hashcat/nv/m05000_a3.cu

/**
 * Author......: Jens Steube <jens.steube@gmail.com>
 * License.....: MIT
 */

#define _KECCAK_

#include "include/constants.h"
#include "include/kernel_vendor.h"

#ifdef  VLIW1
#define VECT_SIZE1
#endif

#ifdef  VLIW2
#define VECT_SIZE1
#endif

#define DGST_R0 2
#define DGST_R1 3
#define DGST_R2 4
#define DGST_R3 5

#include "include/kernel_functions.c"
#include "types_nv.c"
#include "common_nv.c"

#ifdef  VECT_SIZE1
#define VECT_COMPARE_S "check_single_vect1_comp4.c"
#define VECT_COMPARE_M "check_multi_vect1_comp4.c"
#endif

#ifdef  VECT_SIZE2
#define VECT_COMPARE_S "check_single_vect2_comp4.c"
#define VECT_COMPARE_M "check_multi_vect2_comp4.c"
#endif

#ifdef  VECT_SIZE4
#define VECT_COMPARE_S "check_single_vect4_comp4.c"
#define VECT_COMPARE_M "check_multi_vect4_comp4.c"
#endif

#ifndef KECCAK_ROUNDS
#define KECCAK_ROUNDS 24
#endif

#define Theta1(s) (st[0 + s] ^ st[5 + s] ^ st[10 + s] ^ st[15 + s] ^ st[20 + s])

#define Theta2(s)               \
{                               \
  st[ 0 + s] ^= t;              \
  st[ 5 + s] ^= t;              \
  st[10 + s] ^= t;              \
  st[15 + s] ^= t;              \
  st[20 + s] ^= t;              \
}

#define Rho_Pi(s)               \
{                               \
  u32 j = keccakf_piln[s];     \
  u32 k = keccakf_rotc[s];     \
  bc0 = st[j];                  \
  st[j] = rotl64 (t, k);        \
  t = bc0;                      \
}

#define Chi(s)                  \
{                               \
  bc0 = st[0 + s];              \
  bc1 = st[1 + s];              \
  bc2 = st[2 + s];              \
  bc3 = st[3 + s];              \
  bc4 = st[4 + s];              \
  st[0 + s] ^= ~bc1 & bc2;      \
  st[1 + s] ^= ~bc2 & bc3;      \
  st[2 + s] ^= ~bc3 & bc4;      \
  st[3 + s] ^= ~bc4 & bc0;      \
  st[4 + s] ^= ~bc0 & bc1;      \
}

__device__ __constant__ bf_t c_bfs[1024];

__device__ static void m05000m (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], const u32 pw_len, const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 bfs_cnt, const u32 digests_cnt, const u32 digests_offset)
{
  /**
   * modifier
   */

  const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
  const u32 lid = threadIdx.x;

  /**
   * constants
   */

  const u64 keccakf_rndc[24] =
  {
    0x0000000000000001, 0x0000000000008082, 0x800000000000808a,
    0x8000000080008000, 0x000000000000808b, 0x0000000080000001,
    0x8000000080008081, 0x8000000000008009, 0x000000000000008a,
    0x0000000000000088, 0x0000000080008009, 0x000000008000000a,
    0x000000008000808b, 0x800000000000008b, 0x8000000000008089,
    0x8000000000008003, 0x8000000000008002, 0x8000000000000080,
    0x000000000000800a, 0x800000008000000a, 0x8000000080008081,
    0x8000000000008080, 0x0000000080000001, 0x8000000080008008
  };

  const u32 keccakf_rotc[24] =
  {
     1,  3,  6, 10, 15, 21, 28, 36, 45, 55,  2, 14,
    27, 41, 56,  8, 25, 43, 62, 18, 39, 61, 20, 44
  };

  const u32 keccakf_piln[24] =
  {
    10,  7, 11, 17, 18,  3,  5, 16,  8, 21, 24,  4,
    15, 23, 19, 13, 12,  2, 20, 14, 22,  9,  6,  1
  };

  /**
   * 0x80 keccak, very special
   */

  const u32 mdlen = salt_bufs[salt_pos].keccak_mdlen;

  const u32 rsiz = 200 - (2 * mdlen);

  const u32 add80w = (rsiz - 1) / 8;

