diff --git a/OpenCL/m05000_a0-optimized.cl b/OpenCL/m05000_a0-optimized.cl
new file mode 100644
index 000000000..d3615bd2c
--- /dev/null
+++ b/OpenCL/m05000_a0-optimized.cl
@@ -0,0 +1,926 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */ 
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_rp_optimized.h"
+#include "inc_rp_optimized.cl"
+#include "inc_simd.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if   VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m05000_m04 (KERN_ATTR_RULES ())
+{
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+  const u64 lsz = get_local_size (0);
+
+  /**
+   * bin2asc table
+   */
+
+  LOCAL_VK u32 l_bin2asc[256];
+
+  for (u32 i = lid; i < 256; i += lsz)
+  {
+    const u32 i0 = (i >> 0) & 15;
+    const u32 i1 = (i >> 4) & 15;
+
+    l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+                 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+  }
+
+  SYNC_THREADS ();
+
+  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 & 63;
+
+  /**
+   * salt
+   */
+
+  u32 salt_buf0[4];
+  u32 salt_buf1[4];
+  u32 salt_buf2[4];
+  u32 salt_buf3[4];
+
+  salt_buf0[0] = salt_bufs[SALT_POS].salt_buf[ 0];
+  salt_buf0[1] = salt_bufs[SALT_POS].salt_buf[ 1];
+  salt_buf0[2] = salt_bufs[SALT_POS].salt_buf[ 2];
+  salt_buf0[3] = salt_bufs[SALT_POS].salt_buf[ 3];
+  salt_buf1[0] = salt_bufs[SALT_POS].salt_buf[ 4];
+  salt_buf1[1] = salt_bufs[SALT_POS].salt_buf[ 5];
+  salt_buf1[2] = salt_bufs[SALT_POS].salt_buf[ 6];
+  salt_buf1[3] = salt_bufs[SALT_POS].salt_buf[ 7];
+  salt_buf2[0] = salt_bufs[SALT_POS].salt_buf[ 8];
+  salt_buf2[1] = salt_bufs[SALT_POS].salt_buf[ 9];
+  salt_buf2[2] = salt_bufs[SALT_POS].salt_buf[10];
+  salt_buf2[3] = salt_bufs[SALT_POS].salt_buf[11];
+  salt_buf3[0] = salt_bufs[SALT_POS].salt_buf[12];
+  salt_buf3[1] = salt_bufs[SALT_POS].salt_buf[13];
+  salt_buf3[2] = salt_bufs[SALT_POS].salt_buf[14];
+  salt_buf3[3] = salt_bufs[SALT_POS].salt_buf[15];
+
+  const u32 salt_len = salt_bufs[SALT_POS].salt_len;
+
+  /**
+   * 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_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+    /**
+     * prepend salt
+     */
+
+    const u32x out_salt_len = out_len + salt_len;
+
+    switch_buffer_by_offset_le_VV (w0, w1, w2, w3, salt_len);
+
+    w0[0] |= salt_buf0[0];
+    w0[1] |= salt_buf0[1];
+    w0[2] |= salt_buf0[2];
+    w0[3] |= salt_buf0[3];
+    w1[0] |= salt_buf1[0];
+    w1[1] |= salt_buf1[1];
+    w1[2] |= salt_buf1[2];
+    w1[3] |= salt_buf1[3];
+    w2[0] |= salt_buf2[0];
+    w2[1] |= salt_buf2[1];
+    w2[2] |= salt_buf2[2];
+    w2[3] |= salt_buf2[3];
+    w3[0] |= salt_buf3[0];
+    w3[1] |= salt_buf3[1];
+    w3[2] |= salt_buf3[2];
+    w3[3] |= salt_buf3[3];
+
+    /**
+     * append salt
+     */
+
+    u32x s0[4];
+    u32x s1[4];
+    u32x s2[4];
+    u32x s3[4];
+
+    s0[0] = salt_buf0[0];
+    s0[1] = salt_buf0[1];
+    s0[2] = salt_buf0[2];
+    s0[3] = salt_buf0[3];
+    s1[0] = salt_buf1[0];
+    s1[1] = salt_buf1[1];
+    s1[2] = salt_buf1[2];
+    s1[3] = salt_buf1[3];
+    s2[0] = salt_buf2[0];
+    s2[1] = salt_buf2[1];
+    s2[2] = salt_buf2[2];
+    s2[3] = salt_buf2[3];
+    s3[0] = salt_buf3[0];
+    s3[1] = salt_buf3[1];
+    s3[2] = salt_buf3[2];
+    s3[3] = salt_buf3[3];
+
+    switch_buffer_by_offset_le_VV (s0, s1, s2, s3, out_salt_len);
+
+    w0[0] |= s0[0];
+    w0[1] |= s0[1];
+    w0[2] |= s0[2];
+    w0[3] |= s0[3];
+    w1[0] |= s1[0];
+    w1[1] |= s1[1];
+    w1[2] |= s1[2];
+    w1[3] |= s1[3];
+    w2[0] |= s2[0];
+    w2[1] |= s2[1];
+    w2[2] |= s2[2];
+    w2[3] |= s2[3];
+    w3[0] |= s3[0];
+    w3[1] |= s3[1];
+    w3[2] |= s3[2];
+    w3[3] |= s3[3];
+
+    const u32x salt_out_salt_len = salt_len + out_len + salt_len;
+
+    append_0x80_4x4_VV (w0, w1, w2, w3, salt_out_salt_len);
+
+    /**
+     * sha1
+     */
+
+    u32x w0_t = hc_swap32 (w0[0]);
+    u32x w1_t = hc_swap32 (w0[1]);
+    u32x w2_t = hc_swap32 (w0[2]);
+    u32x w3_t = hc_swap32 (w0[3]);
+    u32x w4_t = hc_swap32 (w1[0]);
+    u32x w5_t = hc_swap32 (w1[1]);
+    u32x w6_t = hc_swap32 (w1[2]);
+    u32x w7_t = hc_swap32 (w1[3]);
+    u32x w8_t = hc_swap32 (w2[0]);
+    u32x w9_t = hc_swap32 (w2[1]);
+    u32x wa_t = hc_swap32 (w2[2]);
+    u32x wb_t = hc_swap32 (w2[3]);
+    u32x wc_t = hc_swap32 (w3[0]);
+    u32x wd_t = hc_swap32 (w3[1]);
+    u32x we_t = 0;
+    u32x wf_t = salt_out_salt_len * 8;
+
+    u32x a = SHA1M_A;
+    u32x b = SHA1M_B;
+    u32x c = SHA1M_C;
+    u32x d = SHA1M_D;
+    u32x e = SHA1M_E;
+
+    #undef K
+    #define K SHA1C00
+
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+    #undef K
+    #define K SHA1C01
+
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+    #undef K
+    #define K SHA1C02
+
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+    #undef K
+    #define K SHA1C03
+
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+    a += SHA1M_A;
+    b += SHA1M_B;
+    c += SHA1M_C;
+    d += SHA1M_D;
+    e += SHA1M_E;
+
+    /**
+     * 2nd SHA1
+     */
+
+    w0_t = uint_to_hex_lower8_le ((a >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+    w1_t = uint_to_hex_lower8_le ((a >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((a >>  8) & 255) << 16;
+    w2_t = uint_to_hex_lower8_le ((b >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+    w3_t = uint_to_hex_lower8_le ((b >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((b >>  8) & 255) << 16;
+    w4_t = uint_to_hex_lower8_le ((c >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+    w5_t = uint_to_hex_lower8_le ((c >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((c >>  8) & 255) << 16;
+    w6_t = uint_to_hex_lower8_le ((d >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+    w7_t = uint_to_hex_lower8_le ((d >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((d >>  8) & 255) << 16;
+    w8_t = uint_to_hex_lower8_le ((e >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+    w9_t = uint_to_hex_lower8_le ((e >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((e >>  8) & 255) << 16;
+
+    wa_t = 0x80000000;
+    wb_t = 0;
+    wc_t = 0;
+    wd_t = 0;
+    we_t = 0;
+    wf_t = 40 * 8;
+
+    a = SHA1M_A;
+    b = SHA1M_B;
+    c = SHA1M_C;
+    d = SHA1M_D;
+    e = SHA1M_E;
+
+    #undef K
+    #define K SHA1C00
+
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+    #undef K
+    #define K SHA1C01
+
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+    #undef K
+    #define K SHA1C02
+
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+    #undef K
+    #define K SHA1C03
+
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+    COMPARE_M_SIMD (d, e, c, b);
+  }
+}
+
+KERNEL_FQ void m05000_m08 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m05000_m16 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m05000_s04 (KERN_ATTR_RULES ())
+{
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+  const u64 lsz = get_local_size (0);
+
+  /**
+   * bin2asc table
+   */
+
+  LOCAL_VK u32 l_bin2asc[256];
+
+  for (u32 i = lid; i < 256; i += lsz)
+  {
+    const u32 i0 = (i >> 0) & 15;
+    const u32 i1 = (i >> 4) & 15;
+
+    l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+                 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+  }
+
+  SYNC_THREADS ();
+
+  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 & 63;
+
+  /**
+   * salt
+   */
+
+  u32 salt_buf0[4];
+  u32 salt_buf1[4];
+  u32 salt_buf2[4];
+  u32 salt_buf3[4];
+
+  salt_buf0[0] = salt_bufs[SALT_POS].salt_buf[ 0];
+  salt_buf0[1] = salt_bufs[SALT_POS].salt_buf[ 1];
+  salt_buf0[2] = salt_bufs[SALT_POS].salt_buf[ 2];
+  salt_buf0[3] = salt_bufs[SALT_POS].salt_buf[ 3];
+  salt_buf1[0] = salt_bufs[SALT_POS].salt_buf[ 4];
+  salt_buf1[1] = salt_bufs[SALT_POS].salt_buf[ 5];
+  salt_buf1[2] = salt_bufs[SALT_POS].salt_buf[ 6];
+  salt_buf1[3] = salt_bufs[SALT_POS].salt_buf[ 7];
+  salt_buf2[0] = salt_bufs[SALT_POS].salt_buf[ 8];
+  salt_buf2[1] = salt_bufs[SALT_POS].salt_buf[ 9];
+  salt_buf2[2] = salt_bufs[SALT_POS].salt_buf[10];
+  salt_buf2[3] = salt_bufs[SALT_POS].salt_buf[11];
+  salt_buf3[0] = salt_bufs[SALT_POS].salt_buf[12];
+  salt_buf3[1] = salt_bufs[SALT_POS].salt_buf[13];
+  salt_buf3[2] = salt_bufs[SALT_POS].salt_buf[14];
+  salt_buf3[3] = salt_bufs[SALT_POS].salt_buf[15];
+
+  const u32 salt_len = salt_bufs[SALT_POS].salt_len;
+
+  /**
+   * 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]
+  };
+
+  /**
+   * reverse
+   */
+
+  const u32 e_rev = hc_rotl32_S (search[1], 2u);
+
+  /**
+   * 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_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+    /**
+     * prepend salt
+     */
+
+    const u32x out_salt_len = out_len + salt_len;
+
+    switch_buffer_by_offset_le_VV (w0, w1, w2, w3, salt_len);
+
+    w0[0] |= salt_buf0[0];
+    w0[1] |= salt_buf0[1];
+    w0[2] |= salt_buf0[2];
+    w0[3] |= salt_buf0[3];
+    w1[0] |= salt_buf1[0];
+    w1[1] |= salt_buf1[1];
+    w1[2] |= salt_buf1[2];
+    w1[3] |= salt_buf1[3];
+    w2[0] |= salt_buf2[0];
+    w2[1] |= salt_buf2[1];
+    w2[2] |= salt_buf2[2];
+    w2[3] |= salt_buf2[3];
+    w3[0] |= salt_buf3[0];
+    w3[1] |= salt_buf3[1];
+    w3[2] |= salt_buf3[2];
+    w3[3] |= salt_buf3[3];
+
+    /**
+     * append salt
+     */
+
+    u32x s0[4];
+    u32x s1[4];
+    u32x s2[4];
+    u32x s3[4];
+
+    s0[0] = salt_buf0[0];
+    s0[1] = salt_buf0[1];
+    s0[2] = salt_buf0[2];
+    s0[3] = salt_buf0[3];
+    s1[0] = salt_buf1[0];
+    s1[1] = salt_buf1[1];
+    s1[2] = salt_buf1[2];
+    s1[3] = salt_buf1[3];
+    s2[0] = salt_buf2[0];
+    s2[1] = salt_buf2[1];
+    s2[2] = salt_buf2[2];
+    s2[3] = salt_buf2[3];
+    s3[0] = salt_buf3[0];
+    s3[1] = salt_buf3[1];
+    s3[2] = salt_buf3[2];
