hashcat/OpenCL/m08400_a3-optimized.cl

/**
 * Author......: See docs/credits.txt
 * License.....: MIT
 */

#define NEW_SIMD_CODE

#include "inc_vendor.cl"
#include "inc_hash_constants.h"
#include "inc_hash_functions.cl"
#include "inc_types.cl"
#include "inc_common.cl"
#include "inc_simd.cl"
#include "inc_hash_sha1.cl"

#if   VECT_SIZE == 1
#define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i)])
#elif VECT_SIZE == 2
#define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
#elif VECT_SIZE == 4
#define uint_to_hex_lower8_le(i) (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) (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) (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 m08400m (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_len, __global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, __local 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];

  salt_buf0[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
  salt_buf0[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
  salt_buf0[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
  salt_buf0[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
  salt_buf1[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
  salt_buf1[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
  salt_buf1[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
  salt_buf1[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
  salt_buf2[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
  salt_buf2[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
  salt_buf2[2] = 0;
  salt_buf2[3] = 0;

  const u32 salt_len = salt_bufs[salt_pos].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 w0_t[4];
    u32x w1_t[4];
    u32x w2_t[4];
    u32x w3_t[4];

    w0_t[0] = w0lr;
    w0_t[1] = w0[1];
    w0_t[2] = w0[2];
    w0_t[3] = w0[3];
    w1_t[0] = w1[0];
    w1_t[1] = w1[1];
    w1_t[2] = w1[2];
    w1_t[3] = w1[3];
    w2_t[0] = w2[0];
    w2_t[1] = w2[1];
    w2_t[2] = w2[2];
    w2_t[3] = w2[3];
    w3_t[0] = w3[0];
    w3_t[1] = w3[1];
    w3_t[2] = 0;
    w3_t[3] = pw_len * 8;

    /**
     * SHA1
     */

    u32x digest[5];

    digest[0] = SHA1M_A;
    digest[1] = SHA1M_B;
    digest[2] = SHA1M_C;
    digest[3] = SHA1M_D;
    digest[4] = SHA1M_E;

    sha1_transform_vector (w0_t, w1_t, w2_t, w3_t, digest);

    u32x a;
    u32x b;
    u32x c;
    u32x d;
    u32x e;

    a = digest[0];
    b = digest[1];
    c = digest[2];
    d = digest[3];
    e = digest[4];

    w0_t[0] = salt_buf0[0];
    w0_t[1] = salt_buf0[1];
    w0_t[2] = salt_buf0[2];
    w0_t[3] = salt_buf0[3];
    w1_t[0] = salt_buf1[0];
    w1_t[1] = salt_buf1[1];
    w1_t[2] = salt_buf1[2];
    w1_t[3] = salt_buf1[3];
    w2_t[0] = salt_buf2[0];
    w2_t[1] = salt_buf2[1];
    w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) <<  0
            | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
    w2_t[3] = uint_to_hex_lower8_le ((a >>  0) & 255) <<  0
            | uint_to_hex_lower8_le ((a >>  8) & 255) << 16;
    w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) <<  0
            | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
    w3_t[1] = uint_to_hex_lower8_le ((b >>  0) & 255) <<  0
            | uint_to_hex_lower8_le ((b >>  8) & 255) << 16;
    w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) <<  0
            | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
    w3_t[3] = uint_to_hex_lower8_le ((c >>  0) & 255) <<  0
            | uint_to_hex_lower8_le ((c >>  8) & 255) << 16;

    digest[0] = SHA1M_A;
    digest[1] = SHA1M_B;
    digest[2] = SHA1M_C;
    digest[3] = SHA1M_D;
    digest[4] = SHA1M_E;

    sha1_transform_vector (w0_t, w1_t, w2_t, w3_t, digest);

    w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) <<  0
            | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
    w0_t[1] = uint_to_hex_lower8_le ((d >>  0) & 255) <<  0
            | uint_to_hex_lower8_le ((d >>  8) & 255) << 16;
    w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) <<  0
            | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
    w0_t[3] = uint_to_hex_lower8_le ((e >>  0) & 255) <<  0
            | uint_to_hex_lower8_le ((e >>  8) & 255) << 16;
    w1_t[0] = 0x80000000;
    w1_t[1] = 0;
    w1_t[2] = 0;
    w1_t[3] = 0;
    w2_t[0] = 0;
    w2_t[1] = 0;
    w2_t[2] = 0;
    w2_t[3] = 0;
    w3_t[0] = 0;
    w3_t[1] = 0;
    w3_t[2] = 0;
    w3_t[3] = (salt_len + 40) * 8;