  /**
   * loop
   */

  u32x w0l = w0[0];

  for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
  {
    const u32 w0r = c_bfs[il_pos].i;

    w0[0] = w0l | w0r;

    u64x st[25];

    st[ 0] = (u64x) (w0[0]) | (u64x) (w0[1]) << 32;
    st[ 1] = (u64x) (w0[2]) | (u64x) (w0[3]) << 32;
    st[ 2] = (u64x) (w1[0]) | (u64x) (w1[1]) << 32;
    st[ 3] = (u64x) (w1[2]) | (u64x) (w1[3]) << 32;
    st[ 4] = (u64x) (w2[0]) | (u64x) (w2[1]) << 32;
    st[ 5] = (u64x) (w2[2]) | (u64x) (w2[3]) << 32;
    st[ 6] = (u64x) (w3[0]) | (u64x) (w3[1]) << 32;
    st[ 7] = (u64x) (w3[2]) | (u64x) (w3[3]) << 32;
    st[ 8] = 0;
    st[ 9] = 0;
    st[10] = 0;
    st[11] = 0;
    st[12] = 0;
    st[13] = 0;
    st[14] = 0;
    st[15] = 0;
    st[16] = 0;
    st[17] = 0;
    st[18] = 0;
    st[19] = 0;
    st[20] = 0;
    st[21] = 0;
    st[22] = 0;
    st[23] = 0;
    st[24] = 0;

    st[add80w] |= 0x8000000000000000;

    int round;

    for (round = 0; round < KECCAK_ROUNDS; round++)
    {
      // Theta

      u64x bc0 = Theta1 (0);
      u64x bc1 = Theta1 (1);
      u64x bc2 = Theta1 (2);
      u64x bc3 = Theta1 (3);
      u64x bc4 = Theta1 (4);

      u64x t;

      t = bc4 ^ rotl64 (bc1, 1); Theta2 (0);
      t = bc0 ^ rotl64 (bc2, 1); Theta2 (1);
      t = bc1 ^ rotl64 (bc3, 1); Theta2 (2);
      t = bc2 ^ rotl64 (bc4, 1); Theta2 (3);
      t = bc3 ^ rotl64 (bc0, 1); Theta2 (4);

      // Rho Pi

      t = st[1];

      Rho_Pi (0);
      Rho_Pi (1);
      Rho_Pi (2);
      Rho_Pi (3);
      Rho_Pi (4);
      Rho_Pi (5);
      Rho_Pi (6);
      Rho_Pi (7);
      Rho_Pi (8);
      Rho_Pi (9);
      Rho_Pi (10);
      Rho_Pi (11);
      Rho_Pi (12);
      Rho_Pi (13);
      Rho_Pi (14);
      Rho_Pi (15);
      Rho_Pi (16);
      Rho_Pi (17);
      Rho_Pi (18);
      Rho_Pi (19);
      Rho_Pi (20);
      Rho_Pi (21);
      Rho_Pi (22);
      Rho_Pi (23);

      //  Chi

      Chi (0);
      Chi (5);
      Chi (10);
      Chi (15);
      Chi (20);

      //  Iota

      st[0] ^= keccakf_rndc[round];
    }

    const u32x r0 = l32_from_64 (st[1]);
    const u32x r1 = h32_from_64 (st[1]);
    const u32x r2 = l32_from_64 (st[2]);
    const u32x r3 = h32_from_64 (st[2]);

    #include VECT_COMPARE_M
  }
}

__device__ static void m05000s (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], const u32 pw_len, const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 bfs_cnt, const u32 digests_cnt, const u32 digests_offset)
{
  /**
   * modifier
   */

  const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
  const u32 lid = threadIdx.x;

  /**
   * 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]
  };

  /**
   * constants
   */

  const u64 keccakf_rndc[24] =
  {
    0x0000000000000001, 0x0000000000008082, 0x800000000000808a,
    0x8000000080008000, 0x000000000000808b, 0x0000000080000001,
    0x8000000080008081, 0x8000000000008009, 0x000000000000008a,
    0x0000000000000088, 0x0000000080008009, 0x000000008000000a,
    0x000000008000808b, 0x800000000000008b, 0x8000000000008089,
    0x8000000000008003, 0x8000000000008002, 0x8000000000000080,
    0x000000000000800a, 0x800000008000000a, 0x8000000080008081,
    0x8000000000008080, 0x0000000080000001, 0x8000000080008008
  };

  const u32 keccakf_rotc[24] =
  {
     1,  3,  6, 10, 15, 21, 28, 36, 45, 55,  2, 14,
    27, 41, 56,  8, 25, 43, 62, 18, 39, 61, 20, 44
  };

  const u32 keccakf_piln[24] =
  {
    10,  7, 11, 17, 18,  3,  5, 16,  8, 21, 24,  4,
    15, 23, 19, 13, 12,  2, 20, 14, 22,  9,  6,  1
  };

  /**
   * 0x80 keccak, very special
   */

  const u32 mdlen = salt_bufs[salt_pos].keccak_mdlen;

  const u32 rsiz = 200 - (2 * mdlen);

  const u32 add80w = (rsiz - 1) / 8;