+    s3[3] = salt_buf3[3];
+
+    switch_buffer_by_offset_le_VV (s0, s1, s2, s3, out_salt_len);
+
+    w0[0] |= s0[0];
+    w0[1] |= s0[1];
+    w0[2] |= s0[2];
+    w0[3] |= s0[3];
+    w1[0] |= s1[0];
+    w1[1] |= s1[1];
+    w1[2] |= s1[2];
+    w1[3] |= s1[3];
+    w2[0] |= s2[0];
+    w2[1] |= s2[1];
+    w2[2] |= s2[2];
+    w2[3] |= s2[3];
+    w3[0] |= s3[0];
+    w3[1] |= s3[1];
+    w3[2] |= s3[2];
+    w3[3] |= s3[3];
+
+    const u32x salt_out_salt_len = salt_len + out_len + salt_len;
+
+    append_0x80_4x4_VV (w0, w1, w2, w3, salt_out_salt_len);
+
+    /**
+     * sha1
+     */
+
+    u32x w0_t = hc_swap32 (w0[0]);
+    u32x w1_t = hc_swap32 (w0[1]);
+    u32x w2_t = hc_swap32 (w0[2]);
+    u32x w3_t = hc_swap32 (w0[3]);
+    u32x w4_t = hc_swap32 (w1[0]);
+    u32x w5_t = hc_swap32 (w1[1]);
+    u32x w6_t = hc_swap32 (w1[2]);
+    u32x w7_t = hc_swap32 (w1[3]);
+    u32x w8_t = hc_swap32 (w2[0]);
+    u32x w9_t = hc_swap32 (w2[1]);
+    u32x wa_t = hc_swap32 (w2[2]);
+    u32x wb_t = hc_swap32 (w2[3]);
+    u32x wc_t = hc_swap32 (w3[0]);
+    u32x wd_t = hc_swap32 (w3[1]);
+    u32x we_t = 0;
+    u32x wf_t = salt_out_salt_len * 8;
+
+    u32x a = SHA1M_A;
+    u32x b = SHA1M_B;
+    u32x c = SHA1M_C;
+    u32x d = SHA1M_D;
+    u32x e = SHA1M_E;
+
+    #undef K
+    #define K SHA1C00
+
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+    #undef K
+    #define K SHA1C01
+
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+    #undef K
+    #define K SHA1C02
+
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+    #undef K
+    #define K SHA1C03
+
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+    a += SHA1M_A;
+    b += SHA1M_B;
+    c += SHA1M_C;
+    d += SHA1M_D;
+    e += SHA1M_E;
+
+    /**
+     * 2nd SHA1
+     */
+
+    w0_t = uint_to_hex_lower8_le ((a >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+    w1_t = uint_to_hex_lower8_le ((a >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((a >>  8) & 255) << 16;
+    w2_t = uint_to_hex_lower8_le ((b >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+    w3_t = uint_to_hex_lower8_le ((b >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((b >>  8) & 255) << 16;
+    w4_t = uint_to_hex_lower8_le ((c >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+    w5_t = uint_to_hex_lower8_le ((c >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((c >>  8) & 255) << 16;
+    w6_t = uint_to_hex_lower8_le ((d >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+    w7_t = uint_to_hex_lower8_le ((d >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((d >>  8) & 255) << 16;
+    w8_t = uint_to_hex_lower8_le ((e >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+    w9_t = uint_to_hex_lower8_le ((e >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((e >>  8) & 255) << 16;
+
+    wa_t = 0x80000000;
+    wb_t = 0;
+    wc_t = 0;
+    wd_t = 0;
+    we_t = 0;
+    wf_t = 40 * 8;
+
+    a = SHA1M_A;
+    b = SHA1M_B;
+    c = SHA1M_C;
+    d = SHA1M_D;
+    e = SHA1M_E;
+
+    #undef K
+    #define K SHA1C00
+
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+    #undef K
+    #define K SHA1C01
+
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+    #undef K
+    #define K SHA1C02
+
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+    #undef K
+    #define K SHA1C03
+
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+
+    if (MATCHES_NONE_VS (e, e_rev)) continue;
+
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+    COMPARE_S_SIMD (d, e, c, b);
+  }
+}
+
+KERNEL_FQ void m05000_s08 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m05000_s16 (KERN_ATTR_RULES ())
+{
+}
diff --git a/OpenCL/m05000_a0-pure.cl b/OpenCL/m05000_a0-pure.cl
new file mode 100644
index 000000000..dfa97da46
--- /dev/null
+++ b/OpenCL/m05000_a0-pure.cl
@@ -0,0 +1,265 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_rp.h"
+#include "inc_rp.cl"
+#include "inc_scalar.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if   VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m05000_mxx (KERN_ATTR_RULES ())
+{
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+  const u64 gid = get_global_id (0);
+  const u64 lsz = get_local_size (0);
+
+  /**
+   * bin2asc table
+   */
+
+  LOCAL_VK u32 l_bin2asc[256];
+
+  for (u32 i = lid; i < 256; i += lsz)
+  {
+    const u32 i0 = (i >> 0) & 15;
+    const u32 i1 = (i >> 4) & 15;
+
+    l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+                 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+  }
+
+  SYNC_THREADS ();
+
+  if (gid >= gid_max) return;
+
+  /**
+   * base
+   */
+
+  COPY_PW (pws[gid]);
+
+  const u32 salt_len = salt_bufs[SALT_POS].salt_len;
+
+  u32 s[64] = { 0 };
+
+  for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+  {
+    s[idx] = hc_swap32_S (salt_bufs[SALT_POS].salt_buf[idx]);
+  }
+
+  sha1_ctx_t ctx0;
+
+  sha1_init (&ctx0);
+
+  sha1_update (&ctx0, s, salt_len);
+
+  /**
+   * loop
+   */
+
+  for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+  {
+    pw_t tmp = PASTE_PW;
+
+    tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
+
+    sha1_ctx_t ctx = ctx0;
+
+    sha1_update_swap (&ctx, tmp.i, tmp.pw_len);
+
+    sha1_update (&ctx, s, salt_len);
+
+    sha1_final (&ctx);
+
+    const u32 a = ctx.h[0];
+    const u32 b = ctx.h[1];
+    const u32 c = ctx.h[2];
+    const u32 d = ctx.h[3];
+    const u32 e = ctx.h[4];
+
+    sha1_ctx_t ctx1;
+
+    sha1_init (&ctx1);
+
+    ctx1.w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+    ctx1.w0[1] = uint_to_hex_lower8_le ((a >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((a >>  8) & 255) << 16;
+    ctx1.w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+    ctx1.w0[3] = uint_to_hex_lower8_le ((b >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((b >>  8) & 255) << 16;
+    ctx1.w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+    ctx1.w1[1] = uint_to_hex_lower8_le ((c >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((c >>  8) & 255) << 16;
+    ctx1.w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+    ctx1.w1[3] = uint_to_hex_lower8_le ((d >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((d >>  8) & 255) << 16;
+    ctx1.w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+    ctx1.w2[1] = uint_to_hex_lower8_le ((e >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((e >>  8) & 255) << 16;
+
+    ctx1.len = 40;
+
+    sha1_final (&ctx1);
+
+    const u32 r0 = ctx1.h[DGST_R0];
+    const u32 r1 = ctx1.h[DGST_R1];
+    const u32 r2 = ctx1.h[DGST_R2];
+    const u32 r3 = ctx1.h[DGST_R3];
+
+    COMPARE_M_SCALAR (r0, r1, r2, r3);
+  }
+}
+
+KERNEL_FQ void m05000_sxx (KERN_ATTR_RULES ())
+{
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+  const u64 gid = get_global_id (0);
+  const u64 lsz = get_local_size (0);
+
+  /**
+   * bin2asc table
+   */
+
+  LOCAL_VK u32 l_bin2asc[256];
+
+  for (u32 i = lid; i < 256; i += lsz)
+  {
+    const u32 i0 = (i >> 0) & 15;
+    const u32 i1 = (i >> 4) & 15;
+
+    l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+                 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+  }
+
+  SYNC_THREADS ();
+
+  if (gid >= gid_max) return;
+
+  /**
+   * 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]
+  };
+
+  /**
+   * base
+   */
+
+  COPY_PW (pws[gid]);
+
+  const u32 salt_len = salt_bufs[SALT_POS].salt_len;
+
+  u32 s[64] = { 0 };
+
+  for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+  {
+    s[idx] = hc_swap32_S (salt_bufs[SALT_POS].salt_buf[idx]);
+  }
+
+  sha1_ctx_t ctx0;
+
+  sha1_init (&ctx0);
+
+  sha1_update (&ctx0, s, salt_len);
+
+  /**
+   * loop
+   */
+
+  for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+  {
+    pw_t tmp = PASTE_PW;
+
+    tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
+
+    sha1_ctx_t ctx = ctx0;
+
+    sha1_update_swap (&ctx, tmp.i, tmp.pw_len);
+
+    sha1_update (&ctx, s, salt_len);
+
+    sha1_final (&ctx);
+
+    const u32 a = ctx.h[0];
+    const u32 b = ctx.h[1];
+    const u32 c = ctx.h[2];
+    const u32 d = ctx.h[3];
+    const u32 e = ctx.h[4];
+
+    sha1_ctx_t ctx1;
+
+    sha1_init (&ctx1);
+
+    ctx1.w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+    ctx1.w0[1] = uint_to_hex_lower8_le ((a >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((a >>  8) & 255) << 16;
+    ctx1.w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+    ctx1.w0[3] = uint_to_hex_lower8_le ((b >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((b >>  8) & 255) << 16;
+    ctx1.w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+    ctx1.w1[1] = uint_to_hex_lower8_le ((c >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((c >>  8) & 255) << 16;
+    ctx1.w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+    ctx1.w1[3] = uint_to_hex_lower8_le ((d >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((d >>  8) & 255) << 16;
+    ctx1.w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+    ctx1.w2[1] = uint_to_hex_lower8_le ((e >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((e >>  8) & 255) << 16;
+
+    ctx1.len = 40;
+
+    sha1_final (&ctx1);
+
+    const u32 r0 = ctx1.h[DGST_R0];
+    const u32 r1 = ctx1.h[DGST_R1];
+    const u32 r2 = ctx1.h[DGST_R2];
+    const u32 r3 = ctx1.h[DGST_R3];
+
+    COMPARE_S_SCALAR (r0, r1, r2, r3);
+  }
+}
diff --git a/OpenCL/m05000_a1-optimized.cl b/OpenCL/m05000_a1-optimized.cl
new file mode 100644
index 000000000..ce43c1d9c
--- /dev/null
+++ b/OpenCL/m05000_a1-optimized.cl
@@ -0,0 +1,1044 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if   VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m05000_m04 (KERN_ATTR_BASIC ())
+{
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+  const u64 lsz = get_local_size (0);
+
+  /**
+   * bin2asc table
