diff --git a/OpenCL/m24900_a0-optimized.cl b/OpenCL/m24900_a0-optimized.cl new file mode 100644 index 000000000..033b1ee72 --- /dev/null +++ b/OpenCL/m24900_a0-optimized.cl @@ -0,0 +1,401 @@ +/** + * Author......: See docs/credits.txt + * License.....: MIT + */ + +#define NEW_SIMD_CODE + +#ifdef KERNEL_STATIC +#include "inc_vendor.h" +#include "inc_types.h" +#include "inc_platform.cl" +#include "inc_common.cl" +#include "inc_rp_optimized.h" +#include "inc_rp_optimized.cl" +#include "inc_simd.cl" +#include "inc_hash_md5.cl" +#endif + +KERNEL_FQ void m24900_m04 (KERN_ATTR_RULES ()) +{ + /** + * 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 & 63; + + /** + * lookup table + */ + + const u8 sof_lut[64] = + { + 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, + 0x38, 0x39, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, + 0x47, 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, + 0x4f, 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, + 0x57, 0x58, 0x59, 0x5a, 0x61, 0x62, 0x63, 0x64, + 0x65, 0x66, 0x67, 0x68, 0x69, 0x6a, 0x6b, 0x6c, + 0x6d, 0x6e, 0x6f, 0x70, 0x71, 0x72, 0x73, 0x74, + 0x75, 0x76, 0x77, 0x78, 0x79, 0x7a, 0x00, 0x00 + }; + + /** + * 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_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1); + + append_0x80_2x4_VV (w0, w1, out_len); + + w3[2] = out_len * 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); + + u32x t; + + MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22); + MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23); + MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22); + MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23); + MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22); + MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23); + MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22); + MD5_STEP (MD5_H2, 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 += MD5M_A; + b += MD5M_B; + c += MD5M_C; + d += MD5M_D; + + u16 t_abcd = ((a & 0xff) + ((a >> 8) & 0xff)); + u8 a_12 = (t_abcd % 0x3e); + + t_abcd = (((a >> 16 )& 0xff) + ((a >> 24) & 0xff)); + u8 a_34 = (t_abcd % 0x3e); + + t_abcd = ((b & 0xff) + ((b >> 8) & 0xff)); + u8 b_12 = (t_abcd % 0x3e); + + t_abcd = (((b >> 16) & 0xff) + ((b >> 24) & 0xff)); + u8 b_34 = (t_abcd % 0x3e); + + t_abcd = ((c & 0xff) + ((c >> 8) & 0xff)); + u8 c_12 = (t_abcd % 0x3e); + + t_abcd = (((c >> 16 )& 0xff) + ((c >> 24) & 0xff)); + u8 c_34 = (t_abcd % 0x3e); + + t_abcd = ((d & 0xff) + ((d >> 8) & 0xff)); + u8 d_12 = (t_abcd % 0x3e); + + t_abcd = (((d >> 16) & 0xff) + ((d >> 24) & 0xff)); + u8 d_34 = (t_abcd % 0x3e); + + a = (sof_lut[a_12]) + (sof_lut[a_34] << 8) + (sof_lut[b_12] << 16) + (sof_lut[b_34] << 24); + b = (sof_lut[c_12]) + (sof_lut[c_34] << 8) + (sof_lut[d_12] << 16) + (sof_lut[d_34] << 24); + + u32x z = 0; + + COMPARE_M_SIMD (a, b, z, z); + + } +} + +KERNEL_FQ void m24900_m08 (KERN_ATTR_RULES ()) +{ +} + +KERNEL_FQ void m24900_m16 (KERN_ATTR_RULES ()) +{ +} + +KERNEL_FQ void m24900_s04 (KERN_ATTR_RULES ()) +{ + /** + * 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 & 63; + + /** + * digest + */ + + const u32 search[4] = + { + digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R0], + digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R1], + 0, + 0 + }; + + /** + * lookup table + */ + + const u8 sof_lut[64] = + { + 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, + 0x38, 0x39, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, + 0x47, 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, + 0x4f, 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, + 0x57, 0x58, 0x59, 0x5a, 0x61, 0x62, 0x63, 0x64, + 0x65, 0x66, 0x67, 0x68, 0x69, 0x6a, 0x6b, 0x6c, + 0x6d, 0x6e, 0x6f, 0x70, 0x71, 0x72, 0x73, 0x74, + 0x75, 0x76, 0x77, 0x78, 0x79, 0x7a, 0x00, 0x00 + }; + + /** + * 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_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1); + + append_0x80_2x4_VV (w0, w1, out_len); + + w3[2] = out_len * 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); + + u32x t; + + MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22); + MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23); + MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22); + MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23); + MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22); + MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23); + MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22); + MD5_STEP (MD5_H2, 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 += MD5M_A; + b += MD5M_B; + c += MD5M_C; + d += MD5M_D; + + u16 t_abcd = ((a & 0xff) + ((a >> 8) & 0xff)); + u8 a_12 = (t_abcd % 0x3e); + + t_abcd = (((a >> 16 )& 0xff) + ((a >> 24) & 0xff)); + u8 a_34 = (t_abcd % 0x3e); + + t_abcd = ((b & 0xff) + ((b >> 8) & 0xff)); + u8 b_12 = (t_abcd % 0x3e); + + t_abcd = (((b >> 16) & 0xff) + ((b >> 24) & 0xff)); + u8 b_34 = (t_abcd % 0x3e); + + t_abcd = ((c & 0xff) + ((c >> 8) & 0xff)); + u8 c_12 = (t_abcd % 0x3e); + + t_abcd = (((c >> 16 )& 0xff) + ((c >> 24) & 0xff)); + u8 c_34 = (t_abcd % 0x3e); + + t_abcd = ((d & 0xff) + ((d >> 8) & 0xff)); + u8 d_12 = (t_abcd % 0x3e); + + t_abcd = (((d >> 16) & 0xff) + ((d >> 24) & 0xff)); + u8 d_34 = (t_abcd % 0x3e); + + a = (sof_lut[a_12]) + (sof_lut[a_34] << 8) + (sof_lut[b_12] << 16) + (sof_lut[b_34] << 24); + b = (sof_lut[c_12]) + (sof_lut[c_34] << 8) + (sof_lut[d_12] << 16) + (sof_lut[d_34] << 24); + + u32x z = 0; + + COMPARE_S_SIMD (a, b, z, z); + + } +} + +KERNEL_FQ void m24900_s08 (KERN_ATTR_RULES ()) +{ +} + +KERNEL_FQ void m24900_s16 (KERN_ATTR_RULES ()) +{ +} diff --git a/OpenCL/m24900_a1-optimized.cl b/OpenCL/m24900_a1-optimized.cl new file mode 100644 index 000000000..3a44018fc --- /dev/null +++ b/OpenCL/m24900_a1-optimized.cl @@ -0,0 +1,516 @@ +/** + * Author......: See docs/credits.txt + * License.....: MIT + */ + +#define NEW_SIMD_CODE + +#ifdef KERNEL_STATIC +#include "inc_vendor.h" +#include "inc_types.h" +#include "inc_platform.cl" +#include "inc_common.cl" +#include "inc_scalar.cl" +#include "inc_simd.cl" +#include "inc_hash_md5.cl" +#endif + +KERNEL_FQ void m24900_m04 (KERN_ATTR_BASIC ()) +{ + /** + * 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_l_len = pws[gid].pw_len & 63; + + /** + * lookup table + */ + + const u8 sof_lut[64] = + { + 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, + 0x38, 0x39, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, + 0x47, 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, + 0x4f, 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, + 0x57, 0x58, 0x59, 0x5a, 0x61, 0x62, 0x63, 0x64, + 0x65, 0x66, 0x67, 0x68, 0x69, 0x6a, 0x6b, 0x6c, + 0x6d, 0x6e, 0x6f, 0x70, 0x71, 0x72, 0x73, 0x74, + 0x75, 0x76, 0x77, 0x78, 0x79, 0x7a, 0x00, 0x00 + }; + + /** + * loop + */ + + for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE) + { + const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63; + + const u32x pw_len = (pw_l_len + pw_r_len) & 63; + + /** + * concat password candidate + */ + + u32x wordl0[4] = { 0 }; + u32x wordl1[4] = { 0 }; + u32x wordl2[4] = { 0 }; + u32x wordl3[4] = { 0 }; + + wordl0[0] = pw_buf0[0]; + wordl0[1] = pw_buf0[1]; + wordl0[2] = pw_buf0[2]; + wordl0[3] = pw_buf0[3]; + wordl1[0] = pw_buf1[0]; + wordl1[1] = pw_buf1[1]; + wordl1[2] = pw_buf1[2]; + wordl1[3] = pw_buf1[3]; + + u32x wordr0[4] = { 0 }; + u32x wordr1[4] = { 0 }; + u32x wordr2[4] = { 0 }; + u32x wordr3[4] = { 0 }; + + wordr0[0] = ix_create_combt (combs_buf, il_pos, 0); + wordr0[1] = ix_create_combt (combs_buf, il_pos, 1); + wordr0[2] = ix_create_combt (combs_buf, il_pos, 2); + wordr0[3] = ix_create_combt (combs_buf, il_pos, 3); + wordr1[0] = ix_create_combt (combs_buf, il_pos, 4); + wordr1[1] = ix_create_combt (combs_buf, il_pos, 5); + wordr1[2] = ix_create_combt (combs_buf, il_pos, 6); + wordr1[3] = ix_create_combt (combs_buf, il_pos, 7); + + if (combs_mode == COMBINATOR_MODE_BASE_LEFT) + { + switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len); + } + else + { + switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len); + } + + u32x w0[4]; + u32x w1[4]; + u32x w2[4]; + u32x w3[4]; + + w0[0] = wordl0[0] | wordr0[0]; + w0[1] = wordl0[1] | wordr0[1]; + w0[2] = wordl0[2] | wordr0[2]; + w0[3] = wordl0[3] | wordr0[3]; + w1[0] = wordl1[0] | wordr1[0]; + w1[1] = wordl1[1] | wordr1[1]; + w1[2] = wordl1[2] | wordr1[2]; + w1[3] = wordl1[3] | wordr1[3]; + w2[0] = wordl2[0] | wordr2[0]; + w2[1] = wordl2[1] | wordr2[1]; + w2[2] = wordl2[2] | wordr2[2]; + w2[3] = wordl2[3] | wordr2[3]; + w3[0] = wordl3[0] | wordr3[0]; + w3[1] = wordl3[1] | wordr3[1]; + w3[2] = pw_len * 8; + w3[3] = 0; + + /** + * md5 + */ + + 