Fixed two major problems

[hashcat.git] / OpenCL / m08100_a1.cl

diff --git a/OpenCL/m08100_a1.cl b/OpenCL/m08100_a1.cl
index fa5f44b..144bf82 100644 (file)
--- a/OpenCL/m08100_a1.cl
+++ b/OpenCL/m08100_a1.cl
@@ -14,13 +14,13 @@
 #define DGST_R3 1
 
 #include "include/kernel_functions.c"
-#include "types_ocl.c"
-#include "common.c"
+#include "OpenCL/types_ocl.c"
+#include "OpenCL/common.c"
 
-#define COMPARE_S "check_single_comp4.c"
-#define COMPARE_M "check_multi_comp4.c"
+#define COMPARE_S "OpenCL/check_single_comp4.c"
+#define COMPARE_M "OpenCL/check_multi_comp4.c"
 
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08100_m04 (__global pw_t *pws, __global gpu_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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m08100_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
@@ -68,7 +68,7 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08100_m04 (__glo
 
   if (combs_mode == COMBINATOR_MODE_BASE_RIGHT)
   {
-    switch_buffer_by_offset (wordl0, wordl1, wordl2, wordl3, combs_buf[0].pw_len);
+    switch_buffer_by_offset_le (wordl0, wordl1, wordl2, wordl3, combs_buf[0].pw_len);
   }
 
   /**
@@ -77,8 +77,8 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08100_m04 (__glo
 
   u32 salt_buf0[2];
 
-  salt_buf0[0] = swap_workaround (salt_bufs[salt_pos].salt_buf[0]);
-  salt_buf0[1] = swap_workaround (salt_bufs[salt_pos].salt_buf[1]);
+  salt_buf0[0] = swap32 (salt_bufs[salt_pos].salt_buf[0]);
+  salt_buf0[1] = swap32 (salt_bufs[salt_pos].salt_buf[1]);
 
   const u32 salt_len = salt_bufs[salt_pos].salt_len;
 
@@ -86,7 +86,7 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08100_m04 (__glo
    * loop
    */
 
-  for (u32 il_pos = 0; il_pos < combs_cnt; il_pos++)
+  for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
   {
     const u32 pw_r_len = combs_buf[il_pos].pw_len;
 
@@ -116,7 +116,7 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08100_m04 (__glo
 
     if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
     {
-      switch_buffer_by_offset (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+      switch_buffer_by_offset_le (wordr0, wordr1, wordr2, wordr3, pw_l_len);
     }
 
     u32 w0[4];
@@ -169,28 +169,28 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08100_m04 (__glo
     w3_t[2] = 0;
     w3_t[3] = (pw_salt_len + 1) * 8;
 
-    append_0x80_4 (w0_t, w1_t, w2_t, w3_t, pw_salt_len + 1);
+    append_0x80_4x4 (w0_t, w1_t, w2_t, w3_t, pw_salt_len + 1);
 
     /**
      * sha1
      */
 
-    w0_t[0] = swap_workaround (w0_t[0]);
-    w0_t[1] = swap_workaround (w0_t[1]);
-    w0_t[2] = swap_workaround (w0_t[2]);
-    w0_t[3] = swap_workaround (w0_t[3]);
-    w1_t[0] = swap_workaround (w1_t[0]);
-    w1_t[1] = swap_workaround (w1_t[1]);
-    w1_t[2] = swap_workaround (w1_t[2]);
-    w1_t[3] = swap_workaround (w1_t[3]);
-    w2_t[0] = swap_workaround (w2_t[0]);
-    w2_t[1] = swap_workaround (w2_t[1]);
-    w2_t[2] = swap_workaround (w2_t[2]);
-    w2_t[3] = swap_workaround (w2_t[3]);
-    w3_t[0] = swap_workaround (w3_t[0]);
-    w3_t[1] = swap_workaround (w3_t[1]);
-    //w3_t[2] = swap_workaround (w3_t[2]);
-    //w3_t[3] = swap_workaround (w3_t[3]);
+    w0_t[0] = swap32 (w0_t[0]);
+    w0_t[1] = swap32 (w0_t[1]);
+    w0_t[2] = swap32 (w0_t[2]);
+    w0_t[3] = swap32 (w0_t[3]);
+    w1_t[0] = swap32 (w1_t[0]);
+    w1_t[1] = swap32 (w1_t[1]);
+    w1_t[2] = swap32 (w1_t[2]);
+    w1_t[3] = swap32 (w1_t[3]);
+    w2_t[0] = swap32 (w2_t[0]);
+    w2_t[1] = swap32 (w2_t[1]);
+    w2_t[2] = swap32 (w2_t[2]);
+    w2_t[3] = swap32 (w2_t[3]);
+    w3_t[0] = swap32 (w3_t[0]);
+    w3_t[1] = swap32 (w3_t[1]);
+    //w3_t[2] = swap32 (w3_t[2]);
+    //w3_t[3] = swap32 (w3_t[3]);
 
     u32 a = SHA1M_A;
     u32 b = SHA1M_B;
@@ -303,15 +303,15 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08100_m04 (__glo
   }
 }
 