+   */
+
+  LOCAL_VK u32 l_bin2asc[256];
+
+  for (u32 i = lid; i < 256; i += lsz)
+  {
+    const u32 i0 = (i >> 0) & 15;
+    const u32 i1 = (i >> 4) & 15;
+
+    l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+                 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+  }
+
+  SYNC_THREADS ();
+
+  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 & 63;
+
+  /**
+   * salt
+   */
+
+  u32 salt_buf0[4];
+  u32 salt_buf1[4];
+  u32 salt_buf2[4];
+  u32 salt_buf3[4];
+
+  salt_buf0[0] = salt_bufs[SALT_POS].salt_buf[ 0];
+  salt_buf0[1] = salt_bufs[SALT_POS].salt_buf[ 1];
+  salt_buf0[2] = salt_bufs[SALT_POS].salt_buf[ 2];
+  salt_buf0[3] = salt_bufs[SALT_POS].salt_buf[ 3];
+  salt_buf1[0] = salt_bufs[SALT_POS].salt_buf[ 4];
+  salt_buf1[1] = salt_bufs[SALT_POS].salt_buf[ 5];
+  salt_buf1[2] = salt_bufs[SALT_POS].salt_buf[ 6];
+  salt_buf1[3] = salt_bufs[SALT_POS].salt_buf[ 7];
+  salt_buf2[0] = salt_bufs[SALT_POS].salt_buf[ 8];
+  salt_buf2[1] = salt_bufs[SALT_POS].salt_buf[ 9];
+  salt_buf2[2] = salt_bufs[SALT_POS].salt_buf[10];
+  salt_buf2[3] = salt_bufs[SALT_POS].salt_buf[11];
+  salt_buf3[0] = salt_bufs[SALT_POS].salt_buf[12];
+  salt_buf3[1] = salt_bufs[SALT_POS].salt_buf[13];
+  salt_buf3[2] = salt_bufs[SALT_POS].salt_buf[14];
+  salt_buf3[3] = salt_bufs[SALT_POS].salt_buf[15];
+
+  const u32 salt_len = salt_bufs[SALT_POS].salt_len;
+
+  /**
+   * 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) & 63;
+
+    const u32x pw_len = (pw_l_len + pw_r_len) & 63;
+
+    /**
+     * 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];
+
+    /**
+     * prepend salt
+     */
+
+    switch_buffer_by_offset_le (w0, w1, w2, w3, salt_len);
+
+    const u32x pw_salt_len = pw_len + salt_len;
+
+    w0[0] |= salt_buf0[0];
+    w0[1] |= salt_buf0[1];
+    w0[2] |= salt_buf0[2];
+    w0[3] |= salt_buf0[3];
+    w1[0] |= salt_buf1[0];
+    w1[1] |= salt_buf1[1];
+    w1[2] |= salt_buf1[2];
+    w1[3] |= salt_buf1[3];
+    w2[0] |= salt_buf2[0];
+    w2[1] |= salt_buf2[1];
+    w2[2] |= salt_buf2[2];
+    w2[3] |= salt_buf2[3];
+    w3[0] |= salt_buf3[0];
+    w3[1] |= salt_buf3[1];
+    w3[2] |= salt_buf3[2];
+    w3[3] |= salt_buf3[3];
+
+    /**
+     * append salt
+     */
+
+    u32x s0[4];
+    u32x s1[4];
+    u32x s2[4];
+    u32x s3[4];
+
+    s0[0] = salt_buf0[0];
+    s0[1] = salt_buf0[1];
+    s0[2] = salt_buf0[2];
+    s0[3] = salt_buf0[3];
+    s1[0] = salt_buf1[0];
+    s1[1] = salt_buf1[1];
+    s1[2] = salt_buf1[2];
+    s1[3] = salt_buf1[3];
+    s2[0] = salt_buf2[0];
+    s2[1] = salt_buf2[1];
+    s2[2] = salt_buf2[2];
+    s2[3] = salt_buf2[3];
+    s3[0] = salt_buf3[0];
+    s3[1] = salt_buf3[1];
+    s3[2] = salt_buf3[2];
+    s3[3] = salt_buf3[3];
+
+    switch_buffer_by_offset_le_VV (s0, s1, s2, s3, pw_salt_len);
+
+    w0[0] |= s0[0];
+    w0[1] |= s0[1];
+    w0[2] |= s0[2];
+    w0[3] |= s0[3];
+    w1[0] |= s1[0];
+    w1[1] |= s1[1];
+    w1[2] |= s1[2];
+    w1[3] |= s1[3];
+    w2[0] |= s2[0];
+    w2[1] |= s2[1];
+    w2[2] |= s2[2];
+    w2[3] |= s2[3];
+    w3[0] |= s3[0];
+    w3[1] |= s3[1];
+    w3[2] |= s3[2];
+    w3[3] |= s3[3];
+
+    const u32x salt_pw_salt_len = salt_len + pw_len + salt_len;
+
+    append_0x80_4x4_VV (w0, w1, w2, w3, salt_pw_salt_len);
+
+    /**
+     * sha1
+     */
+
+    u32x w0_t = hc_swap32 (w0[0]);
+    u32x w1_t = hc_swap32 (w0[1]);
+    u32x w2_t = hc_swap32 (w0[2]);
+    u32x w3_t = hc_swap32 (w0[3]);
+    u32x w4_t = hc_swap32 (w1[0]);
+    u32x w5_t = hc_swap32 (w1[1]);
+    u32x w6_t = hc_swap32 (w1[2]);
+    u32x w7_t = hc_swap32 (w1[3]);
+    u32x w8_t = hc_swap32 (w2[0]);
+    u32x w9_t = hc_swap32 (w2[1]);
+    u32x wa_t = hc_swap32 (w2[2]);
+    u32x wb_t = hc_swap32 (w2[3]);
+    u32x wc_t = hc_swap32 (w3[0]);
+    u32x wd_t = hc_swap32 (w3[1]);
+    u32x we_t = 0;
+    u32x wf_t = salt_pw_salt_len * 8;
+
+    u32x a = SHA1M_A;
+    u32x b = SHA1M_B;
+    u32x c = SHA1M_C;
+    u32x d = SHA1M_D;
+    u32x e = SHA1M_E;
+
+    #undef K
+    #define K SHA1C00
+
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+    #undef K
+    #define K SHA1C01
+
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+    #undef K
+    #define K SHA1C02
+
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+    #undef K
+    #define K SHA1C03
+
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+    a += SHA1M_A;
+    b += SHA1M_B;
+    c += SHA1M_C;
+    d += SHA1M_D;
+    e += SHA1M_E;
+
+    /**
+     * 2nd SHA1
+     */
+
+    w0_t = uint_to_hex_lower8_le ((a >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+    w1_t = uint_to_hex_lower8_le ((a >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((a >>  8) & 255) << 16;
+    w2_t = uint_to_hex_lower8_le ((b >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+    w3_t = uint_to_hex_lower8_le ((b >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((b >>  8) & 255) << 16;
+    w4_t = uint_to_hex_lower8_le ((c >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+    w5_t = uint_to_hex_lower8_le ((c >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((c >>  8) & 255) << 16;
+    w6_t = uint_to_hex_lower8_le ((d >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+    w7_t = uint_to_hex_lower8_le ((d >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((d >>  8) & 255) << 16;
+    w8_t = uint_to_hex_lower8_le ((e >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+    w9_t = uint_to_hex_lower8_le ((e >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((e >>  8) & 255) << 16;
+
+    wa_t = 0x80000000;
+    wb_t = 0;
+    wc_t = 0;
+    wd_t = 0;
+    we_t = 0;
+    wf_t = 40 * 8;
+
+    a = SHA1M_A;
+    b = SHA1M_B;
+    c = SHA1M_C;
+    d = SHA1M_D;
+    e = SHA1M_E;
+
+    #undef K
+    #define K SHA1C00
+
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+    #undef K
+    #define K SHA1C01
+
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+    #undef K
+    #define K SHA1C02
+
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+    #undef K
+    #define K SHA1C03
+
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+    COMPARE_M_SIMD (d, e, c, b);
+  }
+}
+
+KERNEL_FQ void m05000_m08 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m05000_m16 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m05000_s04 (KERN_ATTR_BASIC ())
+{
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+  const u64 lsz = get_local_size (0);
+
+  /**
+   * bin2asc table
+   */
+
+  LOCAL_VK u32 l_bin2asc[256];
+
+  for (u32 i = lid; i < 256; i += lsz)
+  {
+    const u32 i0 = (i >> 0) & 15;
+    const u32 i1 = (i >> 4) & 15;
+
+    l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+                 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+  }
+
+  SYNC_THREADS ();
+
+  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 & 63;
+
+  /**
+   * salt
+   */
+
+  u32 salt_buf0[4];
+  u32 salt_buf1[4];
+  u32 salt_buf2[4];
+  u32 salt_buf3[4];
+
+  salt_buf0[0] = salt_bufs[SALT_POS].salt_buf[ 0];
+  salt_buf0[1] = salt_bufs[SALT_POS].salt_buf[ 1];
+  salt_buf0[2] = salt_bufs[SALT_POS].salt_buf[ 2];
+  salt_buf0[3] = salt_bufs[SALT_POS].salt_buf[ 3];
+  salt_buf1[0] = salt_bufs[SALT_POS].salt_buf[ 4];
+  salt_buf1[1] = salt_bufs[SALT_POS].salt_buf[ 5];
+  salt_buf1[2] = salt_bufs[SALT_POS].salt_buf[ 6];
+  salt_buf1[3] = salt_bufs[SALT_POS].salt_buf[ 7];
+  salt_buf2[0] = salt_bufs[SALT_POS].salt_buf[ 8];
+  salt_buf2[1] = salt_bufs[SALT_POS].salt_buf[ 9];
+  salt_buf2[2] = salt_bufs[SALT_POS].salt_buf[10];
+  salt_buf2[3] = salt_bufs[SALT_POS].salt_buf[11];
+  salt_buf3[0] = salt_bufs[SALT_POS].salt_buf[12];
+  salt_buf3[1] = salt_bufs[SALT_POS].salt_buf[13];
+  salt_buf3[2] = salt_bufs[SALT_POS].salt_buf[14];
+  salt_buf3[3] = salt_bufs[SALT_POS].salt_buf[15];
+
+  const u32 salt_len = salt_bufs[SALT_POS].salt_len;
+
+  /**
+   * 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]
+  };
+
+  /**
+   * reverse
+   */
+
+  const u32 e_rev = hc_rotl32_S (search[1], 2u);
+
+  /**
+   * 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) & 63;
+
+    const u32x pw_len = (pw_l_len + pw_r_len) & 63;
+
+    /**
+     * 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];
+
+    /**
+     * prepend salt
+     */
+
+    switch_buffer_by_offset_le (w0, w1, w2, w3, salt_len);
+
+    const u32x pw_salt_len = pw_len + salt_len;
+
+    w0[0] |= salt_buf0[0];
+    w0[1] |= salt_buf0[1];
+    w0[2] |= salt_buf0[2];
+    w0[3] |= salt_buf0[3];
+    w1[0] |= salt_buf1[0];
+    w1[1] |= salt_buf1[1];
+    w1[2] |= salt_buf1[2];
+    w1[3] |= salt_buf1[3];
+    w2[0] |= salt_buf2[0];
+    w2[1] |= salt_buf2[1];
+    w2[2] |= salt_buf2[2];
+    w2[3] |= salt_buf2[3];
+    w3[0] |= salt_buf3[0];
+    w3[1] |= salt_buf3[1];
+    w3[2] |= salt_buf3[2];
+    w3[3] |= salt_buf3[3];
+
+    /**
+     * append salt
+     */
+
+    u32x s0[4];
+    u32x s1[4];
+    u32x s2[4];
+    u32x s3[4];
+
+    s0[0] = salt_buf0[0];
+    s0[1] = salt_buf0[1];
+    s0[2] = salt_buf0[2];
+    s0[3] = salt_buf0[3];
+    s1[0] = salt_buf1[0];
+    s1[1] = salt_buf1[1];
+    s1[2] = salt_buf1[2];
+    s1[3] = salt_buf1[3];
+    s2[0] = salt_buf2[0];
+    s2[1] = salt_buf2[1];
+    s2[2] = salt_buf2[2];
+    s2[3] = salt_buf2[3];
+    s3[0] = salt_buf3[0];
+    s3[1] = salt_buf3[1];
+    s3[2] = salt_buf3[2];
+    s3[3] = salt_buf3[3];
+
+    switch_buffer_by_offset_le_VV (s0, s1, s2, s3, pw_salt_len);
+
+    w0[0] |= s0[0];
+    w0[1] |= s0[1];
+    w0[2] |= s0[2];
+    w0[3] |= s0[3];
+    w1[0] |= s1[0];
+    w1[1] |= s1[1];
+    w1[2] |= s1[2];
+    w1[3] |= s1[3];
+    w2[0] |= s2[0];
+    w2[1] |= s2[1];
+    w2[2] |= s2[2];
+    w2[3] |= s2[3];
+    w3[0] |= s3[0];
+    w3[1] |= s3[1];
+    w3[2] |= s3[2];
+    w3[3] |= s3[3];
+
+    const u32x salt_pw_salt_len = salt_len + pw_len + salt_len;
