X-Git-Url: https://www.flypig.org.uk/git/?a=blobdiff_plain;f=OpenCL%2Fm07900.cl;h=599facdca98721f1db1a415a59cc09abf89e5e37;hb=161a6eb4bc643d8e636e96eda613f5137d30da59;hp=66061ea373cc182390a5714d1f01868d2cb13459;hpb=50f39b3563fa429dbec441288bd9a21fc328c21e;p=hashcat.git

diff --git a/OpenCL/m07900.cl b/OpenCL/m07900.cl
index 66061ea..599facd 100644
--- a/OpenCL/m07900.cl
+++ b/OpenCL/m07900.cl
@@ -5,21 +5,14 @@
 
 #define _SHA512_
 
-#include "include/constants.h"
-#include "include/kernel_vendor.h"
+#include "inc_vendor.cl"
+#include "inc_hash_constants.h"
+#include "inc_hash_functions.cl"
+#include "inc_types.cl"
+#include "inc_common.cl"
 
-#define DGST_R0 0
-#define DGST_R1 1
-#define DGST_R2 2
-#define DGST_R3 3
-
-#include "include/kernel_functions.c"
-#include "types_ocl.c"
-#include "common.c"
-
-#ifdef  VECT_SIZE1
-#define COMPARE_M "check_multi_vect1_comp4.c"
-#endif
+#define COMPARE_S "inc_comp_single.cl"
+#define COMPARE_M "inc_comp_multi.cl"
 
 __constant u64 k_sha512[80] =
 {
@@ -45,7 +38,7 @@ __constant u64 k_sha512[80] =
   SHA512C4c, SHA512C4d, SHA512C4e, SHA512C4f,
 };
 
-static void sha512_transform (const u64 w[16], u64 dgst[8])
+void sha512_transform (const u64 w[16], u64 dgst[8])
 {
   u64 a = dgst[0];
   u64 b = dgst[1];
@@ -115,7 +108,9 @@ static void sha512_transform (const u64 w[16], u64 dgst[8])
 
   ROUND_STEP (0);
 
+  #ifdef _unroll
   #pragma unroll
+  #endif
   for (int i = 16; i < 80; i += 16)
   {
     ROUND_EXPAND (); ROUND_STEP (i);
@@ -131,7 +126,7 @@ static void sha512_transform (const u64 w[16], u64 dgst[8])
   dgst[7] += h;
 }
 
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m07900_init (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global drupal7_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 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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m07900_init (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global drupal7_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 void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_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
@@ -190,15 +185,15 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m07900_init (__gl
 
   u64 w[16];
 
-  w[ 0] = ((u64) swap_workaround (salt_buf[0])) << 32 | (u64) swap_workaround (salt_buf[1]);
-  w[ 1] = ((u64) swap_workaround (w0[0])) << 32 | (u64) swap_workaround (w0[1]);
-  w[ 2] = ((u64) swap_workaround (w0[2])) << 32 | (u64) swap_workaround (w0[3]);
-  w[ 3] = ((u64) swap_workaround (w1[0])) << 32 | (u64) swap_workaround (w1[1]);
-  w[ 4] = ((u64) swap_workaround (w1[2])) << 32 | (u64) swap_workaround (w1[3]);
-  w[ 5] = ((u64) swap_workaround (w2[0])) << 32 | (u64) swap_workaround (w2[1]);
-  w[ 6] = ((u64) swap_workaround (w2[2])) << 32 | (u64) swap_workaround (w2[3]);
-  w[ 7] = ((u64) swap_workaround (w3[0])) << 32 | (u64) swap_workaround (w3[1]);
-  w[ 8] = ((u64) swap_workaround (w3[2])) << 32 | (u64) swap_workaround (w3[3]);
+  w[ 0] = ((u64) swap32 (salt_buf[0])) << 32 | (u64) swap32 (salt_buf[1]);
+  w[ 1] = ((u64) swap32 (w0[0])) << 32 | (u64) swap32 (w0[1]);
+  w[ 2] = ((u64) swap32 (w0[2])) << 32 | (u64) swap32 (w0[3]);
+  w[ 3] = ((u64) swap32 (w1[0])) << 32 | (u64) swap32 (w1[1]);
+  w[ 4] = ((u64) swap32 (w1[2])) << 32 | (u64) swap32 (w1[3]);
+  w[ 5] = ((u64) swap32 (w2[0])) << 32 | (u64) swap32 (w2[1]);
+  w[ 6] = ((u64) swap32 (w2[2])) << 32 | (u64) swap32 (w2[3]);
+  w[ 7] = ((u64) swap32 (w3[0])) << 32 | (u64) swap32 (w3[1]);
+  w[ 8] = ((u64) swap32 (w3[2])) << 32 | (u64) swap32 (w3[3]);
   w[ 9] = 0;
   w[10] = 0;
   w[11] = 0;
@@ -234,7 +229,7 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m07900_init (__gl
   tmps[gid].digest_buf[7] = digest[7];
 }
 
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m07900_loop (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global drupal7_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 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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m07900_loop (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global drupal7_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 void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_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
@@ -307,12 +302,12 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m07900_loop (__gl
   w[ 5] = 0;
   w[ 6] = 0;
   w[ 7] = 0;
-  w[ 8] = ((u64) swap_workaround (w0[0])) << 32 | (u64) swap_workaround (w0[1]);
-  w[ 9] = ((u64) swap_workaround (w0[2])) << 32 | (u64) swap_workaround (w0[3]);
-  w[10] = ((u64) swap_workaround (w1[0])) << 32 | (u64) swap_workaround (w1[1]);
-  w[11] = ((u64) swap_workaround (w1[2])) << 32 | (u64) swap_workaround (w1[3]);
-  w[12] = ((u64) swap_workaround (w2[0])) << 32 | (u64) swap_workaround (w2[1]);
-  w[13] = ((u64) swap_workaround (w2[2])) << 32 | (u64) swap_workaround (w2[3]);
+  w[ 8] = ((u64) swap32 (w0[0])) << 32 | (u64) swap32 (w0[1]);
+  w[ 9] = ((u64) swap32 (w0[2])) << 32 | (u64) swap32 (w0[3]);
+  w[10] = ((u64) swap32 (w1[0])) << 32 | (u64) swap32 (w1[1]);
+  w[11] = ((u64) swap32 (w1[2])) << 32 | (u64) swap32 (w1[3]);
+  w[12] = ((u64) swap32 (w2[0])) << 32 | (u64) swap32 (w2[1]);
+  w[13] = ((u64) swap32 (w2[2])) << 32 | (u64) swap32 (w2[3]);
   w[14] = 0;
   w[15] = block_len * 8;
 
@@ -353,7 +348,7 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m07900_loop (__gl
   tmps[gid].digest_buf[7] = digest[7];
 }
 
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m07900_comp (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global drupal7_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 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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m07900_comp (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global drupal7_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 void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_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