Revert "Zero pws_buf before reuse"

[hashcat.git] / OpenCL / m00020_a3.cl

diff --git a/OpenCL/m00020_a3.cl b/OpenCL/m00020_a3.cl
index 7ebb5a5..d74fbd7 100644 (file)
--- a/OpenCL/m00020_a3.cl
+++ b/OpenCL/m00020_a3.cl
@@ -65,6 +65,51 @@ static void m00020m (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_le
 
   const u32 pw_salt_len = pw_len + salt_len;
 
+  /**
+   * prepend salt
+   */
+
+  u32 w0_t[4];
+  u32 w1_t[4];
+  u32 w2_t[4];
+  u32 w3_t[4];
+
+  w0_t[0] = w0[0];
+  w0_t[1] = w0[1];
+  w0_t[2] = w0[2];
+  w0_t[3] = w0[3];
+  w1_t[0] = w1[0];
+  w1_t[1] = w1[1];
+  w1_t[2] = w1[2];
+  w1_t[3] = w1[3];
+  w2_t[0] = w2[0];
+  w2_t[1] = w2[1];
+  w2_t[2] = w2[2];
+  w2_t[3] = w2[3];
+  w3_t[0] = w3[0];
+  w3_t[1] = w3[1];
+  w3_t[2] = w3[2];
+  w3_t[3] = w3[3];
+
+  switch_buffer_by_offset_le_S (w0_t, w1_t, w2_t, w3_t, salt_len);
+
+  w0_t[0] |= salt_buf0[0];
+  w0_t[1] |= salt_buf0[1];
+  w0_t[2] |= salt_buf0[2];
+  w0_t[3] |= salt_buf0[3];
+  w1_t[0] |= salt_buf1[0];
+  w1_t[1] |= salt_buf1[1];
+  w1_t[2] |= salt_buf1[2];
+  w1_t[3] |= salt_buf1[3];
+  w2_t[0] |= salt_buf2[0];
+  w2_t[1] |= salt_buf2[1];
+  w2_t[2] |= salt_buf2[2];
+  w2_t[3] |= salt_buf2[3];
+  w3_t[0] |= salt_buf3[0];
+  w3_t[1] |= salt_buf3[1];
+  w3_t[2] |= salt_buf3[2];
+  w3_t[3] |= salt_buf3[3];
+
   /**
    * loop
    */
@@ -73,71 +118,57 @@ static void m00020m (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_le
 
   for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos += VECT_SIZE)
   {
-    #if   VECT_SIZE == 1
-    const u32x w0r = (u32x) (bfs_buf[il_pos + 0].i);
-    #elif VECT_SIZE == 2
-    const u32x w0r = (u32x) (bfs_buf[il_pos + 0].i, bfs_buf[il_pos + 1].i);
-    #elif VECT_SIZE == 4
-    const u32x w0r = (u32x) (bfs_buf[il_pos + 0].i, bfs_buf[il_pos + 1].i, bfs_buf[il_pos + 2].i, bfs_buf[il_pos + 3].i);
-    #elif VECT_SIZE == 8
-    const u32x w0r = (u32x) (bfs_buf[il_pos + 0].i, bfs_buf[il_pos + 1].i, bfs_buf[il_pos + 2].i, bfs_buf[il_pos + 3].i, bfs_buf[il_pos + 4].i, bfs_buf[il_pos + 5].i, bfs_buf[il_pos + 6].i, bfs_buf[il_pos + 7].i);
-    #endif
+    const u32x w0r = ix_create_bft (bfs_buf, il_pos);
 
     const u32x w0lr = w0l | w0r;
 
-    /**
-     * prepend salt
-     */
+    u32x wx[16];
+
+    wx[ 0] = w0_t[0];
+    wx[ 1] = w0_t[1];
+    wx[ 2] = w0_t[2];
+    wx[ 3] = w0_t[3];
+    wx[ 4] = w1_t[0];
+    wx[ 5] = w1_t[1];
+    wx[ 6] = w1_t[2];
+    wx[ 7] = w1_t[3];
+    wx[ 8] = w2_t[0];
+    wx[ 9] = w2_t[1];
+    wx[10] = w2_t[2];
+    wx[11] = w2_t[3];
+    wx[12] = w3_t[0];
+    wx[13] = w3_t[1];
+    wx[14] = w3_t[2];
+    wx[15] = w3_t[3];
+
+    overwrite_at_le (wx, w0lr, salt_len);
 
     u32x w0_t[4];
     u32x w1_t[4];
     u32x w2_t[4];
     u32x w3_t[4];
 