+
+    append_0x80_4x4_VV (w0, w1, w2, w3, salt_pw_salt_len);
+
+    /**
+     * sha1
+     */
+
+    u32x w0_t = hc_swap32 (w0[0]);
+    u32x w1_t = hc_swap32 (w0[1]);
+    u32x w2_t = hc_swap32 (w0[2]);
+    u32x w3_t = hc_swap32 (w0[3]);
+    u32x w4_t = hc_swap32 (w1[0]);
+    u32x w5_t = hc_swap32 (w1[1]);
+    u32x w6_t = hc_swap32 (w1[2]);
+    u32x w7_t = hc_swap32 (w1[3]);
+    u32x w8_t = hc_swap32 (w2[0]);
+    u32x w9_t = hc_swap32 (w2[1]);
+    u32x wa_t = hc_swap32 (w2[2]);
+    u32x wb_t = hc_swap32 (w2[3]);
+    u32x wc_t = hc_swap32 (w3[0]);
+    u32x wd_t = hc_swap32 (w3[1]);
+    u32x we_t = 0;
+    u32x wf_t = salt_pw_salt_len * 8;
+
+    u32x a = SHA1M_A;
+    u32x b = SHA1M_B;
+    u32x c = SHA1M_C;
+    u32x d = SHA1M_D;
+    u32x e = SHA1M_E;
+
+    #undef K
+    #define K SHA1C00
+
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+    #undef K
+    #define K SHA1C01
+
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+    #undef K
+    #define K SHA1C02
+
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+    #undef K
+    #define K SHA1C03
+
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+    a += SHA1M_A;
+    b += SHA1M_B;
+    c += SHA1M_C;
+    d += SHA1M_D;
+    e += SHA1M_E;
+
+    /**
+     * 2nd SHA1
+     */
+
+    w0_t = uint_to_hex_lower8_le ((a >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+    w1_t = uint_to_hex_lower8_le ((a >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((a >>  8) & 255) << 16;
+    w2_t = uint_to_hex_lower8_le ((b >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+    w3_t = uint_to_hex_lower8_le ((b >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((b >>  8) & 255) << 16;
+    w4_t = uint_to_hex_lower8_le ((c >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+    w5_t = uint_to_hex_lower8_le ((c >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((c >>  8) & 255) << 16;
+    w6_t = uint_to_hex_lower8_le ((d >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+    w7_t = uint_to_hex_lower8_le ((d >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((d >>  8) & 255) << 16;
+    w8_t = uint_to_hex_lower8_le ((e >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+    w9_t = uint_to_hex_lower8_le ((e >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((e >>  8) & 255) << 16;
+
+    wa_t = 0x80000000;
+    wb_t = 0;
+    wc_t = 0;
+    wd_t = 0;
+    we_t = 0;
+    wf_t = 40 * 8;
+
+    a = SHA1M_A;
+    b = SHA1M_B;
+    c = SHA1M_C;
+    d = SHA1M_D;
+    e = SHA1M_E;
+
+    #undef K
+    #define K SHA1C00
+
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+    #undef K
+    #define K SHA1C01
+
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+    #undef K
+    #define K SHA1C02
+
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+    #undef K
+    #define K SHA1C03
+
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+
+    if (MATCHES_NONE_VS (e, e_rev)) continue;
+
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+    COMPARE_S_SIMD (d, e, c, b);
+  }
+}
+
+KERNEL_FQ void m05000_s08 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m05000_s16 (KERN_ATTR_BASIC ())
+{
+}
diff --git a/OpenCL/m05000_a1-pure.cl b/OpenCL/m05000_a1-pure.cl
new file mode 100644
index 000000000..b5961a063
--- /dev/null
+++ b/OpenCL/m05000_a1-pure.cl
@@ -0,0 +1,255 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_scalar.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if   VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m05000_mxx (KERN_ATTR_BASIC ())
+{
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+  const u64 gid = get_global_id (0);
+  const u64 lsz = get_local_size (0);
+
+  /**
+   * bin2asc table
+   */
+
+  LOCAL_VK u32 l_bin2asc[256];
+
+  for (u32 i = lid; i < 256; i += lsz)
+  {
+    const u32 i0 = (i >> 0) & 15;
+    const u32 i1 = (i >> 4) & 15;
+
+    l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+                 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+  }
+
+  SYNC_THREADS ();
+
+  if (gid >= gid_max) return;
+
+  /**
+   * base
+   */
+
+  const u32 salt_len = salt_bufs[SALT_POS].salt_len;
+
+  u32 s[64] = { 0 };
+
+  for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+  {
+    s[idx] = hc_swap32_S (salt_bufs[SALT_POS].salt_buf[idx]);
+  }
+
+  sha1_ctx_t ctx0;
+
+  sha1_init (&ctx0);
+
+  sha1_update (&ctx0, s, salt_len);
+
+  sha1_update_global_swap (&ctx0, pws[gid].i, pws[gid].pw_len);
+
+  /**
+   * loop
+   */
+
+  for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+  {
+    sha1_ctx_t ctx = ctx0;
+
+    sha1_update_global_swap (&ctx, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
+
+    sha1_update (&ctx, s, salt_len);
+
+    sha1_final (&ctx);
+
+    const u32 a = ctx.h[0];
+    const u32 b = ctx.h[1];
+    const u32 c = ctx.h[2];
+    const u32 d = ctx.h[3];
+    const u32 e = ctx.h[4];
+
+    sha1_ctx_t ctx1;
+
+    sha1_init (&ctx1);
+
+    ctx1.w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+    ctx1.w0[1] = uint_to_hex_lower8_le ((a >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((a >>  8) & 255) << 16;
+    ctx1.w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+    ctx1.w0[3] = uint_to_hex_lower8_le ((b >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((b >>  8) & 255) << 16;
+    ctx1.w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+    ctx1.w1[1] = uint_to_hex_lower8_le ((c >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((c >>  8) & 255) << 16;
+    ctx1.w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+    ctx1.w1[3] = uint_to_hex_lower8_le ((d >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((d >>  8) & 255) << 16;
+    ctx1.w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+    ctx1.w2[1] = uint_to_hex_lower8_le ((e >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((e >>  8) & 255) << 16;
+
+    ctx1.len = 40;
+
+    sha1_final (&ctx1);
+
+    const u32 r0 = ctx1.h[DGST_R0];
+    const u32 r1 = ctx1.h[DGST_R1];
+    const u32 r2 = ctx1.h[DGST_R2];
+    const u32 r3 = ctx1.h[DGST_R3];
+
+    COMPARE_M_SCALAR (r0, r1, r2, r3);
+  }
+}
+
+KERNEL_FQ void m05000_sxx (KERN_ATTR_BASIC ())
+{
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+  const u64 gid = get_global_id (0);
+  const u64 lsz = get_local_size (0);
+
+  /**
+   * bin2asc table
+   */
+
+  LOCAL_VK u32 l_bin2asc[256];
+
+  for (u32 i = lid; i < 256; i += lsz)
+  {
+    const u32 i0 = (i >> 0) & 15;
+    const u32 i1 = (i >> 4) & 15;
+
+    l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+                 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+  }
+
+  SYNC_THREADS ();
+
+  if (gid >= gid_max) return;
+
+  /**
+   * 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]
+  };
+
+  /**
+   * base
+   */
+
+  const u32 salt_len = salt_bufs[SALT_POS].salt_len;
+
+  u32 s[64] = { 0 };
+
+  for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+  {
+    s[idx] = hc_swap32_S (salt_bufs[SALT_POS].salt_buf[idx]);
+  }
+
+  sha1_ctx_t ctx0;
+
+  sha1_init (&ctx0);
+
+  sha1_update (&ctx0, s, salt_len);
+
+  sha1_update_global_swap (&ctx0, pws[gid].i, pws[gid].pw_len);
+
+  /**
+   * loop
+   */
+
+  for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+  {
+    sha1_ctx_t ctx = ctx0;
+
+    sha1_update_global_swap (&ctx, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
+
+    sha1_update (&ctx, s, salt_len);
+
+    sha1_final (&ctx);
+
+    const u32 a = ctx.h[0];
+    const u32 b = ctx.h[1];
+    const u32 c = ctx.h[2];
+    const u32 d = ctx.h[3];
+    const u32 e = ctx.h[4];
+
+    sha1_ctx_t ctx1;
+
+    sha1_init (&ctx1);
+
+    ctx1.w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+    ctx1.w0[1] = uint_to_hex_lower8_le ((a >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((a >>  8) & 255) << 16;
+    ctx1.w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+    ctx1.w0[3] = uint_to_hex_lower8_le ((b >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((b >>  8) & 255) << 16;
+    ctx1.w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+    ctx1.w1[1] = uint_to_hex_lower8_le ((c >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((c >>  8) & 255) << 16;
+    ctx1.w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+    ctx1.w1[3] = uint_to_hex_lower8_le ((d >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((d >>  8) & 255) << 16;
+    ctx1.w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+    ctx1.w2[1] = uint_to_hex_lower8_le ((e >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((e >>  8) & 255) << 16;
+
+    ctx1.len = 40;
+
+    sha1_final (&ctx1);
+
+    const u32 r0 = ctx1.h[DGST_R0];
+    const u32 r1 = ctx1.h[DGST_R1];
+    const u32 r2 = ctx1.h[DGST_R2];
+    const u32 r3 = ctx1.h[DGST_R3];
+
+    COMPARE_S_SCALAR (r0, r1, r2, r3);
+  }
+}
diff --git a/OpenCL/m05000_a3-optimized.cl b/OpenCL/m05000_a3-optimized.cl
new file mode 100644
index 000000000..09c4be2c1
--- /dev/null
+++ b/OpenCL/m05000_a3-optimized.cl
@@ -0,0 +1,1288 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */ 
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if   VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+DECLSPEC void m05000m (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
+{
+  /**
+   * modifier
+   */
+
+  const u64 gid = get_global_id (0);
+  const u64 lid = get_local_id (0);
+
+  /**
+   * salt
+   */
+
+  u32 salt_buf0[4];
+  u32 salt_buf1[4];
+  u32 salt_buf2[4];
+  u32 salt_buf3[4];
+
+  salt_buf0[0] = salt_bufs[SALT_POS].salt_buf[ 0];
+  salt_buf0[1] = salt_bufs[SALT_POS].salt_buf[ 1];
+  salt_buf0[2] = salt_bufs[SALT_POS].salt_buf[ 2];
+  salt_buf0[3] = salt_bufs[SALT_POS].salt_buf[ 3];
+  salt_buf1[0] = salt_bufs[SALT_POS].salt_buf[ 4];
+  salt_buf1[1] = salt_bufs[SALT_POS].salt_buf[ 5];
+  salt_buf1[2] = salt_bufs[SALT_POS].salt_buf[ 6];
