Move macros DGST_R0 - DGST_R3 to host, define dgst_size for opencl kernel from host...

[hashcat.git] / OpenCL / m06100_a3.cl

diff --git a/OpenCL/m06100_a3.cl b/OpenCL/m06100_a3.cl
index 516789d..af2bd71 100644 (file)
--- a/OpenCL/m06100_a3.cl
+++ b/OpenCL/m06100_a3.cl
@@ -10,18 +10,12 @@
 
 #define NEW_SIMD_CODE
 
-#include "include/constants.h"
-#include "include/kernel_vendor.h"
-
-#define DGST_R0 0
-#define DGST_R1 1
-#define DGST_R2 2
-#define DGST_R3 3
-
-#include "include/kernel_functions.c"
-#include "OpenCL/types_ocl.c"
-#include "OpenCL/common.c"
-#include "OpenCL/simd.c"
+#include "inc_vendor.cl"
+#include "inc_hash_constants.h"
+#include "inc_hash_functions.cl"
+#include "inc_types.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
 
 #define R 10
 
@@ -1133,7 +1127,7 @@ __constant u32 rcl[R + 1] =
 
 // this is a highly optimized that assumes dgst[16] = { 0 }; only reuse of no 2nd transform is needed
 
-static void whirlpool_transform (const u32x w[16], u32x dgst[16], __local u32 (*s_Ch)[256], __local u32 (*s_Cl)[256])
+void whirlpool_transform (const u32x w[16], u32x dgst[16], __local u32 (*s_Ch)[256], __local u32 (*s_Cl)[256])
 {
   u32x Kh[8];
   u32x Kl[8];
@@ -1178,7 +1172,9 @@ static void whirlpool_transform (const u32x w[16], u32x dgst[16], __local u32 (*
   u32x Lh[8];
   u32x Ll[8];
 
+  #ifdef _unroll
   #pragma unroll
+  #endif
   for (int i = 0; i < 8; i++)
   {
     const u32x Lp0 = stateh[(i + 8) & 7] >> 24;
@@ -1231,7 +1227,9 @@ static void whirlpool_transform (const u32x w[16], u32x dgst[16], __local u32 (*
     u32x Lh[8];
     u32x Ll[8];
 
+    #ifdef _unroll
     #pragma unroll
+    #endif
     for (int i = 0; i < 8; i++)
     {
       const u32x Lp0 = Kh[(i + 8) & 7] >> 24;
@@ -1279,7 +1277,9 @@ static void whirlpool_transform (const u32x w[16], u32x dgst[16], __local u32 (*
     Kh[7] = Lh[7];
     Kl[7] = Ll[7];
 
-    #pragma unroll 8
+    #ifdef _unroll
+    #pragma unroll
+    #endif
     for (int i = 0; i < 8; i++)
     {
       const u32x Lp0 = stateh[(i + 8) & 7] >> 24;
@@ -1346,7 +1346,7 @@ static void whirlpool_transform (const u32x w[16], u32x dgst[16], __local u32 (*
   dgst[15] = statel[7] ^ w[15];
 }
 
-static void m06100m (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 (*s_Cl)[256], __local u32 (*s_Ch)[256])
+void m06100m (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 (*s_Cl)[256], __local u32 (*s_Ch)[256])
 {
   /**
    * modifier
@@ -1415,7 +1415,7 @@ static void m06100m (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_le
   }
 }
 
-static void m06100s (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 (*s_Cl)[256], __local u32 (*s_Ch)[256])
+void m06100s (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 (*s_Cl)[256], __local u32 (*s_Ch)[256])
 {
   /**
    * modifier