diff --git a/OpenCL/m07701_a0-optimized.cl b/OpenCL/m07701_a0-optimized.cl
new file mode 100644
index 000000000..7fab20f15
--- /dev/null
+++ b/OpenCL/m07701_a0-optimized.cl
@@ -0,0 +1,488 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//too much register pressure
+//#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_optimized.h"
+#include "inc_rp_optimized.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+
+#define GETCHAR(a,p)  (((a)[(p) / 4] >> (((p) & 3) * 8)) & 0xff)
+#define PUTCHAR(a,p,c) ((a)[(p) / 4] = (((a)[(p) / 4] & ~(0xff << (((p) & 3) * 8))) | ((c) << (((p) & 3) * 8))))
+
+#define SETSHIFTEDINT(a,n,v)        \
+{                                   \
+  const u32 s = ((n) & 3) * 8;     \
+  const u64 x = (u64) (v) << s; \
+  (a)[((n)/4)+0] &= ~(0xff << ((n & 3) * 8)); \
+  (a)[((n)/4)+0] |= x;              \
+  (a)[((n)/4)+1]  = x >> 32;        \
+}
+
+__constant u32a sapb_trans_tbl[256] =
+{
+  // first value hack for 0 byte as part of an optimization
+  0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0x3f, 0x40, 0x41, 0x50, 0x43, 0x44, 0x45, 0x4b, 0x47, 0x48, 0x4d, 0x4e, 0x54, 0x51, 0x53, 0x46,
+  0x35, 0x36, 0x37, 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x56, 0x55, 0x5c, 0x49, 0x5d, 0x4a,
+  0x42, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
+  0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x58, 0x5b, 0x59, 0xff, 0x52,
+  0x4c, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
+  0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x57, 0x5e, 0x5a, 0x4f, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+};
+
+__constant u32a bcodeArray[48] =
+{
+  0x14, 0x77, 0xf3, 0xd4, 0xbb, 0x71, 0x23, 0xd0, 0x03, 0xff, 0x47, 0x93, 0x55, 0xaa, 0x66, 0x91,
+  0xf2, 0x88, 0x6b, 0x99, 0xbf, 0xcb, 0x32, 0x1a, 0x19, 0xd9, 0xa7, 0x82, 0x22, 0x49, 0xa2, 0x51,
+  0xe2, 0xb7, 0x33, 0x71, 0x8b, 0x9f, 0x5d, 0x01, 0x44, 0x70, 0xae, 0x11, 0xef, 0x28, 0xf0, 0x0d
+};
+
+DECLSPEC u32 sapb_trans (const u32 in)
+{
+  u32 out = 0;
+
+  out |= (sapb_trans_tbl[(in >>  0) & 0xff]) <<  0;
+  out |= (sapb_trans_tbl[(in >>  8) & 0xff]) <<  8;
+  out |= (sapb_trans_tbl[(in >> 16) & 0xff]) << 16;
+  out |= (sapb_trans_tbl[(in >> 24) & 0xff]) << 24;
+
+  return out;
+}
+
+DECLSPEC u32 walld0rf_magic (const u32 w0[4], const u32 pw_len, const u32 salt_buf0[4], const u32 salt_len, const u32 a, const u32 b, const u32 c, const u32 d, u32 t[16])
+{
+  t[ 0] = 0;
+  t[ 1] = 0;
+  t[ 2] = 0;
+  t[ 3] = 0;
+  t[ 4] = 0;
+  t[ 5] = 0;
+  t[ 6] = 0;
+  t[ 7] = 0;
+  t[ 8] = 0;
+  t[ 9] = 0;
+  t[10] = 0;
+  t[11] = 0;
+  t[12] = 0;
+  t[13] = 0;
+  t[14] = 0;
+  t[15] = 0;
+
+  u32 sum20 = ((a >> 24) & 3)
+            + ((a >> 16) & 3)
+            + ((a >>  8) & 3)
+            + ((a >>  0) & 3)
+            + ((b >>  8) & 3);
+
+  sum20 |= 0x20;
+
+  const u32 w[2] = { w0[0], w0[1] };
+
+  const u32 s[3] = { salt_buf0[0], salt_buf0[1], salt_buf0[2] };
+
+  u32 saved_key[4] = { a, b, c, d };
+
+  u32 i1 = 0;
+  u32 i2 = 0;
+  u32 i3 = 0;
+
+  while (i2 < sum20)
+  {
+    if (i1 < pw_len)
+    {
+      if (GETCHAR (saved_key, 15 - i1) & 1)
+      {
+        PUTCHAR (t, i2, bcodeArray[48 - 1 - i1]);
+
+        i2++;
+
+        if (i2 == sum20) break;
+      }
+
+      PUTCHAR (t, i2, GETCHAR (w, i1));
+
+      i2++;
+
+      if (i2 == sum20) break;
+
+      i1++;
+    }
+
+    if (i3 < salt_len)
+    {
+      PUTCHAR (t, i2, GETCHAR (s, i3));
+
+      i2++;
+
+      if (i2 == sum20) break;
+
+      i3++;
+    }
+
+    PUTCHAR (t, i2, bcodeArray[i2 - i1 - i3]);
+
+    i2++;
+    i2++;
+  }
+
+  return sum20;
+}
+
+__kernel void m07701_m04 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+
+  if (gid >= gid_max) return;
+
+  u32 pw_buf0[4];
+  u32 pw_buf1[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];
+  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;
+
+  /**
+   * salt
+   */
+
+  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] = 0;
+
+  const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+  salt_buf0[0] = sapb_trans (salt_buf0[0]);
+  salt_buf0[1] = sapb_trans (salt_buf0[1]);
+  salt_buf0[2] = sapb_trans (salt_buf0[2]);
+
+  /**
+   * loop
+   */
+
+  for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+  {
+    u32x w0[4] = { 0 };
+    u32x w1[4] = { 0 };
+    u32x w2[4] = { 0 };
+    u32x w3[4] = { 0 };
+
+    const u32x out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+    if (out_len > 8) continue; // otherwise it overflows in waldorf function
+
+    /**
+     * SAP
+     */
+
+    w0[0] = sapb_trans (w0[0]);
+    w0[1] = sapb_trans (w0[1]);
+
+    /**
+     * append salt
+     */
+
+    u32 s0[4];
+    u32 s1[4];
+    u32 s2[4];
+    u32 s3[4];
+
+    s0[0] = salt_buf0[0];
+    s0[1] = salt_buf0[1];
+    s0[2] = salt_buf0[2];
+    s0[3] = 0;
+    s1[0] = 0;
+    s1[1] = 0;
+    s1[2] = 0;
+    s1[3] = 0;
+    s2[0] = 0;
+    s2[1] = 0;
+    s2[2] = 0;
+    s2[3] = 0;
+    s3[0] = 0;
+    s3[1] = 0;
+    s3[2] = 0;
+    s3[3] = 0;
+
+    switch_buffer_by_offset_le (s0, s1, s2, s3, out_len);
+
+    const u32 pw_salt_len = out_len + salt_len;
+
+    u32 t[16];
+
+    t[ 0] = s0[0] | w0[0];
+    t[ 1] = s0[1] | w0[1];
+    t[ 2] = s0[2];
+    t[ 3] = s0[3];
+    t[ 4] = s1[0];
+    t[ 5] = 0;
+    t[ 6] = 0;
+    t[ 7] = 0;
+    t[ 8] = 0;
+    t[ 9] = 0;
+    t[10] = 0;
+    t[11] = 0;
+    t[12] = 0;
+    t[13] = 0;
+    t[14] = pw_salt_len * 8;
+    t[15] = 0;
+
+    append_0x80_4x4_S (t + 0, t + 4, t + 8, t + 12, pw_salt_len);
+
+    /**
+     * md5
+     */
+
+    u32 digest[4];
+
+    digest[0] = MD5M_A;
+    digest[1] = MD5M_B;
+    digest[2] = MD5M_C;
+    digest[3] = MD5M_D;
+
+    md5_transform (t + 0, t + 4, t + 8, t + 12, digest);
+
+    const u32 sum20 = walld0rf_magic (w0, pw_len, salt_buf0, salt_len, digest[0], digest[1], digest[2], digest[3], t);
+
+    append_0x80_4x4_S (t + 0, t + 4, t + 8, t + 12, sum20);
+
+    t[14] = sum20 * 8;
+    t[15] = 0;
+
+    digest[0] = MD5M_A;
+    digest[1] = MD5M_B;
+    digest[2] = MD5M_C;
+    digest[3] = MD5M_D;
+
+    md5_transform (t + 0, t + 4, t + 8, t + 12, digest);
+
+    const u32 r0 = digest[0] ^ digest[2];
+    const u32 r1 = 0;
+    const u32 r2 = 0;
+    const u32 r3 = 0;
+
+    COMPARE_M_SIMD (r0, r1, r2, r3);
+  }
+}
+
+__kernel void m07701_m08 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+}
+
+__kernel void m07701_m16 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+}
+
+__kernel void m07701_s04 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+
+  if (gid >= gid_max) return;
+
+  u32 pw_buf0[4];
+  u32 pw_buf1[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];
+  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;
+
+  /**
+   * salt
+   */
+
+  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] = 0;
+
+  const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+  salt_buf0[0] = sapb_trans (salt_buf0[0]);
+  salt_buf0[1] = sapb_trans (salt_buf0[1]);
+  salt_buf0[2] = sapb_trans (salt_buf0[2]);
+
+  /**
+   * digest
+   */
+
+  const u32 search[4] =
+  {
+    digests_buf[digests_offset].digest_buf[DGST_R0],
+    digests_buf[digests_offset].digest_buf[DGST_R1],
+    0,
+    0
+  };
+
+  /**
+   * loop
+   */
+
+  for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+  {
+    u32x w0[4] = { 0 };
+    u32x w1[4] = { 0 };
+    u32x w2[4] = { 0 };
+    u32x w3[4] = { 0 };
+
+    const u32x out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+    if (out_len > 8) continue; // otherwise it overflows in waldorf function
+
+    /**
+     * SAP
+     */
+
+    w0[0] = sapb_trans (w0[0]);
+    w0[1] = sapb_trans (w0[1]);
+
+    /**
+     * append salt
+     */
+
+    u32 s0[4];
+    u32 s1[4];
+    u32 s2[4];
+    u32 s3[4];
+
+    s0[0] = salt_buf0[0];
+    s0[1] = salt_buf0[1];
+    s0[2] = salt_buf0[2];
+    s0[3] = 0;
+    s1[0] = 0;
+    s1[1] = 0;
+    s1[2] = 0;
+    s1[3] = 0;
+    s2[0] = 0;
+    s2[1] = 0;
+    s2[2] = 0;
+    s2[3] = 0;
+    s3[0] = 0;
+    s3[1] = 0;
+    s3[2] = 0;
+    s3[3] = 0;
+
+    switch_buffer_by_offset_le (s0, s1, s2, s3, out_len);
+
+    const u32 pw_salt_len = out_len + salt_len;
+
+    u32 t[16];
+
+    t[ 0] = s0[0] | w0[0];
+    t[ 1] = s0[1] | w0[1];
+    t[ 2] = s0[2];
+    t[ 3] = s0[3];
+    t[ 4] = s1[0];
+    t[ 5] = 0;
+    t[ 6] = 0;
+    t[ 7] = 0;
+    t[ 8] = 0;
+    t[ 9] = 0;
+    t[10] = 0;
+    t[11] = 0;
+    t[12] = 0;
+    t[13] = 0;
+    t[14] = pw_salt_len * 8;
+    t[15] = 0;
+
+    append_0x80_4x4_S (t + 0, t + 4, t + 8, t + 12, pw_salt_len);
+
+    /**
+     * md5
+     */
+
+    u32 digest[4];
+
+    digest[0] = MD5M_A;
+    digest[1] = MD5M_B;
+    digest[2] = MD5M_C;
+    digest[3] = MD5M_D;
+
+    md5_transform (t + 0, t + 4, t + 8, t + 12, digest);
+
+    const u32 sum20 = walld0rf_magic (w0, pw_len, salt_buf0, salt_len, digest[0], digest[1], digest[2], digest[3], t);
+
+    append_0x80_4x4_S (t + 0, t + 4, t + 8, t + 12, sum20);
+
+    t[14] = sum20 * 8;
+    t[15] = 0;
+
+    digest[0] = MD5M_A;
+    digest[1] = MD5M_B;
+    digest[2] = MD5M_C;
+    digest[3] = MD5M_D;
+
+    md5_transform (t + 0, t + 4, t + 8, t + 12, digest);
+
+    const u32 r0 = digest[0] ^ digest[2];
+    const u32 r1 = 0;
+    const u32 r2 = 0;
+    const u32 r3 = 0;
+
+    COMPARE_S_SIMD (r0, r1, r2, r3);
+  }
+}
+
+__kernel void m07701_s08 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+}
+
+__kernel void m07701_s16 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+}
diff --git a/OpenCL/m07701_a1-optimized.cl b/OpenCL/m07701_a1-optimized.cl
new file mode 100644
index 000000000..421d76d49
--- /dev/null
+++ b/OpenCL/m07701_a1-optimized.cl
@@ -0,0 +1,572 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//too much register pressure
+//#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_simd.cl"
+#include "inc_hash_md5.cl"
+
+#define GETCHAR(a,p)  (((a)[(p) / 4] >> (((p) & 3) * 8)) & 0xff)
+#define PUTCHAR(a,p,c) ((a)[(p) / 4] = (((a)[(p) / 4] & ~(0xff << (((p) & 3) * 8))) | ((c) << (((p) & 3) * 8))))
+
+#define SETSHIFTEDINT(a,n,v)        \
+{                                   \
+  const u32 s = ((n) & 3) * 8;     \
+  const u64 x = (u64) (v) << s; \
+  (a)[((n)/4)+0] &= ~(0xff << ((n & 3) * 8)); \
+  (a)[((n)/4)+0] |= x;              \
+  (a)[((n)/4)+1]  = x >> 32;        \
+}
+
+__constant u32a sapb_trans_tbl[256] =
+{
+  // first value hack for 0 byte as part of an optimization
+  0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0x3f, 0x40, 0x41, 0x50, 0x43, 0x44, 0x45, 0x4b, 0x47, 0x48, 0x4d, 0x4e, 0x54, 0x51, 0x53, 0x46,
+  0x35, 0x36, 0x37, 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x56, 0x55, 0x5c, 0x49, 0x5d, 0x4a,
+  0x42, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
+  0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x58, 0x5b, 0x59, 0xff, 0x52,
+  0x4c, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
+  0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x57, 0x5e, 0x5a, 0x4f, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+};
+
+__constant u32a bcodeArray[48] =
+{
+  0x14, 0x77, 0xf3, 0xd4, 0xbb, 0x71, 0x23, 0xd0, 0x03, 0xff, 0x47, 0x93, 0x55, 0xaa, 0x66, 0x91,
