X-Git-Url: https://www.flypig.org.uk/git/?a=blobdiff_plain;f=OpenCL%2Fm01420_a0.cl;h=92224e20b46c482a83fe0fc6459d6211c4601394;hb=161a6eb4bc643d8e636e96eda613f5137d30da59;hp=3dff2b94b205b4ae25165ad27e931ca783a845ec;hpb=5f7c47b461b7e3ffb727baeee62f41ac537cc0ba;p=hashcat.git

diff --git a/OpenCL/m01420_a0.cl b/OpenCL/m01420_a0.cl
index 3dff2b9..92224e2 100644
--- a/OpenCL/m01420_a0.cl
+++ b/OpenCL/m01420_a0.cl
@@ -5,24 +5,18 @@
 
 #define _SHA256_
 
-#include "include/constants.h"
-#include "include/kernel_vendor.h"
-
-#define DGST_R0 3
-#define DGST_R1 7
-#define DGST_R2 2
-#define DGST_R3 6
-
-#include "include/kernel_functions.c"
-#include "OpenCL/types_ocl.c"
-#include "OpenCL/common.c"
-#include "include/rp_gpu.h"
-#include "rp.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)
+#define NEW_SIMD_CODE
+
+#include "inc_vendor.cl"
+#include "inc_hash_constants.h"
+#include "inc_hash_functions.cl"
+#include "inc_types.cl"
+#include "inc_common.cl"
+#include "inc_rp.h"
+#include "inc_rp.cl"
+#include "inc_simd.cl"
+
+__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_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
@@ -39,18 +33,16 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01420_m04 (__glo
   if (gid >= gid_max) return;
 
   u32 pw_buf0[4];
-
-  pw_buf0[0] = pws[gid].i[ 0];
-  pw_buf0[1] = pws[gid].i[ 1];
-  pw_buf0[2] = pws[gid].i[ 2];
-  pw_buf0[3] = pws[gid].i[ 3];
-
   u32 pw_buf1[4];
 
-  pw_buf1[0] = pws[gid].i[ 4];
-  pw_buf1[1] = pws[gid].i[ 5];
-  pw_buf1[2] = pws[gid].i[ 6];
-  pw_buf1[3] = pws[gid].i[ 7];
+  pw_buf0[0] = pws[gid].i[0];
+  pw_buf0[1] = pws[gid].i[1];
+  pw_buf0[2] = pws[gid].i[2];
+  pw_buf0[3] = pws[gid].i[3];
+  pw_buf1[0] = pws[gid].i[4];
+  pw_buf1[1] = pws[gid].i[5];
+  pw_buf1[2] = pws[gid].i[6];
+  pw_buf1[3] = pws[gid].i[7];
 
   const u32 pw_len = pws[gid].pw_len;
 
@@ -59,18 +51,26 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01420_m04 (__glo
    */
 
   u32 salt_buf0[4];
-
-  salt_buf0[0] = salt_bufs[salt_pos].salt_buf[0];
-  salt_buf0[1] = salt_bufs[salt_pos].salt_buf[1];
-  salt_buf0[2] = salt_bufs[salt_pos].salt_buf[2];
-  salt_buf0[3] = salt_bufs[salt_pos].salt_buf[3];
-
   u32 salt_buf1[4];
-
-  salt_buf1[0] = salt_bufs[salt_pos].salt_buf[4];
-  salt_buf1[1] = salt_bufs[salt_pos].salt_buf[5];
-  salt_buf1[2] = salt_bufs[salt_pos].salt_buf[6];
-  salt_buf1[3] = salt_bufs[salt_pos].salt_buf[7];
+  u32 salt_buf2[4];
+  u32 salt_buf3[4];
+
+  salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
+  salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
+  salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
+  salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
+  salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
+  salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
+  salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
+  salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
+  salt_buf2[0] = salt_bufs[salt_pos].salt_buf[ 8];
+  salt_buf2[1] = salt_bufs[salt_pos].salt_buf[ 9];
+  salt_buf2[2] = salt_bufs[salt_pos].salt_buf[10];
+  salt_buf2[3] = salt_bufs[salt_pos].salt_buf[11];
+  salt_buf3[0] = salt_bufs[salt_pos].salt_buf[12];
+  salt_buf3[1] = salt_bufs[salt_pos].salt_buf[13];
+  salt_buf3[2] = salt_bufs[salt_pos].salt_buf[14];
+  salt_buf3[3] = salt_bufs[salt_pos].salt_buf[15];
 
   const u32 salt_len = salt_bufs[salt_pos].salt_len;
 
