X-Git-Url: https://www.flypig.org.uk/git/?a=blobdiff_plain;f=OpenCL%2Fm08400_a0.cl;h=d5edecb21e7ad1ab27e650320b4a14fb6d35b28e;hb=51e1d11b2d6dff4ae331cff6098169455733c412;hp=182fa4e75e3814ce73df8069b1b80f0dbb1a4fee;hpb=dad03e394d815bc45b3f2c571f7195aab8746156;p=hashcat.git diff --git a/OpenCL/m08400_a0.cl b/OpenCL/m08400_a0.cl index 182fa4e..d5edecb 100644 --- a/OpenCL/m08400_a0.cl +++ b/OpenCL/m08400_a0.cl @@ -9,20 +9,14 @@ #define NEW_SIMD_CODE -#include "include/constants.h" -#include "include/kernel_vendor.h" - -#define DGST_R0 3 -#define DGST_R1 4 -#define DGST_R2 2 -#define DGST_R3 1 - -#include "include/kernel_functions.c" -#include "OpenCL/types_ocl.c" -#include "OpenCL/common.c" -#include "include/rp_kernel.h" -#include "OpenCL/rp.c" -#include "OpenCL/simd.c" +#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.h" +#include "inc_rp.cl" +#include "inc_simd.cl" #if VECT_SIZE == 1 #define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i)]) @@ -36,7 +30,7 @@ #define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf]) #endif -static void sha1_transform (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u32x digest[5]) +void sha1_transform (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u32x digest[5]) { u32x A = digest[0]; u32x B = digest[1]; @@ -164,7 +158,7 @@ static void sha1_transform (const u32x w0[4], const u32x w1[4], const u32x w2[4] digest[4] += E; } -__kernel void m08400_m04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max) +__kernel void m08400_m04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *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) { /** * modifier @@ -198,18 +192,16 @@ __kernel void m08400_m04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, */ u32 pw_buf0[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]; - u32 pw_buf1[4]; - 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]; + 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; @@ -218,21 +210,17 @@ __kernel void m08400_m04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, */ u32 salt_buf0[4]; + u32 salt_buf1[4]; + u32 salt_buf2[4]; salt_buf0[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 0]); salt_buf0[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 1]); salt_buf0[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 2]); salt_buf0[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 3]); - - u32 salt_buf1[4]; - salt_buf1[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 4]); salt_buf1[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 5]); salt_buf1[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 6]); salt_buf1[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 7]); - - u32 salt_buf2[4]; - salt_buf2[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 8]); salt_buf2[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 9]); salt_buf2[2] = 0; @@ -255,33 +243,26 @@ __kernel void m08400_m04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, append_0x80_2x4_VV (w0, w1, out_len); - u32x w0_t[4]; - - w0_t[0] = swap32 (w0[0]); - w0_t[1] = swap32 (w0[1]); - w0_t[2] = swap32 (w0[2]); - w0_t[3] = swap32 (w0[3]); - - u32x w1_t[4]; - - w1_t[0] = swap32 (w1[0]); - w1_t[1] = swap32 (w1[1]); - w1_t[2] = swap32 (w1[2]); - w1_t[3] = swap32 (w1[3]); - - u32x w2_t[4]; - - w2_t[0] = swap32 (w2[0]); - w2_t[1] = swap32 (w2[1]); - w2_t[2] = swap32 (w2[2]); - w2_t[3] = swap32 (w2[3]); - - u32x w3_t[4]; - - w3_t[0] = swap32 (w3[0]); - w3_t[1] = swap32 (w3[1]); - w3_t[2] = 0; - w3_t[3] = out_len * 8; + /** + * SHA1 + */ + + 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] = 0; + w3[3] = out_len * 8; u32x digest[5]; @@ -291,7 +272,7 @@ __kernel void m08400_m04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, digest[3] = SHA1M_D; digest[4] = SHA1M_E; - sha1_transform (w0_t, w1_t, w2_t, w3_t, digest); + sha1_transform (w0, w1, w2, w3, digest); u32x a; u32x b; @@ -305,28 +286,28 @@ __kernel void m08400_m04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, d = digest[3]; e = digest[4]; - w0_t[0] = salt_buf0[0]; - w0_t[1] = salt_buf0[1]; - w0_t[2] = salt_buf0[2]; - w0_t[3] = salt_buf0[3]; - w1_t[0] = salt_buf1[0]; - w1_t[1] = salt_buf1[1]; - w1_t[2] = salt_buf1[2]; - w1_t[3] = salt_buf1[3]; - w2_t[0] = salt_buf2[0]; - w2_t[1] = salt_buf2[1]; - w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 - | uint_to_hex_lower8_le ((a >> 24) & 255) << 16; - w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 - | uint_to_hex_lower8_le ((a >> 8) & 255) << 16; - w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 - | uint_to_hex_lower8_le ((b >> 24) & 255) << 16; - w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 - | uint_to_hex_lower8_le ((b >> 8) & 255) << 16; - w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 - | uint_to_hex_lower8_le ((c >> 24) & 255) << 16; - w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 - | uint_to_hex_lower8_le ((c >> 8) & 255) << 16; + w0[0] = salt_buf0[0]; + w0[1] = salt_buf0[1]; + w0[2] = salt_buf0[2]; + w0[3] = salt_buf0[3]; + w1[0] = salt_buf1[0]; + w1[1] = salt_buf1[1]; + w1[2] = salt_buf1[2]; + w1[3] = salt_buf1[3]; + w2[0] = salt_buf2[0]; + w2[1] = salt_buf2[1]; + w2[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 24) & 255) << 16; + w2[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 8) & 255) << 16; + w3[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 24) & 255) << 16; + w3[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 8) & 255) << 16; + w3[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 24) & 255) << 16; + w3[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 8) & 255) << 16; digest[0] = SHA1M_A; digest[1] = SHA1M_B; @@ -334,30 +315,30 @@ __kernel void m08400_m04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, digest[3] = SHA1M_D; digest[4] = SHA1M_E; - sha1_transform (w0_t, w1_t, w2_t, w3_t, digest); - - w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 - | uint_to_hex_lower8_le ((d >> 24) & 255) << 16; - w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 - | uint_to_hex_lower8_le ((d >> 8) & 255) << 16; - w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 - | uint_to_hex_lower8_le ((e >> 24) & 255) << 16; - w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 - | uint_to_hex_lower8_le ((e >> 8) & 255) << 16; - w1_t[0] = 0x80000000; - w1_t[1] = 0; - w1_t[2] = 0; - w1_t[3] = 0; - w2_t[0] = 0; - w2_t[1] = 0; - w2_t[2] = 0; - w2_t[3] = 0; - w3_t[0] = 0; - w3_t[1] = 0; - w3_t[2] = 0; - w3_t[3] = 80 * 8; - - sha1_transform (w0_t, w1_t, w2_t, w3_t, digest); + sha1_transform (w0, w1, w2, w3, digest); + + w0[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 24) & 255) << 16; + w0[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 8) & 255) << 16; + w0[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 24) & 255) << 16; + w0[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 8) & 255) << 16; + w1[0] = 0x80000000; + w1[1] = 0; + w1[2] = 0; + w1[3] = 0; + w2[0] = 0; + w2[1] = 0; + w2[2] = 0; + w2[3] = 0; + w3[0] = 0; + w3[1] = 0; + w3[2] = 0; + w3[3] = 80 * 8; + + sha1_transform (w0, w1, w2, w3, digest); a = digest[0]; b = digest[1]; @@ -365,28 +346,28 @@ __kernel void m08400_m04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, d = digest[3]; e = digest[4]; - w0_t[0] = salt_buf0[0]; - w0_t[1] = salt_buf0[1]; - w0_t[2] = salt_buf0[2]; - w0_t[3] = salt_buf0[3]; - w1_t[0] = salt_buf1[0]; - w1_t[1] = salt_buf1[1]; - w1_t[2] = salt_buf1[2]; - w1_t[3] = salt_buf1[3]; - w2_t[0] = salt_buf2[0]; - w2_t[1] = salt_buf2[1]; - w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 - | uint_to_hex_lower8_le ((a >> 24) & 255) << 16; - w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 - | uint_to_hex_lower8_le ((a >> 8) & 255) << 16; - w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 - | uint_to_hex_lower8_le ((b >> 24) & 255) << 16; - w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 - | uint_to_hex_lower8_le ((b >> 8) & 255) << 16; - w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 - | uint_to_hex_lower8_le ((c >> 24) & 255) << 16; - w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 - | uint_to_hex_lower8_le ((c >> 8) & 255) << 16; + w0[0] = salt_buf0[0]; + w0[1] = salt_buf0[1]; + w0[2] = salt_buf0[2]; + w0[3] = salt_buf0[3]; + w1[0] = salt_buf1[0]; + w1[1] = salt_buf1[1]; + w1[2] = salt_buf1[2]; + w1[3] = salt_buf1[3]; + w2[0] = salt_buf2[0]; + w2[1] = salt_buf2[1]; + w2[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 24) & 255) << 16; + w2[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 8) & 255) << 16; + w3[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 24) & 255) << 16; + w3[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 8) & 255) << 16; + w3[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 24) & 255) << 16; + w3[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 8) & 255) << 16; digest[0] = SHA1M_A; digest[1] = SHA1M_B; @@ -394,44 +375,44 @@ __kernel void m08400_m04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, digest[3] = SHA1M_D; digest[4] = SHA1M_E; - sha1_transform (w0_t, w1_t, w2_t, w3_t, digest); - - w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 - | uint_to_hex_lower8_le ((d >> 24) & 255) << 16; - w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 - | uint_to_hex_lower8_le ((d >> 8) & 255) << 16; - w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 - | uint_to_hex_lower8_le ((e >> 24) & 255) << 16; - w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 - | uint_to_hex_lower8_le ((e >> 8) & 255) << 16; - w1_t[0] = 0x80000000; - w1_t[1] = 0; - w1_t[2] = 0; - w1_t[3] = 0; - w2_t[0] = 0; - w2_t[1] = 0; - w2_t[2] = 0; - w2_t[3] = 0; - w3_t[0] = 0; - w3_t[1] = 0; - w3_t[2] = 0; - w3_t[3] = 80 * 8; - - sha1_transform (w0_t, w1_t, w2_t, w3_t, digest); + sha1_transform (w0, w1, w2, w3, digest); + + w0[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 24) & 255) << 16; + w0[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 8) & 255) << 16; + w0[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 24) & 255) << 16; + w0[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 8) & 255) << 16; + w1[0] = 0x80000000; + w1[1] = 0; + w1[2] = 0; + w1[3] = 0; + w2[0] = 0; + w2[1] = 0; + w2[2] = 0; + w2[3] = 0; + w3[0] = 0; + w3[1] = 0; + w3[2] = 0; + w3[3] = 80 * 8; + + sha1_transform (w0, w1, w2, w3, digest); COMPARE_M_SIMD (digest[3], digest[4], digest[2], digest[1]); } } -__kernel void m08400_m08 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max) +__kernel void m08400_m08 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *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) { } -__kernel void m08400_m16 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max) +__kernel void m08400_m16 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *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) { } -__kernel void m08400_s04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max) +__kernel void m08400_s04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *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) { /** * modifier @@ -465,18 +446,16 @@ __kernel void m08400_s04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, */ u32 pw_buf0[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]; - u32 pw_buf1[4]; - 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]; + 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; @@ -485,21 +464,17 @@ __kernel void m08400_s04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, */ u32 salt_buf0[4]; + u32 salt_buf1[4]; + u32 salt_buf2[4]; salt_buf0[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 0]); salt_buf0[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 1]); salt_buf0[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 2]); salt_buf0[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 3]); - - u32 salt_buf1[4]; - salt_buf1[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 4]); salt_buf1[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 5]); salt_buf1[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 6]); salt_buf1[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 7]); - - u32 salt_buf2[4]; - salt_buf2[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 