-    w0_t[0] = w0lr;
-    w0_t[1] = w0[1];
-    w0_t[2] = w0[2];
-    w0_t[3] = w0[3];
-    w1_t[0] = w1[0];
-    w1_t[1] = w1[1];
-    w1_t[2] = w1[2];
-    w1_t[3] = w1[3];
-    w2_t[0] = w2[0];
-    w2_t[1] = w2[1];
-    w2_t[2] = w2[2];
-    w2_t[3] = w2[3];
-    w3_t[0] = w3[0];
-    w3_t[1] = w3[1];
-    w3_t[2] = w3[2];
-    w3_t[3] = w3[3];
-
-    switch_buffer_by_offset (w0_t, w1_t, w2_t, w3_t, salt_len);
-
+    w0_t[0] = wx[ 0];
+    w0_t[1] = wx[ 1];
+    w0_t[2] = wx[ 2];
+    w0_t[3] = wx[ 3];
+    w1_t[0] = wx[ 4];
+    w1_t[1] = wx[ 5];
+    w1_t[2] = wx[ 6];
+    w1_t[3] = wx[ 7];
+    w2_t[0] = wx[ 8];
+    w2_t[1] = wx[ 9];
+    w2_t[2] = wx[10];
+    w2_t[3] = wx[11];
+    w3_t[0] = wx[12];
+    w3_t[1] = wx[13];
     w3_t[2] = pw_salt_len * 8;
-
-    w0_t[0] |= salt_buf0[0];
-    w0_t[1] |= salt_buf0[1];
-    w0_t[2] |= salt_buf0[2];
-    w0_t[3] |= salt_buf0[3];
-    w1_t[0] |= salt_buf1[0];
-    w1_t[1] |= salt_buf1[1];
-    w1_t[2] |= salt_buf1[2];
-    w1_t[3] |= salt_buf1[3];
-    w2_t[0] |= salt_buf2[0];
-    w2_t[1] |= salt_buf2[1];
-    w2_t[2] |= salt_buf2[2];
-    w2_t[3] |= salt_buf2[3];
-    w3_t[0] |= salt_buf3[0];
-    w3_t[1] |= salt_buf3[1];
-    w3_t[2] |= salt_buf3[2];
-    w3_t[3] |= salt_buf3[3];
+    w3_t[3] = 0;
 
     /**
      * md5
      */
 
-    u32x tmp2;
-
     u32x a = MD5M_A;
     u32x b = MD5M_B;
     u32x c = MD5M_C;
@@ -177,22 +208,22 @@ static void m00020m (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_le
     MD5_STEP (MD5_Go, c, d, a, b, w1_t[3], MD5C1e, MD5S12);
     MD5_STEP (MD5_Go, b, c, d, a, w3_t[0], MD5C1f, MD5S13);
 