@@ -78,45 +78,22 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01420_m04 (__glo
    * loop
    */
 
-  for (u32 il_pos = 0; il_pos < rules_cnt; il_pos++)
+  for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
   {
-    u32 w0[4];
+    u32x w0[4] = { 0 };
+    u32x w1[4] = { 0 };
+    u32x w2[4] = { 0 };
+    u32x w3[4] = { 0 };
 
-    w0[0] = pw_buf0[0];
-    w0[1] = pw_buf0[1];
-    w0[2] = pw_buf0[2];
-    w0[3] = pw_buf0[3];
-
-    u32 w1[4];
-
-    w1[0] = pw_buf1[0];
-    w1[1] = pw_buf1[1];
-    w1[2] = pw_buf1[2];
-    w1[3] = pw_buf1[3];
-
-    u32 w2[4];
-
-    w2[0] = 0;
-    w2[1] = 0;
-    w2[2] = 0;
-    w2[3] = 0;
-
-    u32 w3[4];
-
-    w3[0] = 0;
-    w3[1] = 0;
-    w3[2] = 0;
-    w3[3] = 0;
-
-    const u32 out_len = apply_rules (rules_buf[il_pos].cmds, w0, w1, pw_len);
+    const u32x out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
 
     /**
      * prepend salt
      */
 
-    const u32 out_salt_len = out_len + salt_len;
+    const u32x out_salt_len = out_len + salt_len;
 
-    switch_buffer_by_offset (w0, w1, w2, w3, salt_len);
+    switch_buffer_by_offset_le_VV (w0, w1, w2, w3, salt_len);
 
     w0[0] |= salt_buf0[0];
     w0[1] |= salt_buf0[1];
@@ -126,38 +103,46 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01420_m04 (__glo
     w1[1] |= salt_buf1[1];
     w1[2] |= salt_buf1[2];
     w1[3] |= salt_buf1[3];
+    w2[0] |= salt_buf2[0];
+    w2[1] |= salt_buf2[1];
+    w2[2] |= salt_buf2[2];
+    w2[3] |= salt_buf2[3];
+    w3[0] |= salt_buf3[0];
+    w3[1] |= salt_buf3[1];
+    w3[2] |= salt_buf3[2];
+    w3[3] |= salt_buf3[3];
 
-    append_0x80_4x4 (w0, w1, w2, w3, out_salt_len);
+    append_0x80_4x4_VV (w0, w1, w2, w3, out_salt_len);
 
     /**
      * sha256
      */
 
-    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;
-
-    u32 a = SHA256M_A;
-    u32 b = SHA256M_B;
-    u32 c = SHA256M_C;
-    u32 d = SHA256M_D;
-    u32 e = SHA256M_E;
-    u32 f = SHA256M_F;
-    u32 g = SHA256M_G;
-    u32 h = SHA256M_H;
+    u32x w0_t = swap32 (w0[0]);
+    u32x w1_t = swap32 (w0[1]);
+    u32x w2_t = swap32 (w0[2]);
+    u32x w3_t = swap32 (w0[3]);
+    u32x w4_t = swap32 (w1[0]);
+    u32x w5_t = swap32 (w1[1]);
+    u32x w6_t = swap32 (w1[2]);
+    u32x w7_t = swap32 (w1[3]);
+    u32x w8_t = swap32 (w2[0]);
+    u32x w9_t = swap32 (w2[1]);
+    u32x wa_t = swap32 (w2[2]);
+    u32x wb_t = swap32 (w2[3]);
+    u32x wc_t = swap32 (w3[0]);
+    u32x wd_t = swap32 (w3[1]);
+    u32x we_t = 0;
+    u32x wf_t = out_salt_len * 8;
+
+    u32x a = SHA256M_A;
+    u32x b = SHA256M_B;
+    u32x c = SHA256M_C;
+    u32x d = SHA256M_D;
+    u32x e = SHA256M_E;
+    u32x f = SHA256M_F;
+    u32x g = SHA256M_G;
+    u32x h = SHA256M_H;
 
     SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
     SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
@@ -227,25 +212,19 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01420_m04 (__glo
     we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
     wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
 
-
-    const u32 r0 = d;
-    const u32 r1 = h;
-    const u32 r2 = c;
-    const u32 r3 = g;
-
-    #include COMPARE_M
+    COMPARE_M_SIMD (d, h, c, g);
   }
 }
 
-__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_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)
 {
 }
 
-__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_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)
 {
 }
 
-__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_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
@@ -262,18 +241,16 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01420_s04 (__glo
   if (gid >= gid_max) return;
 
   u32 pw_buf0[4];
-
-  pw_buf0[0] = pws[gid].i[ 0];
-  pw_buf0[1] = pws[gid].i[ 1];
-  pw_buf0[2] = pws[gid].i[ 2];
-  pw_buf0[3] = pws[gid].i[ 3];
-
   u32 pw_buf1[4];
 
-  pw_buf1[0] = pws[gid].i[ 4];
-  pw_buf1[1] = pws[gid].i[ 5];
-  pw_buf1[2] = pws[gid].i[ 6];
-  pw_buf1[3] = pws[gid].i[ 7];
+  pw_buf0[0] = pws[gid].i[0];
+  pw_buf0[1] = pws[gid].i[1];
+  pw_buf0[2] = pws[gid].i[2];
+  pw_buf0[3] = pws[gid].i[3];
+  pw_buf1[0] = pws[gid].i[4];
+  pw_buf1[1] = pws[gid].i[5];
+  pw_buf1[2] = pws[gid].i[6];
+  pw_buf1[3] = pws[gid].i[7];
 
   const u32 pw_len = pws[gid].pw_len;
 
@@ -282,18 +259,26 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01420_s04 (__glo
    */
 
   u32 salt_buf0[4];
-
-  salt_buf0[0] = salt_bufs[salt_pos].salt_buf[0];
-  salt_buf0[1] = salt_bufs[salt_pos].salt_buf[1];
-  salt_buf0[2] = salt_bufs[salt_pos].salt_buf[2];
-  salt_buf0[3] = salt_bufs[salt_pos].salt_buf[3];
-
   u32 salt_buf1[4];
-
-  salt_buf1[0] = salt_bufs[salt_pos].salt_buf[4];
-  salt_buf1[1] = salt_bufs[salt_pos].salt_buf[5];
-  salt_buf1[2] = salt_bufs[salt_pos].salt_buf[6];
-  salt_buf1[3] = salt_bufs[salt_pos].salt_buf[7];
+  u32 salt_buf2[4];
+  u32 salt_buf3[4];
+
+  salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
+  salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
+  salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
+  salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
+  salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
+  salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
+  salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
+  salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
+  salt_buf2[0] = salt_bufs[salt_pos].salt_buf[ 8];
+  salt_buf2[1] = salt_bufs[salt_pos].salt_buf[ 9];
+  salt_buf2[2] = salt_bufs[salt_pos].salt_buf[10];
+  salt_buf2[3] = salt_bufs[salt_pos].salt_buf[11];
+  salt_buf3[0] = salt_bufs[salt_pos].salt_buf[12];
+  salt_buf3[1] = salt_bufs[salt_pos].salt_buf[13];
+  salt_buf3[2] = salt_bufs[salt_pos].salt_buf[14];
+  salt_buf3[3] = salt_bufs[salt_pos].salt_buf[15];
 
   const u32 salt_len = salt_bufs[salt_pos].salt_len;
 
@@ -313,45 +298,22 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01420_s04 (__glo
    * loop
    */
 
