2] = swap32 (w2[2]);
+ w2[3] = swap32 (w2[3]);
+ w3[0] = swap32 (w3[0]);
+ w3[1] = swap32 (w3[1]);
+ w3[2] = swap32 (w3[2]);
+ w3[3] = swap32 (w3[3]);
u32 ipad[5];
u32 opad[5];
append_0x80_3x4 (w0, w1, w2, salt_len + 4);
- w0[0] = swap_workaround (w0[0]);
- w0[1] = swap_workaround (w0[1]);
- w0[2] = swap_workaround (w0[2]);
- w0[3] = swap_workaround (w0[3]);
- w1[0] = swap_workaround (w1[0]);
- w1[1] = swap_workaround (w1[1]);
- w1[2] = swap_workaround (w1[2]);
- w1[3] = swap_workaround (w1[3]);
- w2[0] = swap_workaround (w2[0]);
- w2[1] = swap_workaround (w2[1]);
+ w0[0] = swap32 (w0[0]);
+ w0[1] = swap32 (w0[1]);
+ w0[2] = swap32 (w0[2]);
+ w0[3] = swap32 (w0[3]);
+ w1[0] = swap32 (w1[0]);
+ w1[1] = swap32 (w1[1]);
+ w1[2] = swap32 (w1[2]);
+ w1[3] = swap32 (w1[3]);
+ w2[0] = swap32 (w2[0]);
+ w2[1] = swap32 (w2[1]);
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
}
}
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m02500_loop (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global wpa_tmp_t *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 wpa_t *wpa_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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m02500_loop (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global wpa_tmp_t *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 wpa_t *wpa_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)
{
const u32 gid = get_global_id (0);
}
}
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m02500_comp (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global wpa_tmp_t *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 wpa_t *wpa_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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m02500_comp (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global wpa_tmp_t *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 wpa_t *wpa_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)
{
const u32 gid = get_global_id (0);
hmac_sha1_run (w0, w1, w2, w3, ipad, opad, digest);
{
- w0[0] = swap_workaround (digest[0]);
- w0[1] = swap_workaround (digest[1]);
- w0[2] = swap_workaround (digest[2]);
- w0[3] = swap_workaround (digest[3]);
+ w0[0] = swap32 (digest[0]);
+ w0[1] = swap32 (digest[1]);
+ w0[2] = swap32 (digest[2]);
+ w0[3] = swap32 (digest[3]);
w1[0] = 0;
w1[1] = 0;
w1[2] = 0;