1
0
mirror of https://github.com/hashcat/hashcat.git synced 2024-11-22 16:18:09 +00:00
hashcat/OpenCL/m06100_a0-optimized.cl

314 lines
12 KiB
Common Lisp

/**
* 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_rp_optimized.h"
#include "inc_rp_optimized.cl"
#include "inc_simd.cl"
#include "inc_hash_whirlpool.cl"
DECLSPEC void whirlpool_transform_transport_vector (const u32x *w, u32x *digest, SHM_TYPE u32 (*s_Ch)[256], SHM_TYPE u32 (*s_Cl)[256])
{
whirlpool_transform_vector (w + 0, w + 4, w + 8, w + 12, digest, s_Ch, s_Cl);
}
__kernel void m06100_m04 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global netntlm_t *netntlm_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u64 gid_max)
{
/**
* modifier
*/
const u64 gid = get_global_id (0);
const u64 lid = get_local_id (0);
const u64 lsz = get_local_size (0);
/**
* shared
*/
#ifdef REAL_SHM
__local u32 s_Ch[8][256];
__local u32 s_Cl[8][256];
for (u32 i = lid; i < 256; i += lsz)
{
s_Ch[0][i] = Ch[0][i];
s_Ch[1][i] = Ch[1][i];
s_Ch[2][i] = Ch[2][i];
s_Ch[3][i] = Ch[3][i];
s_Ch[4][i] = Ch[4][i];
s_Ch[5][i] = Ch[5][i];
s_Ch[6][i] = Ch[6][i];
s_Ch[7][i] = Ch[7][i];
s_Cl[0][i] = Cl[0][i];
s_Cl[1][i] = Cl[1][i];
s_Cl[2][i] = Cl[2][i];
s_Cl[3][i] = Cl[3][i];
s_Cl[4][i] = Cl[4][i];
s_Cl[5][i] = Cl[5][i];
s_Cl[6][i] = Cl[6][i];
s_Cl[7][i] = Cl[7][i];
}
barrier (CLK_LOCAL_MEM_FENCE);
#else
__constant u32 (*s_Ch)[256] = Ch;
__constant u32 (*s_Cl)[256] = Cl;
#endif
if (gid >= gid_max) return;
/**
* base
*/
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;
/**
* loop
*/
for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
{
u32x w0[4] = { 0 };
u32x w1[4] = { 0 };
u32x w2[4] = { 0 };
u32x w3[4] = { 0 };
const u32x out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
append_0x80_2x4_VV (w0, w1, out_len);
u32x w[16];
w[ 0] = swap32 (w0[0]);
w[ 1] = swap32 (w0[1]);
w[ 2] = swap32 (w0[2]);
w[ 3] = swap32 (w0[3]);
w[ 4] = swap32 (w1[0]);
w[ 5] = swap32 (w1[1]);
w[ 6] = swap32 (w1[2]);
w[ 7] = swap32 (w1[3]);
w[ 8] = 0;
w[ 9] = 0;
w[10] = 0;
w[11] = 0;
w[12] = 0;
w[13] = 0;
w[14] = 0;
w[15] = out_len * 8;
/**
* Whirlpool
*/
u32x dgst[16];
dgst[ 0] = 0;
dgst[ 1] = 0;
dgst[ 2] = 0;
dgst[ 3] = 0;
dgst[ 4] = 0;
dgst[ 5] = 0;
dgst[ 6] = 0;
dgst[ 7] = 0;
dgst[ 8] = 0;
dgst[ 9] = 0;
dgst[10] = 0;
dgst[11] = 0;
dgst[12] = 0;
dgst[13] = 0;
dgst[14] = 0;
dgst[15] = 0;
whirlpool_transform_transport_vector (w, dgst, s_Ch, s_Cl);
COMPARE_M_SIMD (dgst[0], dgst[1], dgst[2], dgst[3]);
}
}
__kernel void m06100_m08 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u64 gid_max)
{
}
__kernel void m06100_m16 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u64 gid_max)
{
}
__kernel void m06100_s04 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global netntlm_t *netntlm_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u64 gid_max)
{
/**
* modifier
*/
const u64 gid = get_global_id (0);
const u64 lid = get_local_id (0);
const u64 lsz = get_local_size (0);
/**
* shared
*/
#ifdef REAL_SHM
__local u32 s_Ch[8][256];
__local u32 s_Cl[8][256];
for (u32 i = lid; i < 256; i += lsz)
{
s_Ch[0][i] = Ch[0][i];
s_Ch[1][i] = Ch[1][i];
s_Ch[2][i] = Ch[2][i];
s_Ch[3][i] = Ch[3][i];
s_Ch[4][i] = Ch[4][i];
s_Ch[5][i] = Ch[5][i];
s_Ch[6][i] = Ch[6][i];
s_Ch[7][i] = Ch[7][i];
s_Cl[0][i] = Cl[0][i];
s_Cl[1][i] = Cl[1][i];
s_Cl[2][i] = Cl[2][i];
s_Cl[3][i] = Cl[3][i];
s_Cl[4][i] = Cl[4][i];
s_Cl[5][i] = Cl[5][i];
s_Cl[6][i] = Cl[6][i];
s_Cl[7][i] = Cl[7][i];
}
barrier (CLK_LOCAL_MEM_FENCE);
#else
__constant u32 (*s_Ch)[256] = Ch;
__constant u32 (*s_Cl)[256] = Cl;
#endif
if (gid >= gid_max) return;
/**
* base
*/
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;
/**
* digest
*/
const u32 search[4] =
{
digests_buf[digests_offset].digest_buf[DGST_R0],
digests_buf[digests_offset].digest_buf[DGST_R1],
digests_buf[digests_offset].digest_buf[DGST_R2],
digests_buf[digests_offset].digest_buf[DGST_R3]
};
/**
* loop
*/
for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
{
u32x w0[4] = { 0 };
u32x w1[4] = { 0 };
u32x w2[4] = { 0 };
u32x w3[4] = { 0 };
const u32x out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
append_0x80_2x4_VV (w0, w1, out_len);
u32x w[16];
w[ 0] = swap32 (w0[0]);
w[ 1] = swap32 (w0[1]);
w[ 2] = swap32 (w0[2]);
w[ 3] = swap32 (w0[3]);
w[ 4] = swap32 (w1[0]);
w[ 5] = swap32 (w1[1]);
w[ 6] = swap32 (w1[2]);
w[ 7] = swap32 (w1[3]);
w[ 8] = 0;
w[ 9] = 0;
w[10] = 0;
w[11] = 0;
w[12] = 0;
w[13] = 0;
w[14] = 0;
w[15] = out_len * 8;
/**
* Whirlpool
*/
u32x dgst[16];
dgst[ 0] = 0;
dgst[ 1] = 0;
dgst[ 2] = 0;
dgst[ 3] = 0;
dgst[ 4] = 0;
dgst[ 5] = 0;
dgst[ 6] = 0;
dgst[ 7] = 0;
dgst[ 8] = 0;
dgst[ 9] = 0;
dgst[10] = 0;
dgst[11] = 0;
dgst[12] = 0;
dgst[13] = 0;
dgst[14] = 0;
dgst[15] = 0;
whirlpool_transform_transport_vector (w, dgst, s_Ch, s_Cl);
COMPARE_S_SIMD (dgst[0], dgst[1], dgst[2], dgst[3]);
}
}
__kernel void m06100_s08 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u64 gid_max)
{
}
__kernel void m06100_s16 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u64 gid_max)
{
}