Replace the substring GPU to a more appropriate "device" or "kernel" substring depend...

[hashcat.git] / OpenCL / m09800_a1.cl

diff --git a/OpenCL/m09800_a1.cl b/OpenCL/m09800_a1.cl
index fd77036..f66b403 100644 (file)
--- a/OpenCL/m09800_a1.cl
+++ b/OpenCL/m09800_a1.cl
@@ -14,11 +14,11 @@
 #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"
 
-#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"
 
 typedef struct
 {
@@ -52,7 +52,6 @@ static void rc4_init_16 (__local RC4_KEY *rc4_key, const u32 data[4])
 
   u32 j = 0;
 
-  #pragma unroll
   for (u32 i = 0; i < 16; i++)
   {
     u32 idx = i * 16;
@@ -268,7 +267,7 @@ static void sha1_transform (const u32 w0[4], const u32 w1[4], const u32 w2[4], c
   digest[4] += E;
 }
 
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m09800_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 oldoffice34_t *oldoffice34_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 __attribute__((reqd_work_group_size (64, 1, 1))) m09800_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 oldoffice34_t *oldoffice34_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)
 {
   /**
    * modifier
@@ -438,16 +437,16 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m09800_m04 (__glo
     w0_t[1] = salt_buf[1];
     w0_t[2] = salt_buf[2];
     w0_t[3] = salt_buf[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]);
+    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] = 0;
     w3_t[3] = pw_salt_len * 8;
 
@@ -488,10 +487,10 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m09800_m04 (__glo
 
     u32 key[4];
 
-    key[0] = swap_workaround (digest[0]);
-    key[1] = swap_workaround (digest[1]);
-    key[2] = swap_workaround (digest[2]);
-    key[3] = swap_workaround (digest[3]);
+    key[0] = swap32 (digest[0]);
+    key[1] = swap32 (digest[1]);
+    key[2] = swap32 (digest[2]);
+    key[3] = swap32 (digest[3]);
 
     if (version == 3)
     {
@@ -506,10 +505,10 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m09800_m04 (__glo
 
     u8 j = rc4_next_16 (rc4_key, 0, 0, encryptedVerifier, out);
 
-    w0_t[0] = swap_workaround (out[0]);
-    w0_t[1] = swap_workaround (out[1]);
-    w0_t[2] = swap_workaround (out[2]);
-    w0_t[3] = swap_workaround (out[3]);
+    w0_t[0] = swap32 (out[0]);
+    w0_t[1] = swap32 (out[1]);
+    w0_t[2] = swap32 (out[2]);
+    w0_t[3] = swap32 (out[3]);
     w1_t[0] = 0x80000000;
     w1_t[1] = 0;
     w1_t[2] = 0;
@@ -531,10 +530,10 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m09800_m04 (__glo
 
     sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
 
-    digest[0] = swap_workaround (digest[0]);
-    digest[1] = swap_workaround (digest[1]);
-    digest[2] = swap_workaround (digest[2]);
-    digest[3] = swap_workaround (digest[3]);
+    digest[0] = swap32 (digest[0]);
+    digest[1] = swap32 (digest[1]);
+    digest[2] = swap32 (digest[2]);
+    digest[3] = swap32 (digest[3]);
 
     rc4_next_16 (rc4_key, 16, j, digest, out);
 
@@ -547,15 +546,15 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m09800_m04 (__glo
   }
 }
 
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m09800_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 oldoffice34_t *oldoffice34_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 __attribute__((reqd_work_group_size (64, 1, 1))) m09800_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 oldoffice34_t *oldoffice34_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 __attribute__((reqd_work_group_size (64, 1, 1))) m09800_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 oldoffice34_t *oldoffice34_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 __attribute__((reqd_work_group_size (64, 1, 1))) m09800_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 oldoffice34_t *oldoffice34_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 __attribute__((reqd_work_group_size (64, 1, 1))) m09800_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 oldoffice34_t *oldoffice34_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 __attribute__((reqd_work_group_size (64, 1, 1))) m09800_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 oldoffice34_t *oldoffice34_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)
 {
   /**
    * modifier
@@ -737,16 +736,16 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m09800_s04 (__glo
     w0_t[1] = salt_buf[1];
     w0_t[2] = salt_buf[2];
     w0_t[3] = salt_buf[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]);
+    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] = 0;
     w3_t[3] = pw_salt_len * 8;
 
@@ -787,10 +786,10 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m09800_s04 (__glo
 
     u32 key[4];
 
-    key[0] = swap_workaround (digest[0]);
-    key[1] = swap_workaround (digest[1]);
-    key[2] = swap_workaround (digest[2]);
-    key[3] = swap_workaround (digest[3]);
+    key[0] = swap32 (digest[0]);
+    key[1] = swap32 (digest[1]);
+    key[2] = swap32 (digest[2]);
+    key[3] = swap32 (digest[3]);
 
     if (version == 3)
     {
@@ -805,10 +804,10 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m09800_s04 (__glo
 
     u8 j = rc4_next_16 (rc4_key, 0, 0, encryptedVerifier, out);
 
-    w0_t[0] = swap_workaround (out[0]);
-    w0_t[1] = swap_workaround (out[1]);
-    w0_t[2] = swap_workaround (out[2]);
-    w0_t[3] = swap_workaround (out[3]);
+    w0_t[0] = swap32 (out[0]);
+    w0_t[1] = swap32 (out[1]);
+    w0_t[2] = swap32 (out[2]);
+    w0_t[3] = swap32 (out[3]);
     w1_t[0] = 0x80000000;
     w1_t[1] = 0;
     w1_t[2] = 0;
@@ -830,10 +829,10 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m09800_s04 (__glo
 
     sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
 
-    digest[0] = swap_workaround (digest[0]);
-    digest[1] = swap_workaround (digest[1]);
-    digest[2] = swap_workaround (digest[2]);
-    digest[3] = swap_workaround (digest[3]);
+    digest[0] = swap32 (digest[0]);
+    digest[1] = swap32 (digest[1]);
+    digest[2] = swap32 (digest[2]);
+    digest[3] = swap32 (digest[3]);
 
     rc4_next_16 (rc4_key, 16, j, digest, out);
 
@@ -846,10 +845,10 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m09800_s04 (__glo
   }
 }
 
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m09800_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 oldoffice34_t *oldoffice34_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 __attribute__((reqd_work_group_size (64, 1, 1))) m09800_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 oldoffice34_t *oldoffice34_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 __attribute__((reqd_work_group_size (64, 1, 1))) m09800_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 oldoffice34_t *oldoffice34_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 __attribute__((reqd_work_group_size (64, 1, 1))) m09800_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 oldoffice34_t *oldoffice34_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)
 {
 }