+  0xf2, 0x88, 0x6b, 0x99, 0xbf, 0xcb, 0x32, 0x1a, 0x19, 0xd9, 0xa7, 0x82, 0x22, 0x49, 0xa2, 0x51,
+  0xe2, 0xb7, 0x33, 0x71, 0x8b, 0x9f, 0x5d, 0x01, 0x44, 0x70, 0xae, 0x11, 0xef, 0x28, 0xf0, 0x0d
+};
+
+DECLSPEC u32 sapb_trans (const u32 in)
+{
+  u32 out = 0;
+
+  out |= (sapb_trans_tbl[(in >>  0) & 0xff]) <<  0;
+  out |= (sapb_trans_tbl[(in >>  8) & 0xff]) <<  8;
+  out |= (sapb_trans_tbl[(in >> 16) & 0xff]) << 16;
+  out |= (sapb_trans_tbl[(in >> 24) & 0xff]) << 24;
+
+  return out;
+}
+
+DECLSPEC u32 walld0rf_magic (const u32 w0[4], const u32 pw_len, const u32 salt_buf0[4], const u32 salt_len, const u32 a, const u32 b, const u32 c, const u32 d, u32 t[16])
+{
+  t[ 0] = 0;
+  t[ 1] = 0;
+  t[ 2] = 0;
+  t[ 3] = 0;
+  t[ 4] = 0;
+  t[ 5] = 0;
+  t[ 6] = 0;
+  t[ 7] = 0;
+  t[ 8] = 0;
+  t[ 9] = 0;
+  t[10] = 0;
+  t[11] = 0;
+  t[12] = 0;
+  t[13] = 0;
+  t[14] = 0;
+  t[15] = 0;
+
+  u32 sum20 = ((a >> 24) & 3)
+            + ((a >> 16) & 3)
+            + ((a >>  8) & 3)
+            + ((a >>  0) & 3)
+            + ((b >>  8) & 3);
+
+  sum20 |= 0x20;
+
+  const u32 w[2] = { w0[0], w0[1] };
+
+  const u32 s[3] = { salt_buf0[0], salt_buf0[1], salt_buf0[2] };
+
+  u32 saved_key[4] = { a, b, c, d };
+
+  u32 i1 = 0;
+  u32 i2 = 0;
+  u32 i3 = 0;
+
+  while (i2 < sum20)
+  {
+    if (i1 < pw_len)
+    {
+      if (GETCHAR (saved_key, 15 - i1) & 1)
+      {
+        PUTCHAR (t, i2, bcodeArray[48 - 1 - i1]);
+
+        i2++;
+
+        if (i2 == sum20) break;
+      }
+
+      PUTCHAR (t, i2, GETCHAR (w, i1));
+
+      i2++;
+
+      if (i2 == sum20) break;
+
+      i1++;
+    }
+
+    if (i3 < salt_len)
+    {
+      PUTCHAR (t, i2, GETCHAR (s, i3));
+
+      i2++;
+
+      if (i2 == sum20) break;
+
+      i3++;
+    }
+
+    PUTCHAR (t, i2, bcodeArray[i2 - i1 - i3]);
+
+    i2++;
+    i2++;
+  }
+
+  return sum20;
+}
+
+__kernel void m07700_m04 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+
+  if (gid >= gid_max) return;
+
+  u32 pw_buf0[4];
+  u32 pw_buf1[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];
+  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_l_len = pws[gid].pw_len;
+
+  /**
+   * salt
+   */
+
+  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] = 0;
+
+  const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+  salt_buf0[0] = sapb_trans (salt_buf0[0]);
+  salt_buf0[1] = sapb_trans (salt_buf0[1]);
+  salt_buf0[2] = sapb_trans (salt_buf0[2]);
+
+  /**
+   * loop
+   */
+
+  for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+  {
+    const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos);
+
+    const u32x pw_len = pw_l_len + pw_r_len;
+
+    /**
+     * concat password candidate
+     */
+
+    u32x wordl0[4] = { 0 };
+    u32x wordl1[4] = { 0 };
+    u32x wordl2[4] = { 0 };
+    u32x wordl3[4] = { 0 };
+
+    wordl0[0] = pw_buf0[0];
+    wordl0[1] = pw_buf0[1];
+    wordl0[2] = pw_buf0[2];
+    wordl0[3] = pw_buf0[3];
+    wordl1[0] = pw_buf1[0];
+    wordl1[1] = pw_buf1[1];
+    wordl1[2] = pw_buf1[2];
+    wordl1[3] = pw_buf1[3];
+
+    u32x wordr0[4] = { 0 };
+    u32x wordr1[4] = { 0 };
+    u32x wordr2[4] = { 0 };
+    u32x wordr3[4] = { 0 };
+
+    wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+    wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+    wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+    wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+    wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+    wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+    wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+    wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+    if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+    {
+      switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+    }
+    else
+    {
+      switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+    }
+
+    u32x w0[4];
+
+    w0[0] = wordl0[0] | wordr0[0];
+    w0[1] = wordl0[1] | wordr0[1];
+
+    if (pw_len > 8) continue; // otherwise it overflows in waldorf function
+
+    /**
+     * SAP
+     */
+
+    w0[0] = sapb_trans (w0[0]);
+    w0[1] = sapb_trans (w0[1]);
+
+    /**
+     * append salt
+     */
+
+    u32 s0[4];
+    u32 s1[4];
+    u32 s2[4];
+    u32 s3[4];
+
+    s0[0] = salt_buf0[0];
+    s0[1] = salt_buf0[1];
+    s0[2] = salt_buf0[2];
+    s0[3] = 0;
+    s1[0] = 0;
+    s1[1] = 0;
+    s1[2] = 0;
+    s1[3] = 0;
+    s2[0] = 0;
+    s2[1] = 0;
+    s2[2] = 0;
+    s2[3] = 0;
+    s3[0] = 0;
+    s3[1] = 0;
+    s3[2] = 0;
+    s3[3] = 0;
+
+    switch_buffer_by_offset_le (s0, s1, s2, s3, pw_len);
+
+    const u32 pw_salt_len = pw_len + salt_len;
+
+    u32 t[16];
+
+    t[ 0] = s0[0] | w0[0];
+    t[ 1] = s0[1] | w0[1];
+    t[ 2] = s0[2];
+    t[ 3] = s0[3];
+    t[ 4] = s1[0];
+    t[ 5] = 0;
+    t[ 6] = 0;
+    t[ 7] = 0;
+    t[ 8] = 0;
+    t[ 9] = 0;
+    t[10] = 0;
+    t[11] = 0;
+    t[12] = 0;
+    t[13] = 0;
+    t[14] = pw_salt_len * 8;
+    t[15] = 0;
+
+    append_0x80_4x4_S (t + 0, t + 4, t + 8, t + 12, pw_salt_len);
+
+    /**
+     * md5
+     */
+
+    u32 digest[4];
+
+    digest[0] = MD5M_A;
+    digest[1] = MD5M_B;
+    digest[2] = MD5M_C;
+    digest[3] = MD5M_D;
+
+    md5_transform (t + 0, t + 4, t + 8, t + 12, digest);
+
+    const u32 sum20 = walld0rf_magic (w0, pw_len, salt_buf0, salt_len, digest[0], digest[1], digest[2], digest[3], t);
+
+    append_0x80_4x4_S (t + 0, t + 4, t + 8, t + 12, sum20);
+
+    t[14] = sum20 * 8;
+    t[15] = 0;
+
+    digest[0] = MD5M_A;
+    digest[1] = MD5M_B;
+    digest[2] = MD5M_C;
+    digest[3] = MD5M_D;
+
+    md5_transform (t + 0, t + 4, t + 8, t + 12, digest);
+
+    const u32 r0 = digest[0] ^ digest[2];
+    const u32 r1 = 0;
+    const u32 r2 = 0;
+    const u32 r3 = 0;
+
+    COMPARE_M_SIMD (r0, r1, r2, r3);
+  }
+}
+
+__kernel void m07700_m08 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+}
+
+__kernel void m07700_m16 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+}
+
+__kernel void m07700_s04 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+
+  if (gid >= gid_max) return;
+
+  u32 pw_buf0[4];
+  u32 pw_buf1[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];
+  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_l_len = pws[gid].pw_len;
+
+  /**
+   * salt
+   */
+
+  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] = 0;
+
+  const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+  salt_buf0[0] = sapb_trans (salt_buf0[0]);
+  salt_buf0[1] = sapb_trans (salt_buf0[1]);
+  salt_buf0[2] = sapb_trans (salt_buf0[2]);
+
+  /**
+   * digest
+   */
+
+  const u32 search[4] =
+  {
+    digests_buf[digests_offset].digest_buf[DGST_R0],
+    digests_buf[digests_offset].digest_buf[DGST_R1],
+    0,
+    0
+  };
+
+  /**
+   * loop
+   */
+
+  for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+  {
+    const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos);
+
+    const u32x pw_len = pw_l_len + pw_r_len;
+
+    /**
+     * concat password candidate
+     */
+
+    u32x wordl0[4] = { 0 };
+    u32x wordl1[4] = { 0 };
+    u32x wordl2[4] = { 0 };
+    u32x wordl3[4] = { 0 };
+
+    wordl0[0] = pw_buf0[0];
+    wordl0[1] = pw_buf0[1];
+    wordl0[2] = pw_buf0[2];
+    wordl0[3] = pw_buf0[3];
+    wordl1[0] = pw_buf1[0];
+    wordl1[1] = pw_buf1[1];
+    wordl1[2] = pw_buf1[2];
+    wordl1[3] = pw_buf1[3];
+
+    u32x wordr0[4] = { 0 };
+    u32x wordr1[4] = { 0 };
+    u32x wordr2[4] = { 0 };
+    u32x wordr3[4] = { 0 };
+
+    wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+    wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+    wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+    wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+    wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+    wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+    wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+    wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+    if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+    {
+      switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+    }
+    else
+    {
+      switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+    }
+
+    u32x w0[4];
+
+    w0[0] = wordl0[0] | wordr0[0];
+    w0[1] = wordl0[1] | wordr0[1];
+
+    if (pw_len > 8) continue; // otherwise it overflows in waldorf function
+
+    /**
+     * SAP
+     */
+
+    w0[0] = sapb_trans (w0[0]);
+    w0[1] = sapb_trans (w0[1]);
+
+    /**
+     * append salt
+     */
+
+    u32 s0[4];
+    u32 s1[4];
+    u32 s2[4];
+    u32 s3[4];
+
+    s0[0] = salt_buf0[0];
+    s0[1] = salt_buf0[1];
+    s0[2] = salt_buf0[2];
+    s0[3] = 0;
+    s1[0] = 0;
+    s1[1] = 0;
+    s1[2] = 0;
+    s1[3] = 0;
+    s2[0] = 0;
+    s2[1] = 0;
+    s2[2] = 0;
+    s2[3] = 0;
+    s3[0] = 0;
+    s3[1] = 0;
+    s3[2] = 0;
+    s3[3] = 0;
+
+    switch_buffer_by_offset_le (s0, s1, s2, s3, pw_len);
+
+    const u32 pw_salt_len = pw_len + salt_len;
+
+    u32 t[16];
+
+    t[ 0] = s0[0] | w0[0];
+    t[ 1] = s0[1] | w0[1];
+    t[ 2] = s0[2];
+    t[ 3] = s0[3];
+    t[ 4] = s1[0];
+    t[ 5] = 0;
+    t[ 6] = 0;
+    t[ 7] = 0;
+    t[ 8] = 0;
+    t[ 9] = 0;
+    t[10] = 0;
+    t[11] = 0;
+    t[12] = 0;
+    t[13] = 0;
+    t[14] = pw_salt_len * 8;
+    t[15] = 0;
+
+    append_0x80_4x4_S (t + 0, t + 4, t + 8, t + 12, pw_salt_len);
+
+    /**
+     * md5
+     */
+
+    u32 digest[4];
+
+    digest[0] = MD5M_A;
+    digest[1] = MD5M_B;
+    digest[2] = MD5M_C;
+    digest[3] = MD5M_D;
+
+    md5_transform (t + 0, t + 4, t + 8, t + 12, digest);
+
+    const u32 sum20 = walld0rf_magic (w0, pw_len, salt_buf0, salt_len, digest[0], digest[1], digest[2], digest[3], t);
+
+    append_0x80_4x4_S (t + 0, t + 4, t + 8, t + 12, sum20);
+
+    t[14] = sum20 * 8;
+    t[15] = 0;
+
+    digest[0] = MD5M_A;
+    digest[1] = MD5M_B;
+    digest[2] = MD5M_C;
+    digest[3] = MD5M_D;
+
+    md5_transform (t + 0, t + 4, t + 8, t + 12, digest);
+
+    const u32 r0 = digest[0] ^ digest[2];
+    const u32 r1 = 0;
+    const u32 r2 = 0;
+    const u32 r3 = 0;
+
+    COMPARE_S_SIMD (r0, r1, r2, r3);
+  }
+}
+
+__kernel void m07700_s08 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+}
+
+__kernel void m07700_s16 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+}
diff --git a/OpenCL/m07701_a3-optimized.cl b/OpenCL/m07701_a3-optimized.cl
new file mode 100644
index 000000000..43acffae1
--- /dev/null
+++ b/OpenCL/m07701_a3-optimized.cl
@@ -0,0 +1,619 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//too much register pressure
+//#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_simd.cl"
+#include "inc_hash_md5.cl"
+
+#define GETCHAR(a,p)  (((a)[(p) / 4] >> (((p) & 3) * 8)) & 0xff)
+#define PUTCHAR(a,p,c) ((a)[(p) / 4] = (((a)[(p) / 4] & ~(0xff << (((p) & 3) * 8))) | ((c) << (((p) & 3) * 8))))
+
+__constant u32a sapb_trans_tbl[256] =
+{
+  // first value hack for 0 byte as part of an optimization
+  0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0x3f, 0x40, 0x41, 0x50, 0x43, 0x44, 0x45, 0x4b, 0x47, 0x48, 0x4d, 0x4e, 0x54, 0x51, 0x53, 0x46,
