X-Git-Url: https://www.flypig.org.uk/git/?a=blobdiff_plain;f=OpenCL%2Fm12700.cl;h=2893c677e8cdd8d0f110465d865f23f03993958c;hb=161a6eb4bc643d8e636e96eda613f5137d30da59;hp=2c5635058daf79528af79c3683bc9b10a956df2e;hpb=0bf4e3c34a6a799ccc34f403bed70119574ca9c8;p=hashcat.git diff --git a/OpenCL/m12700.cl b/OpenCL/m12700.cl index 2c56350..2893c67 100644 --- a/OpenCL/m12700.cl +++ b/OpenCL/m12700.cl @@ -1,29 +1,20 @@ /** - * Author......: Jens Steube + * Authors.....: Jens Steube + * Gabriele Gristina + * * License.....: MIT */ #define _SHA1_ -#include "include/constants.h" -#include "include/kernel_vendor.h" +#include "inc_vendor.cl" +#include "inc_hash_constants.h" +#include "inc_hash_functions.cl" +#include "inc_types.cl" +#include "inc_common.cl" -#define DGST_R0 0 -#define DGST_R1 1 -#define DGST_R2 2 -#define DGST_R3 3 - -#include "include/kernel_functions.c" -#include "types_ocl.c" -#include "common.c" - -#ifdef VECT_SIZE1 -#define COMPARE_M "check_multi_vect1_comp4.c" -#endif - -#ifdef VECT_SIZE2 -#define COMPARE_M "check_multi_vect2_comp4.c" -#endif +#define COMPARE_S "inc_comp_single.cl" +#define COMPARE_M "inc_comp_multi.cl" __constant u32 te0[256] = { @@ -712,7 +703,7 @@ __constant u32 rcon[] = 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]) +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]; @@ -768,7 +759,7 @@ static void AES256_ExpandKey (u32 *userkey, u32 *rek, __local u32 s_te0[256], __ } } -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]) +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) { @@ -808,7 +799,7 @@ static void AES256_InvertKey (u32 *rdk, __local u32 s_td0[256], __local u32 s_td } } -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]) +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]; @@ -898,7 +889,7 @@ static void AES256_decrypt (const u32 *in, u32 *out, const u32 *rdk, __local u32 ^ rdk[59]; } -static void sha1_transform (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[5]) +void sha1_transform (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[5]) { u32 A = digest[0]; u32 B = digest[1]; @@ -1026,7 +1017,7 @@ static void sha1_transform (const u32 w0[4], const u32 w1[4], const u32 w2[4], c digest[4] += E; } -static void hmac_sha1_pad (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5]) +void hmac_sha1_pad (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5]) { w0[0] = w0[0] ^ 0x36363636; w0[1] = w0[1] ^ 0x36363636; @@ -1079,7 +1070,7 @@ static void hmac_sha1_pad (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[ sha1_transform (w0, w1, w2, w3, opad); } -static void hmac_sha1_run (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5], u32 digest[5]) +void hmac_sha1_run (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5], u32 digest[5]) { digest[0] = ipad[0]; digest[1] = ipad[1]; @@ -1115,7 +1106,7 @@ static void hmac_sha1_run (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[ sha1_transform (w0, w1, w2, w3, digest); } -__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m12700_init (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global mywallet_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 void *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 m12700_init (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global mywallet_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 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 u32 gid_max) { /** * base @@ -1170,22 +1161,22 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m12700_init (__gl * pads */ - w0[0] = swap_workaround (w0[0]); - w0[1] = swap_workaround (w0[1]); - w0[2] = swap_workaround (w0[2]); - w0[3] = swap_workaround (w0[3]); - w1[0] = swap_workaround (w1[0]); - w1[1] = swap_workaround (w1[1]); - w1[2] = swap_workaround (w1[2]); - w1[3] = swap_workaround (w1[3]); - w2[0] = swap_workaround (w2[0]); - w2[1] = swap_workaround (w2[1]); - w2[2] = swap_workaround (w2[2]); - w2[3] = swap_workaround (w2[3]); - w3[0] = swap_workaround (w3[0]); - w3[1] = swap_workaround (w3[1]); - w3[2] = swap_workaround (w3[2]); - w3[3] = swap_workaround (w3[3]); + w0[0] = swap32 (w0[0]); + w0[1] = swap32 (w0[1]); + w0[2] = swap32 (w0[2]); + w0[3] = swap32 (w0[3]); + w1[0] = swap32 (w1[0]); + w1[1] = swap32 (w1[1]); + w1[2] = swap32 (w1[2]); + w1[3] = swap32 (w1[3]); + w2[0] = swap32 (w2[0]); + w2[1] = swap32 (w2[1]); + w2[2] = swap32 (w2[2]); + w2[3] = swap32 (w2[3]); + w3[0] = swap32 (w3[0]); + w3[1] = swap32 (w3[1]); + w3[2] = swap32 (w3[2]); + w3[3] = swap32 (w3[3]); u32 ipad[5]; u32 opad[5]; @@ -1279,7 +1270,7 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m12700_init (__gl } } -__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m12700_loop (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global mywallet_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 void *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 m12700_loop (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global mywallet_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 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 u32 gid_max) { const u32 gid = get_global_id (0); @@ -1429,7 +1420,7 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m12700_loop (__gl } } -__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m12700_comp (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global mywallet_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 void *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 m12700_comp (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global mywallet_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 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 u32 gid_max) { /** * base @@ -1437,13 +1428,12 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m12700_comp (__gl 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]; @@ -1456,55 +1446,20 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m12700_comp (__gl __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); @@ -1558,10 +1513,10 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m12700_comp (__gl out[2] ^= iv[2]; out[3] ^= iv[3]; - out[0] = swap_workaround (out[0]); - out[1] = swap_workaround (out[1]); - out[2] = swap_workaround (out[2]); - out[3] = swap_workaround (out[3]); + out[0] = swap32 (out[0]); + out[1] = swap32 (out[1]); + out[2] = swap32 (out[2]); + out[3] = swap32 (out[3]); if ((out[0] & 0xff) != '{') return;