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); + + u32x t; + + MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22); + MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23); + MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22); + MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23); + MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22); + MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23); + MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22); + MD5_STEP (MD5_H2, 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 += MD5M_A; + b += MD5M_B; + c += MD5M_C; + d += MD5M_D; + + u16 t_abcd = ((a & 0xff) + ((a >> 8) & 0xff)); + u8 a_12 = (t_abcd % 0x3e); + + t_abcd = (((a >> 16 )& 0xff) + ((a >> 24) & 0xff)); + u8 a_34 = (t_abcd % 0x3e); + + t_abcd = ((b & 0xff) + ((b >> 8) & 0xff)); + u8 b_12 = (t_abcd % 0x3e); + + t_abcd = (((b >> 16) & 0xff) + ((b >> 24) & 0xff)); + u8 b_34 = (t_abcd % 0x3e); + + t_abcd = ((c & 0xff) + ((c >> 8) & 0xff)); + u8 c_12 = (t_abcd % 0x3e); + + t_abcd = (((c >> 16 )& 0xff) + ((c >> 24) & 0xff)); + u8 c_34 = (t_abcd % 0x3e); + + t_abcd = ((d & 0xff) + ((d >> 8) & 0xff)); + u8 d_12 = (t_abcd % 0x3e); + + t_abcd = (((d >> 16) & 0xff) + ((d >> 24) & 0xff)); + u8 d_34 = (t_abcd % 0x3e); + + a = (sof_lut[a_12]) + (sof_lut[a_34] << 8) + (sof_lut[b_12] << 16) + (sof_lut[b_34] << 24); + b = (sof_lut[c_12]) + (sof_lut[c_34] << 8) + (sof_lut[d_12] << 16) + (sof_lut[d_34] << 24); + + u32x z = 0; + + COMPARE_M_SIMD (a, b, z, z); + } +} + +KERNEL_FQ void m24900_m08 (KERN_ATTR_BASIC ()) +{ +} + +KERNEL_FQ void m24900_m16 (KERN_ATTR_BASIC ()) +{ +} + +KERNEL_FQ void m24900_s04 (KERN_ATTR_BASIC ()) +{ + /** + * 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_l_len = pws[gid].pw_len & 63; + + /** + * lookup table + */ + + const u8 sof_lut[64] = + { + 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, + 0x38, 0x39, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, + 0x47, 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, + 0x4f, 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, + 0x57, 0x58, 0x59, 0x5a, 0x61, 0x62, 0x63, 0x64, + 0x65, 0x66, 0x67, 0x68, 0x69, 0x6a, 0x6b, 0x6c, + 0x6d, 0x6e, 0x6f, 0x70, 0x71, 0x72, 0x73, 0x74, + 0x75, 0x76, 0x77, 0x78, 0x79, 0x7a, 0x00, 0x00 + }; + + /** + * digest + */ + + const u32 search[4] = + { + digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R0], + digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R1], + 0, + 0 + }; + + /** + * loop + */ + + for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE) + { + const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63; + + const u32x pw_len = (pw_l_len + pw_r_len) & 63; + + /** + * concat password candidate + */ + + u32x wordl0[4] = { 0 }; + u32x wordl1[4] = { 0 }; + u32x wordl2[4] = { 0 }; + u32x wordl3[4] = { 0 }; + + wordl0[0] = pw_buf0[0]; + wordl0[1] = pw_buf0[1]; + wordl0[2] = pw_buf0[2]; + wordl0[3] = pw_buf0[3]; + wordl1[0] = pw_buf1[0]; + wordl1[1] = pw_buf1[1]; + wordl1[2] = pw_buf1[2]; + wordl1[3] = pw_buf1[3]; + + u32x wordr0[4] = { 0 }; + u32x wordr1[4] = { 0 }; + u32x wordr2[4] = { 0 }; + u32x wordr3[4] = { 0 }; + + wordr0[0] = ix_create_combt (combs_buf, il_pos, 0); + wordr0[1] = ix_create_combt (combs_buf, il_pos, 1); + wordr0[2] = ix_create_combt (combs_buf, il_pos, 2); + wordr0[3] = ix_create_combt (combs_buf, il_pos, 3); + wordr1[0] = ix_create_combt (combs_buf, il_pos, 4); + wordr1[1] = ix_create_combt (combs_buf, il_pos, 5); + wordr1[2] = ix_create_combt (combs_buf, il_pos, 6); + wordr1[3] = ix_create_combt (combs_buf, il_pos, 7); + + if (combs_mode == COMBINATOR_MODE_BASE_LEFT) + { + switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len); + } + else + { + switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len); + } + + u32x w0[4]; + u32x w1[4]; + u32x w2[4]; + u32x w3[4]; + + w0[0] = wordl0[0] | wordr0[0]; + w0[1] = wordl0[1] | wordr0[1]; + w0[2] = wordl0[2] | wordr0[2]; + w0[3] = wordl0[3] | wordr0[3]; + w1[0] = wordl1[0] | wordr1[0]; + w1[1] = wordl1[1] | wordr1[1]; + w1[2] = wordl1[2] | wordr1[2]; + w1[3] = wordl1[3] | wordr1[3]; + w2[0] = wordl2[0] | wordr2[0]; + w2[1] = wordl2[1] | wordr2[1]; + w2[2] = wordl2[2] | wordr2[2]; + w2[3] = wordl2[3] | wordr2[3]; + w3[0] = wordl3[0] | wordr3[0]; + w3[1] = wordl3[1] | wordr3[1]; + w3[2] = pw_len * 8; + w3[3] = 0; + + /** + * md5 + */ + + 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); + + u32x t; + + MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22); + MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23); + MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22); + MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23); + MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22); + MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23); + MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22); + MD5_STEP (MD5_H2, 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 += MD5M_A; + b += MD5M_B; + c += MD5M_C; + d += MD5M_D; + + u16 t_abcd = ((a & 0xff) + ((a >> 8) & 0xff)); + u8 a_12 = (t_abcd % 0x3e); + + t_abcd = (((a >> 16 )& 0xff) + ((a >> 24) & 0xff)); + u8 a_34 = (t_abcd % 0x3e); + + t_abcd = ((b & 0xff) + ((b >> 8) & 0xff)); + u8 b_12 = (t_abcd % 0x3e); + + t_abcd = (((b >> 16) & 0xff) + ((b >> 24) & 0xff)); + u8 b_34 = (t_abcd % 0x3e); + + t_abcd = ((c & 0xff) + ((c >> 8) & 0xff)); + u8 c_12 = (t_abcd % 0x3e); + + t_abcd = (((c >> 16 )& 0xff) + ((c >> 24) & 0xff)); + u8 c_34 = (t_abcd % 0x3e); + + t_abcd = ((d & 0xff) + ((d >> 8) & 0xff)); + u8 d_12 = (t_abcd % 0x3e); + + t_abcd = (((d >> 16) & 0xff) + ((d >> 24) & 0xff)); + u8 d_34 = (t_abcd % 0x3e); + + a = (sof_lut[a_12]) + (sof_lut[a_34] << 8) + (sof_lut[b_12] << 16) + (sof_lut[b_34] << 24); + b = (sof_lut[c_12]) + (sof_lut[c_34] << 8) + (sof_lut[d_12] << 16) + (sof_lut[d_34] << 24); + + u32x