+  0x35, 0x36, 0x37, 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x56, 0x55, 0x5c, 0x49, 0x5d, 0x4a,
+  0x42, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
+  0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x58, 0x5b, 0x59, 0xff, 0x52,
+  0x4c, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
+  0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x57, 0x5e, 0x5a, 0x4f, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+};
+
+__constant u32a bcodeArray[48] =
+{
+  0x14, 0x77, 0xf3, 0xd4, 0xbb, 0x71, 0x23, 0xd0, 0x03, 0xff, 0x47, 0x93, 0x55, 0xaa, 0x66, 0x91,
+  0xf2, 0x88, 0x6b, 0x99, 0xbf, 0xcb, 0x32, 0x1a, 0x19, 0xd9, 0xa7, 0x82, 0x22, 0x49, 0xa2, 0x51,
+  0xe2, 0xb7, 0x33, 0x71, 0x8b, 0x9f, 0x5d, 0x01, 0x44, 0x70, 0xae, 0x11, 0xef, 0x28, 0xf0, 0x0d
+};
+
+DECLSPEC u32 sapb_trans (const u32 in)
+{
+  u32 out = 0;
+
+  out |= (sapb_trans_tbl[(in >>  0) & 0xff]) <<  0;
+  out |= (sapb_trans_tbl[(in >>  8) & 0xff]) <<  8;
+  out |= (sapb_trans_tbl[(in >> 16) & 0xff]) << 16;
+  out |= (sapb_trans_tbl[(in >> 24) & 0xff]) << 24;
+
+  return out;
+}
+
+DECLSPEC u32 walld0rf_magic (const u32 w0[4], const u32 pw_len, const u32 salt_buf0[4], const u32 salt_len, const u32 a, const u32 b, const u32 c, const u32 d, u32 t[16])
+{
+  t[ 0] = 0;
+  t[ 1] = 0;
+  t[ 2] = 0;
+  t[ 3] = 0;
+  t[ 4] = 0;
+  t[ 5] = 0;
+  t[ 6] = 0;
+  t[ 7] = 0;
+  t[ 8] = 0;
+  t[ 9] = 0;
+  t[10] = 0;
+  t[11] = 0;
+  t[12] = 0;
+  t[13] = 0;
+  t[14] = 0;
+  t[15] = 0;
+
+  u32 sum20 = ((a >> 24) & 3)
+            + ((a >> 16) & 3)
+            + ((a >>  8) & 3)
+            + ((a >>  0) & 3)
+            + ((b >>  8) & 3);
+
+  sum20 |= 0x20;
+
+  const u32 w[2] = { w0[0], w0[1] };
+
+  const u32 s[3] = { salt_buf0[0], salt_buf0[1], salt_buf0[2] };
+
+  u32 saved_key[4] = { a, b, c, d };
+
+  u32 i1 = 0;
+  u32 i2 = 0;
+  u32 i3 = 0;
+
+  while (i2 < sum20)
+  {
+    if (i1 < pw_len)
+    {
+      if (GETCHAR (saved_key, 15 - i1) & 1)
+      {
+        PUTCHAR (t, i2, bcodeArray[48 - 1 - i1]);
+
+        i2++;
+
+        if (i2 == sum20) break;
+      }
+
+      PUTCHAR (t, i2, GETCHAR (w, i1));
+
+      i2++;
+
+      if (i2 == sum20) break;
+
+      i1++;
+    }
+
+    if (i3 < salt_len)
+    {
+      PUTCHAR (t, i2, GETCHAR (s, i3));
+
+      i2++;
+
+      if (i2 == sum20) break;
+
+      i3++;
+    }
+
+    PUTCHAR (t, i2, bcodeArray[i2 - i1 - i3]);
+
+    i2++;
+    i2++;
+  }
+
+  return sum20;
+}
+
+DECLSPEC void m07701m (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_len, __global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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)
+{
+  /**
+   * modifier
+   */
+
+  const u64 gid = get_global_id (0);
+  const u64 lid = get_local_id (0);
+
+  w0[0] = sapb_trans (w0[0]);
+  w0[1] = sapb_trans (w0[1]);
+
+  /**
+   * salt
+   */
+
+  u32 salt_buf0[3];
+
+  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[0] = sapb_trans (salt_buf0[0]);
+  salt_buf0[1] = sapb_trans (salt_buf0[1]);
+  salt_buf0[2] = sapb_trans (salt_buf0[2]);
+
+  const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+  u32 s0[4];
+  u32 s1[4];
+  u32 s2[4];
+  u32 s3[4];
+
+  s0[0] = salt_buf0[0];
+  s0[1] = salt_buf0[1];
+  s0[2] = salt_buf0[2];
+  s0[3] = 0;
+  s1[0] = 0;
+  s1[1] = 0;
+  s1[2] = 0;
+  s1[3] = 0;
+  s2[0] = 0;
+  s2[1] = 0;
+  s2[2] = 0;
+  s2[3] = 0;
+  s3[0] = 0;
+  s3[1] = 0;
+  s3[2] = 0;
+  s3[3] = 0;
+
+  append_0x80_4x4_S (s0, s1, s2, s3, salt_len);
+
+  switch_buffer_by_offset_le (s0, s1, s2, s3, pw_len);
+
+  const u32 pw_salt_len = pw_len + salt_len;
+
+  /**
+   * loop
+   */
+
+  u32 w0l = w0[0];
+
+  for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+  {
+    const u32x w0r = sapb_trans (ix_create_bft (bfs_buf, il_pos));
+
+    const u32x w0lr = w0l | w0r;
+
+    w0[0] = w0lr;
+
+    u32 t[16];
+
+    t[ 0] = s0[0] | w0[0];
+    t[ 1] = s0[1] | w0[1];
+    t[ 2] = s0[2];
+    t[ 3] = s0[3];
+    t[ 4] = s1[0];
+    t[ 5] = s1[1];
+    t[ 6] = 0;
+    t[ 7] = 0;
+    t[ 8] = 0;
+    t[ 9] = 0;
+    t[10] = 0;
+    t[11] = 0;
+    t[12] = 0;
+    t[13] = 0;
+    t[14] = pw_salt_len * 8;
+    t[15] = 0;
+
+    /**
+     * md5
+     */
+
+    u32 digest[4];
+
+    digest[0] = MD5M_A;
+    digest[1] = MD5M_B;
+    digest[2] = MD5M_C;
+    digest[3] = MD5M_D;
+
+    md5_transform (t + 0, t + 4, t + 8, t + 12, digest);
+
+    const u32 sum20 = walld0rf_magic (w0, pw_len, salt_buf0, salt_len, digest[0], digest[1], digest[2], digest[3], t);
+
+    append_0x80_4x4_S (t + 0, t + 4, t + 8, t + 12, sum20);
+
+    t[14] = sum20 * 8;
+    t[15] = 0;
+
+    digest[0] = MD5M_A;
+    digest[1] = MD5M_B;
+    digest[2] = MD5M_C;
+    digest[3] = MD5M_D;
+
+    md5_transform (t + 0, t + 4, t + 8, t + 12, digest);
+
+    const u32 r0 = digest[0] ^ digest[2];
+    const u32 r1 = 0;
+    const u32 r2 = 0;
+    const u32 r3 = 0;
+
+    COMPARE_M_SIMD (r0, r1, r2, r3);
+  }
+}
+
+DECLSPEC void m07701s (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_len, __global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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)
+{
+  /**
+   * modifier
+   */
+
+  const u64 gid = get_global_id (0);
+  const u64 lid = get_local_id (0);
+
+  w0[0] = sapb_trans (w0[0]);
+  w0[1] = sapb_trans (w0[1]);
+
+  /**
+   * salt
+   */
+
+  u32 salt_buf0[3];
+
+  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[0] = sapb_trans (salt_buf0[0]);
+  salt_buf0[1] = sapb_trans (salt_buf0[1]);
+  salt_buf0[2] = sapb_trans (salt_buf0[2]);
+
+  const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+  u32 s0[4];
+  u32 s1[4];
+  u32 s2[4];
+  u32 s3[4];
+
+  s0[0] = salt_buf0[0];
+  s0[1] = salt_buf0[1];
+  s0[2] = salt_buf0[2];
+  s0[3] = 0;
+  s1[0] = 0;
+  s1[1] = 0;
+  s1[2] = 0;
+  s1[3] = 0;
+  s2[0] = 0;
+  s2[1] = 0;
+  s2[2] = 0;
+  s2[3] = 0;
+  s3[0] = 0;
+  s3[1] = 0;
+  s3[2] = 0;
+  s3[3] = 0;
+
+  append_0x80_4x4_S (s0, s1, s2, s3, salt_len);
+
+  switch_buffer_by_offset_le (s0, s1, s2, s3, pw_len);
+
+  const u32 pw_salt_len = pw_len + salt_len;
+
+  /**
+   * digest
+   */
+
+  const u32 search[4] =
+  {
+    digests_buf[digests_offset].digest_buf[DGST_R0],
+    digests_buf[digests_offset].digest_buf[DGST_R1],
+    0,
+    0
+  };
+
+  /**
+   * loop
+   */
+
+  u32 w0l = w0[0];
+
+  for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+  {
+    const u32x w0r = sapb_trans (ix_create_bft (bfs_buf, il_pos));
+
+    const u32x w0lr = w0l | w0r;
+
+    w0[0] = w0lr;
+
+    u32 t[16];
+
+    t[ 0] = s0[0] | w0[0];
+    t[ 1] = s0[1] | w0[1];
+    t[ 2] = s0[2];
+    t[ 3] = s0[3];
+    t[ 4] = s1[0];
+    t[ 5] = s1[1];
+    t[ 6] = 0;
+    t[ 7] = 0;
+    t[ 8] = 0;
+    t[ 9] = 0;
+    t[10] = 0;
+    t[11] = 0;
+    t[12] = 0;
+    t[13] = 0;
+    t[14] = pw_salt_len * 8;
+    t[15] = 0;
+
+    /**
+     * md5
+     */
+
+    u32 digest[4];
+
+    digest[0] = MD5M_A;
+    digest[1] = MD5M_B;
+    digest[2] = MD5M_C;
+    digest[3] = MD5M_D;
+
+    md5_transform (t + 0, t + 4, t + 8, t + 12, digest);
+
+    const u32 sum20 = walld0rf_magic (w0, pw_len, salt_buf0, salt_len, digest[0], digest[1], digest[2], digest[3], t);
+
+    append_0x80_4x4_S (t + 0, t + 4, t + 8, t + 12, sum20);
+
+    t[14] = sum20 * 8;
+    t[15] = 0;
+
+    digest[0] = MD5M_A;
+    digest[1] = MD5M_B;
+    digest[2] = MD5M_C;
+    digest[3] = MD5M_D;
+
+    md5_transform (t + 0, t + 4, t + 8, t + 12, digest);
+
+    const u32 r0 = digest[0] ^ digest[2];
+    const u32 r1 = 0;
+    const u32 r2 = 0;
+    const u32 r3 = 0;
+
+    COMPARE_S_SIMD (r0, r1, r2, r3);
+  }
+}
+
+__kernel void m07701_m04 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+
+  if (gid >= gid_max) return;
+
+  /**
+   * modifier
+   */
+
+  //const u64 lid = get_local_id (0);
+
+  u32 w0[4];
+
+  w0[0] = pws[gid].i[ 0];
+  w0[1] = pws[gid].i[ 1];
+  w0[2] = pws[gid].i[ 2];
+  w0[3] = pws[gid].i[ 3];
+
+  u32 w1[4];
+
+  w1[0] = 0;
+  w1[1] = 0;
+  w1[2] = 0;
+  w1[3] = 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 pw_len = pws[gid].pw_len;
+
+  /**
+   * main
+   */
+
+  m07701m (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_scryptV0_buf, d_scryptV1_buf, d_scryptV2_buf, d_scryptV3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
+}
+
+__kernel void m07701_m08 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+
+  if (gid >= gid_max) return;
+
+  /**
+   * modifier
+   */
+
+  //const u64 lid = get_local_id (0);
+
+  u32 w0[4];
+
+  w0[0] = pws[gid].i[ 0];
+  w0[1] = pws[gid].i[ 1];
+  w0[2] = pws[gid].i[ 2];
+  w0[3] = pws[gid].i[ 3];
+
+  u32 w1[4];
+
+  w1[0] = pws[gid].i[ 4];
+  w1[1] = pws[gid].i[ 5];
+  w1[2] = pws[gid].i[ 6];
+  w1[3] = pws[gid].i[ 7];
+
+  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 pw_len = pws[gid].pw_len;
+
+  /**
+   * main
+   */
+
+  m07701m (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_scryptV0_buf, d_scryptV1_buf, d_scryptV2_buf, d_scryptV3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
+}
+
+__kernel void m07701_m16 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+}
+
+__kernel void m07701_s04 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+
+  if (gid >= gid_max) return;
+
+  /**
+   * modifier
+   */
+
+  //const u64 lid = get_local_id (0);
+
+  u32 w0[4];
+
+  w0[0] = pws[gid].i[ 0];
+  w0[1] = pws[gid].i[ 1];
+  w0[2] = pws[gid].i[ 2];
+  w0[3] = pws[gid].i[ 3];
+
+  u32 w1[4];
+
+  w1[0] = 0;
+  w1[1] = 0;
+  w1[2] = 0;
+  w1[3] = 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 pw_len = pws[gid].pw_len;
+
+  /**
+   * main
+   */
+
+  m07701s (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_scryptV0_buf, d_scryptV1_buf, d_scryptV2_buf, d_scryptV3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
+}
+
+__kernel void m07701_s08 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+
+  if (gid >= gid_max) return;
+
+  /**
+   * modifier
+   */
+
+  //const u64 lid = get_local_id (0);
+
+  u32 w0[4];
+
+  w0[0] = pws[gid].i[ 0];
+  w0[1] = pws[gid].i[ 1];
+  w0[2] = pws[gid].i[ 2];
+  w0[3] = pws[gid].i[ 3];
+
+  u32 w1[4];
+
+  w1[0] = pws[gid].i[ 4];
+  w1[1] = pws[gid].i[ 5];
+  w1[2] = pws[gid].i[ 6];
+  w1[3] = pws[gid].i[ 7];
+
+  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 pw_len = pws[gid].pw_len;
+
+  /**
+   * main
+   */
+
+  m07701s (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_scryptV0_buf, d_scryptV1_buf, d_scryptV2_buf, d_scryptV3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
+}
+
+__kernel void m07701_s16 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+}
diff --git a/OpenCL/m07801_a0-optimized.cl b/OpenCL/m07801_a0-optimized.cl
new file mode 100644
index 000000000..c076e5912
--- /dev/null
+++ b/OpenCL/m07801_a0-optimized.cl
@@ -0,0 +1,562 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//incompatible data-dependant code
+//#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_optimized.h"
+#include "inc_rp_optimized.cl"
+#include "inc_simd.cl"
+#include "inc_hash_sha1.cl"
+
+__constant u32a theMagicArray[64] =
+{