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08100_m08 (__global pw_t *pws, __global gpu_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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m08100_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 __attribute__((reqd_work_group_size (64, 1, 1))) m08100_m16 (__global pw_t *pws, __global gpu_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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m08100_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 __attribute__((reqd_work_group_size (64, 1, 1))) m08100_s04 (__global pw_t *pws, __global gpu_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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m08100_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
@@ -359,7 +359,7 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08100_s04 (__glo
 
   if (combs_mode == COMBINATOR_MODE_BASE_RIGHT)
   {
-    switch_buffer_by_offset (wordl0, wordl1, wordl2, wordl3, combs_buf[0].pw_len);
+    switch_buffer_by_offset_le (wordl0, wordl1, wordl2, wordl3, combs_buf[0].pw_len);
   }
 
   /**
@@ -368,8 +368,8 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08100_s04 (__glo
 
   u32 salt_buf0[2];
 
-  salt_buf0[0] = swap_workaround (salt_bufs[salt_pos].salt_buf[0]);
-  salt_buf0[1] = swap_workaround (salt_bufs[salt_pos].salt_buf[1]);
+  salt_buf0[0] = swap32 (salt_bufs[salt_pos].salt_buf[0]);
+  salt_buf0[1] = swap32 (salt_bufs[salt_pos].salt_buf[1]);
 
   const u32 salt_len = salt_bufs[salt_pos].salt_len;
 
@@ -395,7 +395,7 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08100_s04 (__glo
    * loop
    */
 
-  for (u32 il_pos = 0; il_pos < combs_cnt; il_pos++)
+  for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
   {
     const u32 pw_r_len = combs_buf[il_pos].pw_len;
 
@@ -425,7 +425,7 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08100_s04 (__glo
 
     if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
     {
-      switch_buffer_by_offset (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+      switch_buffer_by_offset_le (wordr0, wordr1, wordr2, wordr3, pw_l_len);
     }
 
     u32 w0[4];
@@ -478,28 +478,28 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08100_s04 (__glo
     w3_t[2] = 0;
     w3_t[3] = (pw_salt_len + 1) * 8;
 
-    append_0x80_4 (w0_t, w1_t, w2_t, w3_t, pw_salt_len + 1);
+    append_0x80_4x4 (w0_t, w1_t, w2_t, w3_t, pw_salt_len + 1);
 
     /**
      * sha1
      */
 
-    w0_t[0] = swap_workaround (w0_t[0]);
-    w0_t[1] = swap_workaround (w0_t[1]);
-    w0_t[2] = swap_workaround (w0_t[2]);
-    w0_t[3] = swap_workaround (w0_t[3]);
-    w1_t[0] = swap_workaround (w1_t[0]);
-    w1_t[1] = swap_workaround (w1_t[1]);
-    w1_t[2] = swap_workaround (w1_t[2]);
-    w1_t[3] = swap_workaround (w1_t[3]);
-    w2_t[0] = swap_workaround (w2_t[0]);
-    w2_t[1] = swap_workaround (w2_t[1]);
-    w2_t[2] = swap_workaround (w2_t[2]);
-    w2_t[3] = swap_workaround (w2_t[3]);
-    w3_t[0] = swap_workaround (w3_t[0]);
-    w3_t[1] = swap_workaround (w3_t[1]);
-    //w3_t[2] = swap_workaround (w3_t[2]);
-    //w3_t[3] = swap_workaround (w3_t[3]);
+    w0_t[0] = swap32 (w0_t[0]);
+    w0_t[1] = swap32 (w0_t[1]);
+    w0_t[2] = swap32 (w0_t[2]);
+    w0_t[3] = swap32 (w0_t[3]);
+    w1_t[0] = swap32 (w1_t[0]);
+    w1_t[1] = swap32 (w1_t[1]);
+    w1_t[2] = swap32 (w1_t[2]);
+    w1_t[3] = swap32 (w1_t[3]);
+    w2_t[0] = swap32 (w2_t[0]);
+    w2_t[1] = swap32 (w2_t[1]);
+    w2_t[2] = swap32 (w2_t[2]);
+    w2_t[3] = swap32 (w2_t[3]);
+    w3_t[0] = swap32 (w3_t[0]);
+    w3_t[1] = swap32 (w3_t[1]);
+    //w3_t[2] = swap32 (w3_t[2]);
+    //w3_t[3] = swap32 (w3_t[3]);
 
     u32 a = SHA1M_A;
     u32 b = SHA1M_B;
@@ -615,10 +615,10 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08100_s04 (__glo
   }
 }
 
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08100_s08 (__global pw_t *pws, __global gpu_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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m08100_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 __attribute__((reqd_work_group_size (64, 1, 1))) m08100_s16 (__global pw_t *pws, __global gpu_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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m08100_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)
 {
 }