-    MD5_STEP (MD5_H1, a, b, c, d, w1_t[1], MD5C20, MD5S20);
-    MD5_STEP (MD5_H2, d, a, b, c, w2_t[0], MD5C21, MD5S21);
-    MD5_STEP (MD5_H1, c, d, a, b, w2_t[3], MD5C22, MD5S22);
-    MD5_STEP (MD5_H2, b, c, d, a, w3_t[2], MD5C23, MD5S23);
-    MD5_STEP (MD5_H1, a, b, c, d, w0_t[1], MD5C24, MD5S20);
-    MD5_STEP (MD5_H2, d, a, b, c, w1_t[0], MD5C25, MD5S21);
-    MD5_STEP (MD5_H1, c, d, a, b, w1_t[3], MD5C26, MD5S22);
-    MD5_STEP (MD5_H2, b, c, d, a, w2_t[2], MD5C27, MD5S23);
-    MD5_STEP (MD5_H1, a, b, c, d, w3_t[1], MD5C28, MD5S20);
-    MD5_STEP (MD5_H2, d, a, b, c, w0_t[0], MD5C29, MD5S21);
-    MD5_STEP (MD5_H1, c, d, a, b, w0_t[3], MD5C2a, MD5S22);
-    MD5_STEP (MD5_H2, b, c, d, a, w1_t[2], MD5C2b, MD5S23);
-    MD5_STEP (MD5_H1, a, b, c, d, w2_t[1], MD5C2c, MD5S20);
-    MD5_STEP (MD5_H2, d, a, b, c, w3_t[0], MD5C2d, MD5S21);
-    MD5_STEP (MD5_H1, c, d, a, b, w3_t[3], MD5C2e, MD5S22);
-    MD5_STEP (MD5_H2, b, c, d, a, w0_t[2], MD5C2f, MD5S23);
+    MD5_STEP (MD5_H , a, b, c, d, w1_t[1], MD5C20, MD5S20);
+    MD5_STEP (MD5_H , d, a, b, c, w2_t[0], MD5C21, MD5S21);
+    MD5_STEP (MD5_H , c, d, a, b, w2_t[3], MD5C22, MD5S22);
+    MD5_STEP (MD5_H , b, c, d, a, w3_t[2], MD5C23, MD5S23);
+    MD5_STEP (MD5_H , a, b, c, d, w0_t[1], MD5C24, MD5S20);
+    MD5_STEP (MD5_H , d, a, b, c, w1_t[0], MD5C25, MD5S21);
+    MD5_STEP (MD5_H , c, d, a, b, w1_t[3], MD5C26, MD5S22);
+    MD5_STEP (MD5_H , b, c, d, a, w2_t[2], MD5C27, MD5S23);
+    MD5_STEP (MD5_H , a, b, c, d, w3_t[1], MD5C28, MD5S20);
+    MD5_STEP (MD5_H , d, a, b, c, w0_t[0], MD5C29, MD5S21);
+    MD5_STEP (MD5_H , c, d, a, b, w0_t[3], MD5C2a, MD5S22);
+    MD5_STEP (MD5_H , b, c, d, a, w1_t[2], MD5C2b, MD5S23);
+    MD5_STEP (MD5_H , a, b, c, d, w2_t[1], MD5C2c, MD5S20);
+    MD5_STEP (MD5_H , d, a, b, c, w3_t[0], MD5C2d, MD5S21);
+    MD5_STEP (MD5_H , c, d, a, b, w3_t[3], MD5C2e, MD5S22);
+    MD5_STEP (MD5_H , b, c, d, a, w0_t[2], MD5C2f, MD5S23);
 
     MD5_STEP (MD5_I , a, b, c, d, w0_t[0], MD5C30, MD5S30);
     MD5_STEP (MD5_I , d, a, b, c, w1_t[3], MD5C31, MD5S31);
@@ -272,6 +303,51 @@ static void m00020s (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_le
 
   const u32 pw_salt_len = pw_len + salt_len;
 
+  /**
+   * prepend salt
+   */
+
+  u32 w0_t[4];
+  u32 w1_t[4];
+  u32 w2_t[4];
+  u32 w3_t[4];
+
+  w0_t[0] = w0[0];
+  w0_t[1] = w0[1];
+  w0_t[2] = w0[2];
+  w0_t[3] = w0[3];
+  w1_t[0] = w1[0];
+  w1_t[1] = w1[1];
+  w1_t[2] = w1[2];
+  w1_t[3] = w1[3];
+  w2_t[0] = w2[0];
+  w2_t[1] = w2[1];
+  w2_t[2] = w2[2];
+  w2_t[3] = w2[3];
+  w3_t[0] = w3[0];
+  w3_t[1] = w3[1];
+  w3_t[2] = w3[2];
+  w3_t[3] = w3[3];
+
+  switch_buffer_by_offset_le_S (w0_t, w1_t, w2_t, w3_t, salt_len);
+
+  w0_t[0] |= salt_buf0[0];
+  w0_t[1] |= salt_buf0[1];
+  w0_t[2] |= salt_buf0[2];
+  w0_t[3] |= salt_buf0[3];
+  w1_t[0] |= salt_buf1[0];
+  w1_t[1] |= salt_buf1[1];
+  w1_t[2] |= salt_buf1[2];
+  w1_t[3] |= salt_buf1[3];
+  w2_t[0] |= salt_buf2[0];
+  w2_t[1] |= salt_buf2[1];
+  w2_t[2] |= salt_buf2[2];
+  w2_t[3] |= salt_buf2[3];
+  w3_t[0] |= salt_buf3[0];
+  w3_t[1] |= salt_buf3[1];
+  w3_t[2] |= salt_buf3[2];
+  w3_t[3] |= salt_buf3[3];
+
   /**
    * loop
    */
@@ -280,71 +356,57 @@ static void m00020s (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_le
 
   for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos += VECT_SIZE)
   {
-    #if   VECT_SIZE == 1
-    const u32x w0r = (u32x) (bfs_buf[il_pos + 0].i);
-    #elif VECT_SIZE == 2
-    const u32x w0r = (u32x) (bfs_buf[il_pos + 0].i, bfs_buf[il_pos + 1].i);
-    #elif VECT_SIZE == 4
-    const u32x w0r = (u32x) (bfs_buf[il_pos + 0].i, bfs_buf[il_pos + 1].i, bfs_buf[il_pos + 2].i, bfs_buf[il_pos + 3].i);
-    #elif VECT_SIZE == 8
-    const u32x w0r = (u32x) (bfs_buf[il_pos + 0].i, bfs_buf[il_pos + 1].i, bfs_buf[il_pos + 2].i, bfs_buf[il_pos + 3].i, bfs_buf[il_pos + 4].i, bfs_buf[il_pos + 5].i, bfs_buf[il_pos + 6].i, bfs_buf[il_pos + 7].i);
-    #endif
+    const u32x w0r = ix_create_bft (bfs_buf, il_pos);
 
     const u32x w0lr = w0l | w0r;
 