    sha1_transform_vector (w0_t, w1_t, w2_t, w3_t, digest);

    a = digest[0];
    b = digest[1];
    c = digest[2];
    d = digest[3];
    e = digest[4];

    w0_t[0] = salt_buf0[0];
    w0_t[1] = salt_buf0[1];
    w0_t[2] = salt_buf0[2];
    w0_t[3] = salt_buf0[3];
    w1_t[0] = salt_buf1[0];
    w1_t[1] = salt_buf1[1];
    w1_t[2] = salt_buf1[2];
    w1_t[3] = salt_buf1[3];
    w2_t[0] = salt_buf2[0];
    w2_t[1] = salt_buf2[1];
    w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) <<  0
            | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
    w2_t[3] = uint_to_hex_lower8_le ((a >>  0) & 255) <<  0
            | uint_to_hex_lower8_le ((a >>  8) & 255) << 16;
    w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) <<  0
            | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
    w3_t[1] = uint_to_hex_lower8_le ((b >>  0) & 255) <<  0
            | uint_to_hex_lower8_le ((b >>  8) & 255) << 16;
    w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) <<  0
            | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
    w3_t[3] = uint_to_hex_lower8_le ((c >>  0) & 255) <<  0
            | uint_to_hex_lower8_le ((c >>  8) & 255) << 16;

    digest[0] = SHA1M_A;
    digest[1] = SHA1M_B;
    digest[2] = SHA1M_C;
    digest[3] = SHA1M_D;
    digest[4] = SHA1M_E;

    sha1_transform_vector (w0_t, w1_t, w2_t, w3_t, digest);

    w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) <<  0
            | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
    w0_t[1] = uint_to_hex_lower8_le ((d >>  0) & 255) <<  0
            | uint_to_hex_lower8_le ((d >>  8) & 255) << 16;
    w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) <<  0
            | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
    w0_t[3] = uint_to_hex_lower8_le ((e >>  0) & 255) <<  0
            | uint_to_hex_lower8_le ((e >>  8) & 255) << 16;
    w1_t[0] = 0x80000000;
    w1_t[1] = 0;
    w1_t[2] = 0;
    w1_t[3] = 0;
    w2_t[0] = 0;
    w2_t[1] = 0;
    w2_t[2] = 0;
    w2_t[3] = 0;
    w3_t[0] = 0;
    w3_t[1] = 0;
    w3_t[2] = 0;
    w3_t[3] = (salt_len + 40) * 8;

    sha1_transform_vector (w0_t, w1_t, w2_t, w3_t, digest);

    COMPARE_M_SIMD (digest[3], digest[4], digest[2], digest[1]);
  }
}

DECLSPEC void m08400s (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_len, __global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, __local 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];

  salt_buf0[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
  salt_buf0[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
  salt_buf0[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
  salt_buf0[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
  salt_buf1[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
  salt_buf1[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
  salt_buf1[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
  salt_buf1[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
  salt_buf2[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
  salt_buf2[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
  salt_buf2[2] = 0;
  salt_buf2[3] = 0;

  const u32 salt_len = salt_bufs[salt_pos].salt_len;

  /**
   * digest
   */

  const u32 search[4] =
  {
    digests_buf[digests_offset].digest_buf[DGST_R0],
    digests_buf[digests_offset].digest_buf[DGST_R1],
    digests_buf[digests_offset].digest_buf[DGST_R2],
    digests_buf[digests_offset].digest_buf[DGST_R3]
  };

  /**
   * loop
   */

  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 w0_t[4];
    u32x w1_t[4];
    u32x w2_t[4];
    u32x w3_t[4];

    w0_t[0] = w0lr;
    w0_t[1] = w0[1];
    w0_t[2] = w0[2];
    w0_t[3] = w0[3];
    w1_t[0] = w1[0];
    w1_t[1] = w1[1];
    w1_t[2] = w1[2];
    w1_t[3] = w1[3];
    w2_t[0] = w2[0];
    w2_t[1] = w2[1];
    w2_t[2] = w2[2];
    w2_t[3] = w2[3];
    w3_t[0] = w3[0];
    w3_t[1] = w3[1];
    w3_t[2] = 0;
    w3_t[3] = pw_len * 8;