+  salt_buf1[3] = salt_bufs[SALT_POS].salt_buf[ 7];
+  salt_buf2[0] = salt_bufs[SALT_POS].salt_buf[ 8];
+  salt_buf2[1] = salt_bufs[SALT_POS].salt_buf[ 9];
+  salt_buf2[2] = salt_bufs[SALT_POS].salt_buf[10];
+  salt_buf2[3] = salt_bufs[SALT_POS].salt_buf[11];
+  salt_buf3[0] = salt_bufs[SALT_POS].salt_buf[12];
+  salt_buf3[1] = salt_bufs[SALT_POS].salt_buf[13];
+  salt_buf3[2] = salt_bufs[SALT_POS].salt_buf[14];
+  salt_buf3[3] = salt_bufs[SALT_POS].salt_buf[15];
+
+  u32 salt_buf0_t[4];
+  u32 salt_buf1_t[4];
+  u32 salt_buf2_t[4];
+  u32 salt_buf3_t[4];
+
+  salt_buf0_t[0] = salt_bufs[SALT_POS].salt_buf[ 0];
+  salt_buf0_t[1] = salt_bufs[SALT_POS].salt_buf[ 1];
+  salt_buf0_t[2] = salt_bufs[SALT_POS].salt_buf[ 2];
+  salt_buf0_t[3] = salt_bufs[SALT_POS].salt_buf[ 3];
+  salt_buf1_t[0] = salt_bufs[SALT_POS].salt_buf[ 4];
+  salt_buf1_t[1] = salt_bufs[SALT_POS].salt_buf[ 5];
+  salt_buf1_t[2] = salt_bufs[SALT_POS].salt_buf[ 6];
+  salt_buf1_t[3] = salt_bufs[SALT_POS].salt_buf[ 7];
+  salt_buf2_t[0] = salt_bufs[SALT_POS].salt_buf[ 8];
+  salt_buf2_t[1] = salt_bufs[SALT_POS].salt_buf[ 9];
+  salt_buf2_t[2] = salt_bufs[SALT_POS].salt_buf[10];
+  salt_buf2_t[3] = salt_bufs[SALT_POS].salt_buf[11];
+  salt_buf3_t[0] = salt_bufs[SALT_POS].salt_buf[12];
+  salt_buf3_t[1] = salt_bufs[SALT_POS].salt_buf[13];
+  salt_buf3_t[2] = salt_bufs[SALT_POS].salt_buf[14];
+  salt_buf3_t[3] = salt_bufs[SALT_POS].salt_buf[15];
+
+  const u32 salt_len = salt_bufs[SALT_POS].salt_len;
+
+  const u32 pw_salt_len = pw_len + salt_len;
+
+  const u32 salt_pw_salt_len = salt_len + pw_len + salt_len;
+
+  switch_buffer_by_offset_le_S (salt_buf0_t, salt_buf1_t, salt_buf2_t, salt_buf3_t, pw_salt_len);
+
+  salt_buf0[0] |= salt_buf0_t[0];
+  salt_buf0[1] |= salt_buf0_t[1];
+  salt_buf0[2] |= salt_buf0_t[2];
+  salt_buf0[3] |= salt_buf0_t[3];
+  salt_buf1[0] |= salt_buf1_t[0];
+  salt_buf1[1] |= salt_buf1_t[1];
+  salt_buf1[2] |= salt_buf1_t[2];
+  salt_buf1[3] |= salt_buf1_t[3];
+  salt_buf2[0] |= salt_buf2_t[0];
+  salt_buf2[1] |= salt_buf2_t[1];
+  salt_buf2[2] |= salt_buf2_t[2];
+  salt_buf2[3] |= salt_buf2_t[3];
+  salt_buf3[0] |= salt_buf3_t[0];
+  salt_buf3[1] |= salt_buf3_t[1];
+  salt_buf3[2] |= salt_buf3_t[2];
+  salt_buf3[3] |= salt_buf3_t[3];
+
+  append_0x80_4x4_S (salt_buf0, salt_buf1, salt_buf2, salt_buf3, salt_pw_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;
+
+    u32x t0[4];
+    u32x t1[4];
+    u32x t2[4];
+    u32x t3[4];
+
+    t0[0] = w0lr;
+    t0[1] = w0[1];
+    t0[2] = w0[2];
+    t0[3] = w0[3];
+    t1[0] = w1[0];
+    t1[1] = w1[1];
+    t1[2] = w1[2];
+    t1[3] = w1[3];
+    t2[0] = w2[0];
+    t2[1] = w2[1];
+    t2[2] = w2[2];
+    t2[3] = w2[3];
+    t3[0] = w3[0];
+    t3[1] = w3[1];
+    t3[2] = w3[2];
+    t3[3] = w3[3];
+
+    /**
+     * put the password after the first salt but before the second salt
+     */
+
+    switch_buffer_by_offset_le (t0, t1, t2, t3, salt_len);
+
+    t0[0] |= salt_buf0[0];
+    t0[1] |= salt_buf0[1];
+    t0[2] |= salt_buf0[2];
+    t0[3] |= salt_buf0[3];
+    t1[0] |= salt_buf1[0];
+    t1[1] |= salt_buf1[1];
+    t1[2] |= salt_buf1[2];
+    t1[3] |= salt_buf1[3];
+    t2[0] |= salt_buf2[0];
+    t2[1] |= salt_buf2[1];
+    t2[2] |= salt_buf2[2];
+    t2[3] |= salt_buf2[3];
+    t3[0] |= salt_buf3[0];
+    t3[1] |= salt_buf3[1];
+    t3[2] |= salt_buf3[2];
+
+    /**
+     * sha1
+     */
+
+    u32x w0_t = hc_swap32 (t0[0]);
+    u32x w1_t = hc_swap32 (t0[1]);
+    u32x w2_t = hc_swap32 (t0[2]);
+    u32x w3_t = hc_swap32 (t0[3]);
+    u32x w4_t = hc_swap32 (t1[0]);
+    u32x w5_t = hc_swap32 (t1[1]);
+    u32x w6_t = hc_swap32 (t1[2]);
+    u32x w7_t = hc_swap32 (t1[3]);
+    u32x w8_t = hc_swap32 (t2[0]);
+    u32x w9_t = hc_swap32 (t2[1]);
+    u32x wa_t = hc_swap32 (t2[2]);
+    u32x wb_t = hc_swap32 (t2[3]);
+    u32x wc_t = hc_swap32 (t3[0]);
+    u32x wd_t = hc_swap32 (t3[1]);
+    u32x we_t = 0;
+    u32x wf_t = salt_pw_salt_len * 8;
+
+    u32x a = SHA1M_A;
+    u32x b = SHA1M_B;
+    u32x c = SHA1M_C;
+    u32x d = SHA1M_D;
+    u32x e = SHA1M_E;
+
+    #undef K
+    #define K SHA1C00
+
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+    #undef K
+    #define K SHA1C01
+
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+    #undef K
+    #define K SHA1C02
+
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+    #undef K
+    #define K SHA1C03
+
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+    a += SHA1M_A;
+    b += SHA1M_B;
+    c += SHA1M_C;
+    d += SHA1M_D;
+    e += SHA1M_E;
+
+    /**
+     * 2nd SHA1
+     */
+
+    w0_t = uint_to_hex_lower8_le ((a >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+    w1_t = uint_to_hex_lower8_le ((a >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((a >>  8) & 255) << 16;
+    w2_t = uint_to_hex_lower8_le ((b >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+    w3_t = uint_to_hex_lower8_le ((b >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((b >>  8) & 255) << 16;
+    w4_t = uint_to_hex_lower8_le ((c >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+    w5_t = uint_to_hex_lower8_le ((c >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((c >>  8) & 255) << 16;
+    w6_t = uint_to_hex_lower8_le ((d >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+    w7_t = uint_to_hex_lower8_le ((d >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((d >>  8) & 255) << 16;
+    w8_t = uint_to_hex_lower8_le ((e >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+    w9_t = uint_to_hex_lower8_le ((e >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((e >>  8) & 255) << 16;
+
+    wa_t = 0x80000000;
+    wb_t = 0;
+    wc_t = 0;
+    wd_t = 0;
+    we_t = 0;
+    wf_t = 40 * 8;
+
+    a = SHA1M_A;
+    b = SHA1M_B;
+    c = SHA1M_C;
+    d = SHA1M_D;
+    e = SHA1M_E;
+
+    #undef K
+    #define K SHA1C00
+
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+    #undef K
+    #define K SHA1C01
+
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+    #undef K
+    #define K SHA1C02
+
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+    #undef K
+    #define K SHA1C03
+
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+    COMPARE_M_SIMD (d, e, c, b);
+  }
+}
+
+DECLSPEC void m05000s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
+{
+  /**
+   * modifier
+   */
+
+  const u64 gid = get_global_id (0);
+  const u64 lid = get_local_id (0);
+
+  /**
+   * salt
+   */
+
+  u32 salt_buf0[4];
+  u32 salt_buf1[4];
+  u32 salt_buf2[4];
+  u32 salt_buf3[4];
+
+  salt_buf0[0] = salt_bufs[SALT_POS].salt_buf[ 0];
+  salt_buf0[1] = salt_bufs[SALT_POS].salt_buf[ 1];
+  salt_buf0[2] = salt_bufs[SALT_POS].salt_buf[ 2];
+  salt_buf0[3] = salt_bufs[SALT_POS].salt_buf[ 3];
+  salt_buf1[0] = salt_bufs[SALT_POS].salt_buf[ 4];
+  salt_buf1[1] = salt_bufs[SALT_POS].salt_buf[ 5];
+  salt_buf1[2] = salt_bufs[SALT_POS].salt_buf[ 6];
+  salt_buf1[3] = salt_bufs[SALT_POS].salt_buf[ 7];
+  salt_buf2[0] = salt_bufs[SALT_POS].salt_buf[ 8];
+  salt_buf2[1] = salt_bufs[SALT_POS].salt_buf[ 9];
+  salt_buf2[2] = salt_bufs[SALT_POS].salt_buf[10];
+  salt_buf2[3] = salt_bufs[SALT_POS].salt_buf[11];
+  salt_buf3[0] = salt_bufs[SALT_POS].salt_buf[12];
+  salt_buf3[1] = salt_bufs[SALT_POS].salt_buf[13];
+  salt_buf3[2] = salt_bufs[SALT_POS].salt_buf[14];
+  salt_buf3[3] = salt_bufs[SALT_POS].salt_buf[15];
+
+  u32 salt_buf0_t[4];
+  u32 salt_buf1_t[4];
+  u32 salt_buf2_t[4];
+  u32 salt_buf3_t[4];
+
+  salt_buf0_t[0] = salt_bufs[SALT_POS].salt_buf[ 0];
+  salt_buf0_t[1] = salt_bufs[SALT_POS].salt_buf[ 1];
+  salt_buf0_t[2] = salt_bufs[SALT_POS].salt_buf[ 2];
+  salt_buf0_t[3] = salt_bufs[SALT_POS].salt_buf[ 3];
+  salt_buf1_t[0] = salt_bufs[SALT_POS].salt_buf[ 4];
+  salt_buf1_t[1] = salt_bufs[SALT_POS].salt_buf[ 5];
+  salt_buf1_t[2] = salt_bufs[SALT_POS].salt_buf[ 6];
+  salt_buf1_t[3] = salt_bufs[SALT_POS].salt_buf[ 7];
+  salt_buf2_t[0] = salt_bufs[SALT_POS].salt_buf[ 8];
+  salt_buf2_t[1] = salt_bufs[SALT_POS].salt_buf[ 9];
+  salt_buf2_t[2] = salt_bufs[SALT_POS].salt_buf[10];
+  salt_buf2_t[3] = salt_bufs[SALT_POS].salt_buf[11];
+  salt_buf3_t[0] = salt_bufs[SALT_POS].salt_buf[12];
+  salt_buf3_t[1] = salt_bufs[SALT_POS].salt_buf[13];
+  salt_buf3_t[2] = salt_bufs[SALT_POS].salt_buf[14];
+  salt_buf3_t[3] = salt_bufs[SALT_POS].salt_buf[15];
+
+  const u32 salt_len = salt_bufs[SALT_POS].salt_len;
+
+  const u32 pw_salt_len = pw_len + salt_len;
+
+  const u32 salt_pw_salt_len = salt_len + pw_len + salt_len;
+
+  switch_buffer_by_offset_le_S (salt_buf0_t, salt_buf1_t, salt_buf2_t, salt_buf3_t, pw_salt_len);
+
+  salt_buf0[0] |= salt_buf0_t[0];
+  salt_buf0[1] |= salt_buf0_t[1];
+  salt_buf0[2] |= salt_buf0_t[2];
+  salt_buf0[3] |= salt_buf0_t[3];
+  salt_buf1[0] |= salt_buf1_t[0];
+  salt_buf1[1] |= salt_buf1_t[1];
+  salt_buf1[2] |= salt_buf1_t[2];
+  salt_buf1[3] |= salt_buf1_t[3];
+  salt_buf2[0] |= salt_buf2_t[0];
+  salt_buf2[1] |= salt_buf2_t[1];
+  salt_buf2[2] |= salt_buf2_t[2];
+  salt_buf2[3] |= salt_buf2_t[3];
+  salt_buf3[0] |= salt_buf3_t[0];
+  salt_buf3[1] |= salt_buf3_t[1];
+  salt_buf3[2] |= salt_buf3_t[2];
+  salt_buf3[3] |= salt_buf3_t[3];
+
+  append_0x80_4x4_S (salt_buf0, salt_buf1, salt_buf2, salt_buf3, salt_pw_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]
+  };
+
+  /**
+   * reverse
+   */
+
+  const u32 e_rev = hc_rotl32_S (search[1], 2u);
+
+  /**
+   * 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;
+
+    u32x t0[4];
+    u32x t1[4];
+    u32x t2[4];
+    u32x t3[4];
+
+    t0[0] = w0lr;
+    t0[1] = w0[1];
+    t0[2] = w0[2];
+    t0[3] = w0[3];
+    t1[0] = w1[0];
+    t1[1] = w1[1];
+    t1[2] = w1[2];
+    t1[3] = w1[3];
+    t2[0] = w2[0];
+    t2[1] = w2[1];
+    t2[2] = w2[2];
+    t2[3] = w2[3];
+    t3[0] = w3[0];
+    t3[1] = w3[1];