-    /**
-     * prepend salt
-     */
+    u32x wx[16];
+
+    wx[ 0] = w0_t[0];
+    wx[ 1] = w0_t[1];
+    wx[ 2] = w0_t[2];
+    wx[ 3] = w0_t[3];
+    wx[ 4] = w1_t[0];
+    wx[ 5] = w1_t[1];
+    wx[ 6] = w1_t[2];
+    wx[ 7] = w1_t[3];
+    wx[ 8] = w2_t[0];
+    wx[ 9] = w2_t[1];
+    wx[10] = w2_t[2];
+    wx[11] = w2_t[3];
+    wx[12] = w3_t[0];
+    wx[13] = w3_t[1];
+    wx[14] = w3_t[2];
+    wx[15] = w3_t[3];
+
+    overwrite_at_le (wx, w0lr, salt_len);
 
     u32x w0_t[4];
     u32x w1_t[4];
     u32x w2_t[4];
     u32x w3_t[4];
 
-    w0_t[0] = w0lr;
-    w0_t[1] = w0[1];
-    w0_t[2] = w0[2];
-    w0_t[3] = w0[3];
-    w1_t[0] = w1[0];
-    w1_t[1] = w1[1];
-    w1_t[2] = w1[2];
-    w1_t[3] = w1[3];
-    w2_t[0] = w2[0];
-    w2_t[1] = w2[1];
-    w2_t[2] = w2[2];
-    w2_t[3] = w2[3];
-    w3_t[0] = w3[0];
-    w3_t[1] = w3[1];
-    w3_t[2] = w3[2];
-    w3_t[3] = w3[3];
-
-    switch_buffer_by_offset (w0_t, w1_t, w2_t, w3_t, salt_len);
-
+    w0_t[0] = wx[ 0];
+    w0_t[1] = wx[ 1];
+    w0_t[2] = wx[ 2];
+    w0_t[3] = wx[ 3];
+    w1_t[0] = wx[ 4];
+    w1_t[1] = wx[ 5];
+    w1_t[2] = wx[ 6];
+    w1_t[3] = wx[ 7];
+    w2_t[0] = wx[ 8];
+    w2_t[1] = wx[ 9];
+    w2_t[2] = wx[10];
+    w2_t[3] = wx[11];
+    w3_t[0] = wx[12];
+    w3_t[1] = wx[13];
     w3_t[2] = pw_salt_len * 8;
-
-    w0_t[0] |= salt_buf0[0];
-    w0_t[1] |= salt_buf0[1];
-    w0_t[2] |= salt_buf0[2];
-    w0_t[3] |= salt_buf0[3];
-    w1_t[0] |= salt_buf1[0];
-    w1_t[1] |= salt_buf1[1];
-    w1_t[2] |= salt_buf1[2];
-    w1_t[3] |= salt_buf1[3];
-    w2_t[0] |= salt_buf2[0];
-    w2_t[1] |= salt_buf2[1];
-    w2_t[2] |= salt_buf2[2];
-    w2_t[3] |= salt_buf2[3];
-    w3_t[0] |= salt_buf3[0];
-    w3_t[1] |= salt_buf3[1];
-    w3_t[2] |= salt_buf3[2];
-    w3_t[3] |= salt_buf3[3];
+    w3_t[3] = 0;
 
     /**
      * md5
      */
 
-    u32x tmp2;
-
     u32x a = MD5M_A;
     u32x b = MD5M_B;
     u32x c = MD5M_C;
@@ -384,22 +446,22 @@ static void m00020s (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_le
     MD5_STEP (MD5_Go, c, d, a, b, w1_t[3], MD5C1e, MD5S12);
     MD5_STEP (MD5_Go, b, c, d, a, w3_t[0], MD5C1f, MD5S13);
 