z = 0; + + COMPARE_S_SIMD (a, b, z, z); + } +} + +KERNEL_FQ void m24900_s08 (KERN_ATTR_BASIC ()) +{ +} + +KERNEL_FQ void m24900_s16 (KERN_ATTR_BASIC ()) +{ +} diff --git a/OpenCL/m24900_a3-optimized.cl b/OpenCL/m24900_a3-optimized.cl new file mode 100644 index 000000000..71a5c01d8 --- /dev/null +++ b/OpenCL/m24900_a3-optimized.cl @@ -0,0 +1,661 @@ +/** + * Author......: See docs/credits.txt + * License.....: MIT + */ + +#define NEW_SIMD_CODE + +#ifdef KERNEL_STATIC +#include "inc_vendor.h" +#include "inc_types.h" +#include "inc_platform.cl" +#include "inc_common.cl" +#include "inc_simd.cl" +#include "inc_hash_md5.cl" +#endif + +DECLSPEC void m24900m (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC ()) +{ + /** + * modifier + */ + + const u64 gid = get_global_id (0); + const u64 lid = get_local_id (0); + + /** + * lookup table + */ + + const u8 sof_lut[64] = + { + 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, + 0x38, 0x39, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, + 0x47, 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, + 0x4f, 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, + 0x57, 0x58, 0x59, 0x5a, 0x61, 0x62, 0x63, 0x64, + 0x65, 0x66, 0x67, 0x68, 0x69, 0x6a, 0x6b, 0x6c, + 0x6d, 0x6e, 0x6f, 0x70, 0x71, 0x72, 0x73, 0x74, + 0x75, 0x76, 0x77, 0x78, 0x79, 0x7a, 0x00, 0x00 + }; + + /** + * loop + */ + + const u32 w0l = w0[0]; + + for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE) + { + const u32x w0r = ix_create_bft (bfs_buf, il_pos); + + const u32x w0lr = w0l | w0r; + + u32x t0[4]; + u32x t1[4]; + u32x t2[4]; + u32x t3[4]; + + t0[0] = w0lr; + t0[1] = w0[1]; + t0[2] = w0[2]; + t0[3] = w0[3]; + t1[0] = w1[0]; + t1[1] = w1[1]; + t1[2] = w1[2]; + t1[3] = w1[3]; + t2[0] = w2[0]; + t2[1] = w2[1]; + t2[2] = w2[2]; + t2[3] = w2[3]; + t3[0] = w3[0]; + t3[1] = w3[1]; + t3[2] = pw_len * 8; + t3[3] = 0; + + /** + * md5 + */ + + u32x a = MD5M_A; + u32x b = MD5M_B; + u32x c = MD5M_C; + u32x d = MD5M_D; + + MD5_STEP (MD5_Fo, a, b, c, d, t0[0], MD5C00, MD5S00); + MD5_STEP (MD5_Fo, d, a, b, c, t0[1], MD5C01, MD5S01); + MD5_STEP (MD5_Fo, c, d, a, b, t0[2], MD5C02, MD5S02); + MD5_STEP (MD5_Fo, b, c, d, a, t0[3], MD5C03, MD5S03); + MD5_STEP (MD5_Fo, a, b, c, d, t1[0], MD5C04, MD5S00); + MD5_STEP (MD5_Fo, d, a, b, c, t1[1], MD5C05, MD5S01); + MD5_STEP (MD5_Fo, c, d, a, b, t1[2], MD5C06, MD5S02); + MD5_STEP (MD5_Fo, b, c, d, a, t1[3], MD5C07, MD5S03); + MD5_STEP (MD5_Fo, a, b, c, d, t2[0], MD5C08, MD5S00); + MD5_STEP (MD5_Fo, d, a, b, c, t2[1], MD5C09, MD5S01); + MD5_STEP (MD5_Fo, c, d, a, b, t2[2], MD5C0a, MD5S02); + MD5_STEP (MD5_Fo, b, c, d, a, t2[3], MD5C0b, MD5S03); + MD5_STEP (MD5_Fo, a, b, c, d, t3[0], MD5C0c, MD5S00); + MD5_STEP (MD5_Fo, d, a, b, c, t3[1], MD5C0d, MD5S01); + MD5_STEP (MD5_Fo, c, d, a, b, t3[2], MD5C0e, MD5S02); + MD5_STEP (MD5_Fo, b, c, d, a, t3[3], MD5C0f, MD5S03); + + MD5_STEP (MD5_Go, a, b, c, d, t0[1], MD5C10, MD5S10); + MD5_STEP (MD5_Go, d, a, b, c, t1[2], MD5C11, MD5S11); + MD5_STEP (MD5_Go, c, d, a, b, t2[3], MD5C12, MD5S12); + MD5_STEP (MD5_Go, b, c, d, a, t0[0], MD5C13, MD5S13); + MD5_STEP (MD5_Go, a, b, c, d, t1[1], MD5C14, MD5S10); + MD5_STEP (MD5_Go, d, a, b, c, t2[2], MD5C15, MD5S11); + MD5_STEP (MD5_Go, c, d, a, b, t3[3], MD5C16, MD5S12); + MD5_STEP (MD5_Go, b, c, d, a, t1[0], MD5C17, MD5S13); + MD5_STEP (MD5_Go, a, b, c, d, t2[1], MD5C18, MD5S10); + MD5_STEP (MD5_Go, d, a, b, c, t3[2], MD5C19, MD5S11); + MD5_STEP (MD5_Go, c, d, a, b, t0[3], MD5C1a, MD5S12); + MD5_STEP (MD5_Go, b, c, d, a, t2[0], MD5C1b, MD5S13); + MD5_STEP (MD5_Go, a, b, c, d, t3[1], MD5C1c, MD5S10); + MD5_STEP (MD5_Go, d, a, b, c, t0[2], MD5C1d, MD5S11); + MD5_STEP (MD5_Go, c, d, a, b, t1[3], MD5C1e, MD5S12); + MD5_STEP (MD5_Go, b, c, d, a, t3[0], MD5C1f, MD5S13); + + u32x t; + + MD5_STEP (MD5_H1, a, b, c, d, t1[1], MD5C20, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, t2[0], MD5C21, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, t2[3], MD5C22, MD5S22); + MD5_STEP (MD5_H2, b, c, d, a, t3[2], MD5C23, MD5S23); + MD5_STEP (MD5_H1, a, b, c, d, t0[1], MD5C24, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, t1[0], MD5C25, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, t1[3], MD5C26, MD5S22); + MD5_STEP (MD5_H2, b, c, d, a, t2[2], MD5C27, MD5S23); + MD5_STEP (MD5_H1, a, b, c, d, t3[1], MD5C28, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, t0[0], MD5C29, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, t0[3], MD5C2a, MD5S22); + MD5_STEP (MD5_H2, b, c, d, a, t1[2], MD5C2b, MD5S23); + MD5_STEP (MD5_H1, a, b, c, d, t2[1], MD5C2c, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, t3[0], MD5C2d, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, t3[3], MD5C2e, MD5S22); + MD5_STEP (MD5_H2, b, c, d, a, t0[2], MD5C2f, MD5S23); + + MD5_STEP (MD5_I , a, b, c, d, t0[0], MD5C30, MD5S30); + MD5_STEP (MD5_I , d, a, b, c, t1[3], MD5C31, MD5S31); + MD5_STEP (MD5_I , c, d, a, b, t3[2], MD5C32, MD5S32); + MD5_STEP (MD5_I , b, c, d, a, t1[1], MD5C33, MD5S33); + MD5_STEP (MD5_I , a, b, c, d, t3[0], MD5C34, MD5S30); + MD5_STEP (MD5_I , d, a, b, c, t0[3], MD5C35, MD5S31); + MD5_STEP (MD5_I , c, d, a, b, t2[2], MD5C36, MD5S32); + MD5_STEP (MD5_I , b, c, d, a, t0[1], MD5C37, MD5S33); + MD5_STEP (MD5_I , a, b, c, d, t2[0], MD5C38, MD5S30); + MD5_STEP (MD5_I , d, a, b, c, t3[3], MD5C39, MD5S31); + MD5_STEP (MD5_I , c, d, a, b, t1[2], MD5C3a, MD5S32); + MD5_STEP (MD5_I , b, c, d, a, t3[1], MD5C3b, MD5S33); + MD5_STEP (MD5_I , a, b, c, d, t1[0], MD5C3c, MD5S30); + MD5_STEP (MD5_I , d, a, b, c, t2[3], MD5C3d, MD5S31); + MD5_STEP (MD5_I , c, d, a, b, t0[2], MD5C3e, MD5S32); + MD5_STEP (MD5_I , b, c, d, a, t2[1], MD5C3f, MD5S33); + + a += MD5M_A; + b += MD5M_B; + c += MD5M_C; + d += MD5M_D; + + u16 t_abcd = ((a & 0xff) + ((a >> 8) & 0xff)); + u8 a_12 = (t_abcd % 