+    t3[2] = w3[2];
+    t3[3] = w3[3];
+
+    /**
+     * put the password after the first salt but before the second salt
+     */
+
+    switch_buffer_by_offset_le (t0, t1, t2, t3, salt_len);
+
+    t0[0] |= salt_buf0[0];
+    t0[1] |= salt_buf0[1];
+    t0[2] |= salt_buf0[2];
+    t0[3] |= salt_buf0[3];
+    t1[0] |= salt_buf1[0];
+    t1[1] |= salt_buf1[1];
+    t1[2] |= salt_buf1[2];
+    t1[3] |= salt_buf1[3];
+    t2[0] |= salt_buf2[0];
+    t2[1] |= salt_buf2[1];
+    t2[2] |= salt_buf2[2];
+    t2[3] |= salt_buf2[3];
+    t3[0] |= salt_buf3[0];
+    t3[1] |= salt_buf3[1];
+    t3[2] |= salt_buf3[2];
+
+    /**
+     * sha1
+     */
+
+    u32x w0_t = hc_swap32 (t0[0]);
+    u32x w1_t = hc_swap32 (t0[1]);
+    u32x w2_t = hc_swap32 (t0[2]);
+    u32x w3_t = hc_swap32 (t0[3]);
+    u32x w4_t = hc_swap32 (t1[0]);
+    u32x w5_t = hc_swap32 (t1[1]);
+    u32x w6_t = hc_swap32 (t1[2]);
+    u32x w7_t = hc_swap32 (t1[3]);
+    u32x w8_t = hc_swap32 (t2[0]);
+    u32x w9_t = hc_swap32 (t2[1]);
+    u32x wa_t = hc_swap32 (t2[2]);
+    u32x wb_t = hc_swap32 (t2[3]);
+    u32x wc_t = hc_swap32 (t3[0]);
+    u32x wd_t = hc_swap32 (t3[1]);
+    u32x we_t = 0;
+    u32x wf_t = salt_pw_salt_len * 8;
+
+    u32x a = SHA1M_A;
+    u32x b = SHA1M_B;
+    u32x c = SHA1M_C;
+    u32x d = SHA1M_D;
+    u32x e = SHA1M_E;
+
+    #undef K
+    #define K SHA1C00
+
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+    #undef K
+    #define K SHA1C01
+
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+    #undef K
+    #define K SHA1C02
+
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+    #undef K
+    #define K SHA1C03
+
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+    a += SHA1M_A;
+    b += SHA1M_B;
+    c += SHA1M_C;
+    d += SHA1M_D;
+    e += SHA1M_E;
+
+    /**
+     * 2nd SHA1
+     */
+
+    w0_t = uint_to_hex_lower8_le ((a >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+    w1_t = uint_to_hex_lower8_le ((a >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((a >>  8) & 255) << 16;
+    w2_t = uint_to_hex_lower8_le ((b >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+    w3_t = uint_to_hex_lower8_le ((b >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((b >>  8) & 255) << 16;
+    w4_t = uint_to_hex_lower8_le ((c >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+    w5_t = uint_to_hex_lower8_le ((c >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((c >>  8) & 255) << 16;
+    w6_t = uint_to_hex_lower8_le ((d >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+    w7_t = uint_to_hex_lower8_le ((d >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((d >>  8) & 255) << 16;
+    w8_t = uint_to_hex_lower8_le ((e >> 16) & 255) <<  0
+         | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+    w9_t = uint_to_hex_lower8_le ((e >>  0) & 255) <<  0
+         | uint_to_hex_lower8_le ((e >>  8) & 255) << 16;
+
+    wa_t = 0x80000000;
+    wb_t = 0;
+    wc_t = 0;
+    wd_t = 0;
+    we_t = 0;
+    wf_t = 40 * 8;
+
+    a = SHA1M_A;
+    b = SHA1M_B;
+    c = SHA1M_C;
+    d = SHA1M_D;
+    e = SHA1M_E;
+
+    #undef K
+    #define K SHA1C00
+
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+    SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+    SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+    SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+    SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+    SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+    #undef K
+    #define K SHA1C01
+
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+    #undef K
+    #define K SHA1C02
+
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+    #undef K
+    #define K SHA1C03
+
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+    w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+    w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+    w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+    w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+    w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+    w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+    w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+    w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+    w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+    w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+    wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+    wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+
+    if (MATCHES_NONE_VS (e, e_rev)) continue;
+
+    wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+    wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+    we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+    wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+    COMPARE_S_SIMD (d, e, c, b);
+  }
+}
+
+KERNEL_FQ void m05000_m04 (KERN_ATTR_BASIC ())
+{
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+
+  if (gid >= gid_max) return;
+
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+  const u64 lsz = get_local_size (0);
+
+  /**
+   * bin2asc table
+   */
+
+  LOCAL_VK u32 l_bin2asc[256];
+
+  for (u32 i = lid; i < 256; i += lsz)
+  {
+    const u32 i0 = (i >> 0) & 15;
+    const u32 i1 = (i >> 4) & 15;
+
+    l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+                 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+  }
+
+  SYNC_THREADS ();
+
+  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] = pws[gid].i[14];
+  w3[3] = 0;
+
+  const u32 pw_len = pws[gid].pw_len & 63;
+
+  /**
+   * main
+   */
+
+  m05000m (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, pws_pos, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m05000_m08 (KERN_ATTR_BASIC ())
+{
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+
+  if (gid >= gid_max) return;
+
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+  const u64 lsz = get_local_size (0);
+
+  /**
+   * bin2asc table
+   */
+
+  LOCAL_VK u32 l_bin2asc[256];
+
+  for (u32 i = lid; i < 256; i += lsz)
+  {
+    const u32 i0 = (i >> 0) & 15;
+    const u32 i1 = (i >> 4) & 15;
+
+    l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+                 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+  }
+
+  SYNC_THREADS ();
+
+  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] = pws[gid].i[14];
+  w3[3] = 0;
+
+  const u32 pw_len = pws[gid].pw_len & 63;
+
+  /**
+   * main
+   */
+
+  m05000m (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, pws_pos, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m05000_m16 (KERN_ATTR_BASIC ())
+{
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+
+  if (gid >= gid_max) return;
+
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+  const u64 lsz = get_local_size (0);
+
+  /**
+   * bin2asc table
+   */
+
+  LOCAL_VK u32 l_bin2asc[256];
+
+  for (u32 i = lid; i < 256; i += lsz)
+  {
+    const u32 i0 = (i >> 0) & 15;
+    const u32 i1 = (i >> 4) & 15;
+
+    l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+                 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+  }
+
+  SYNC_THREADS ();
+
+  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] = pws[gid].i[ 8];
+  w2[1] = pws[gid].i[ 9];
+  w2[2] = pws[gid].i[10];
+  w2[3] = pws[gid].i[11];
+
+  u32 w3[4];
+
+  w3[0] = pws[gid].i[12];
+  w3[1] = pws[gid].i[13];
+  w3[2] = pws[gid].i[14];
+  w3[3] = pws[gid].i[15];
+
+  const u32 pw_len = pws[gid].pw_len & 63;
+
+  /**
+   * main
+   */
+
+  m05000m (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, pws_pos, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m05000_s04 (KERN_ATTR_BASIC ())
+{
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+
+  if (gid >= gid_max) return;
+
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+  const u64 lsz = get_local_size (0);
+
+  /**
+   * bin2asc table
+   */
+
+  LOCAL_VK u32 l_bin2asc[256];
+
+  for (u32 i = lid; i < 256; i += lsz)
+  {
+    const u32 i0 = (i >> 0) & 15;
+    const u32 i1 = (i >> 4) & 15;
+
+    l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+                 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+  }
+
+  SYNC_THREADS ();
+
+  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] = pws[gid].i[14];
+  w3[3] = 0;
+
+  const u32 pw_len = pws[gid].pw_len & 63;
+
+  /**
+   * main
+   */
+
+  m05000s (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, pws_pos, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m05000_s08 (KERN_ATTR_BASIC ())
+{
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+
+  if (gid >= gid_max) return;
+
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+  const u64 lsz = get_local_size (0);
+
+  /**
+   * bin2asc table
+   */
+
+  LOCAL_VK u32 l_bin2asc[256];
+
+  for (u32 i = lid; i < 256; i += lsz)
+  {
+    const u32 i0 = (i >> 0) & 15;
+    const u32 i1 = (i >> 4) & 15;
+
+    l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+                 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+  }
+
+  SYNC_THREADS ();
+
+  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] = pws[gid].i[14];
+  w3[3] = 0;
+
+  const u32 pw_len = pws[gid].pw_len & 63;
+
+  /**
+   * main
+   */
+
+  m05000s (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, pws_pos, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m05000_s16 (KERN_ATTR_BASIC ())
+{
+  /**
+   * base
+   */
+
+  const u64 gid = get_global_id (0);
+
+  if (gid >= gid_max) return;
+
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+  const u64 lsz = get_local_size (0);
+
+  /**
+   * bin2asc table
+   */
+
+  LOCAL_VK u32 l_bin2asc[256];
+
+  for (u32 i = lid; i < 256; i += lsz)
+  {
+    const u32 i0 = (i >> 0) & 15;
+    const u32 i1 = (i >> 4) & 15;
+
+    l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+                 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+  }