+  0x91ac5114, 0x9f675443, 0x24e73be0, 0x28747bc2, 0x863313eb, 0x5a4fcb5c, 0x080a7337, 0x0e5d1c2f,
+  0x338fe6e5, 0xf89baedd, 0x16f24b8d, 0x2ce1d4dc, 0xb0cbdf9d, 0xd4706d17, 0xf94d423f, 0x9b1b1194,
+  0x9f5bc19b, 0x06059d03, 0x9d5e138a, 0x1e9a6ae8, 0xd97c1417, 0x58c72af6, 0xa199630a, 0xd7fd70c3,
+  0xf65e7413, 0x03c90b04, 0x2698f726, 0x8a929325, 0xb0a20d23, 0xed63796d, 0x1332fa3c, 0x35029aa3,
+  0xb3dd8e0a, 0x24bf51c3, 0x7ccd559f, 0x37af944c, 0x29085282, 0xb23b4e37, 0x9f170791, 0x113bfdcd,
+  0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+  0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+  0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+};
+
+DECLSPEC u32 GETSHIFTEDINT_CONST (__constant u32 *a, const int n)
+{
+  const int d = n / 4;
+  const int m = n & 3;
+
+  u64 tmp = hl32_to_64_S (a[d + 0], a[d + 1]);
+
+  tmp <<= m * 8;
+
+  return h32_from_64_S (tmp);
+}
+
+DECLSPEC void SETSHIFTEDINT (u32 *a, const int n, const u32 v)
+{
+  const int d = n / 4;
+  const int m = n & 3;
+
+  u64 tmp = hl32_to_64_S (v, 0);
+
+  tmp >>= m * 8;
+
+  a[d + 0] |= h32_from_64_S (tmp);
+  a[d + 1]  = l32_from_64_S (tmp);
+}
+
+__kernel void m07801_m04 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+
+  if (gid >= gid_max) return;
+
+  u32 pw_buf0[4];
+  u32 pw_buf1[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];
+  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;
+
+  /**
+   * salt
+   */
+
+  u32 salt_buf[8];
+
+  salt_buf[0] = salt_bufs[salt_pos].salt_buf[0];
+  salt_buf[1] = salt_bufs[salt_pos].salt_buf[1];
+  salt_buf[2] = salt_bufs[salt_pos].salt_buf[2];
+  salt_buf[3] = salt_bufs[salt_pos].salt_buf[3];
+  salt_buf[4] = salt_bufs[salt_pos].salt_buf[4];
+  salt_buf[5] = salt_bufs[salt_pos].salt_buf[5];
+  salt_buf[6] = salt_bufs[salt_pos].salt_buf[6];
+  salt_buf[7] = salt_bufs[salt_pos].salt_buf[7];
+
+  const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+  /**
+   * loop
+   */
+
+  for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+  {
+    u32x w0[4] = { 0 };
+    u32x w1[4] = { 0 };
+    u32x w2[4] = { 0 };
+    u32x w3[4] = { 0 };
+
+    const u32x out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+    /**
+     * SAP
+     */
+
+    u32 s0[4];
+    u32 s1[4];
+    u32 s2[4];
+    u32 s3[4];
+
+    s0[0] = salt_buf[0];
+    s0[1] = salt_buf[1];
+    s0[2] = salt_buf[2];
+    s0[3] = salt_buf[3];
+    s1[0] = salt_buf[4];
+    s1[1] = salt_buf[5];
+    s1[2] = salt_buf[6];
+    s1[3] = salt_buf[7];
+    s2[0] = 0;
+    s2[1] = 0;
+    s2[2] = 0;
+    s2[3] = 0;
+    s3[0] = 0;
+    s3[1] = 0;
+    s3[2] = 0;
+    s3[3] = 0;
+
+    switch_buffer_by_offset_le_VV (s0, s1, s2, s3, out_len);
+
+    const u32x pw_salt_len = out_len + salt_len;
+
+    /**
+     * sha1
+     */
+
+    u32 final[32];
+
+    final[ 0] = swap32_S (w0[0] | s0[0]);
+    final[ 1] = swap32_S (w0[1] | s0[1]);
+    final[ 2] = swap32_S (w0[2] | s0[2]);
+    final[ 3] = swap32_S (w0[3] | s0[3]);
+    final[ 4] = swap32_S (w1[0] | s1[0]);
+    final[ 5] = swap32_S (w1[1] | s1[1]);
+    final[ 6] = swap32_S (w1[2] | s1[2]);
+    final[ 7] = swap32_S (w1[3] | s1[3]);
+    final[ 8] = swap32_S (w2[0] | s2[0]);
+    final[ 9] = swap32_S (w2[1] | s2[1]);
+    final[10] = swap32_S (w2[2] | s2[2]);
+    final[11] = swap32_S (w2[3] | s2[3]);
+    final[12] = swap32_S (w3[0] | s3[0]);
+    final[13] = swap32_S (w3[1] | s3[1]);
+    final[14] = 0;
+    final[15] = pw_salt_len * 8;
+    final[16] = 0;
+    final[17] = 0;
+    final[18] = 0;
+    final[19] = 0;
+    final[20] = 0;
+    final[21] = 0;
+    final[22] = 0;
+    final[23] = 0;
+    final[24] = 0;
+    final[25] = 0;
+    final[26] = 0;
+    final[27] = 0;
+    final[28] = 0;
+    final[29] = 0;
+    final[30] = 0;
+    final[31] = 0;
+
+    u32 digest[5];
+
+    digest[0] = SHA1M_A;
+    digest[1] = SHA1M_B;
+    digest[2] = SHA1M_C;
+    digest[3] = SHA1M_D;
+    digest[4] = SHA1M_E;
+
+    sha1_transform (&final[0], &final[4], &final[8], &final[12], digest);
+
+    // prepare magic array range
+
+    u32 lengthMagicArray = 0x20;
+    u32 offsetMagicArray = 0;
+
+    lengthMagicArray += ((digest[0] >> 24) & 0xff) % 6;
+    lengthMagicArray += ((digest[0] >> 16) & 0xff) % 6;
+    lengthMagicArray += ((digest[0] >>  8) & 0xff) % 6;
+    lengthMagicArray += ((digest[0] >>  0) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >> 24) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >> 16) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >>  8) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >>  0) & 0xff) % 6;
+    lengthMagicArray += ((digest[2] >> 24) & 0xff) % 6;
+    lengthMagicArray += ((digest[2] >> 16) & 0xff) % 6;
+    offsetMagicArray += ((digest[2] >>  8) & 0xff) % 8;
+    offsetMagicArray += ((digest[2] >>  0) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >> 24) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >> 16) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >>  8) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >>  0) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >> 24) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >> 16) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >>  8) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >>  0) & 0xff) % 8;
+
+    // final
+
+    digest[0] = SHA1M_A;
+    digest[1] = SHA1M_B;
+    digest[2] = SHA1M_C;
+    digest[3] = SHA1M_D;
+    digest[4] = SHA1M_E;
+
+    final[ 0] = swap32_S (w0[0]);
+    final[ 1] = swap32_S (w0[1]);
+    final[ 2] = swap32_S (w0[2]);
+    final[ 3] = swap32_S (w0[3]);
+    final[ 4] = swap32_S (w1[0]);
+    final[ 5] = swap32_S (w1[1]);
+    final[ 6] = swap32_S (w1[2]);
+    final[ 7] = swap32_S (w1[3]);
+    final[ 8] = 0;
+    final[ 9] = 0;
+    final[10] = 0;
+    final[11] = 0;
+    final[12] = 0;
+    final[13] = 0;
+    final[14] = 0;
+    final[15] = 0;
+
+    u32 final_len = pw_len;
+
+    u32 i;
+
+    // append MagicArray
+
+    for (i = 0; i < lengthMagicArray - 4; i += 4)
+    {
+      const u32 tmp = GETSHIFTEDINT_CONST (theMagicArray, offsetMagicArray + i);
+
+      SETSHIFTEDINT (final, final_len + i, tmp);
+    }
+
+    const u32 mask = 0xffffffff << (((4 - (lengthMagicArray - i)) & 3) * 8);
+
+    const u32 tmp = GETSHIFTEDINT_CONST (theMagicArray, offsetMagicArray + i) & mask;
+
+    SETSHIFTEDINT (final, final_len + i, tmp);
+
+    final_len += lengthMagicArray;
+
+    // append Salt
+
+    for (i = 0; i < salt_len + 1; i += 4) // +1 for the 0x80
+    {
+      const u32 tmp = swap32_S (salt_buf[i / 4]); // attention, int[] not char[]
+
+      SETSHIFTEDINT (final, final_len + i, tmp);
+    }
+
+    final_len += salt_len;
+
+    // calculate
+
+    int left;
+    int off;
+
+    for (left = final_len, off = 0; left >= 56; left -= 64, off += 16)
+    {
+      sha1_transform (&final[off + 0], &final[off + 4], &final[off + 8], &final[off + 12], digest);
+    }
+
+    final[off + 15] = final_len * 8;
+
+    sha1_transform (&final[off + 0], &final[off + 4], &final[off + 8], &final[off + 12], digest);
+
+    COMPARE_M_SIMD (0, 0, digest[2] & 0xffff0000, digest[1]);
+  }
+}
+
+__kernel void m07801_m08 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+}
+
+__kernel void m07801_m16 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+}
+
+__kernel void m07801_s04 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+
+  if (gid >= gid_max) return;
+
+  u32 pw_buf0[4];
+  u32 pw_buf1[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];
+  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;
+
+  /**
+   * salt
+   */
+
+  u32 salt_buf[8];
+
+  salt_buf[0] = salt_bufs[salt_pos].salt_buf[0];
+  salt_buf[1] = salt_bufs[salt_pos].salt_buf[1];
+  salt_buf[2] = salt_bufs[salt_pos].salt_buf[2];
+  salt_buf[3] = salt_bufs[salt_pos].salt_buf[3];
+  salt_buf[4] = salt_bufs[salt_pos].salt_buf[4];
+  salt_buf[5] = salt_bufs[salt_pos].salt_buf[5];
+  salt_buf[6] = salt_bufs[salt_pos].salt_buf[6];
+  salt_buf[7] = salt_bufs[salt_pos].salt_buf[7];
+
+  const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+  /**
+   * digest
+   */
+
+  const u32 search[4] =
+  {
+    digests_buf[digests_offset].digest_buf[DGST_R0],
+    digests_buf[digests_offset].digest_buf[DGST_R1],
+    digests_buf[digests_offset].digest_buf[DGST_R2],
+    digests_buf[digests_offset].digest_buf[DGST_R3]
+  };
+
+  /**
+   * loop
+   */
+
+  for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+  {
+    u32x w0[4] = { 0 };
+    u32x w1[4] = { 0 };
+    u32x w2[4] = { 0 };
+    u32x w3[4] = { 0 };
+
+    const u32x out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+    /**
+     * SAP
+     */
+
+    u32 s0[4];
+    u32 s1[4];
+    u32 s2[4];
+    u32 s3[4];
+
+    s0[0] = salt_buf[0];
+    s0[1] = salt_buf[1];
+    s0[2] = salt_buf[2];
+    s0[3] = salt_buf[3];
+    s1[0] = salt_buf[4];
+    s1[1] = salt_buf[5];
+    s1[2] = salt_buf[6];
+    s1[3] = salt_buf[7];
+    s2[0] = 0;
+    s2[1] = 0;
+    s2[2] = 0;
+    s2[3] = 0;
+    s3[0] = 0;
+    s3[1] = 0;
+    s3[2] = 0;
+    s3[3] = 0;
+
+    switch_buffer_by_offset_le_VV (s0, s1, s2, s3, out_len);
+
+    const u32x pw_salt_len = out_len + salt_len;
+
+    /**
+     * sha1
+     */
+
+    u32 final[32];
+
+    final[ 0] = swap32_S (w0[0] | s0[0]);
+    final[ 1] = swap32_S (w0[1] | s0[1]);
+    final[ 2] = swap32_S (w0[2] | s0[2]);
+    final[ 3] = swap32_S (w0[3] | s0[3]);
+    final[ 4] = swap32_S (w1[0] | s1[0]);
+    final[ 5] = swap32_S (w1[1] | s1[1]);
+    final[ 6] = swap32_S (w1[2] | s1[2]);
+    final[ 7] = swap32_S (w1[3] | s1[3]);
+    final[ 8] = swap32_S (w2[0] | s2[0]);
+    final[ 9] = swap32_S (w2[1] | s2[1]);
+    final[10] = swap32_S (w2[2] | s2[2]);
+    final[11] = swap32_S (w2[3] | s2[3]);
+    final[12] = swap32_S (w3[0] | s3[0]);
+    final[13] = swap32_S (w3[1] | s3[1]);
+    final[14] = 0;
+    final[15] = pw_salt_len * 8;
+    final[16] = 0;
+    final[17] = 0;
+    final[18] = 0;
+    final[19] = 0;
+    final[20] = 0;
+    final[21] = 0;
+    final[22] = 0;
+    final[23] = 0;
+    final[24] = 0;
+    final[25] = 0;
+    final[26] = 0;
+    final[27] = 0;
+    final[28] = 0;
+    final[29] = 0;
+    final[30] = 0;
+    final[31] = 0;
+
+    u32 digest[5];
+
+    digest[0] = SHA1M_A;
+    digest[1] = SHA1M_B;
+    digest[2] = SHA1M_C;
+    digest[3] = SHA1M_D;
+    digest[4] = SHA1M_E;
+
+    sha1_transform (&final[0], &final[4], &final[8], &final[12], digest);
+
+    // prepare magic array range
+
+    u32 lengthMagicArray = 0x20;
+    u32 offsetMagicArray = 0;
+
+    lengthMagicArray += ((digest[0] >> 24) & 0xff) % 6;
+    lengthMagicArray += ((digest[0] >> 16) & 0xff) % 6;
+    lengthMagicArray += ((digest[0] >>  8) & 0xff) % 6;
+    lengthMagicArray += ((digest[0] >>  0) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >> 24) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >> 16) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >>  8) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >>  0) & 0xff) % 6;
+    lengthMagicArray += ((digest[2] >> 24) & 0xff) % 6;
+    lengthMagicArray += ((digest[2] >> 16) & 0xff) % 6;
