/** * 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" __kernel void m02400_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 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) { /** * modifier */ const u64 lid = get_local_id (0); /** * base */ const u64 gid = get_global_id (0); if (gid >= gid_max) return; 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); w1[0] = 0x80; 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] = 16 * 8; w3[3] = 0; u32x a = MD5M_A; u32x b = MD5M_B; u32x c = MD5M_C; u32x d = MD5M_D; MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00); MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01); MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02); MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03); MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00); MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01); MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02); MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03); MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00); MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01); MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02); MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03); MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00); MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01); MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02); MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03); MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10); MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11); MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12); MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13); MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10); MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11); MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12); MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13); MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10); MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11); MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12); MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13); MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10); MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11); MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12); MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13); MD5_STEP (MD5_H , a, b, c, d, w1[1], MD5C20, MD5S20); MD5_STEP (MD5_H , d, a, b, c, w2[0], MD5C21, MD5S21); MD5_STEP (MD5_H , c, d, a, b, w2[3], MD5C22, MD5S22); MD5_STEP (MD5_H , b, c, d, a, w3[2], MD5C23, MD5S23); MD5_STEP (MD5_H , a, b, c, d, w0[1], MD5C24, MD5S20); MD5_STEP (MD5_H , d, a, b, c, w1[0], MD5C25, MD5S21); MD5_STEP (MD5_H , c, d, a, b, w1[3], MD5C26, MD5S22); MD5_STEP (MD5_H , b, c, d, a, w2[2], MD5C27, MD5S23); MD5_STEP (MD5_H , a, b, c, d, w3[1], MD5C28, MD5S20); MD5_STEP (MD5_H , d, a, b, c, w0[0], MD5C29, MD5S21); MD5_STEP (MD5_H , c, d, a, b, w0[3], MD5C2a, MD5S22); MD5_STEP (MD5_H , b, c, d, a, w1[2], MD5C2b, MD5S23); MD5_STEP (MD5_H , a, b, c, d, w2[1], MD5C2c, MD5S20); MD5_STEP (MD5_H , d, a, b, c, w3[0], MD5C2d, MD5S21); MD5_STEP (MD5_H , c, d, a, b, w3[3], MD5C2e, MD5S22); MD5_STEP (MD5_H , b, c, d, a, w0[2], MD5C2f, MD5S23); MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30); MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31); MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32); MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33); MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30); MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31); MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32); MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33); MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30); MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31); MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32); MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33); MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30); MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31); MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32); MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33); a &= 0x00ffffff; d &= 0x00ffffff; c &= 0x00ffffff; b &= 0x00ffffff; COMPARE_M_SIMD (a, d, c, b); } } __kernel void m02400_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 m02400_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 m02400_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 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) { /** * modifier */ const u64 lid = get_local_id (0); /** * base */ const u64 gid = get_global_id (0); if (gid >= gid_max) return; 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); w1[0] = 0x80; 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] = 16 * 8; w3[3] = 0; u32x a = MD5M_A; u32x b = MD5M_B; u32x c = MD5M_C; u32x d = MD5M_D; MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00); MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01); MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02); MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03); MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00); MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01); MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02); MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03); MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00); MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01); MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02); MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03); MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00); MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01); MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02); MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03); MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10); MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11); MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12); MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13); MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10); MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11); MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12); MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13); MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10); MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11); MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12); MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13); MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10); MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11); MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12); MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13); MD5_STEP (MD5_H , a, b, c, d, w1[1], MD5C20, MD5S20); MD5_STEP (MD5_H , d, a, b, c, w2[0], MD5C21, MD5S21); MD5_STEP (MD5_H , c, d, a, b, w2[3], MD5C22, MD5S22); MD5_STEP (MD5_H , b, c, d, a, w3[2], MD5C23, MD5S23); MD5_STEP (MD5_H , a, b, c, d, w0[1], MD5C24, MD5S20); MD5_STEP (MD5_H , d, a, b, c, w1[0], MD5C25, MD5S21); MD5_STEP (MD5_H , c, d, a, b, w1[3], MD5C26, MD5S22); MD5_STEP (MD5_H , b, c, d, a, w2[2], MD5C27, MD5S23); MD5_STEP (MD5_H , a, b, c, d, w3[1], MD5C28, MD5S20); MD5_STEP (MD5_H , d, a, b, c, w0[0], MD5C29, MD5S21); MD5_STEP (MD5_H , c, d, a, b, w0[3], MD5C2a, MD5S22); MD5_STEP (MD5_H , b, c, d, a, w1[2], MD5C2b, MD5S23); MD5_STEP (MD5_H , a, b, c, d, w2[1], MD5C2c, MD5S20); MD5_STEP (MD5_H , d, a, b, c, w3[0], MD5C2d, MD5S21); MD5_STEP (MD5_H , c, d, a, b, w3[3], MD5C2e, MD5S22); MD5_STEP (MD5_H , b, c, d, a, w0[2], MD5C2f, MD5S23); MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30); MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31); MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32); MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33); MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30); MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31); MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32); MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33); MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30); MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31); MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32); MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33); MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30); if (MATCHES_NONE_VS ((a & 0x00ffffff), search[0])) continue; MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31); MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32); MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33); a &= 0x00ffffff; d &= 0x00ffffff; c &= 0x00ffffff; b &= 0x00ffffff; COMPARE_S_SIMD (a, d, c, b); } } __kernel void m02400_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 m02400_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) { }