+
+  SYNC_THREADS ();
+
+  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] = pws[gid].i[ 8];
+  w2[1] = pws[gid].i[ 9];
+  w2[2] = pws[gid].i[10];
+  w2[3] = pws[gid].i[11];
+
+  u32 w3[4];
+
+  w3[0] = pws[gid].i[12];
+  w3[1] = pws[gid].i[13];
+  w3[2] = pws[gid].i[14];
+  w3[3] = pws[gid].i[15];
+
+  const u32 pw_len = pws[gid].pw_len & 63;
+
+  /**
+   * main
+   */
+
+  m05000s (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, pws_pos, gid_max, l_bin2asc);
+}
diff --git a/OpenCL/m05000_a3-pure.cl b/OpenCL/m05000_a3-pure.cl
new file mode 100644
index 000000000..8e020e7c0
--- /dev/null
+++ b/OpenCL/m05000_a3-pure.cl
@@ -0,0 +1,289 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if   VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m05000_mxx (KERN_ATTR_VECTOR ())
+{
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+  const u64 gid = get_global_id (0);
+  const u64 lsz = get_local_size (0);
+
+  /**
+   * bin2asc table
+   */
+
+  LOCAL_VK u32 l_bin2asc[256];
+
+  for (u32 i = lid; i < 256; i += lsz)
+  {
+    const u32 i0 = (i >> 0) & 15;
+    const u32 i1 = (i >> 4) & 15;
+
+    l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+                 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+  }
+
+  SYNC_THREADS ();
+
+  if (gid >= gid_max) return;
+
+  /**
+   * base
+   */
+
+  const u32 pw_len = pws[gid].pw_len;
+
+  u32x w[64] = { 0 };
+
+  for (u32 i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
+  {
+    w[idx] = pws[gid].i[idx];
+  }
+
+  const u32 salt_len = salt_bufs[SALT_POS].salt_len;
+
+  u32x s[64] = { 0 };
+
+  for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+  {
+    s[idx] = hc_swap32 (salt_bufs[SALT_POS].salt_buf[idx]);
+  }
+
+  sha1_ctx_t ctx0;
+
+  sha1_init (&ctx0);
+
+  sha1_update_global_swap (&ctx0, salt_bufs[SALT_POS].salt_buf, salt_bufs[SALT_POS].salt_len);
+
+  /**
+   * loop
+   */
+
+  u32x w0l = w[0];
+
+  for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+  {
+    const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+    const u32x w0 = w0l | w0r;
+
+    w[0] = w0;
+
+    sha1_ctx_vector_t ctx;
+
+    sha1_init_vector_from_scalar (&ctx, &ctx0);
+
+    sha1_update_vector_swap (&ctx, w, pw_len);
+
+    sha1_update_vector (&ctx, s, salt_len);
+
+    sha1_final_vector (&ctx);
+
+    const u32x a = ctx.h[0];
+    const u32x b = ctx.h[1];
+    const u32x c = ctx.h[2];
+    const u32x d = ctx.h[3];
+    const u32x e = ctx.h[4];
+
+    sha1_ctx_vector_t ctx1;
+
+    sha1_init_vector (&ctx1);
+
+    ctx1.w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+    ctx1.w0[1] = uint_to_hex_lower8_le ((a >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((a >>  8) & 255) << 16;
+    ctx1.w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+    ctx1.w0[3] = uint_to_hex_lower8_le ((b >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((b >>  8) & 255) << 16;
+    ctx1.w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+    ctx1.w1[1] = uint_to_hex_lower8_le ((c >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((c >>  8) & 255) << 16;
+    ctx1.w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+    ctx1.w1[3] = uint_to_hex_lower8_le ((d >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((d >>  8) & 255) << 16;
+    ctx1.w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+    ctx1.w2[1] = uint_to_hex_lower8_le ((e >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((e >>  8) & 255) << 16;
+
+    ctx1.len = 40;
+
+    sha1_final_vector (&ctx1);
+
+    const u32x r0 = ctx1.h[DGST_R0];
+    const u32x r1 = ctx1.h[DGST_R1];
+    const u32x r2 = ctx1.h[DGST_R2];
+    const u32x r3 = ctx1.h[DGST_R3];
+
+    COMPARE_M_SIMD (r0, r1, r2, r3);
+  }
+}
+
+KERNEL_FQ void m05000_sxx (KERN_ATTR_VECTOR ())
+{
+  /**
+   * modifier
+   */
+
+  const u64 lid = get_local_id (0);
+  const u64 gid = get_global_id (0);
+  const u64 lsz = get_local_size (0);
+
+  /**
+   * bin2asc table
+   */
+
+  LOCAL_VK u32 l_bin2asc[256];
+
+  for (u32 i = lid; i < 256; i += lsz)
+  {
+    const u32 i0 = (i >> 0) & 15;
+    const u32 i1 = (i >> 4) & 15;
+
+    l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+                 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+  }
+
+  SYNC_THREADS ();
+
+  if (gid >= gid_max) return;
+
+  /**
+   * 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]
+  };
+
+  /**
+   * base
+   */
+
+  const u32 pw_len = pws[gid].pw_len;
+
+  u32x w[64] = { 0 };
+
+  for (u32 i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
+  {
+    w[idx] = pws[gid].i[idx];
+  }
+
+  const u32 salt_len = salt_bufs[SALT_POS].salt_len;
+
+  u32x s[64] = { 0 };
+
+  for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+  {
+    s[idx] = hc_swap32 (salt_bufs[SALT_POS].salt_buf[idx]);
+  }
+
+  sha1_ctx_t ctx0;
+
+  sha1_init (&ctx0);
+
+  sha1_update_global_swap (&ctx0, salt_bufs[SALT_POS].salt_buf, salt_bufs[SALT_POS].salt_len);
+
+  /**
+   * loop
+   */
+
+  u32x w0l = w[0];
+
+  for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+  {
+    const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+    const u32x w0 = w0l | w0r;
+
+    w[0] = w0;
+
+    sha1_ctx_vector_t ctx;
+
+    sha1_init_vector_from_scalar (&ctx, &ctx0);
+
+    sha1_update_vector_swap (&ctx, w, pw_len);
+
+    sha1_update_vector (&ctx, s, salt_len);
+
+    sha1_final_vector (&ctx);
+
+    const u32x a = ctx.h[0];
+    const u32x b = ctx.h[1];
+    const u32x c = ctx.h[2];
+    const u32x d = ctx.h[3];
+    const u32x e = ctx.h[4];
+
+    sha1_ctx_vector_t ctx1;
+
+    sha1_init_vector (&ctx1);
+
+    ctx1.w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+    ctx1.w0[1] = uint_to_hex_lower8_le ((a >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((a >>  8) & 255) << 16;
+    ctx1.w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+    ctx1.w0[3] = uint_to_hex_lower8_le ((b >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((b >>  8) & 255) << 16;
+    ctx1.w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+    ctx1.w1[1] = uint_to_hex_lower8_le ((c >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((c >>  8) & 255) << 16;
+    ctx1.w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+    ctx1.w1[3] = uint_to_hex_lower8_le ((d >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((d >>  8) & 255) << 16;
+    ctx1.w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) <<  0
+              | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+    ctx1.w2[1] = uint_to_hex_lower8_le ((e >>  0) & 255) <<  0
+              | uint_to_hex_lower8_le ((e >>  8) & 255) << 16;
+
+    ctx1.len = 40;
+
+    sha1_final_vector (&ctx1);
+
+    const u32x r0 = ctx1.h[DGST_R0];
+    const u32x r1 = ctx1.h[DGST_R1];
+    const u32x r2 = ctx1.h[DGST_R2];
+    const u32x r3 = ctx1.h[DGST_R3];
+
+    COMPARE_S_SIMD (r0, r1, r2, r3);
+  }
+}
diff --git a/docs/changes.txt b/docs/changes.txt
index d202f1791..9c30ed4a3 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -90,6 +90,7 @@
 - Added hash-mode: Umbraco HMAC-SHA1
 - Added hash-mode: sha1($salt.sha1($pass.$salt))
 - Added hash-mode: sha1(sha1($pass).$salt)
+- Added hash-mode: sha1(sha1($salt.$pass.$salt))
 
 ##
 ## Features
diff --git a/docs/readme.txt b/docs/readme.txt
index b3e540470..2513dd7d1 100644
--- a/docs/readme.txt
+++ b/docs/readme.txt
@@ -91,6 +91,7 @@ NVIDIA GPUs require "NVIDIA Driver" (440.64 or later) and "CUDA Toolkit" (9.0 or
 - sha1($pass.$salt)
 - sha1($salt.$pass)
 - sha1($salt.$pass.$salt)
+- sha1(sha1($salt.$pass.$salt))
 - sha1($salt.sha1($pass))
 - sha1($salt.sha1($pass.$salt))
 - sha1($salt.utf16le($pass))
diff --git a/src/modules/module_05000.c b/src/modules/module_05000.c
new file mode 100644
index 000000000..67ef974ce
--- /dev/null
+++ b/src/modules/module_05000.c
@@ -0,0 +1,231 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#include "common.h"
+#include "types.h"
+#include "modules.h"
+#include "bitops.h"
+#include "convert.h"
+#include "shared.h"
+
+static const u32   ATTACK_EXEC    = ATTACK_EXEC_INSIDE_KERNEL;
+static const u32   DGST_POS0      = 3;
+static const u32   DGST_POS1      = 4;
+static const u32   DGST_POS2      = 2;
+static const u32   DGST_POS3      = 1;
+static const u32   DGST_SIZE      = DGST_SIZE_4_5;
+static const u32   HASH_CATEGORY  = HASH_CATEGORY_RAW_HASH_SALTED;
+static const char *HASH_NAME      = "sha1(sha1($salt.$pass.$salt))";
+static const u64   KERN_TYPE      = 5000;
+static const u32   OPTI_TYPE      = OPTI_TYPE_ZERO_BYTE
+                                  | OPTI_TYPE_PRECOMPUTE_INIT
+                                  | OPTI_TYPE_EARLY_SKIP;
+static const u64   OPTS_TYPE      = OPTS_TYPE_PT_GENERATE_LE;
+static const u32   SALT_TYPE      = SALT_TYPE_GENERIC;
+static const char *ST_PASS        = "hashcat";
+static const char *ST_HASH        = "05ac0c544060af48f993f9c3cdf2fc03937ea35b:232725102020";
+
+u32         module_attack_exec    (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ATTACK_EXEC;     }
+u32         module_dgst_pos0      (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS0;       }
+u32         module_dgst_pos1      (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS1;       }
+u32         module_dgst_pos2      (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS2;       }
+u32         module_dgst_pos3      (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS3;       }
+u32         module_dgst_size      (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_SIZE;       }
+u32         module_hash_category  (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_CATEGORY;   }
+const char *module_hash_name      (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_NAME;       }