    /**
     * SHA1
     */

    u32x digest[5];

    digest[0] = SHA1M_A;
    digest[1] = SHA1M_B;
    digest[2] = SHA1M_C;
    digest[3] = SHA1M_D;
    digest[4] = SHA1M_E;

    sha1_transform_vector (w0_t, w1_t, w2_t, w3_t, digest);

    u32x a;
    u32x b;
    u32x c;
    u32x d;
    u32x e;

    a = digest[0];
    b = digest[1];
    c = digest[2];
    d = digest[3];
    e = digest[4];

    w0_t[0] = salt_buf0[0];
    w0_t[1] = salt_buf0[1];
    w0_t[2] = salt_buf0[2];
    w0_t[3] = salt_buf0[3];
    w1_t[0] = salt_buf1[0];
    w1_t[1] = salt_buf1[1];
    w1_t[2] = salt_buf1[2];
    w1_t[3] = salt_buf1[3];
    w2_t[0] = salt_buf2[0];
    w2_t[1] = salt_buf2[1];
    w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) <<  0
            | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
    w2_t[3] = uint_to_hex_lower8_le ((a >>  0) & 255) <<  0
            | uint_to_hex_lower8_le ((a >>  8) & 255) << 16;
    w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) <<  0
            | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
    w3_t[1] = uint_to_hex_lower8_le ((b >>  0) & 255) <<  0
            | uint_to_hex_lower8_le ((b >>  8) & 255) << 16;
    w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) <<  0
            | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
    w3_t[3] = uint_to_hex_lower8_le ((c >>  0) & 255) <<  0
            | uint_to_hex_lower8_le ((c >>  8) & 255) << 16;

    digest[0] = SHA1M_A;
    digest[1] = SHA1M_B;
    digest[2] = SHA1M_C;
    digest[3] = SHA1M_D;
    digest[4] = SHA1M_E;

    sha1_transform_vector (w0_t, w1_t, w2_t, w3_t, digest);

    w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) <<  0
            | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
    w0_t[1] = uint_to_hex_lower8_le ((d >>  0) & 255) <<  0
            | uint_to_hex_lower8_le ((d >>  8) & 255) << 16;
    w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) <<  0
            | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
    w0_t[3] = uint_to_hex_lower8_le ((e >>  0) & 255) <<  0
            | uint_to_hex_lower8_le ((e >>  8) & 255) << 16;
    w1_t[0] = 0x80000000;
    w1_t[1] = 0;
    w1_t[2] = 0;
    w1_t[3] = 0;
    w2_t[0] = 0;
    w2_t[1] = 0;
    w2_t[2] = 0;
    w2_t[3] = 0;
    w3_t[0] = 0;
    w3_t[1] = 0;
    w3_t[2] = 0;
    w3_t[3] = (salt_len + 40) * 8;

    sha1_transform_vector (w0_t, w1_t, w2_t, w3_t, digest);

    a = digest[0];
    b = digest[1];
    c = digest[2];
    d = digest[3];
    e = digest[4];

    w0_t[0] = salt_buf0[0];
    w0_t[1] = salt_buf0[1];
    w0_t[2] = salt_buf0[2];
    w0_t[3] = salt_buf0[3];
    w1_t[0] = salt_buf1[0];
    w1_t[1] = salt_buf1[1];
    w1_t[2] = salt_buf1[2];
    w1_t[3] = salt_buf1[3];
    w2_t[0] = salt_buf2[0];
    w2_t[1] = salt_buf2[1];
    w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) <<  0
            | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
    w2_t[3] = uint_to_hex_lower8_le ((a >>  0) & 255) <<  0
            | uint_to_hex_lower8_le ((a >>  8) & 255) << 16;
    w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) <<  0
            | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
    w3_t[1] = uint_to_hex_lower8_le ((b >>  0) & 255) <<  0
            | uint_to_hex_lower8_le ((b >>  8) & 255) << 16;
    w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) <<  0
            | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
    w3_t[3] = uint_to_hex_lower8_le ((c >>  0) & 255) <<  0
            | uint_to_hex_lower8_le ((c >>  8) & 255) << 16;

