/**
 * 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_blake2b.cl"
#endif

DECLSPEC void m00600m (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
{
  /**
   * modifier
   */

  const u64 gid = get_global_id (0);

  /**
   * loop
   */

  u32 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 w0x = w0l | w0r;

    u32x w0[4];
    u32x w1[4];
    u32x w2[4];
    u32x w3[4];

    w0[0] = w0x;
    w0[1] = w[ 1];
    w0[2] = w[ 2];
    w0[3] = w[ 3];
    w1[0] = w[ 4];
    w1[1] = w[ 5];
    w1[2] = w[ 6];
    w1[3] = w[ 7];
    w2[0] = w[ 8];
    w2[1] = w[ 9];
    w2[2] = w[10];
    w2[3] = w[11];
    w3[0] = w[12];
    w3[1] = w[13];
    w3[2] = w[14];
    w3[3] = w[15];

    u64x m[16];

    m[ 0] = hl32_to_64 (w0[1], w0[0]);
    m[ 1] = hl32_to_64 (w0[3], w0[2]);
    m[ 2] = hl32_to_64 (w1[1], w1[0]);
    m[ 3] = hl32_to_64 (w1[3], w1[2]);
    m[ 4] = hl32_to_64 (w2[1], w2[0]);
    m[ 5] = hl32_to_64 (w2[3], w2[2]);
    m[ 6] = hl32_to_64 (w3[1], w3[0]);
    m[ 7] = hl32_to_64 (w3[3], w3[2]);
    m[ 8] = 0;
    m[ 9] = 0;
    m[10] = 0;
    m[11] = 0;
    m[12] = 0;
    m[13] = 0;
    m[14] = 0;
    m[15] = 0;

    u64x h[8];

    h[0] = BLAKE2B_IV_00 ^ 0x01010040;
    h[1] = BLAKE2B_IV_01;
    h[2] = BLAKE2B_IV_02;
    h[3] = BLAKE2B_IV_03;
    h[4] = BLAKE2B_IV_04;
    h[5] = BLAKE2B_IV_05;
    h[6] = BLAKE2B_IV_06;
    h[7] = BLAKE2B_IV_07;

    blake2b_transform_vector (h, m, pw_len, BLAKE2B_FINAL);

    const u32x r0 = h32_from_64 (h[0]);
    const u32x r1 = l32_from_64 (h[0]);
    const u32x r2 = h32_from_64 (h[1]);
    const u32x r3 = l32_from_64 (h[1]);

    COMPARE_M_SIMD (r0, r1, r2, r3);
  }
}

DECLSPEC void m00600s (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
{
  /**
   * modifier
   */

  const u64 gid = get_global_id (0);

  /**
   * 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 = 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 w0x = w0l | w0r;

    u32x w0[4];
    u32x w1[4];
    u32x w2[4];
    u32x w3[4];

    w0[0] = w0x;
    w0[1] = w[ 1];
    w0[2] = w[ 2];
    w0[3] = w[ 3];
    w1[0] = w[ 4];
    w1[1] = w[ 5];
    w1[2] = w[ 6];
    w1[3] = w[ 7];
    w2[0] = w[ 8];
    w2[1] = w[ 9];
    w2[2] = w[10];
    w2[3] = w[11];
    w3[0] = w[12];
    w3[1] = w[13];
    w3[2] = w[14];
    w3[3] = w[15];

    u64x m[16];

    m[ 0] = hl32_to_64 (w0[1], w0[0]);
    m[ 1] = hl32_to_64 (w0[3], w0[2]);
    m[ 2] = hl32_to_64 (w1[1], w1[0]);
    m[ 3] = hl32_to_64 (w1[3], w1[2]);
    m[ 4] = hl32_to_64 (w2[1], w2[0]);
    m[ 5] = hl32_to_64 (w2[3], w2[2]);
    m[ 6] = hl32_to_64 (w3[1], w3[0]);
    m[ 7] = hl32_to_64 (w3[3], w3[2]);
    m[ 8] = 0;
    m[ 9] = 0;
    m[10] = 0;
    m[11] = 0;
    m[12] = 0;
    m[13] = 0;
    m[14] = 0;
    m[15] = 0;

    u64x h[8];

    h[0] = BLAKE2B_IV_00 ^ 0x01010040;
    h[1] = BLAKE2B_IV_01;
    h[2] = BLAKE2B_IV_02;
    h[3] = BLAKE2B_IV_03;
    h[4] = BLAKE2B_IV_04;
    h[5] = BLAKE2B_IV_05;
    h[6] = BLAKE2B_IV_06;
    h[7] = BLAKE2B_IV_07;

    blake2b_transform_vector (h, m, pw_len, BLAKE2B_FINAL);

    const u32x r0 = h32_from_64 (h[0]);
    const u32x r1 = l32_from_64 (h[0]);
    const u32x r2 = h32_from_64 (h[1]);
    const u32x r3 = l32_from_64 (h[1]);

    COMPARE_S_SIMD (r0, r1, r2, r3);
  }
}

KERNEL_FQ void m00600_m04 (KERN_ATTR_VECTOR ())
{
  /**
   * base
   */

  const u64 gid = get_global_id (0);

  if (gid >= gid_max) return;

  u32 w[16];

  w[ 0] = pws[gid].i[ 0];
  w[ 1] = pws[gid].i[ 1];
  w[ 2] = pws[gid].i[ 2];
  w[ 3] = pws[gid].i[ 3];
  w[ 4] = 0;
  w[ 5] = 0;
  w[ 6] = 0;
  w[ 7] = 0;
  w[ 8] = 0;
  w[ 9] = 0;
  w[10] = 0;
  w[11] = 0;
  w[12] = 0;
  w[13] = 0;
  w[14] = 0;
  w[15] = 0;

  const u32 pw_len = pws[gid].pw_len & 63;