8]); salt_buf2[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 9]); salt_buf2[2] = 0; @@ -534,33 +509,26 @@ __kernel void m08400_s04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, append_0x80_2x4_VV (w0, w1, out_len); - u32x w0_t[4]; - - w0_t[0] = swap32 (w0[0]); - w0_t[1] = swap32 (w0[1]); - w0_t[2] = swap32 (w0[2]); - w0_t[3] = swap32 (w0[3]); - - u32x w1_t[4]; - - w1_t[0] = swap32 (w1[0]); - w1_t[1] = swap32 (w1[1]); - w1_t[2] = swap32 (w1[2]); - w1_t[3] = swap32 (w1[3]); - - u32x w2_t[4]; - - w2_t[0] = swap32 (w2[0]); - w2_t[1] = swap32 (w2[1]); - w2_t[2] = swap32 (w2[2]); - w2_t[3] = swap32 (w2[3]); - - u32x w3_t[4]; - - w3_t[0] = swap32 (w3[0]); - w3_t[1] = swap32 (w3[1]); - w3_t[2] = 0; - w3_t[3] = out_len * 8; + /** + * SHA1 + */ + + 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] = 0; + w3[3] = out_len * 8; u32x digest[5]; @@ -570,7 +538,7 @@ __kernel void m08400_s04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, digest[3] = SHA1M_D; digest[4] = SHA1M_E; - sha1_transform (w0_t, w1_t, w2_t, w3_t, digest); + sha1_transform (w0, w1, w2, w3, digest); u32x a; u32x b; @@ -584,28 +552,28 @@ __kernel void m08400_s04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, d = digest[3]; e = digest[4]; - w0_t[0] = salt_buf0[0]; - w0_t[1] = salt_buf0[1]; - w0_t[2] = salt_buf0[2]; - w0_t[3] = salt_buf0[3]; - w1_t[0] = salt_buf1[0]; - w1_t[1] = salt_buf1[1]; - w1_t[2] = salt_buf1[2]; - w1_t[3] = salt_buf1[3]; - w2_t[0] = salt_buf2[0]; - w2_t[1] = salt_buf2[1]; - w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 - | uint_to_hex_lower8_le ((a >> 24) & 255) << 16; - w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 - | uint_to_hex_lower8_le ((a >> 8) & 255) << 16; - w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 - | uint_to_hex_lower8_le ((b >> 24) & 255) << 16; - w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 - | uint_to_hex_lower8_le ((b >> 8) & 255) << 16; - w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 - | uint_to_hex_lower8_le ((c >> 24) & 255) << 16; - w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 - | uint_to_hex_lower8_le ((c >> 8) & 255) << 16; + w0[0] = salt_buf0[0]; + w0[1] = salt_buf0[1]; + w0[2] = salt_buf0[2]; + w0[3] = salt_buf0[3]; + w1[0] = salt_buf1[0]; + w1[1] = salt_buf1[1]; + w1[2] = salt_buf1[2]; + w1[3] = salt_buf1[3]; + w2[0] = salt_buf2[0]; + w2[1] = salt_buf2[1]; + w2[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 24) & 255) << 16; + w2[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 8) & 255) << 16; + w3[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 24) & 255) << 16; + w3[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 8) & 255) << 16; + w3[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 24) & 255) << 16; + w3[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 8) & 255) << 16; digest[0] = SHA1M_A; digest[1] = SHA1M_B; @@ -613,30 +581,30 @@ __kernel void m08400_s04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, digest[3] = SHA1M_D; digest[4] = SHA1M_E; - sha1_transform (w0_t, w1_t, w2_t, w3_t, digest); - - w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 - | uint_to_hex_lower8_le ((d >> 24) & 255) << 16; - w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 - | uint_to_hex_lower8_le ((d >> 8) & 255) << 16; - w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 - | uint_to_hex_lower8_le ((e >> 24) & 255) << 16; - w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 - | uint_to_hex_lower8_le ((e >> 8) & 255) << 16; - w1_t[0] = 0x80000000; - w1_t[1] = 0; - w1_t[2] = 0; - w1_t[3] = 0; - w2_t[0] = 0; - w2_t[1] = 0; - w2_t[2] = 0; - w2_t[3] = 0; - w3_t[0] = 0; - w3_t[1] = 0; - w3_t[2] = 0; - w3_t[3] = (salt_len + 40) * 8; - - sha1_transform (w0_t, w1_t, w2_t, w3_t, digest); + sha1_transform (w0, w1, w2, w3, digest); + + w0[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 24) & 255) << 16; + w0[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 8) & 255) << 16; + w0[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 24) & 255) << 