/**
- * Author......: Jens Steube <jens.steube@gmail.com>
+ * Authors.....: Jens Steube <jens.steube@gmail.com>
+ * Gabriele Gristina <matrix@hashcat.net>
+ *
* License.....: MIT
*/
0x1b000000, 0x36000000,
};
-static void AES256_ExpandKey (u32 *userkey, u32 *rek, __local u32 s_te0[256], __local u32 s_te1[256], __local u32 s_te2[256], __local u32 s_te3[256], __local u32 s_te4[256])
+static void AES256_ExpandKey (u32 *userkey, u32 *rek, __local u32 *s_te0, __local u32 *s_te1, __local u32 *s_te2, __local u32 *s_te3, __local u32 *s_te4)
{
rek[0] = userkey[0];
rek[1] = userkey[1];
}
}
-static void AES256_InvertKey (u32 *rdk, __local u32 s_td0[256], __local u32 s_td1[256], __local u32 s_td2[256], __local u32 s_td3[256], __local u32 s_td4[256], __local u32 s_te0[256], __local u32 s_te1[256], __local u32 s_te2[256], __local u32 s_te3[256], __local u32 s_te4[256])
+static void AES256_InvertKey (u32 *rdk, __local u32 *s_td0, __local u32 *s_td1, __local u32 *s_td2, __local u32 *s_td3, __local u32 *s_td4, __local u32 *s_te0, __local u32 *s_te1, __local u32 *s_te2, __local u32 *s_te3, __local u32 *s_te4)
{
for (u32 i = 0, j = 56; i < j; i += 4, j -= 4)
{
}
}
-static void AES256_decrypt (const u32 *in, u32 *out, const u32 *rdk, __local u32 s_td0[256], __local u32 s_td1[256], __local u32 s_td2[256], __local u32 s_td3[256], __local u32 s_td4[256])
+static void AES256_decrypt (const u32 *in, u32 *out, const u32 *rdk, __local u32 *s_td0, __local u32 *s_td1, __local u32 *s_td2, __local u32 *s_td3, __local u32 *s_td4)
{
u32 s0 = in[0] ^ rdk[0];
u32 s1 = in[1] ^ rdk[1];
tmp2 = __byte_perm (append[1], 0, selector);
#endif
- #if defined IS_AMD || defined IS_UNKNOWN
+ #if defined IS_AMD || defined IS_GENERIC
const int offset_minus_4 = 4 - block_len;
tmp0 = amd_bytealign (append[0], 0, offset_minus_4);
tmp8 = __byte_perm (append[7], 0, selector);
#endif
- #if defined IS_AMD || defined IS_UNKNOWN
+ #if defined IS_AMD || defined IS_GENERIC
const int offset_minus_4 = 4 - block_len;
tmp0 = amd_bytealign (append[0], 0, offset_minus_4);
return new_len;
}
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m11600_init (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global seven_zip_tmp_t *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global seven_zip_t *esalt_bufs, __global u32 *d_return_buf, __global 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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m11600_init (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global seven_zip_tmp_t *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global seven_zip_t *esalt_bufs, __global u32 *d_return_buf, __global 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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
/**
* base
tmps[gid].final_len = final_len;
}
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m11600_loop (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global seven_zip_tmp_t *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global seven_zip_t *esalt_bufs, __global u32 *d_return_buf, __global 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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m11600_loop (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global seven_zip_tmp_t *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global seven_zip_t *esalt_bufs, __global u32 *d_return_buf, __global 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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
/**
* base
tmps[gid].final_len = final_len;
}
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m11600_comp (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global seven_zip_tmp_t *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global seven_zip_t *esalt_bufs, __global u32 *d_return_buf, __global 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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
+__kernel void m11600_comp (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global seven_zip_tmp_t *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global seven_zip_t *esalt_bufs, __global u32 *d_return_buf, __global 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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
/**
* base
const u32 gid = get_global_id (0);
const u32 lid = get_local_id (0);
+ const u32 lsz = get_local_size (0);
/**
* aes shared
*/
- const u32 lid4 = lid * 4;
-
__local u32 s_td0[256];
__local u32 s_td1[256];
__local u32 s_td2[256];
__local u32 s_te3[256];
__local u32 s_te4[256];
- s_td0[lid4 + 0] = td0[lid4 + 0];
- s_td0[lid4 + 1] = td0[lid4 + 1];
- s_td0[lid4 + 2] = td0[lid4 + 2];
- s_td0[lid4 + 3] = td0[lid4 + 3];
-
- s_td1[lid4 + 0] = td1[lid4 + 0];
- s_td1[lid4 + 1] = td1[lid4 + 1];
- s_td1[lid4 + 2] = td1[lid4 + 2];
- s_td1[lid4 + 3] = td1[lid4 + 3];
-
- s_td2[lid4 + 0] = td2[lid4 + 0];
- s_td2[lid4 + 1] = td2[lid4 + 1];
- s_td2[lid4 + 2] = td2[lid4 + 2];
- s_td2[lid4 + 3] = td2[lid4 + 3];
-
- s_td3[lid4 + 0] = td3[lid4 + 0];
- s_td3[lid4 + 1] = td3[lid4 + 1];
- s_td3[lid4 + 2] = td3[lid4 + 2];
- s_td3[lid4 + 3] = td3[lid4 + 3];
-
- s_td4[lid4 + 0] = td4[lid4 + 0];
- s_td4[lid4 + 1] = td4[lid4 + 1];
- s_td4[lid4 + 2] = td4[lid4 + 2];
- s_td4[lid4 + 3] = td4[lid4 + 3];
-
- s_te0[lid4 + 0] = te0[lid4 + 0];
- s_te0[lid4 + 1] = te0[lid4 + 1];
- s_te0[lid4 + 2] = te0[lid4 + 2];
- s_te0[lid4 + 3] = te0[lid4 + 3];
-
- s_te1[lid4 + 0] = te1[lid4 + 0];
- s_te1[lid4 + 1] = te1[lid4 + 1];
- s_te1[lid4 + 2] = te1[lid4 + 2];
- s_te1[lid4 + 3] = te1[lid4 + 3];
-
- s_te2[lid4 + 0] = te2[lid4 + 0];
- s_te2[lid4 + 1] = te2[lid4 + 1];
- s_te2[lid4 + 2] = te2[lid4 + 2];
- s_te2[lid4 + 3] = te2[lid4 + 3];
-
- s_te3[lid4 + 0] = te3[lid4 + 0];
- s_te3[lid4 + 1] = te3[lid4 + 1];
- s_te3[lid4 + 2] = te3[lid4 + 2];
- s_te3[lid4 + 3] = te3[lid4 + 3];
-
- s_te4[lid4 + 0] = te4[lid4 + 0];
- s_te4[lid4 + 1] = te4[lid4 + 1];
- s_te4[lid4 + 2] = te4[lid4 + 2];
- s_te4[lid4 + 3] = te4[lid4 + 3];
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ s_td0[i] = td0[i];
+ s_td1[i] = td1[i];
+ s_td2[i] = td2[i];
+ s_td3[i] = td3[i];
+ s_td4[i] = td4[i];
+
+ s_te0[i] = te0[i];
+ s_te1[i] = te1[i];
+ s_te2[i] = te2[i];
+ s_te3[i] = te3[i];
+ s_te4[i] = te4[i];
+ }
barrier (CLK_LOCAL_MEM_FENCE);
projects / hashcat.git / blobdiff