+    offsetMagicArray += ((digest[2] >>  8) & 0xff) % 8;
+    offsetMagicArray += ((digest[2] >>  0) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >> 24) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >> 16) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >>  8) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >>  0) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >> 24) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >> 16) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >>  8) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >>  0) & 0xff) % 8;
+
+    // final
+
+    digest[0] = SHA1M_A;
+    digest[1] = SHA1M_B;
+    digest[2] = SHA1M_C;
+    digest[3] = SHA1M_D;
+    digest[4] = SHA1M_E;
+
+    final[ 0] = swap32_S (w0[0]);
+    final[ 1] = swap32_S (w0[1]);
+    final[ 2] = swap32_S (w0[2]);
+    final[ 3] = swap32_S (w0[3]);
+    final[ 4] = swap32_S (w1[0]);
+    final[ 5] = swap32_S (w1[1]);
+    final[ 6] = swap32_S (w1[2]);
+    final[ 7] = swap32_S (w1[3]);
+    final[ 8] = 0;
+    final[ 9] = 0;
+    final[10] = 0;
+    final[11] = 0;
+    final[12] = 0;
+    final[13] = 0;
+    final[14] = 0;
+    final[15] = 0;
+
+    u32 final_len = pw_len;
+
+    u32 i;
+
+    // append MagicArray
+
+    for (i = 0; i < lengthMagicArray - 4; i += 4)
+    {
+      const u32 tmp = GETSHIFTEDINT_CONST (theMagicArray, offsetMagicArray + i);
+
+      SETSHIFTEDINT (final, final_len + i, tmp);
+    }
+
+    const u32 mask = 0xffffffff << (((4 - (lengthMagicArray - i)) & 3) * 8);
+
+    const u32 tmp = GETSHIFTEDINT_CONST (theMagicArray, offsetMagicArray + i) & mask;
+
+    SETSHIFTEDINT (final, final_len + i, tmp);
+
+    final_len += lengthMagicArray;
+
+    // append Salt
+
+    for (i = 0; i < salt_len + 1; i += 4) // +1 for the 0x80
+    {
+      const u32 tmp = swap32_S (salt_buf[i / 4]); // attention, int[] not char[]
+
+      SETSHIFTEDINT (final, final_len + i, tmp);
+    }
+
+    final_len += salt_len;
+
+    // calculate
+
+    int left;
+    int off;
+
+    for (left = final_len, off = 0; left >= 56; left -= 64, off += 16)
+    {
+      sha1_transform (&final[off + 0], &final[off + 4], &final[off + 8], &final[off + 12], digest);
+    }
+
+    final[off + 15] = final_len * 8;
+
+    sha1_transform (&final[off + 0], &final[off + 4], &final[off + 8], &final[off + 12], digest);
+
+    COMPARE_S_SIMD (0, 0, digest[2] & 0xffff0000, digest[1]);
+  }
+}
+
+__kernel void m07801_s08 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+}
+
+__kernel void m07801_s16 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+}
diff --git a/OpenCL/m07801_a1-optimized.cl b/OpenCL/m07801_a1-optimized.cl
new file mode 100644
index 000000000..3e2da3895
--- /dev/null
+++ b/OpenCL/m07801_a1-optimized.cl
@@ -0,0 +1,680 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//incompatible data-dependant code
+//#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_simd.cl"
+#include "inc_hash_sha1.cl"
+
+__constant u32a theMagicArray[64] =
+{
+  0x91ac5114, 0x9f675443, 0x24e73be0, 0x28747bc2, 0x863313eb, 0x5a4fcb5c, 0x080a7337, 0x0e5d1c2f,
+  0x338fe6e5, 0xf89baedd, 0x16f24b8d, 0x2ce1d4dc, 0xb0cbdf9d, 0xd4706d17, 0xf94d423f, 0x9b1b1194,
+  0x9f5bc19b, 0x06059d03, 0x9d5e138a, 0x1e9a6ae8, 0xd97c1417, 0x58c72af6, 0xa199630a, 0xd7fd70c3,
+  0xf65e7413, 0x03c90b04, 0x2698f726, 0x8a929325, 0xb0a20d23, 0xed63796d, 0x1332fa3c, 0x35029aa3,
+  0xb3dd8e0a, 0x24bf51c3, 0x7ccd559f, 0x37af944c, 0x29085282, 0xb23b4e37, 0x9f170791, 0x113bfdcd,
+  0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+  0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+  0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+};
+
+DECLSPEC u32 GETSHIFTEDINT_CONST (__constant u32 *a, const int n)
+{
+  const int d = n / 4;
+  const int m = n & 3;
+
+  u64 tmp = hl32_to_64_S (a[d + 0], a[d + 1]);
+
+  tmp <<= m * 8;
+
+  return h32_from_64_S (tmp);
+}
+
+DECLSPEC void SETSHIFTEDINT (u32 *a, const int n, const u32 v)
+{
+  const int d = n / 4;
+  const int m = n & 3;
+
+  u64 tmp = hl32_to_64_S (v, 0);
+
+  tmp >>= m * 8;
+
+  a[d + 0] |= h32_from_64_S (tmp);
+  a[d + 1]  = l32_from_64_S (tmp);
+}
+
+__kernel void m07800_m04 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+
+  if (gid >= gid_max) return;
+
+  u32 pw_buf0[4];
+  u32 pw_buf1[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];
+  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_l_len = pws[gid].pw_len;
+
+  /**
+   * salt
+   */
+
+  u32 salt_buf[8];
+
+  salt_buf[0] = salt_bufs[salt_pos].salt_buf[0];
+  salt_buf[1] = salt_bufs[salt_pos].salt_buf[1];
+  salt_buf[2] = salt_bufs[salt_pos].salt_buf[2];
+  salt_buf[3] = salt_bufs[salt_pos].salt_buf[3];
+  salt_buf[4] = salt_bufs[salt_pos].salt_buf[4];
+  salt_buf[5] = salt_bufs[salt_pos].salt_buf[5];
+  salt_buf[6] = salt_bufs[salt_pos].salt_buf[6];
+  salt_buf[7] = salt_bufs[salt_pos].salt_buf[7];
+
+  const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+  /**
+   * loop
+   */
+
+  for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+  {
+    const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos);
+
+    const u32x pw_len = pw_l_len + pw_r_len;
+
+    /**
+     * concat password candidate
+     */
+
+    u32x wordl0[4] = { 0 };
+    u32x wordl1[4] = { 0 };
+    u32x wordl2[4] = { 0 };
+    u32x wordl3[4] = { 0 };
+
+    wordl0[0] = pw_buf0[0];
+    wordl0[1] = pw_buf0[1];
+    wordl0[2] = pw_buf0[2];
+    wordl0[3] = pw_buf0[3];
+    wordl1[0] = pw_buf1[0];
+    wordl1[1] = pw_buf1[1];
+    wordl1[2] = pw_buf1[2];
+    wordl1[3] = pw_buf1[3];
+
+    u32x wordr0[4] = { 0 };
+    u32x wordr1[4] = { 0 };
+    u32x wordr2[4] = { 0 };
+    u32x wordr3[4] = { 0 };
+
+    wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+    wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+    wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+    wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+    wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+    wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+    wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+    wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+    if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+    {
+      switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+    }
+    else
+    {
+      switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+    }
+
+    u32x w0[4];
+    u32x w1[4];
+    u32x w2[4];
+    u32x w3[4];
+
+    w0[0] = wordl0[0] | wordr0[0];
+    w0[1] = wordl0[1] | wordr0[1];
+    w0[2] = wordl0[2] | wordr0[2];
+    w0[3] = wordl0[3] | wordr0[3];
+    w1[0] = wordl1[0] | wordr1[0];
+    w1[1] = wordl1[1] | wordr1[1];
+    w1[2] = wordl1[2] | wordr1[2];
+    w1[3] = wordl1[3] | wordr1[3];
+    w2[0] = wordl2[0] | wordr2[0];
+    w2[1] = wordl2[1] | wordr2[1];
+    w2[2] = wordl2[2] | wordr2[2];
+    w2[3] = wordl2[3] | wordr2[3];
+    w3[0] = wordl3[0] | wordr3[0];
+    w3[1] = wordl3[1] | wordr3[1];
+    w3[2] = wordl3[2] | wordr3[2];
+    w3[3] = wordl3[3] | wordr3[3];
+
+    /**
+     * SAP
+     */
+
+    u32 s0[4];
+    u32 s1[4];
+    u32 s2[4];
+    u32 s3[4];
+
+    s0[0] = salt_buf[0];
+    s0[1] = salt_buf[1];
+    s0[2] = salt_buf[2];
+    s0[3] = salt_buf[3];
+    s1[0] = salt_buf[4];
+    s1[1] = salt_buf[5];
+    s1[2] = salt_buf[6];
+    s1[3] = salt_buf[7];
+    s2[0] = 0;
+    s2[1] = 0;
+    s2[2] = 0;
+    s2[3] = 0;
+    s3[0] = 0;
+    s3[1] = 0;
+    s3[2] = 0;
+    s3[3] = 0;
+
+    switch_buffer_by_offset_le_VV (s0, s1, s2, s3, pw_len);
+
+    const u32x pw_salt_len = pw_len + salt_len;
+
+    /**
+     * sha1
+     */
+
+    u32 final[32];
+
+    final[ 0] = swap32_S (w0[0] | s0[0]);
+    final[ 1] = swap32_S (w0[1] | s0[1]);
+    final[ 2] = swap32_S (w0[2] | s0[2]);
+    final[ 3] = swap32_S (w0[3] | s0[3]);
+    final[ 4] = swap32_S (w1[0] | s1[0]);
+    final[ 5] = swap32_S (w1[1] | s1[1]);
+    final[ 6] = swap32_S (w1[2] | s1[2]);
+    final[ 7] = swap32_S (w1[3] | s1[3]);
+    final[ 8] = swap32_S (w2[0] | s2[0]);
+    final[ 9] = swap32_S (w2[1] | s2[1]);
+    final[10] = swap32_S (w2[2] | s2[2]);
+    final[11] = swap32_S (w2[3] | s2[3]);
+    final[12] = swap32_S (w3[0] | s3[0]);
+    final[13] = swap32_S (w3[1] | s3[1]);
+    final[14] = 0;
+    final[15] = pw_salt_len * 8;
+    final[16] = 0;
+    final[17] = 0;
+    final[18] = 0;
+    final[19] = 0;
+    final[20] = 0;
+    final[21] = 0;
+    final[22] = 0;
+    final[23] = 0;
+    final[24] = 0;
+    final[25] = 0;
+    final[26] = 0;
+    final[27] = 0;
+    final[28] = 0;
+    final[29] = 0;
+    final[30] = 0;
+    final[31] = 0;
+
+    u32 digest[5];
+
+    digest[0] = SHA1M_A;
+    digest[1] = SHA1M_B;
+    digest[2] = SHA1M_C;
+    digest[3] = SHA1M_D;
+    digest[4] = SHA1M_E;
+
+    sha1_transform (&final[0], &final[4], &final[8], &final[12], digest);
+
+    // prepare magic array range
+
+    u32 lengthMagicArray = 0x20;
+    u32 offsetMagicArray = 0;
+
+    lengthMagicArray += ((digest[0] >> 24) & 0xff) % 6;
+    lengthMagicArray += ((digest[0] >> 16) & 0xff) % 6;
+    lengthMagicArray += ((digest[0] >>  8) & 0xff) % 6;
+    lengthMagicArray += ((digest[0] >>  0) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >> 24) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >> 16) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >>  8) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >>  0) & 0xff) % 6;
+    lengthMagicArray += ((digest[2] >> 24) & 0xff) % 6;
+    lengthMagicArray += ((digest[2] >> 16) & 0xff) % 6;
+    offsetMagicArray += ((digest[2] >>  8) & 0xff) % 8;
+    offsetMagicArray += ((digest[2] >>  0) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >> 24) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >> 16) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >>  8) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >>  0) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >> 24) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >> 16) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >>  8) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >>  0) & 0xff) % 8;
+
+    // final
+
+    digest[0] = SHA1M_A;
+    digest[1] = SHA1M_B;
+    digest[2] = SHA1M_C;
+    digest[3] = SHA1M_D;
+    digest[4] = SHA1M_E;
+
+    final[ 0] = swap32_S (w0[0]);
+    final[ 1] = swap32_S (w0[1]);
+    final[ 2] = swap32_S (w0[2]);
+    final[ 3] = swap32_S (w0[3]);
+    final[ 4] = swap32_S (w1[0]);
+    final[ 5] = swap32_S (w1[1]);
+    final[ 6] = swap32_S (w1[2]);
+    final[ 7] = swap32_S (w1[3]);
+    final[ 8] = swap32_S (w2[0]);
+    final[ 9] = swap32_S (w2[1]);
+    final[10] = swap32_S (w2[2]);
+    final[11] = swap32_S (w2[3]);
+    final[12] = swap32_S (w3[0]);
+    final[13] = swap32_S (w3[1]);
+    final[14] = 0;
+    final[15] = 0;
+
+    u32 final_len = pw_len;
+
+    u32 i;
+
+    // append MagicArray
+
+    for (i = 0; i < lengthMagicArray - 4; i += 4)
+    {
+      const u32 tmp = GETSHIFTEDINT_CONST (theMagicArray, offsetMagicArray + i);
+
+      SETSHIFTEDINT (final, final_len + i, tmp);
+    }
+
+    const u32 mask = 0xffffffff << (((4 - (lengthMagicArray - i)) & 3) * 8);