    digest[0] = SHA1M_A;
    digest[1] = SHA1M_B;
    digest[2] = SHA1M_C;
    digest[3] = SHA1M_D;
    digest[4] = SHA1M_E;

    sha1_transform_vector (w0_t, w1_t, w2_t, w3_t, digest);

    w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) <<  0
            | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
    w0_t[1] = uint_to_hex_lower8_le ((d >>  0) & 255) <<  0
            | uint_to_hex_lower8_le ((d >>  8) & 255) << 16;
    w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) <<  0
            | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
    w0_t[3] = uint_to_hex_lower8_le ((e >>  0) & 255) <<  0
            | uint_to_hex_lower8_le ((e >>  8) & 255) << 16;
    w1_t[0] = 0x80000000;
    w1_t[1] = 0;
    w1_t[2] = 0;
    w1_t[3] = 0;
    w2_t[0] = 0;
    w2_t[1] = 0;
    w2_t[2] = 0;
    w2_t[3] = 0;
    w3_t[0] = 0;
    w3_t[1] = 0;
    w3_t[2] = 0;
    w3_t[3] = (salt_len + 40) * 8;

    sha1_transform_vector (w0_t, w1_t, w2_t, w3_t, digest);

    COMPARE_S_SIMD (digest[3], digest[4], digest[2], digest[1]);
  }
}

__kernel void m08400_m04 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *ss, __global void *ess, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u64 gid_max)
{
  /**
   * modifier
   */

  const u64 gid = get_global_id (0);
  const u64 lid = get_local_id (0);
  const u64 lsz = get_local_size (0);

  /**
   * shared
   */

  __local 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;
  }

  barrier (CLK_LOCAL_MEM_FENCE);

  if (gid >= gid_max) return;

  /**
   * base
   */

  u32 w0[4];

  w0[0] = pws[gid].i[ 0];
  w0[1] = pws[gid].i[ 1];
  w0[2] = pws[gid].i[ 2];
  w0[3] = pws[gid].i[ 3];

  u32 w1[4];

  w1[0] = 0;
  w1[1] = 0;
  w1[2] = 0;
  w1[3] = 0;

  u32 w2[4];

  w2[0] = 0;
  w2[1] = 0;
  w2[2] = 0;
  w2[3] = 0;

  u32 w3[4];

  w3[0] = 0;
  w3[1] = 0;
  w3[2] = 0;
  w3[3] = 0;

  const u32 pw_len = pws[gid].pw_len;

  /**
   * main
   */

  m08400m (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, ss, ess, d_return_buf, d_scryptV0_buf, d_scryptV1_buf, d_scryptV2_buf, d_scryptV3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, l_bin2asc);
}

__kernel void m08400_m08 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *ss, __global void *ess, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u64 gid_max)
{
  /**
   * modifier
   */

  const u64 gid = get_global_id (0);
  const u64 lid = get_local_id (0);
  const u64 lsz = get_local_size (0);

  /**
   * shared
   */

  __local 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;
  }

  barrier (CLK_LOCAL_MEM_FENCE);

  if (gid >= gid_max) return;

  /**
   * base
   */

  u32 w0[4];

  w0[0] = pws[gid].i[ 0];
  w0[1] = pws[gid].i[ 1];
  w0[2] = pws[gid].i[ 2];
  w0[3] = pws[gid].i[ 3];

  u32 w1[4];

  w1[0] = pws[gid].i[ 4];
  w1[1] = pws[gid].i[ 5];
  w1[2] = pws[gid].i[ 6];
  w1[3] = pws[gid].i[ 7];

  u32 w2[4];

  w2[0] = 0;
  w2[1] = 0;
  w2[2] = 0;
  w2[3] = 0;

  u32 w3[4];

  w3[0] = 0;
  w3[1] = 0;
  w3[2] = 0;
  w3[3] = 0;

  const u32 pw_len = pws[gid].pw_len;

  /**
   * main
   */

  m08400m (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, ss, ess, d_return_buf, d_scryptV0_buf, d_scryptV1_buf, d_scryptV2_buf, d_scryptV3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, l_bin2asc);
}

