Converted _a3 kernels, use SIMD for CPU and GPU

[hashcat.git] / OpenCL / m01420_a0.cl

diff --git a/OpenCL/m01420_a0.cl b/OpenCL/m01420_a0.cl
index 71e7f4f..726b992 100644 (file)
--- a/OpenCL/m01420_a0.cl
+++ b/OpenCL/m01420_a0.cl
@@ -14,15 +14,15 @@
 #define DGST_R3 6
 
 #include "include/kernel_functions.c"
-#include "types_ocl.c"
-#include "common.c"
-#include "include/rp_gpu.h"
-#include "rp.c"
+#include "OpenCL/types_ocl.c"
+#include "OpenCL/common.c"
+#include "include/rp_kernel.h"
+#include "OpenCL/rp.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))) m01420_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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m01420_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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
 {
   /**
    * modifier
@@ -116,7 +116,7 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01420_m04 (__glo
 
     const u32 out_salt_len = out_len + salt_len;
 
-    switch_buffer_by_offset (w0, w1, w2, w3, salt_len);
+    switch_buffer_by_offset_le (w0, w1, w2, w3, salt_len);
 
     w0[0] |= salt_buf0[0];
     w0[1] |= salt_buf0[1];
@@ -127,26 +127,26 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01420_m04 (__glo
     w1[2] |= salt_buf1[2];
     w1[3] |= salt_buf1[3];
 
-    append_0x80_4 (w0, w1, w2, w3, out_salt_len);
+    append_0x80_4x4 (w0, w1, w2, w3, out_salt_len);
 
     /**
      * sha256
      */
 
-    u32 w0_t = swap_workaround (w0[0]);
-    u32 w1_t = swap_workaround (w0[1]);
-    u32 w2_t = swap_workaround (w0[2]);
-    u32 w3_t = swap_workaround (w0[3]);
-    u32 w4_t = swap_workaround (w1[0]);
-    u32 w5_t = swap_workaround (w1[1]);
-    u32 w6_t = swap_workaround (w1[2]);
-    u32 w7_t = swap_workaround (w1[3]);
-    u32 w8_t = swap_workaround (w2[0]);
-    u32 w9_t = swap_workaround (w2[1]);
-    u32 wa_t = swap_workaround (w2[2]);
-    u32 wb_t = swap_workaround (w2[3]);
-    u32 wc_t = swap_workaround (w3[0]);
-    u32 wd_t = swap_workaround (w3[1]);
+    u32 w0_t = swap32 (w0[0]);
+    u32 w1_t = swap32 (w0[1]);
+    u32 w2_t = swap32 (w0[2]);
+    u32 w3_t = swap32 (w0[3]);
+    u32 w4_t = swap32 (w1[0]);
+    u32 w5_t = swap32 (w1[1]);
+    u32 w6_t = swap32 (w1[2]);
+    u32 w7_t = swap32 (w1[3]);
+    u32 w8_t = swap32 (w2[0]);
+    u32 w9_t = swap32 (w2[1]);
+    u32 wa_t = swap32 (w2[2]);
+    u32 wb_t = swap32 (w2[3]);
+    u32 wc_t = swap32 (w3[0]);
+    u32 wd_t = swap32 (w3[1]);
     u32 we_t = 0;
     u32 wf_t = out_salt_len * 8;
 
@@ -237,15 +237,15 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01420_m04 (__glo
   }
 }
 
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01420_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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m01420_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 rules_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))) m01420_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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m01420_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 rules_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))) m01420_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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m01420_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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
 {
   /**
    * modifier
@@ -351,7 +351,7 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01420_s04 (__glo
 
     const u32 out_salt_len = out_len + salt_len;
 
-    switch_buffer_by_offset (w0, w1, w2, w3, salt_len);
+    switch_buffer_by_offset_le (w0, w1, w2, w3, salt_len);
 
     w0[0] |= salt_buf0[0];
     w0[1] |= salt_buf0[1];
@@ -362,26 +362,26 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01420_s04 (__glo
     w1[2] |= salt_buf1[2];
     w1[3] |= salt_buf1[3];
 
-    append_0x80_4 (w0, w1, w2, w3, out_salt_len);
+    append_0x80_4x4 (w0, w1, w2, w3, out_salt_len);
 
     /**
      * sha256
      */
 
-    u32 w0_t = swap_workaround (w0[0]);
-    u32 w1_t = swap_workaround (w0[1]);
-    u32 w2_t = swap_workaround (w0[2]);
-    u32 w3_t = swap_workaround (w0[3]);
-    u32 w4_t = swap_workaround (w1[0]);
-    u32 w5_t = swap_workaround (w1[1]);
-    u32 w6_t = swap_workaround (w1[2]);
-    u32 w7_t = swap_workaround (w1[3]);
-    u32 w8_t = swap_workaround (w2[0]);
-    u32 w9_t = swap_workaround (w2[1]);
-    u32 wa_t = swap_workaround (w2[2]);
-    u32 wb_t = swap_workaround (w2[3]);
-    u32 wc_t = swap_workaround (w3[0]);
-    u32 wd_t = swap_workaround (w3[1]);
+    u32 w0_t = swap32 (w0[0]);
+    u32 w1_t = swap32 (w0[1]);
+    u32 w2_t = swap32 (w0[2]);
+    u32 w3_t = swap32 (w0[3]);
+    u32 w4_t = swap32 (w1[0]);
+    u32 w5_t = swap32 (w1[1]);
+    u32 w6_t = swap32 (w1[2]);
+    u32 w7_t = swap32 (w1[3]);
+    u32 w8_t = swap32 (w2[0]);
+    u32 w9_t = swap32 (w2[1]);
+    u32 wa_t = swap32 (w2[2]);
+    u32 wb_t = swap32 (w2[3]);
+    u32 wc_t = swap32 (w3[0]);
+    u32 wd_t = swap32 (w3[1]);
     u32 we_t = 0;
     u32 wf_t = out_salt_len * 8;
 
@@ -472,10 +472,10 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01420_s04 (__glo
   }
 }
 
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01420_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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m01420_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 rules_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))) m01420_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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m01420_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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
 {
 }