+
+    const u32 tmp = GETSHIFTEDINT_CONST (theMagicArray, offsetMagicArray + i) & mask;
+
+    SETSHIFTEDINT (final, final_len + i, tmp);
+
+    final_len += lengthMagicArray;
+
+    // append Salt
+
+    for (i = 0; i < salt_len + 1; i += 4) // +1 for the 0x80
+    {
+      const u32 tmp = swap32_S (salt_buf[i / 4]); // attention, int[] not char[]
+
+      SETSHIFTEDINT (final, final_len + i, tmp);
+    }
+
+    final_len += salt_len;
+
+    // calculate
+
+    int left;
+    int off;
+
+    for (left = final_len, off = 0; left >= 56; left -= 64, off += 16)
+    {
+      sha1_transform (&final[off + 0], &final[off + 4], &final[off + 8], &final[off + 12], digest);
+    }
+
+    final[off + 15] = final_len * 8;
+
+    sha1_transform (&final[off + 0], &final[off + 4], &final[off + 8], &final[off + 12], digest);
+
+    COMPARE_M_SIMD (0, 0, digest[2] & 0xffff0000, digest[1]);
+  }
+}
+
+__kernel void m07800_m08 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+}
+
+__kernel void m07800_m16 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+}
+
+__kernel void m07800_s04 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+
+  if (gid >= gid_max) return;
+
+  u32 pw_buf0[4];
+  u32 pw_buf1[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];
+  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_l_len = pws[gid].pw_len;
+
+  /**
+   * salt
+   */
+
+  u32 salt_buf[8];
+
+  salt_buf[0] = salt_bufs[salt_pos].salt_buf[0];
+  salt_buf[1] = salt_bufs[salt_pos].salt_buf[1];
+  salt_buf[2] = salt_bufs[salt_pos].salt_buf[2];
+  salt_buf[3] = salt_bufs[salt_pos].salt_buf[3];
+  salt_buf[4] = salt_bufs[salt_pos].salt_buf[4];
+  salt_buf[5] = salt_bufs[salt_pos].salt_buf[5];
+  salt_buf[6] = salt_bufs[salt_pos].salt_buf[6];
+  salt_buf[7] = salt_bufs[salt_pos].salt_buf[7];
+
+  const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+  /**
+   * digest
+   */
+
+  const u32 search[4] =
+  {
+    digests_buf[digests_offset].digest_buf[DGST_R0],
+    digests_buf[digests_offset].digest_buf[DGST_R1],
+    digests_buf[digests_offset].digest_buf[DGST_R2],
+    digests_buf[digests_offset].digest_buf[DGST_R3]
+  };
+
+  /**
+   * loop
+   */
+
+  for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+  {
+    const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos);
+
+    const u32x pw_len = pw_l_len + pw_r_len;
+
+    /**
+     * concat password candidate
+     */
+
+    u32x wordl0[4] = { 0 };
+    u32x wordl1[4] = { 0 };
+    u32x wordl2[4] = { 0 };
+    u32x wordl3[4] = { 0 };
+
+    wordl0[0] = pw_buf0[0];
+    wordl0[1] = pw_buf0[1];
+    wordl0[2] = pw_buf0[2];
+    wordl0[3] = pw_buf0[3];
+    wordl1[0] = pw_buf1[0];
+    wordl1[1] = pw_buf1[1];
+    wordl1[2] = pw_buf1[2];
+    wordl1[3] = pw_buf1[3];
+
+    u32x wordr0[4] = { 0 };
+    u32x wordr1[4] = { 0 };
+    u32x wordr2[4] = { 0 };
+    u32x wordr3[4] = { 0 };
+
+    wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+    wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+    wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+    wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+    wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+    wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+    wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+    wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+    if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+    {
+      switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+    }
+    else
+    {
+      switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+    }
+
+    u32x w0[4];
+    u32x w1[4];
+    u32x w2[4];
+    u32x w3[4];
+
+    w0[0] = wordl0[0] | wordr0[0];
+    w0[1] = wordl0[1] | wordr0[1];
+    w0[2] = wordl0[2] | wordr0[2];
+    w0[3] = wordl0[3] | wordr0[3];
+    w1[0] = wordl1[0] | wordr1[0];
+    w1[1] = wordl1[1] | wordr1[1];
+    w1[2] = wordl1[2] | wordr1[2];
+    w1[3] = wordl1[3] | wordr1[3];
+    w2[0] = wordl2[0] | wordr2[0];
+    w2[1] = wordl2[1] | wordr2[1];
+    w2[2] = wordl2[2] | wordr2[2];
+    w2[3] = wordl2[3] | wordr2[3];
+    w3[0] = wordl3[0] | wordr3[0];
+    w3[1] = wordl3[1] | wordr3[1];
+    w3[2] = wordl3[2] | wordr3[2];
+    w3[3] = wordl3[3] | wordr3[3];
+
+    /**
+     * SAP
+     */
+
+    u32 s0[4];
+    u32 s1[4];
+    u32 s2[4];
+    u32 s3[4];
+
+    s0[0] = salt_buf[0];
+    s0[1] = salt_buf[1];
+    s0[2] = salt_buf[2];
+    s0[3] = salt_buf[3];
+    s1[0] = salt_buf[4];
+    s1[1] = salt_buf[5];
+    s1[2] = salt_buf[6];
+    s1[3] = salt_buf[7];
+    s2[0] = 0;
+    s2[1] = 0;
+    s2[2] = 0;
+    s2[3] = 0;
+    s3[0] = 0;
+    s3[1] = 0;
+    s3[2] = 0;
+    s3[3] = 0;
+
+    switch_buffer_by_offset_le_VV (s0, s1, s2, s3, pw_len);
+
+    const u32x pw_salt_len = pw_len + salt_len;
+
+    /**
+     * sha1
+     */
+
+    u32 final[32];
+
+    final[ 0] = swap32_S (w0[0] | s0[0]);
+    final[ 1] = swap32_S (w0[1] | s0[1]);
+    final[ 2] = swap32_S (w0[2] | s0[2]);
+    final[ 3] = swap32_S (w0[3] | s0[3]);
+    final[ 4] = swap32_S (w1[0] | s1[0]);
+    final[ 5] = swap32_S (w1[1] | s1[1]);
+    final[ 6] = swap32_S (w1[2] | s1[2]);
+    final[ 7] = swap32_S (w1[3] | s1[3]);
+    final[ 8] = swap32_S (w2[0] | s2[0]);
+    final[ 9] = swap32_S (w2[1] | s2[1]);
+    final[10] = swap32_S (w2[2] | s2[2]);
+    final[11] = swap32_S (w2[3] | s2[3]);
+    final[12] = swap32_S (w3[0] | s3[0]);
+    final[13] = swap32_S (w3[1] | s3[1]);
+    final[14] = 0;
+    final[15] = pw_salt_len * 8;
+    final[16] = 0;
+    final[17] = 0;
+    final[18] = 0;
+    final[19] = 0;
+    final[20] = 0;
+    final[21] = 0;
+    final[22] = 0;
+    final[23] = 0;
+    final[24] = 0;
+    final[25] = 0;
+    final[26] = 0;
+    final[27] = 0;
+    final[28] = 0;
+    final[29] = 0;
+    final[30] = 0;
+    final[31] = 0;
+
+    u32 digest[5];
+
+    digest[0] = SHA1M_A;
+    digest[1] = SHA1M_B;
+    digest[2] = SHA1M_C;
+    digest[3] = SHA1M_D;
+    digest[4] = SHA1M_E;
+
+    sha1_transform (&final[0], &final[4], &final[8], &final[12], digest);
+
+    // prepare magic array range
+
+    u32 lengthMagicArray = 0x20;
+    u32 offsetMagicArray = 0;
+
+    lengthMagicArray += ((digest[0] >> 24) & 0xff) % 6;
+    lengthMagicArray += ((digest[0] >> 16) & 0xff) % 6;
+    lengthMagicArray += ((digest[0] >>  8) & 0xff) % 6;
+    lengthMagicArray += ((digest[0] >>  0) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >> 24) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >> 16) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >>  8) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >>  0) & 0xff) % 6;
+    lengthMagicArray += ((digest[2] >> 24) & 0xff) % 6;
+    lengthMagicArray += ((digest[2] >> 16) & 0xff) % 6;
+    offsetMagicArray += ((digest[2] >>  8) & 0xff) % 8;
+    offsetMagicArray += ((digest[2] >>  0) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >> 24) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >> 16) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >>  8) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >>  0) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >> 24) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >> 16) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >>  8) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >>  0) & 0xff) % 8;
+
+    // final
+
+    digest[0] = SHA1M_A;
+    digest[1] = SHA1M_B;
+    digest[2] = SHA1M_C;
+    digest[3] = SHA1M_D;
+    digest[4] = SHA1M_E;
+
+    final[ 0] = swap32_S (w0[0]);
+    final[ 1] = swap32_S (w0[1]);
+    final[ 2] = swap32_S (w0[2]);
+    final[ 3] = swap32_S (w0[3]);
+    final[ 4] = swap32_S (w1[0]);
+    final[ 5] = swap32_S (w1[1]);
+    final[ 6] = swap32_S (w1[2]);
+    final[ 7] = swap32_S (w1[3]);
+    final[ 8] = swap32_S (w2[0]);
+    final[ 9] = swap32_S (w2[1]);
+    final[10] = swap32_S (w2[2]);
+    final[11] = swap32_S (w2[3]);
+    final[12] = swap32_S (w3[0]);
+    final[13] = swap32_S (w3[1]);
+    final[14] = 0;
+    final[15] = 0;
+
+    u32 final_len = pw_len;
+
+    u32 i;
+
+    // append MagicArray
+
+    for (i = 0; i < lengthMagicArray - 4; i += 4)
+    {
+      const u32 tmp = GETSHIFTEDINT_CONST (theMagicArray, offsetMagicArray + i);
+
+      SETSHIFTEDINT (final, final_len + i, tmp);
+    }
+
+    const u32 mask = 0xffffffff << (((4 - (lengthMagicArray - i)) & 3) * 8);
+
+    const u32 tmp = GETSHIFTEDINT_CONST (theMagicArray, offsetMagicArray + i) & mask;
+
+    SETSHIFTEDINT (final, final_len + i, tmp);
+
+    final_len += lengthMagicArray;
+
+    // append Salt
+
+    for (i = 0; i < salt_len + 1; i += 4) // +1 for the 0x80
+    {
+      const u32 tmp = swap32_S (salt_buf[i / 4]); // attention, int[] not char[]
+
+      SETSHIFTEDINT (final, final_len + i, tmp);
+    }
+
+    final_len += salt_len;
+
+    // calculate
+
+    int left;
+    int off;
+
+    for (left = final_len, off = 0; left >= 56; left -= 64, off += 16)
+    {
+      sha1_transform (&final[off + 0], &final[off + 4], &final[off + 8], &final[off + 12], digest);
+    }
+
+    final[off + 15] = final_len * 8;
+
+    sha1_transform (&final[off + 0], &final[off + 4], &final[off + 8], &final[off + 12], digest);
+
+    COMPARE_S_SIMD (0, 0, digest[2] & 0xffff0000, digest[1]);
+  }
+}
+
+__kernel void m07800_s08 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+}
+
+__kernel void m07800_s16 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+}
diff --git a/OpenCL/m07801_a3-optimized.cl b/OpenCL/m07801_a3-optimized.cl
new file mode 100644
index 000000000..a4fac21a6
--- /dev/null
+++ b/OpenCL/m07801_a3-optimized.cl
@@ -0,0 +1,716 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//incompatible data-dependant code
+//#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_simd.cl"
+#include "inc_hash_sha1.cl"
+
+__constant u32a theMagicArray[64] =
+{
+  0x91ac5114, 0x9f675443, 0x24e73be0, 0x28747bc2, 0x863313eb, 0x5a4fcb5c, 0x080a7337, 0x0e5d1c2f,
+  0x338fe6e5, 0xf89baedd, 0x16f24b8d, 0x2ce1d4dc, 0xb0cbdf9d, 0xd4706d17, 0xf94d423f, 0x9b1b1194,
+  0x9f5bc19b, 0x06059d03, 0x9d5e138a, 0x1e9a6ae8, 0xd97c1417, 0x58c72af6, 0xa199630a, 0xd7fd70c3,
+  0xf65e7413, 0x03c90b04, 0x2698f726, 0x8a929325, 0xb0a20d23, 0xed63796d, 0x1332fa3c, 0x35029aa3,
+  0xb3dd8e0a, 0x24bf51c3, 0x7ccd559f, 0x37af944c, 0x29085282, 0xb23b4e37, 0x9f170791, 0x113bfdcd,
+  0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+  0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+  0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+};
+
+DECLSPEC u32 GETSHIFTEDINT_CONST (__constant u32 *a, const int n)
+{
+  const int d = n / 4;
+  const int m = n & 3;
+
+  u64 tmp = hl32_to_64_S (a[d + 0], a[d + 1]);
+
+  tmp <<= m * 8;
+
+  return h32_from_64_S (tmp);
+}
+
+DECLSPEC void SETSHIFTEDINT (u32 *a, const int n, const u32 v)
+{
+  const int d = n / 4;
+  const int m = n & 3;
+
+  u64 tmp = hl32_to_64_S (v, 0);
+
+  tmp >>= m * 8;
+
+  a[d + 0] |= h32_from_64_S (tmp);
+  a[d + 1]  = l32_from_64_S (tmp);
+}
+