-  for (u32 il_pos = 0; il_pos < rules_cnt; il_pos++)
+  for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
   {
-    u32 w0[4];
-
-    w0[0] = pw_buf0[0];
-    w0[1] = pw_buf0[1];
-    w0[2] = pw_buf0[2];
-    w0[3] = pw_buf0[3];
-
-    u32 w1[4];
-
-    w1[0] = pw_buf1[0];
-    w1[1] = pw_buf1[1];
-    w1[2] = pw_buf1[2];
-    w1[3] = pw_buf1[3];
+    u32x w0[4] = { 0 };
+    u32x w1[4] = { 0 };
+    u32x w2[4] = { 0 };
+    u32x w3[4] = { 0 };
 
-    u32 w2[4];
-
-    w2[0] = 0;
-    w2[1] = 0;
-    w2[2] = 0;
-    w2[3] = 0;
-
-    u32 w3[4];
-
-    w3[0] = 0;
-    w3[1] = 0;
-    w3[2] = 0;
-    w3[3] = 0;
-
-    const u32 out_len = apply_rules (rules_buf[il_pos].cmds, w0, w1, pw_len);
+    const u32x out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
 
     /**
      * prepend salt
      */
 
-    const u32 out_salt_len = out_len + salt_len;
+    const u32x out_salt_len = out_len + salt_len;
 
-    switch_buffer_by_offset (w0, w1, w2, w3, salt_len);
+    switch_buffer_by_offset_le_VV (w0, w1, w2, w3, salt_len);
 
     w0[0] |= salt_buf0[0];
     w0[1] |= salt_buf0[1];
@@ -361,38 +323,46 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01420_s04 (__glo
     w1[1] |= salt_buf1[1];
     w1[2] |= salt_buf1[2];
     w1[3] |= salt_buf1[3];
+    w2[0] |= salt_buf2[0];
+    w2[1] |= salt_buf2[1];
+    w2[2] |= salt_buf2[2];
+    w2[3] |= salt_buf2[3];
+    w3[0] |= salt_buf3[0];
+    w3[1] |= salt_buf3[1];
+    w3[2] |= salt_buf3[2];
+    w3[3] |= salt_buf3[3];
 
-    append_0x80_4x4 (w0, w1, w2, w3, out_salt_len);
+    append_0x80_4x4_VV (w0, w1, w2, w3, out_salt_len);
 
     /**
      * sha256
      */
 
-    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;
-
-    u32 a = SHA256M_A;
-    u32 b = SHA256M_B;
-    u32 c = SHA256M_C;
-    u32 d = SHA256M_D;
-    u32 e = SHA256M_E;
-    u32 f = SHA256M_F;
-    u32 g = SHA256M_G;
-    u32 h = SHA256M_H;
+    u32x w0_t = swap32 (w0[0]);
+    u32x w1_t = swap32 (w0[1]);
+    u32x w2_t = swap32 (w0[2]);
+    u32x w3_t = swap32 (w0[3]);
+    u32x w4_t = swap32 (w1[0]);
+    u32x w5_t = swap32 (w1[1]);
+    u32x w6_t = swap32 (w1[2]);
+    u32x w7_t = swap32 (w1[3]);
+    u32x w8_t = swap32 (w2[0]);
+    u32x w9_t = swap32 (w2[1]);
+    u32x wa_t = swap32 (w2[2]);
+    u32x wb_t = swap32 (w2[3]);
+    u32x wc_t = swap32 (w3[0]);
+    u32x wd_t = swap32 (w3[1]);
+    u32x we_t = 0;
+    u32x wf_t = out_salt_len * 8;
+
+    u32x a = SHA256M_A;
+    u32x b = SHA256M_B;
+    u32x c = SHA256M_C;
+    u32x d = SHA256M_D;
+    u32x e = SHA256M_E;
+    u32x f = SHA256M_F;
+    u32x g = SHA256M_G;
+    u32x h = SHA256M_H;
 
     SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
     SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
@@ -458,24 +428,21 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01420_s04 (__glo
     wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
     wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
     wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+
+    if (MATCHES_NONE_VS (d, search[0])) continue;
+
     wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
     we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
     wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
 
-
-    const u32 r0 = d;
-    const u32 r1 = h;
-    const u32 r2 = c;
-    const u32 r3 = g;
-
-    #include COMPARE_S
+    COMPARE_S_SIMD (d, h, c, g);
   }
 }
 
-__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_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)
 {
 }
 
-__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_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)
 {
 }