diff --git a/OpenCL/m01100_a0.cl b/OpenCL/m01100_a0.cl
index 9d2254380..867bfeec7 100644
--- a/OpenCL/m01100_a0.cl
+++ b/OpenCL/m01100_a0.cl
@@ -5,6 +5,8 @@
 
 #define _MD4_
 
+#define NEW_SIMD_CODE
+
 #include "include/constants.h"
 #include "include/kernel_vendor.h"
 
@@ -18,9 +20,7 @@
 #include "OpenCL/common.c"
 #include "include/rp_kernel.h"
 #include "OpenCL/rp.c"
-
-#define COMPARE_S "OpenCL/check_single_comp4.c"
-#define COMPARE_M "OpenCL/check_multi_comp4.c"
+#include "OpenCL/simd.c"
 
 __kernel void m01100_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)
 {
@@ -85,54 +85,31 @@ __kernel void m01100_m04 (__global pw_t *pws, __global kernel_rule_t *rules_buf,
    * loop
    */
 
-  for (u32 il_pos = 0; il_pos < rules_cnt; il_pos++)
+  for (u32 il_pos = 0; il_pos < rules_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 u32 out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
 
     append_0x80_2x4 (w0, w1, out_len);
 
-    u32 w0_t[4];
-    u32 w1_t[4];
-    u32 w2_t[4];
-    u32 w3_t[4];
+    u32x w0_t[4];
+    u32x w1_t[4];
+    u32x w2_t[4];
+    u32x w3_t[4];
 
     make_unicode (w0, w0_t, w1_t);
     make_unicode (w1, w2_t, w3_t);
 
     w3_t[2] = out_len * 8 * 2;
 
-    u32 a = MD4M_A;
-    u32 b = MD4M_B;
-    u32 c = MD4M_C;
-    u32 d = MD4M_D;
+    u32x a = MD4M_A;
+    u32x b = MD4M_B;
+    u32x c = MD4M_C;
+    u32x d = MD4M_D;
 
     MD4_STEP (MD4_Fo, a, b, c, d, w0_t[0], MD4C00, MD4S00);
     MD4_STEP (MD4_Fo, d, a, b, c, w0_t[1], MD4C00, MD4S01);
@@ -263,12 +240,7 @@ __kernel void m01100_m04 (__global pw_t *pws, __global kernel_rule_t *rules_buf,
     MD4_STEP (MD4_H , c, d, a, b, w1_t[3], MD4C02, MD4S22);
     MD4_STEP (MD4_H , b, c, d, a, w3_t[3], MD4C02, MD4S23);
 
-    const u32 r0 = a;
-    const u32 r1 = d;
-    const u32 r2 = c;
-    const u32 r3 = b;
-
-    #include COMPARE_M
+    COMPARE_M_SIMD (a, d, c, b);
   }
 }
 
@@ -355,54 +327,31 @@ __kernel void m01100_s04 (__global pw_t *pws, __global kernel_rule_t *rules_buf,
    * loop
    */
 
-  for (u32 il_pos = 0; il_pos < rules_cnt; il_pos++)
+  for (u32 il_pos = 0; il_pos < rules_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 u32 out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
 
     append_0x80_2x4 (w0, w1, out_len);
 
-    u32 w0_t[4];
-    u32 w1_t[4];
-    u32 w2_t[4];
-    u32 w3_t[4];
+    u32x w0_t[4];
+    u32x w1_t[4];
+    u32x w2_t[4];
+    u32x w3_t[4];
 
     make_unicode (w0, w0_t, w1_t);
     make_unicode (w1, w2_t, w3_t);
 
     w3_t[2] = out_len * 8 * 2;
 
-    u32 a = MD4M_A;
-    u32 b = MD4M_B;
-    u32 c = MD4M_C;
-    u32 d = MD4M_D;
+    u32x a = MD4M_A;
+    u32x b = MD4M_B;
+    u32x c = MD4M_C;
+    u32x d = MD4M_D;
 
     MD4_STEP (MD4_Fo, a, b, c, d, w0_t[0], MD4C00, MD4S00);
     MD4_STEP (MD4_Fo, d, a, b, c, w0_t[1], MD4C00, MD4S01);
@@ -530,20 +479,13 @@ __kernel void m01100_s04 (__global pw_t *pws, __global kernel_rule_t *rules_buf,
     MD4_STEP (MD4_H , b, c, d, a, w3_t[1], MD4C02, MD4S23);
     MD4_STEP (MD4_H , a, b, c, d, w0_t[3], MD4C02, MD4S20);
 
-    bool q_cond = allx (search[0] != a);
-
-    if (q_cond) continue;
+    if (MATCHES_NONE_VS (a, search[0])) continue;
 
     MD4_STEP (MD4_H , d, a, b, c, w2_t[3], MD4C02, MD4S21);
     MD4_STEP (MD4_H , c, d, a, b, w1_t[3], MD4C02, MD4S22);
     MD4_STEP (MD4_H , b, c, d, a, w3_t[3], MD4C02, MD4S23);
 
-    const u32 r0 = a;
-    const u32 r1 = d;
-    const u32 r2 = c;
-    const u32 r3 = b;
-
-    #include COMPARE_S
+    COMPARE_S_SIMD (a, d, c, b);
   }
 }