+DECLSPEC void m07801m (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_len, __global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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)
+{
+  /**
+   * modifier
+   */
+
+  const u64 gid = get_global_id (0);
+  const u64 lid = get_local_id (0);
+
+  /**
+   * salt
+   */
+
+  u32 salt_buf[8];
+
+  salt_buf[0] = swap32_S (salt_bufs[salt_pos].salt_buf[0]);
+  salt_buf[1] = swap32_S (salt_bufs[salt_pos].salt_buf[1]);
+  salt_buf[2] = swap32_S (salt_bufs[salt_pos].salt_buf[2]);
+  salt_buf[3] = swap32_S (salt_bufs[salt_pos].salt_buf[3]);
+  salt_buf[4] = swap32_S (salt_bufs[salt_pos].salt_buf[4]);
+  salt_buf[5] = swap32_S (salt_bufs[salt_pos].salt_buf[5]);
+  salt_buf[6] = swap32_S (salt_bufs[salt_pos].salt_buf[6]);
+  salt_buf[7] = swap32_S (salt_bufs[salt_pos].salt_buf[7]);
+
+  const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+  u32 s0[4];
+  u32 s1[4];
+  u32 s2[4];
+  u32 s3[4];
+
+  s0[0] = salt_buf[0];
+  s0[1] = salt_buf[1];
+  s0[2] = salt_buf[2];
+  s0[3] = salt_buf[3];
+  s1[0] = salt_buf[4];
+  s1[1] = salt_buf[5];
+  s1[2] = salt_buf[6];
+  s1[3] = salt_buf[7];
+  s2[0] = 0;
+  s2[1] = 0;
+  s2[2] = 0;
+  s2[3] = 0;
+  s3[0] = 0;
+  s3[1] = 0;
+  s3[2] = 0;
+  s3[3] = 0;
+
+  switch_buffer_by_offset_be_S (s0, s1, s2, s3, pw_len);
+
+  const u32x pw_salt_len = pw_len + salt_len;
+
+  /**
+   * loop
+   */
+
+  u32 w0l = w0[0];
+
+  for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+  {
+    const u32x w0r = ix_create_bft (bfs_buf, il_pos);
+
+    const u32x w0lr = w0l | w0r;
+
+    w0[0] = w0lr;
+
+    /**
+     * SAP
+     */
+
+    u32 final[32];
+
+    final[ 0] = w0[0] | s0[0];
+    final[ 1] = w0[1] | s0[1];
+    final[ 2] = w0[2] | s0[2];
+    final[ 3] = w0[3] | s0[3];
+    final[ 4] = w1[0] | s1[0];
+    final[ 5] = w1[1] | s1[1];
+    final[ 6] = w1[2] | s1[2];
+    final[ 7] = w1[3] | s1[3];
+    final[ 8] = w2[0] | s2[0];
+    final[ 9] = w2[1] | s2[1];
+    final[10] = w2[2] | s2[2];
+    final[11] = w2[3] | s2[3];
+    final[12] = w3[0] | s3[0];
+    final[13] = w3[1] | s3[1];
+    final[14] = 0;
+    final[15] = pw_salt_len * 8;
+    final[16] = 0;
+    final[17] = 0;
+    final[18] = 0;
+    final[19] = 0;
+    final[20] = 0;
+    final[21] = 0;
+    final[22] = 0;
+    final[23] = 0;
+    final[24] = 0;
+    final[25] = 0;
+    final[26] = 0;
+    final[27] = 0;
+    final[28] = 0;
+    final[29] = 0;
+    final[30] = 0;
+    final[31] = 0;
+
+    u32 digest[5];
+
+    digest[0] = SHA1M_A;
+    digest[1] = SHA1M_B;
+    digest[2] = SHA1M_C;
+    digest[3] = SHA1M_D;
+    digest[4] = SHA1M_E;
+
+    sha1_transform (&final[0], &final[4], &final[8], &final[12], digest);
+
+    // prepare magic array range
+
+    u32 lengthMagicArray = 0x20;
+    u32 offsetMagicArray = 0;
+
+    lengthMagicArray += ((digest[0] >> 24) & 0xff) % 6;
+    lengthMagicArray += ((digest[0] >> 16) & 0xff) % 6;
+    lengthMagicArray += ((digest[0] >>  8) & 0xff) % 6;
+    lengthMagicArray += ((digest[0] >>  0) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >> 24) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >> 16) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >>  8) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >>  0) & 0xff) % 6;
+    lengthMagicArray += ((digest[2] >> 24) & 0xff) % 6;
+    lengthMagicArray += ((digest[2] >> 16) & 0xff) % 6;
+    offsetMagicArray += ((digest[2] >>  8) & 0xff) % 8;
+    offsetMagicArray += ((digest[2] >>  0) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >> 24) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >> 16) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >>  8) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >>  0) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >> 24) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >> 16) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >>  8) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >>  0) & 0xff) % 8;
+
+    // final
+
+    digest[0] = SHA1M_A;
+    digest[1] = SHA1M_B;
+    digest[2] = SHA1M_C;
+    digest[3] = SHA1M_D;
+    digest[4] = SHA1M_E;
+
+    final[ 0] = w0[0];
+    final[ 1] = w0[1];
+    final[ 2] = w0[2];
+    final[ 3] = w0[3];
+    final[ 4] = w1[0];
+    final[ 5] = w1[1];
+    final[ 6] = w1[2];
+    final[ 7] = w1[3];
+    final[ 8] = 0;
+    final[ 9] = 0;
+    final[10] = 0;
+    final[11] = 0;
+    final[12] = 0;
+    final[13] = 0;
+    final[14] = 0;
+    final[15] = 0;
+
+    u32 final_len = pw_len;
+
+    u32 i;
+
+    // append MagicArray
+
+    for (i = 0; i < lengthMagicArray - 4; i += 4)
+    {
+      const u32 tmp = GETSHIFTEDINT_CONST (theMagicArray, offsetMagicArray + i);
+
+      SETSHIFTEDINT (final, final_len + i, tmp);
+    }
+
+    const u32 mask = 0xffffffff << (((4 - (lengthMagicArray - i)) & 3) * 8);
+
+    const u32 tmp = GETSHIFTEDINT_CONST (theMagicArray, offsetMagicArray + i) & mask;
+
+    SETSHIFTEDINT (final, final_len + i, tmp);
+
+    final_len += lengthMagicArray;
+
+    // append Salt
+
+    for (i = 0; i < salt_len + 1; i += 4) // +1 for the 0x80
+    {
+      const u32 tmp = salt_buf[i / 4]; // attention, int[] not char[]
+
+      SETSHIFTEDINT (final, final_len + i, tmp);
+    }
+
+    final_len += salt_len;
+
+    // calculate
+
+    int left;
+    int off;
+
+    for (left = final_len, off = 0; left >= 56; left -= 64, off += 16)
+    {
+      sha1_transform (&final[off + 0], &final[off + 4], &final[off + 8], &final[off + 12], digest);
+    }
+
+    final[off + 15] = final_len * 8;
+
+    sha1_transform (&final[off + 0], &final[off + 4], &final[off + 8], &final[off + 12], digest);
+
+    COMPARE_M_SIMD (0, 0, digest[2] & 0xffff0000, digest[1]);
+  }
+}
+
+DECLSPEC void m07801s (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_len, __global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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)
+{
+  /**
+   * modifier
+   */
+
+  const u64 gid = get_global_id (0);
+  const u64 lid = get_local_id (0);
+
+  /**
+   * salt
+   */
+
+  u32 salt_buf[8];
+
+  salt_buf[0] = swap32_S (salt_bufs[salt_pos].salt_buf[0]);
+  salt_buf[1] = swap32_S (salt_bufs[salt_pos].salt_buf[1]);
+  salt_buf[2] = swap32_S (salt_bufs[salt_pos].salt_buf[2]);
+  salt_buf[3] = swap32_S (salt_bufs[salt_pos].salt_buf[3]);
+  salt_buf[4] = swap32_S (salt_bufs[salt_pos].salt_buf[4]);
+  salt_buf[5] = swap32_S (salt_bufs[salt_pos].salt_buf[5]);
+  salt_buf[6] = swap32_S (salt_bufs[salt_pos].salt_buf[6]);
+  salt_buf[7] = swap32_S (salt_bufs[salt_pos].salt_buf[7]);
+
+  const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+  u32 s0[4];
+  u32 s1[4];
+  u32 s2[4];
+  u32 s3[4];
+
+  s0[0] = salt_buf[0];
+  s0[1] = salt_buf[1];
+  s0[2] = salt_buf[2];
+  s0[3] = salt_buf[3];
+  s1[0] = salt_buf[4];
+  s1[1] = salt_buf[5];
+  s1[2] = salt_buf[6];
+  s1[3] = salt_buf[7];
+  s2[0] = 0;
+  s2[1] = 0;
+  s2[2] = 0;
+  s2[3] = 0;
+  s3[0] = 0;
+  s3[1] = 0;
+  s3[2] = 0;
+  s3[3] = 0;
+
+  switch_buffer_by_offset_be_S (s0, s1, s2, s3, pw_len);
+
+  const u32x pw_salt_len = pw_len + salt_len;
+
+  /**
+   * digest
+   */
+
+  const u32 search[4] =
+  {
+    digests_buf[digests_offset].digest_buf[DGST_R0],
+    digests_buf[digests_offset].digest_buf[DGST_R1],
+    digests_buf[digests_offset].digest_buf[DGST_R2],
+    digests_buf[digests_offset].digest_buf[DGST_R3]
+  };
+
+  /**
+   * loop
+   */
+
+  u32 w0l = w0[0];
+
+  for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+  {
+    const u32x w0r = ix_create_bft (bfs_buf, il_pos);
+
+    const u32x w0lr = w0l | w0r;
+
+    w0[0] = w0lr;
+
+    /**
+     * SAP
+     */
+
+    u32 final[32];
+
+    final[ 0] = w0[0] | s0[0];
+    final[ 1] = w0[1] | s0[1];
+    final[ 2] = w0[2] | s0[2];
+    final[ 3] = w0[3] | s0[3];
+    final[ 4] = w1[0] | s1[0];
+    final[ 5] = w1[1] | s1[1];
+    final[ 6] = w1[2] | s1[2];
+    final[ 7] = w1[3] | s1[3];
+    final[ 8] = w2[0] | s2[0];
+    final[ 9] = w2[1] | s2[1];
+    final[10] = w2[2] | s2[2];
+    final[11] = w2[3] | s2[3];
+    final[12] = w3[0] | s3[0];
+    final[13] = w3[1] | s3[1];
+    final[14] = 0;
+    final[15] = pw_salt_len * 8;
+    final[16] = 0;
+    final[17] = 0;
+    final[18] = 0;
+    final[19] = 0;
+    final[20] = 0;
+    final[21] = 0;
+    final[22] = 0;
+    final[23] = 0;
+    final[24] = 0;
+    final[25] = 0;
+    final[26] = 0;
+    final[27] = 0;
+    final[28] = 0;
+    final[29] = 0;
+    final[30] = 0;
+    final[31] = 0;
+
+    u32 digest[5];
+
+    digest[0] = SHA1M_A;
+    digest[1] = SHA1M_B;
+    digest[2] = SHA1M_C;
+    digest[3] = SHA1M_D;
+    digest[4] = SHA1M_E;
+
+    sha1_transform (&final[0], &final[4], &final[8], &final[12], digest);
+
+    // prepare magic array range
+
+    u32 lengthMagicArray = 0x20;
+    u32 offsetMagicArray = 0;
+
+    lengthMagicArray += ((digest[0] >> 24) & 0xff) % 6;
+    lengthMagicArray += ((digest[0] >> 16) & 0xff) % 6;
+    lengthMagicArray += ((digest[0] >>  8) & 0xff) % 6;
+    lengthMagicArray += ((digest[0] >>  0) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >> 24) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >> 16) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >>  8) & 0xff) % 6;
+    lengthMagicArray += ((digest[1] >>  0) & 0xff) % 6;
+    lengthMagicArray += ((digest[2] >> 24) & 0xff) % 6;
+    lengthMagicArray += ((digest[2] >> 16) & 0xff) % 6;
+    offsetMagicArray += ((digest[2] >>  8) & 0xff) % 8;
+    offsetMagicArray += ((digest[2] >>  0) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >> 24) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >> 16) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >>  8) & 0xff) % 8;
+    offsetMagicArray += ((digest[3] >>  0) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >> 24) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >> 16) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >>  8) & 0xff) % 8;
+    offsetMagicArray += ((digest[4] >>  0) & 0xff) % 8;
+
+    // final
+
+    digest[0] = SHA1M_A;
+    digest[1] = SHA1M_B;
+    digest[2] = SHA1M_C;
+    digest[3] = SHA1M_D;
+    digest[4] = SHA1M_E;
+
+    final[ 0] = w0[0];
+    final[ 1] = w0[1];
+    final[ 2] = w0[2];
+    final[ 3] = w0[3];
+    final[ 4] = w1[0];
+    final[ 5] = w1[1];
+    final[ 6] = w1[2];
+    final[ 7] = w1[3];
+    final[ 8] = 0;
+    final[ 9] = 0;
+    final[10] = 0;
+    final[11] = 0;
+    final[12] = 0;
+    final[13] = 0;
+    final[14] = 0;
+    final[15] = 0;
+
+    u32 final_len = pw_len;
+
+    u32 i;
+
+    // append MagicArray
+
+    for (i = 0; i < lengthMagicArray - 4; i += 4)
+    {
+      const u32 tmp = GETSHIFTEDINT_CONST (theMagicArray, offsetMagicArray + i);
+
+      SETSHIFTEDINT (final, final_len + i, tmp);
+    }
+
+    const u32 mask = 0xffffffff << (((4 - (lengthMagicArray - i)) & 3) * 8);
+
+    const u32 tmp = GETSHIFTEDINT_CONST (theMagicArray, offsetMagicArray + i) & mask;
+
+    SETSHIFTEDINT (final, final_len + i, tmp);
+
+    final_len += lengthMagicArray;
+
+    // append Salt
+
+    for (i = 0; i < salt_len + 1; i += 4) // +1 for the 0x80
+    {
+      const u32 tmp = salt_buf[i / 4]; // attention, int[] not char[]