+u64         module_kern_type      (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return KERN_TYPE;       }
+u32         module_opti_type      (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTI_TYPE;       }
+u64         module_opts_type      (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTS_TYPE;       }
+u32         module_salt_type      (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return SALT_TYPE;       }
+const char *module_st_hash        (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_HASH;         }
+const char *module_st_pass        (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_PASS;         }
+
+int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED void *digest_buf, MAYBE_UNUSED salt_t *salt, MAYBE_UNUSED void *esalt_buf, MAYBE_UNUSED void *hook_salt_buf, MAYBE_UNUSED hashinfo_t *hash_info, const char *line_buf, MAYBE_UNUSED const int line_len)
+{
+  u32 *digest = (u32 *) digest_buf;
+
+  token_t token;
+
+  token.token_cnt  = 2;
+
+  token.sep[0]     = hashconfig->separator;
+  token.len_min[0] = 40;
+  token.len_max[0] = 40;
+  token.attr[0]    = TOKEN_ATTR_VERIFY_LENGTH
+                   | TOKEN_ATTR_VERIFY_HEX;
+
+  token.len_min[1] = SALT_MIN;
+  token.len_max[1] = SALT_MAX;
+  token.attr[1]    = TOKEN_ATTR_VERIFY_LENGTH;
+
+  if (hashconfig->opts_type & OPTS_TYPE_ST_HEX)
+  {
+    token.len_min[1] *= 2;
+    token.len_max[1] *= 2;
+
+    token.attr[1] |= TOKEN_ATTR_VERIFY_HEX;
+  }
+
+  const int rc_tokenizer = input_tokenizer ((const u8 *) line_buf, line_len, &token);
+
+  if (rc_tokenizer != PARSER_OK) return (rc_tokenizer);
+
+  const u8 *hash_pos = token.buf[0];
+
+  digest[0] = hex_to_u32 (hash_pos +  0);
+  digest[1] = hex_to_u32 (hash_pos +  8);
+  digest[2] = hex_to_u32 (hash_pos + 16);
+  digest[3] = hex_to_u32 (hash_pos + 24);
+  digest[4] = hex_to_u32 (hash_pos + 32);
+
+  digest[0] = byte_swap_32 (digest[0]);
+  digest[1] = byte_swap_32 (digest[1]);
+  digest[2] = byte_swap_32 (digest[2]);
+  digest[3] = byte_swap_32 (digest[3]);
+  digest[4] = byte_swap_32 (digest[4]);
+
+  if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+  {
+    digest[0] -= SHA1M_A;
+    digest[1] -= SHA1M_B;
+    digest[2] -= SHA1M_C;
+    digest[3] -= SHA1M_D;
+    digest[4] -= SHA1M_E;
+  }
+
+  const u8 *salt_pos = token.buf[1];
+  const int salt_len = token.len[1];
+
+  const bool parse_rc = generic_salt_decode (hashconfig, salt_pos, salt_len, (u8 *) salt->salt_buf, (int *) &salt->salt_len);
+
+  if (parse_rc == false) return (PARSER_SALT_LENGTH);
+
+  return (PARSER_OK);
+}
+
+int module_hash_encode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const void *digest_buf, MAYBE_UNUSED const salt_t *salt, MAYBE_UNUSED const void *esalt_buf, MAYBE_UNUSED const void *hook_salt_buf, MAYBE_UNUSED const hashinfo_t *hash_info, char *line_buf, MAYBE_UNUSED const int line_size)
+{
+  const u32 *digest = (const u32 *) digest_buf;
+
+  // we can not change anything in the original buffer, otherwise destroying sorting
+  // therefore create some local buffer
+
+  u32 tmp[5];
+
+  tmp[0] = digest[0];
+  tmp[1] = digest[1];
+  tmp[2] = digest[2];
+  tmp[3] = digest[3];
+  tmp[4] = digest[4];
+
+  if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+  {
+    tmp[0] += SHA1M_A;
+    tmp[1] += SHA1M_B;
+    tmp[2] += SHA1M_C;
+    tmp[3] += SHA1M_D;
+    tmp[4] += SHA1M_E;
+  }
+
+  tmp[0] = byte_swap_32 (tmp[0]);
+  tmp[1] = byte_swap_32 (tmp[1]);
+  tmp[2] = byte_swap_32 (tmp[2]);
+  tmp[3] = byte_swap_32 (tmp[3]);
+  tmp[4] = byte_swap_32 (tmp[4]);
+
+  u8 *out_buf = (u8 *) line_buf;
+
+  int out_len = 0;
+
+  u32_to_hex (tmp[0], out_buf + out_len); out_len += 8;
+  u32_to_hex (tmp[1], out_buf + out_len); out_len += 8;
+  u32_to_hex (tmp[2], out_buf + out_len); out_len += 8;
+  u32_to_hex (tmp[3], out_buf + out_len); out_len += 8;
+  u32_to_hex (tmp[4], out_buf + out_len); out_len += 8;
+
+  out_buf[out_len] = hashconfig->separator;
+
+  out_len += 1;
+
+  out_len += generic_salt_encode (hashconfig, (const u8 *) salt->salt_buf, (const int) salt->salt_len, out_buf + out_len);
+
+  return out_len;
+}
+
+void module_init (module_ctx_t *module_ctx)
+{
+  module_ctx->module_context_size             = MODULE_CONTEXT_SIZE_CURRENT;
+  module_ctx->module_interface_version        = MODULE_INTERFACE_VERSION_CURRENT;
+
+  module_ctx->module_attack_exec              = module_attack_exec;
+  module_ctx->module_benchmark_esalt          = MODULE_DEFAULT;
+  module_ctx->module_benchmark_hook_salt      = MODULE_DEFAULT;
+  module_ctx->module_benchmark_mask           = MODULE_DEFAULT;
+  module_ctx->module_benchmark_salt           = MODULE_DEFAULT;
+  module_ctx->module_build_plain_postprocess  = MODULE_DEFAULT;
+  module_ctx->module_deep_comp_kernel         = MODULE_DEFAULT;
+  module_ctx->module_dgst_pos0                = module_dgst_pos0;
+  module_ctx->module_dgst_pos1                = module_dgst_pos1;
+  module_ctx->module_dgst_pos2                = module_dgst_pos2;
+  module_ctx->module_dgst_pos3                = module_dgst_pos3;
+  module_ctx->module_dgst_size                = module_dgst_size;
+  module_ctx->module_dictstat_disable         = MODULE_DEFAULT;
+  module_ctx->module_esalt_size               = MODULE_DEFAULT;
+  module_ctx->module_extra_buffer_size        = MODULE_DEFAULT;
+  module_ctx->module_extra_tmp_size           = MODULE_DEFAULT;
+  module_ctx->module_forced_outfile_format    = MODULE_DEFAULT;
+  module_ctx->module_hash_binary_count        = MODULE_DEFAULT;
+  module_ctx->module_hash_binary_parse        = MODULE_DEFAULT;
+  module_ctx->module_hash_binary_save         = MODULE_DEFAULT;
+  module_ctx->module_hash_decode_potfile      = MODULE_DEFAULT;
+  module_ctx->module_hash_decode_zero_hash    = MODULE_DEFAULT;
+  module_ctx->module_hash_decode              = module_hash_decode;
+  module_ctx->module_hash_encode_status       = MODULE_DEFAULT;
+  module_ctx->module_hash_encode_potfile      = MODULE_DEFAULT;
+  module_ctx->module_hash_encode              = module_hash_encode;
+  module_ctx->module_hash_init_selftest       = MODULE_DEFAULT;
+  module_ctx->module_hash_mode                = MODULE_DEFAULT;
+  module_ctx->module_hash_category            = module_hash_category;
+  module_ctx->module_hash_name                = module_hash_name;
+  module_ctx->module_hashes_count_min         = MODULE_DEFAULT;
+  module_ctx->module_hashes_count_max         = MODULE_DEFAULT;
+  module_ctx->module_hlfmt_disable            = MODULE_DEFAULT;
+  module_ctx->module_hook_extra_param_size    = MODULE_DEFAULT;
+  module_ctx->module_hook_extra_param_init    = MODULE_DEFAULT;
+  module_ctx->module_hook_extra_param_term    = MODULE_DEFAULT;
+  module_ctx->module_hook12                   = MODULE_DEFAULT;
+  module_ctx->module_hook23                   = MODULE_DEFAULT;
+  module_ctx->module_hook_salt_size           = MODULE_DEFAULT;
+  module_ctx->module_hook_size                = MODULE_DEFAULT;
+  module_ctx->module_jit_build_options        = MODULE_DEFAULT;
+  module_ctx->module_jit_cache_disable        = MODULE_DEFAULT;
+  module_ctx->module_kernel_accel_max         = MODULE_DEFAULT;
+  module_ctx->module_kernel_accel_min         = MODULE_DEFAULT;
+  module_ctx->module_kernel_loops_max         = MODULE_DEFAULT;
+  module_ctx->module_kernel_loops_min         = MODULE_DEFAULT;
+  module_ctx->module_kernel_threads_max       = MODULE_DEFAULT;
+  module_ctx->module_kernel_threads_min       = MODULE_DEFAULT;
+  module_ctx->module_kern_type                = module_kern_type;
+  module_ctx->module_kern_type_dynamic        = MODULE_DEFAULT;
+  module_ctx->module_opti_type                = module_opti_type;
+  module_ctx->module_opts_type                = module_opts_type;
+  module_ctx->module_outfile_check_disable    = MODULE_DEFAULT;
+  module_ctx->module_outfile_check_nocomp     = MODULE_DEFAULT;
+  module_ctx->module_potfile_custom_check     = MODULE_DEFAULT;
+  module_ctx->module_potfile_disable          = MODULE_DEFAULT;
+  module_ctx->module_potfile_keep_all_hashes  = MODULE_DEFAULT;
+  module_ctx->module_pwdump_column            = MODULE_DEFAULT;
+  module_ctx->module_pw_max                   = MODULE_DEFAULT;
+  module_ctx->module_pw_min                   = MODULE_DEFAULT;
+  module_ctx->module_salt_max                 = MODULE_DEFAULT;
+  module_ctx->module_salt_min                 = MODULE_DEFAULT;
+  module_ctx->module_salt_type                = module_salt_type;
+  module_ctx->module_separator                = MODULE_DEFAULT;
+  module_ctx->module_st_hash                  = module_st_hash;
+  module_ctx->module_st_pass                  = module_st_pass;
+  module_ctx->module_tmp_size                 = MODULE_DEFAULT;
+  module_ctx->module_unstable_warning         = MODULE_DEFAULT;
+  module_ctx->module_warmup_disable           = MODULE_DEFAULT;
+}
diff --git a/tools/test_modules/m05000.pm b/tools/test_modules/m05000.pm
new file mode 100644
index 000000000..84ea18eca
--- /dev/null
+++ b/tools/test_modules/m05000.pm
@@ -0,0 +1,44 @@
+#!/usr/bin/env perl
+
+##
+## Author......: See docs/credits.txt
+## License.....: MIT
+##
+
+use strict;
+use warnings;
+
+use Digest::SHA qw (sha1_hex);
+
+sub module_constraints { [[0, 256], [0, 127], [0, 27], [0, 27], [0, 27]] }
+
+sub module_generate_hash
+{
+  my $word = shift;
+  my $salt = shift;
+
+  my $digest = sha1_hex (sha1_hex ($salt . $word . $salt));
+
+  my $hash = sprintf ("%s:%s", $digest, $salt);
+
+  return $hash;
+}
+
+sub module_verify_hash
+{
+  my $line = shift;
+
+  my ($hash, $salt, $word) = split (':', $line);
+
+  return unless defined $hash;
+  return unless defined $salt;
+  return unless defined $word;
+
+  my $word_packed = pack_if_HEX_notation ($word);
+
+  my $new_hash = module_generate_hash ($word_packed, $salt);
+
+  return ($new_hash, $word);
+}
+
+1;