  /**
   * loop
   */

  u32x w0l = w0[0];

  for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
  {
    const u32 w0r = c_bfs[il_pos].i;

    w0[0] = w0l | w0r;

    u64x st[25];

    st[ 0] = (u64x) (w0[0]) | (u64x) (w0[1]) << 32;
    st[ 1] = (u64x) (w0[2]) | (u64x) (w0[3]) << 32;
    st[ 2] = (u64x) (w1[0]) | (u64x) (w1[1]) << 32;
    st[ 3] = (u64x) (w1[2]) | (u64x) (w1[3]) << 32;
    st[ 4] = (u64x) (w2[0]) | (u64x) (w2[1]) << 32;
    st[ 5] = (u64x) (w2[2]) | (u64x) (w2[3]) << 32;
    st[ 6] = (u64x) (w3[0]) | (u64x) (w3[1]) << 32;
    st[ 7] = (u64x) (w3[2]) | (u64x) (w3[3]) << 32;
    st[ 8] = 0;
    st[ 9] = 0;
    st[10] = 0;
    st[11] = 0;
    st[12] = 0;
    st[13] = 0;
    st[14] = 0;
    st[15] = 0;
    st[16] = 0;
    st[17] = 0;
    st[18] = 0;
    st[19] = 0;
    st[20] = 0;
    st[21] = 0;
    st[22] = 0;
    st[23] = 0;
    st[24] = 0;

    st[add80w] |= 0x8000000000000000;

    int round;

    for (round = 0; round < KECCAK_ROUNDS; round++)
    {
      // Theta

      u64x bc0 = Theta1 (0);
      u64x bc1 = Theta1 (1);
      u64x bc2 = Theta1 (2);
      u64x bc3 = Theta1 (3);
      u64x bc4 = Theta1 (4);

      u64x t;

      t = bc4 ^ rotl64 (bc1, 1); Theta2 (0);
      t = bc0 ^ rotl64 (bc2, 1); Theta2 (1);
      t = bc1 ^ rotl64 (bc3, 1); Theta2 (2);
      t = bc2 ^ rotl64 (bc4, 1); Theta2 (3);
      t = bc3 ^ rotl64 (bc0, 1); Theta2 (4);

      // Rho Pi

      t = st[1];

      Rho_Pi (0);
      Rho_Pi (1);
      Rho_Pi (2);
      Rho_Pi (3);
      Rho_Pi (4);
      Rho_Pi (5);
      Rho_Pi (6);
      Rho_Pi (7);
      Rho_Pi (8);
      Rho_Pi (9);
      Rho_Pi (10);
      Rho_Pi (11);
      Rho_Pi (12);
      Rho_Pi (13);
      Rho_Pi (14);
      Rho_Pi (15);
      Rho_Pi (16);
      Rho_Pi (17);
      Rho_Pi (18);
      Rho_Pi (19);
      Rho_Pi (20);
      Rho_Pi (21);
      Rho_Pi (22);
      Rho_Pi (23);

      //  Chi

      Chi (0);
      Chi (5);
      Chi (10);
      Chi (15);
      Chi (20);

      //  Iota

      st[0] ^= keccakf_rndc[round];
    }

    const u32x r0 = l32_from_64 (st[1]);
    const u32x r1 = h32_from_64 (st[1]);
    const u32x r2 = l32_from_64 (st[2]);
    const u32x r3 = h32_from_64 (st[2]);

    #include VECT_COMPARE_S
  }
}

extern "C" __global__ void __launch_bounds__ (256, 1) m05000_m04 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
  /**
   * base
   */

  const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;

  if (gid >= gid_max) return;

  u32x 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];

  u32x w1[4];

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

  u32x w2[4];

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

  u32x w3[4];

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

  const u32 pw_len = pws[gid].pw_len;

  /**
   * 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_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
}

extern "C" __global__ void __launch_bounds__ (256, 1) m05000_m08 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
  /**
   * base
   */

  const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;

  if (gid >= gid_max) return;

  u32x 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];

  u32x 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];

  u32x w2[4];

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

  u32x w3[4];

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

  const u32 pw_len = pws[gid].pw_len;

  /**
   * 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_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
}

extern "C" __global__ void __launch_bounds__ (256, 1) m05000_m16 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
  /**
   * base
   */

  const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;

  if (gid >= gid_max) return;

  u32x 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];

  u32x 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];

  u32x 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];

  u32x 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
   */

  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_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
}

extern "C" __global__ void __launch_bounds__ (256, 1) m05000_s04 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
  /**
   * base
   */

  const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;

  if (gid >= gid_max) return;

  u32x 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];

  u32x w1[4];

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

  u32x w2[4];

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

  u32x w3[4];

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

  const u32 pw_len = pws[gid].pw_len;

  /**
   * 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_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
}

extern "C" __global__ void __launch_bounds__ (256, 1) m05000_s08 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
  /**
   * base
   */

  const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;

  if (gid >= gid_max) return;

  u32x 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];

  u32x 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];

  u32x w2[4];

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

  u32x w3[4];

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

  const u32 pw_len = pws[gid].pw_len;

  /**
   * 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_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
}

extern "C" __global__ void __launch_bounds__ (256, 1) m05000_s16 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
  /**
   * base
   */

  const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;

  if (gid >= gid_max) return;

  u32x 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];

  u32x 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];

  u32x 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];

  u32x 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
   */

  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_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
}