16; + w0[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 8) & 255) << 16; + w1[0] = 0x80000000; + w1[1] = 0; + w1[2] = 0; + w1[3] = 0; + w2[0] = 0; + w2[1] = 0; + w2[2] = 0; + w2[3] = 0; + w3[0] = 0; + w3[1] = 0; + w3[2] = 0; + w3[3] = 80 * 8; + + sha1_transform (w0, w1, w2, w3, digest); a = digest[0]; b = digest[1]; @@ -644,28 +612,28 @@ __kernel void m08400_s04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, d = digest[3]; e = digest[4]; - w0_t[0] = salt_buf0[0]; - w0_t[1] = salt_buf0[1]; - w0_t[2] = salt_buf0[2]; - w0_t[3] = salt_buf0[3]; - w1_t[0] = salt_buf1[0]; - w1_t[1] = salt_buf1[1]; - w1_t[2] = salt_buf1[2]; - w1_t[3] = salt_buf1[3]; - w2_t[0] = salt_buf2[0]; - w2_t[1] = salt_buf2[1]; - w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 - | uint_to_hex_lower8_le ((a >> 24) & 255) << 16; - w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 - | uint_to_hex_lower8_le ((a >> 8) & 255) << 16; - w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 - | uint_to_hex_lower8_le ((b >> 24) & 255) << 16; - w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 - | uint_to_hex_lower8_le ((b >> 8) & 255) << 16; - w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 - | uint_to_hex_lower8_le ((c >> 24) & 255) << 16; - w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 - | uint_to_hex_lower8_le ((c >> 8) & 255) << 16; + w0[0] = salt_buf0[0]; + w0[1] = salt_buf0[1]; + w0[2] = salt_buf0[2]; + w0[3] = salt_buf0[3]; + w1[0] = salt_buf1[0]; + w1[1] = salt_buf1[1]; + w1[2] = salt_buf1[2]; + w1[3] = salt_buf1[3]; + w2[0] = salt_buf2[0]; + w2[1] = salt_buf2[1]; + w2[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 24) & 255) << 16; + w2[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 8) & 255) << 16; + w3[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 24) & 255) << 16; + w3[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 8) & 255) << 16; + w3[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 24) & 255) << 16; + w3[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 8) & 255) << 16; digest[0] = SHA1M_A; digest[1] = SHA1M_B; @@ -673,39 +641,39 @@ __kernel void m08400_s04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, digest[3] = SHA1M_D; digest[4] = SHA1M_E; - sha1_transform (w0_t, w1_t, w2_t, w3_t, digest); - - w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 - | uint_to_hex_lower8_le ((d >> 24) & 255) << 16; - w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 - | uint_to_hex_lower8_le ((d >> 8) & 255) << 16; - w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 - | uint_to_hex_lower8_le ((e >> 24) & 255) << 16; - w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 - | uint_to_hex_lower8_le ((e >> 8) & 255) << 16; - w1_t[0] = 0x80000000; - w1_t[1] = 0; - w1_t[2] = 0; - w1_t[3] = 0; - w2_t[0] = 0; - w2_t[1] = 0; - w2_t[2] = 0; - w2_t[3] = 0; - w3_t[0] = 0; - w3_t[1] = 0; - w3_t[2] = 0; - w3_t[3] = (salt_len + 40) * 8; - - sha1_transform (w0_t, w1_t, w2_t, w3_t, digest); + sha1_transform (w0, w1, w2, w3, digest); + + w0[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 24) & 255) << 16; + w0[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 8) & 255) << 16; + w0[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 24) & 255) << 16; + w0[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 8) & 255) << 16; + w1[0] = 0x80000000; + w1[1] = 0; + w1[2] = 0; + w1[3] = 0; + w2[0] = 0; + w2[1] = 0; + w2[2] = 0; + w2[3] = 0; + w3[0] = 0; + w3[1] = 0; + w3[2] = 0; + w3[3] = 80 * 8; + + sha1_transform (w0, w1, w2, w3, digest); COMPARE_S_SIMD (digest[3], digest[4], digest[2], digest[1]); } } -__kernel void m08400_s08 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max) +__kernel void m08400_s08 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *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) { } -__kernel void m08400_s16 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max) +__kernel void m08400_s16 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *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) { }