+
+      SETSHIFTEDINT (final, final_len + i, tmp);
+    }
+
+    final_len += salt_len;
+
+    // calculate
+
+    int left;
+    int off;
+
+    for (left = final_len, off = 0; left >= 56; left -= 64, off += 16)
+    {
+      sha1_transform (&final[off + 0], &final[off + 4], &final[off + 8], &final[off + 12], digest);
+    }
+
+    final[off + 15] = final_len * 8;
+
+    sha1_transform (&final[off + 0], &final[off + 4], &final[off + 8], &final[off + 12], digest);
+
+    COMPARE_S_SIMD (0, 0, digest[2] & 0xffff0000, digest[1]);
+  }
+}
+
+__kernel void m07801_m04 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+
+  if (gid >= gid_max) return;
+
+  /**
+   * modifier
+   */
+
+  //const u64 lid = get_local_id (0);
+
+  u32 w0[4];
+
+  w0[0] = pws[gid].i[ 0];
+  w0[1] = pws[gid].i[ 1];
+  w0[2] = pws[gid].i[ 2];
+  w0[3] = pws[gid].i[ 3];
+
+  u32 w1[4];
+
+  w1[0] = 0;
+  w1[1] = 0;
+  w1[2] = 0;
+  w1[3] = 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 pw_len = pws[gid].pw_len;
+
+  /**
+   * main
+   */
+
+  m07801m (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_scryptV0_buf, d_scryptV1_buf, d_scryptV2_buf, d_scryptV3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
+}
+
+__kernel void m07801_m08 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+
+  if (gid >= gid_max) return;
+
+  /**
+   * modifier
+   */
+
+  //const u64 lid = get_local_id (0);
+
+  u32 w0[4];
+
+  w0[0] = pws[gid].i[ 0];
+  w0[1] = pws[gid].i[ 1];
+  w0[2] = pws[gid].i[ 2];
+  w0[3] = pws[gid].i[ 3];
+
+  u32 w1[4];
+
+  w1[0] = pws[gid].i[ 4];
+  w1[1] = pws[gid].i[ 5];
+  w1[2] = pws[gid].i[ 6];
+  w1[3] = pws[gid].i[ 7];
+
+  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 pw_len = pws[gid].pw_len;
+
+  /**
+   * main
+   */
+
+  m07801m (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_scryptV0_buf, d_scryptV1_buf, d_scryptV2_buf, d_scryptV3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
+}
+
+__kernel void m07801_m16 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+}
+
+__kernel void m07801_s04 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+
+  if (gid >= gid_max) return;
+
+  /**
+   * modifier
+   */
+
+  //const u64 lid = get_local_id (0);
+
+  u32 w0[4];
+
+  w0[0] = pws[gid].i[ 0];
+  w0[1] = pws[gid].i[ 1];
+  w0[2] = pws[gid].i[ 2];
+  w0[3] = pws[gid].i[ 3];
+
+  u32 w1[4];
+
+  w1[0] = 0;
+  w1[1] = 0;
+  w1[2] = 0;
+  w1[3] = 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 pw_len = pws[gid].pw_len;
+
+  /**
+   * main
+   */
+
+  m07801s (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_scryptV0_buf, d_scryptV1_buf, d_scryptV2_buf, d_scryptV3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
+}
+
+__kernel void m07801_s08 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+
+  if (gid >= gid_max) return;
+
+  /**
+   * modifier
+   */
+
+  //const u64 lid = get_local_id (0);
+
+  u32 w0[4];
+
+  w0[0] = pws[gid].i[ 0];
+  w0[1] = pws[gid].i[ 1];
+  w0[2] = pws[gid].i[ 2];
+  w0[3] = pws[gid].i[ 3];
+
+  u32 w1[4];
+
+  w1[0] = pws[gid].i[ 4];
+  w1[1] = pws[gid].i[ 5];
+  w1[2] = pws[gid].i[ 6];
+  w1[3] = pws[gid].i[ 7];
+
+  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 pw_len = pws[gid].pw_len;
+
+  /**
+   * main
+   */
+
+  m07801s (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_scryptV0_buf, d_scryptV1_buf, d_scryptV2_buf, d_scryptV3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
+}
+
+__kernel void m07801_s16 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const 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 u64 gid_max)
+{
+}
diff --git a/include/interface.h b/include/interface.h
index 29c582d47..a00009b6e 100644
--- a/include/interface.h
+++ b/include/interface.h
@@ -1587,7 +1587,9 @@ typedef enum kern_type
   KERN_TYPE_SHA256CRYPT             = 7400,
   KERN_TYPE_KRB5PA                  = 7500,
   KERN_TYPE_SAPB                    = 7700,
+  KERN_TYPE_SAPB_MANGLED            = 7701,
   KERN_TYPE_SAPG                    = 7800,
+  KERN_TYPE_SAPG_MANGLED            = 7801,
   KERN_TYPE_DRUPAL7                 = 7900,
   KERN_TYPE_SYBASEASE               = 8000,
   KERN_TYPE_NETSCALER               = 8100,
diff --git a/src/interface.c b/src/interface.c
index f8ebc578e..b6a0a2722 100644
--- a/src/interface.c
+++ b/src/interface.c
@@ -173,7 +173,9 @@ static const char *ST_HASH_07300 = "34373437353333363838313532323234333833333032
 static const char *ST_HASH_07400 = "$5$7777657035274252$XftMj84MW.New1/ViLY5V4CM4Y7EBvfETaZsCW9vcJ8";
 static const char *ST_HASH_07500 = "$krb5pa$23$user$realm$salt$5cbb0c882a2b26956e81644edbdb746326f4f5f0e947144fb3095dffe4b4b03e854fc1d631323632303636373330383333353630";
 static const char *ST_HASH_07700 = "027642760180$77EC38630C08DF8D";
+static const char *ST_HASH_07701 = "027642760180$77EC386300000000";
 static const char *ST_HASH_07800 = "604020408266$32837BA7B97672BA4E5AC74767A4E6E1AE802651";
+static const char *ST_HASH_07801 = "604020408266$32837BA7B97672BA4E5A00000000000000000000";
 static const char *ST_HASH_07900 = "$S$C20340258nzjDWpoQthrdNTR02f0pmev0K/5/Nx80WSkOQcPEQRh";
 static const char *ST_HASH_08000 = "0xc0071808773188715731b69bd4e310b4129913aaf657356c5bdf3c46f249ed42477b5c74af6eaac4d15a";
 static const char *ST_HASH_08100 = "1130725275da09ca13254957f2314a639818d44c37ef6d558";
@@ -423,7 +425,9 @@ static const char *HT_07300 = "IPMI2 RAKP HMAC-SHA1";
 static const char *HT_07400 = "sha256crypt $5$, SHA256 (Unix)";
 static const char *HT_07500 = "Kerberos 5 AS-REQ Pre-Auth etype 23";
 static const char *HT_07700 = "SAP CODVN B (BCODE)";
+static const char *HT_07701 = "SAP CODVN B (BCODE) mangled from RFC_READ_TABLE";
 static const char *HT_07800 = "SAP CODVN F/G (PASSCODE)";
+static const char *HT_07801 = "SAP CODVN F/G (PASSCODE) mangled from RFC_READ_TABLE";
 static const char *HT_07900 = "Drupal7";
 static const char *HT_08000 = "Sybase ASE";
 static const char *HT_08100 = "Citrix NetScaler";
@@ -16795,7 +16799,9 @@ const char *strhashtype (const u32 hash_mode)
     case  7400: return HT_07400;
     case  7500: return HT_07500;
     case  7700: return HT_07700;
+    case  7701: return HT_07701;
     case  7800: return HT_07800;
+    case  7801: return HT_07801;
     case  7900: return HT_07900;
     case  8000: return HT_08000;
     case  8100: return HT_08100;
@@ -18374,14 +18380,14 @@ int ascii_digest (hashcat_ctx_t *hashcat_ctx, char *out_buf, const size_t out_le
       (char *) krb5pa->salt,
       data);
   }
-  else if (hash_mode == 7700)
+  else if ((hash_mode == 7700) || (hash_mode == 7701))
   {
     snprintf (out_buf, out_len - 1, "%s$%08X%08X",
       (char *) salt.salt_buf,
       digest_buf[0],
       digest_buf[1]);
   }
-  else if (hash_mode == 7800)
+  else if ((hash_mode == 7800) || (hash_mode == 7801))
   {
     snprintf (out_buf, out_len - 1, "%s$%08X%08X%08X%08X%08X",
       (char *) salt.salt_buf,
@@ -23572,6 +23578,26 @@ int hashconfig_init (hashcat_ctx_t *hashcat_ctx)
                  hashconfig->st_pass        = ST_PASS_HASHCAT_PLAIN;
                  break;
 
+    case  7701:  hashconfig->hash_type      = HASH_TYPE_SAPB;
+                 hashconfig->salt_type      = SALT_TYPE_EMBEDDED;
+                 hashconfig->attack_exec    = ATTACK_EXEC_INSIDE_KERNEL;
+                 hashconfig->opts_type      = OPTS_TYPE_PT_GENERATE_LE
+                                            | OPTS_TYPE_PT_UPPER
+                                            | OPTS_TYPE_ST_UPPER;
+                 hashconfig->kern_type      = KERN_TYPE_SAPB_MANGLED;
+                 hashconfig->dgst_size      = DGST_SIZE_4_4; // originally DGST_SIZE_4_2
+                 hashconfig->parse_func     = sapb_parse_hash;
+                 hashconfig->opti_type      = OPTI_TYPE_ZERO_BYTE
+                                            | OPTI_TYPE_PRECOMPUTE_INIT
+                                            | OPTI_TYPE_NOT_ITERATED;
+                 hashconfig->dgst_pos0      = 0;
+                 hashconfig->dgst_pos1      = 1;
+                 hashconfig->dgst_pos2      = 2;
+                 hashconfig->dgst_pos3      = 3;
+                 hashconfig->st_hash        = ST_HASH_07701;
+                 hashconfig->st_pass        = ST_PASS_HASHCAT_PLAIN;
+                 break;
+
     case  7800:  hashconfig->hash_type      = HASH_TYPE_SAPG;
                  hashconfig->salt_type      = SALT_TYPE_EMBEDDED;
                  hashconfig->attack_exec    = ATTACK_EXEC_INSIDE_KERNEL;
@@ -23592,6 +23618,26 @@ int hashconfig_init (hashcat_ctx_t *hashcat_ctx)
                  hashconfig->st_pass        = ST_PASS_HASHCAT_PLAIN;
                  break;
 
+    case  7801:  hashconfig->hash_type      = HASH_TYPE_SAPG;
+                 hashconfig->salt_type      = SALT_TYPE_EMBEDDED;
+                 hashconfig->attack_exec    = ATTACK_EXEC_INSIDE_KERNEL;
+                 hashconfig->opts_type      = OPTS_TYPE_PT_GENERATE_BE
+                                            | OPTS_TYPE_ST_ADD80
+                                            | OPTS_TYPE_ST_UPPER;
+                 hashconfig->kern_type      = KERN_TYPE_SAPG_MANGLED;
+                 hashconfig->dgst_size      = DGST_SIZE_4_5;
+                 hashconfig->parse_func     = sapg_parse_hash;
+                 hashconfig->opti_type      = OPTI_TYPE_ZERO_BYTE
+                                            | OPTI_TYPE_PRECOMPUTE_INIT
+                                            | OPTI_TYPE_NOT_ITERATED;
+                 hashconfig->dgst_pos0      = 3;
+                 hashconfig->dgst_pos1      = 4;
+                 hashconfig->dgst_pos2      = 2;
+                 hashconfig->dgst_pos3      = 1;
+                 hashconfig->st_hash        = ST_HASH_07801;
+                 hashconfig->st_pass        = ST_PASS_HASHCAT_PLAIN;
+                 break;
+
     case  7900:  hashconfig->hash_type      = HASH_TYPE_SHA512;
                  hashconfig->salt_type      = SALT_TYPE_EMBEDDED;
                  hashconfig->attack_exec    = ATTACK_EXEC_OUTSIDE_KERNEL;
diff --git a/src/usage.c b/src/usage.c
index 34f938e0f..b0b61cadc 100644
--- a/src/usage.c
+++ b/src/usage.c
@@ -285,7 +285,9 @@ static const char *const USAGE_BIG[] =
   "   9900 | Radmin2                                          | Operating Systems",
   "    125 | ArubaOS                                          | Operating Systems",
   "   7700 | SAP CODVN B (BCODE)                              | Enterprise Application Software (EAS)",
+  "   7701 | SAP CODVN B (BCODE) via RFC_READ_TABLE           | Enterprise Application Software (EAS)",
   "   7800 | SAP CODVN F/G (PASSCODE)                         | Enterprise Application Software (EAS)",
+  "   7801 | SAP CODVN F/G (PASSCODE) via RFC_READ_TABLE      | Enterprise Application Software (EAS)",
   "  10300 | SAP CODVN H (PWDSALTEDHASH) iSSHA-1              | Enterprise Application Software (EAS)",
   "   8600 | Lotus Notes/Domino 5                             | Enterprise Application Software (EAS)",
   "   8700 | Lotus Notes/Domino 6                             | Enterprise Application Software (EAS)",