  /**
   * main
   */

  m00600m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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, salt_repeat, pws_pos, gid_max);
}

KERNEL_FQ void m00600_m08 (KERN_ATTR_VECTOR ())
{
  /**
   * base
   */

  const u64 gid = get_global_id (0);

  if (gid >= gid_max) return;

  u32 w[16];

  w[ 0] = pws[gid].i[ 0];
  w[ 1] = pws[gid].i[ 1];
  w[ 2] = pws[gid].i[ 2];
  w[ 3] = pws[gid].i[ 3];
  w[ 4] = pws[gid].i[ 4];
  w[ 5] = pws[gid].i[ 5];
  w[ 6] = pws[gid].i[ 6];
  w[ 7] = pws[gid].i[ 7];
  w[ 8] = 0;
  w[ 9] = 0;
  w[10] = 0;
  w[11] = 0;
  w[12] = 0;
  w[13] = 0;
  w[14] = 0;
  w[15] = 0;

  const u32 pw_len = pws[gid].pw_len & 63;

  /**
   * main
   */

  m00600m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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, salt_repeat, pws_pos, gid_max);
}

KERNEL_FQ void m00600_m16 (KERN_ATTR_VECTOR ())
{
  /**
   * base
   */

  const u64 gid = get_global_id (0);

  if (gid >= gid_max) return;

  u32 w[16];

  w[ 0] = pws[gid].i[ 0];
  w[ 1] = pws[gid].i[ 1];
  w[ 2] = pws[gid].i[ 2];
  w[ 3] = pws[gid].i[ 3];
  w[ 4] = pws[gid].i[ 4];
  w[ 5] = pws[gid].i[ 5];
  w[ 6] = pws[gid].i[ 6];
  w[ 7] = pws[gid].i[ 7];
  w[ 8] = pws[gid].i[ 8];
  w[ 9] = pws[gid].i[ 9];
  w[10] = pws[gid].i[10];
  w[11] = pws[gid].i[11];
  w[12] = pws[gid].i[12];
  w[13] = pws[gid].i[13];
  w[14] = pws[gid].i[14];
  w[15] = pws[gid].i[15];

  const u32 pw_len = pws[gid].pw_len & 63;

  /**
   * main
   */

  m00600m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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, salt_repeat, pws_pos, gid_max);
}

KERNEL_FQ void m00600_s04 (KERN_ATTR_VECTOR ())
{
  /**
   * base
   */

  const u64 gid = get_global_id (0);

  if (gid >= gid_max) return;

  u32 w[16];

  w[ 0] = pws[gid].i[ 0];
  w[ 1] = pws[gid].i[ 1];
  w[ 2] = pws[gid].i[ 2];
  w[ 3] = pws[gid].i[ 3];
  w[ 4] = 0;
  w[ 5] = 0;
  w[ 6] = 0;
  w[ 7] = 0;
  w[ 8] = 0;
  w[ 9] = 0;
  w[10] = 0;
  w[11] = 0;
  w[12] = 0;
  w[13] = 0;
  w[14] = 0;
  w[15] = 0;

  const u32 pw_len = pws[gid].pw_len & 63;

  /**
   * main
   */

  m00600s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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, salt_repeat, pws_pos, gid_max);
}

KERNEL_FQ void m00600_s08 (KERN_ATTR_VECTOR ())
{
  /**
   * base
   */

  const u64 gid = get_global_id (0);

  if (gid >= gid_max) return;

  u32 w[16];

  w[ 0] = pws[gid].i[ 0];
  w[ 1] = pws[gid].i[ 1];
  w[ 2] = pws[gid].i[ 2];
  w[ 3] = pws[gid].i[ 3];
  w[ 4] = pws[gid].i[ 4];
  w[ 5] = pws[gid].i[ 5];
  w[ 6] = pws[gid].i[ 6];
  w[ 7] = pws[gid].i[ 7];
  w[ 8] = 0;
  w[ 9] = 0;
  w[10] = 0;
  w[11] = 0;
  w[12] = 0;
  w[13] = 0;
  w[14] = 0;
  w[15] = 0;

  const u32 pw_len = pws[gid].pw_len & 63;

  /**
   * main
   */

  m00600s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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, salt_repeat, pws_pos, gid_max);
}

KERNEL_FQ void m00600_s16 (KERN_ATTR_VECTOR ())
{
  /**
   * base
   */

  const u64 gid = get_global_id (0);

  if (gid >= gid_max) return;

  u32 w[16];

  w[ 0] = pws[gid].i[ 0];
  w[ 1] = pws[gid].i[ 1];
  w[ 2] = pws[gid].i[ 2];
  w[ 3] = pws[gid].i[ 3];
  w[ 4] = pws[gid].i[ 4];
  w[ 5] = pws[gid].i[ 5];
  w[ 6] = pws[gid].i[ 6];
  w[ 7] = pws[gid].i[ 7];
  w[ 8] = pws[gid].i[ 8];
  w[ 9] = pws[gid].i[ 9];
  w[10] = pws[gid].i[10];
  w[11] = pws[gid].i[11];
  w[12] = pws[gid].i[12];
  w[13] = pws[gid].i[13];
  w[14] = pws[gid].i[14];
  w[15] = pws[gid].i[15];

  const u32 pw_len = pws[gid].pw_len & 63;

  /**
   * main
   */

  m00600s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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, salt_repeat, pws_pos, gid_max);
}
