X-Git-Url: https://www.flypig.org.uk/git/?a=blobdiff_plain;f=OpenCL%2Fm09600.cl;h=d142feca2202dc637f48535a65791fc2951e0aee;hb=161a6eb4bc643d8e636e96eda613f5137d30da59;hp=3e61effa24fd662c0aa772f3480d28f044899a3f;hpb=7be2c2fd8dff462f0ab8d3cb1993317815679714;p=hashcat.git diff --git a/OpenCL/m09600.cl b/OpenCL/m09600.cl index 3e61eff..d142fec 100644 --- a/OpenCL/m09600.cl +++ b/OpenCL/m09600.cl @@ -1,24 +1,20 @@ /** - * Author......: Jens Steube + * Authors.....: Jens Steube + * Gabriele Gristina + * * License.....: MIT */ #define _OFFICE2013_ -#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" - -#define COMPARE_S "check_single_comp4.c" -#define COMPARE_M "check_multi_comp4.c" +#define COMPARE_S "inc_comp_single.cl" +#define COMPARE_M "inc_comp_multi.cl" __constant u32 te0[256] = { @@ -707,7 +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]; @@ -757,7 +753,7 @@ 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) { @@ -797,7 +793,7 @@ 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]; @@ -887,7 +883,7 @@ static void AES256_decrypt (const u32 *in, u32 *out, const u32 *rdk, __local u32 ^ rdk[59]; } -static void AES256_encrypt (const u32 *in, u32 *out, const 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_encrypt (const u32 *in, u32 *out, const u32 *rek, __local u32 *s_te0, __local u32 *s_te1, __local u32 *s_te2, __local u32 *s_te3, __local u32 *s_te4) { u32 s0 = in[0] ^ rek[0]; u32 s1 = in[1] ^ rek[1]; @@ -1001,7 +997,7 @@ __constant u64 k_sha512[80] = SHA512C4c, SHA512C4d, SHA512C4e, SHA512C4f, }; -static void sha512_transform (const u64 w0[4], const u64 w1[4], const u64 w2[4], const u64 w3[4], u64 dgst[8]) +void sha512_transform (const u64 w0[4], const u64 w1[4], const u64 w2[4], const u64 w3[4], u64 dgst[8]) { u64 a = dgst[0]; u64 b = dgst[1]; @@ -1071,7 +1067,9 @@ static void sha512_transform (const u64 w0[4], const u64 w1[4], const u64 w2[4], ROUND_STEP (0); - //#pragma unroll + #ifdef _unroll + #pragma unroll + #endif for (int i = 16; i < 80; i += 16) { ROUND_EXPAND (); ROUND_STEP (i); @@ -1087,7 +1085,7 @@ static void sha512_transform (const u64 w0[4], const u64 w1[4], const u64 w2[4], dgst[7] += h; } -__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m09600_init (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global office2013_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 office2013_t *office2013_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 m09600_init (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global office2013_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 office2013_t *office2013_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 @@ -1200,7 +1198,7 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m09600_init (__gl tmps[gid].out[7] = digest[7]; } -__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m09600_loop (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global office2013_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 office2013_t *office2013_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 m09600_loop (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global office2013_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 office2013_t *office2013_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); @@ -1236,7 +1234,7 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m09600_loop (__gl for (u32 i = 0, j = loop_pos; i < loop_cnt; i++, j++) { - w0[0] = (u64) swap32 (j) << 32 | w0[0] & 0xffffffff; + w0[0] = (u64) swap32 (j) << 32 | (w0[0] & 0xffffffff); u64 digest[8]; @@ -1272,17 +1270,20 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m09600_loop (__gl tmps[gid].out[7] = w1[3] << 32 | w2[0] >> 32; } -__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m09600_comp (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global office2013_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 office2013_t *office2013_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 m09600_comp (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global office2013_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 office2013_t *office2013_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 + */ + 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]; @@ -1295,60 +1296,29 @@ __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m09600_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); if (gid >= gid_max) return; + /** + * base + */ + u32 encryptedVerifierHashInputBlockKey[2] = { 0xfea7d276, 0x3b4b9e79 }; u32 encryptedVerifierHashValueBlockKey[2] = { 0xd7aa0f6d, 0x3061344e };