__kernel void m08400_m16 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *ss, __global void *ess, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u64 gid_max)
{
  /**
   * modifier
   */

  const u64 gid = get_global_id (0);
  const u64 lid = get_local_id (0);
  const u64 lsz = get_local_size (0);

  /**
   * shared
   */

  __local 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;
  }

  barrier (CLK_LOCAL_MEM_FENCE);

  if (gid >= gid_max) return;

  /**
   * base
   */

  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] = 0;
  w3[3] = 0;

  const u32 pw_len = pws[gid].pw_len;

  /**
   * main
   */

  m08400m (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, ss, ess, d_return_buf, d_scryptV0_buf, d_scryptV1_buf, d_scryptV2_buf, d_scryptV3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, l_bin2asc);
}

__kernel void m08400_s04 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *ss, __global void *ess, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u64 gid_max)
{
  /**
   * modifier
   */

  const u64 gid = get_global_id (0);
  const u64 lid = get_local_id (0);
  const u64 lsz = get_local_size (0);

  /**
   * shared
   */

  __local 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;
  }

  barrier (CLK_LOCAL_MEM_FENCE);

  if (gid >= gid_max) return;

  /**
   * base
   */

  u32 w0[4];

  w0[0] = pws[gid].i[ 0];
  w0[1] = pws[gid].i[ 1];
  w0[2] = pws[gid].i[ 2];
  w0[3] = pws[gid].i[ 3];

  u32 w1[4];

  w1[0] = 0;
  w1[1] = 0;
  w1[2] = 0;
  w1[3] = 0;

  u32 w2[4];

  w2[0] = 0;
  w2[1] = 0;
  w2[2] = 0;
  w2[3] = 0;

  u32 w3[4];

  w3[0] = 0;
  w3[1] = 0;
  w3[2] = 0;
  w3[3] = 0;

  const u32 pw_len = pws[gid].pw_len;

  /**
   * main
   */

  m08400s (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, ss, ess, d_return_buf, d_scryptV0_buf, d_scryptV1_buf, d_scryptV2_buf, d_scryptV3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, l_bin2asc);
}

__kernel void m08400_s08 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *ss, __global void *ess, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u64 gid_max)
{
  /**
   * modifier
   */

  const u64 gid = get_global_id (0);
  const u64 lid = get_local_id (0);
  const u64 lsz = get_local_size (0);

  /**
   * shared
   */

  __local 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;
  }

  barrier (CLK_LOCAL_MEM_FENCE);

  if (gid >= gid_max) return;

  /**
   * base
   */

  u32 w0[4];

  w0[0] = pws[gid].i[ 0];
  w0[1] = pws[gid].i[ 1];
  w0[2] = pws[gid].i[ 2];
  w0[3] = pws[gid].i[ 3];

  u32 w1[4];

  w1[0] = pws[gid].i[ 4];
  w1[1] = pws[gid].i[ 5];
  w1[2] = pws[gid].i[ 6];
  w1[3] = pws[gid].i[ 7];

  u32 w2[4];

  w2[0] = 0;
  w2[1] = 0;
  w2[2] = 0;
  w2[3] = 0;

  u32 w3[4];

  w3[0] = 0;
  w3[1] = 0;
  w3[2] = 0;
  w3[3] = 0;

  const u32 pw_len = pws[gid].pw_len;

  /**
   * main
   */

  m08400s (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, ss, ess, d_return_buf, d_scryptV0_buf, d_scryptV1_buf, d_scryptV2_buf, d_scryptV3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, l_bin2asc);
}

__kernel void m08400_s16 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *ss, __global void *ess, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u64 gid_max)
{
  /**
   * modifier
   */

  const u64 gid = get_global_id (0);
  const u64 lid = get_local_id (0);
  const u64 lsz = get_local_size (0);

  /**
   * shared
   */

  __local 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;
  }

  barrier (CLK_LOCAL_MEM_FENCE);

  if (gid >= gid_max) return;

  /**
   * base
   */

  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] = 0;
  w3[3] = 0;

  const u32 pw_len = pws[gid].pw_len;

  /**
   * main
   */

  m08400s (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, ss, ess, d_return_buf, d_scryptV0_buf, d_scryptV1_buf, d_scryptV2_buf, d_scryptV3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, l_bin2asc);
}