-    MD5_STEP (MD5_H1, a, b, c, d, w1_t[1], MD5C20, MD5S20);
-    MD5_STEP (MD5_H2, d, a, b, c, w2_t[0], MD5C21, MD5S21);
-    MD5_STEP (MD5_H1, c, d, a, b, w2_t[3], MD5C22, MD5S22);
-    MD5_STEP (MD5_H2, b, c, d, a, w3_t[2], MD5C23, MD5S23);
-    MD5_STEP (MD5_H1, a, b, c, d, w0_t[1], MD5C24, MD5S20);
-    MD5_STEP (MD5_H2, d, a, b, c, w1_t[0], MD5C25, MD5S21);
-    MD5_STEP (MD5_H1, c, d, a, b, w1_t[3], MD5C26, MD5S22);
-    MD5_STEP (MD5_H2, b, c, d, a, w2_t[2], MD5C27, MD5S23);
-    MD5_STEP (MD5_H1, a, b, c, d, w3_t[1], MD5C28, MD5S20);
-    MD5_STEP (MD5_H2, d, a, b, c, w0_t[0], MD5C29, MD5S21);
-    MD5_STEP (MD5_H1, c, d, a, b, w0_t[3], MD5C2a, MD5S22);
-    MD5_STEP (MD5_H2, b, c, d, a, w1_t[2], MD5C2b, MD5S23);
-    MD5_STEP (MD5_H1, a, b, c, d, w2_t[1], MD5C2c, MD5S20);
-    MD5_STEP (MD5_H2, d, a, b, c, w3_t[0], MD5C2d, MD5S21);
-    MD5_STEP (MD5_H1, c, d, a, b, w3_t[3], MD5C2e, MD5S22);
-    MD5_STEP (MD5_H2, b, c, d, a, w0_t[2], MD5C2f, MD5S23);
+    MD5_STEP (MD5_H , a, b, c, d, w1_t[1], MD5C20, MD5S20);
+    MD5_STEP (MD5_H , d, a, b, c, w2_t[0], MD5C21, MD5S21);
+    MD5_STEP (MD5_H , c, d, a, b, w2_t[3], MD5C22, MD5S22);
+    MD5_STEP (MD5_H , b, c, d, a, w3_t[2], MD5C23, MD5S23);
+    MD5_STEP (MD5_H , a, b, c, d, w0_t[1], MD5C24, MD5S20);
+    MD5_STEP (MD5_H , d, a, b, c, w1_t[0], MD5C25, MD5S21);
+    MD5_STEP (MD5_H , c, d, a, b, w1_t[3], MD5C26, MD5S22);
+    MD5_STEP (MD5_H , b, c, d, a, w2_t[2], MD5C27, MD5S23);
+    MD5_STEP (MD5_H , a, b, c, d, w3_t[1], MD5C28, MD5S20);
+    MD5_STEP (MD5_H , d, a, b, c, w0_t[0], MD5C29, MD5S21);
+    MD5_STEP (MD5_H , c, d, a, b, w0_t[3], MD5C2a, MD5S22);
+    MD5_STEP (MD5_H , b, c, d, a, w1_t[2], MD5C2b, MD5S23);
+    MD5_STEP (MD5_H , a, b, c, d, w2_t[1], MD5C2c, MD5S20);
+    MD5_STEP (MD5_H , d, a, b, c, w3_t[0], MD5C2d, MD5S21);
+    MD5_STEP (MD5_H , c, d, a, b, w3_t[3], MD5C2e, MD5S22);
+    MD5_STEP (MD5_H , b, c, d, a, w0_t[2], MD5C2f, MD5S23);
 
     MD5_STEP (MD5_I , a, b, c, d, w0_t[0], MD5C30, MD5S30);
     MD5_STEP (MD5_I , d, a, b, c, w1_t[3], MD5C31, MD5S31);
@@ -425,7 +487,7 @@ static void m00020s (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_le
   }
 }
 
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00020_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m00020_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
 {
   /**
    * base
@@ -472,7 +534,7 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00020_m04 (__glo
   m00020m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
 }
 
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00020_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m00020_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
 {
   /**
    * base
@@ -519,7 +581,7 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00020_m08 (__glo
   m00020m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
 }
 
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00020_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m00020_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
 {
   /**
    * base
@@ -566,7 +628,7 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00020_m16 (__glo
   m00020m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
 }
 
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00020_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m00020_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
 {
   /**
    * base
@@ -613,7 +675,7 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00020_s04 (__glo
   m00020s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
 }
 
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00020_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m00020_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
 {
   /**
    * base
@@ -660,7 +722,7 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00020_s08 (__glo
   m00020s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
 }
 
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00020_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m00020_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
 {
   /**
    * base