0x3e); + + t_abcd = (((a >> 16 )& 0xff) + ((a >> 24) & 0xff)); + u8 a_34 = (t_abcd % 0x3e); + + t_abcd = ((b & 0xff) + ((b >> 8) & 0xff)); + u8 b_12 = (t_abcd % 0x3e); + + t_abcd = (((b >> 16) & 0xff) + ((b >> 24) & 0xff)); + u8 b_34 = (t_abcd % 0x3e); + + t_abcd = ((c & 0xff) + ((c >> 8) & 0xff)); + u8 c_12 = (t_abcd % 0x3e); + + t_abcd = (((c >> 16 )& 0xff) + ((c >> 24) & 0xff)); + u8 c_34 = (t_abcd % 0x3e); + + t_abcd = ((d & 0xff) + ((d >> 8) & 0xff)); + u8 d_12 = (t_abcd % 0x3e); + + t_abcd = (((d >> 16) & 0xff) + ((d >> 24) & 0xff)); + u8 d_34 = (t_abcd % 0x3e); + + a = (sof_lut[a_12]) + (sof_lut[a_34] << 8) + (sof_lut[b_12] << 16) + (sof_lut[b_34] << 24); + b = (sof_lut[c_12]) + (sof_lut[c_34] << 8) + (sof_lut[d_12] << 16) + (sof_lut[d_34] << 24); + + u32x z = 0; + + COMPARE_M_SIMD (a, b, z, z); + } +} + +DECLSPEC void m24900s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC ()) +{ + /** + * modifier + */ + + const u64 gid = get_global_id (0); + const u64 lid = get_local_id (0); + + /** + * digest + */ + + const u32 search[4] = + { + digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R0], + digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R1], + 0, + 0 + }; + + /** + * lookup table + */ + + const u8 sof_lut[64] = + { + 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, + 0x38, 0x39, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, + 0x47, 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, + 0x4f, 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, + 0x57, 0x58, 0x59, 0x5a, 0x61, 0x62, 0x63, 0x64, + 0x65, 0x66, 0x67, 0x68, 0x69, 0x6a, 0x6b, 0x6c, + 0x6d, 0x6e, 0x6f, 0x70, 0x71, 0x72, 0x73, 0x74, + 0x75, 0x76, 0x77, 0x78, 0x79, 0x7a, 0x00, 0x00 + }; + + /** + * loop + */ + + const u32 w0l = w0[0]; + + for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE) + { + const u32x w0r = ix_create_bft (bfs_buf, il_pos); + + const u32x w0lr = w0l | w0r; + + u32x t0[4]; + u32x t1[4]; + u32x t2[4]; + u32x t3[4]; + + t0[0] = w0lr; + t0[1] = w0[1]; + t0[2] = w0[2]; + t0[3] = w0[3]; + t1[0] = w1[0]; + t1[1] = w1[1]; + t1[2] = w1[2]; + t1[3] = w1[3]; + t2[0] = w2[0]; + t2[1] = w2[1]; + t2[2] = w2[2]; + t2[3] = w2[3]; + t3[0] = w3[0]; + t3[1] = w3[1]; + t3[2] = pw_len * 8; + t3[3] = 0; + + /** + * md5 + */ + + u32x a = MD5M_A; + u32x b = MD5M_B; + u32x c = MD5M_C; + u32x d = MD5M_D; + + MD5_STEP (MD5_Fo, a, b, c, d, t0[0], MD5C00, MD5S00); + MD5_STEP (MD5_Fo, d, a, b, c, t0[1], MD5C01, MD5S01); + MD5_STEP (MD5_Fo, c, d, a, b, t0[2], MD5C02, MD5S02); + MD5_STEP (MD5_Fo, b, c, d, a, t0[3], MD5C03, MD5S03); + MD5_STEP (MD5_Fo, a, b, c, d, t1[0], MD5C04, MD5S00); + MD5_STEP (MD5_Fo, d, a, b, c, t1[1], MD5C05, MD5S01); + MD5_STEP (MD5_Fo, c, d, a, b, t1[2], MD5C06, MD5S02); + MD5_STEP (MD5_Fo, b, c, d, a, t1[3], MD5C07, MD5S03); + MD5_STEP (MD5_Fo, a, b, c, d, t2[0], MD5C08, MD5S00); + MD5_STEP (MD5_Fo, d, a, b, c, t2[1], MD5C09, MD5S01); + MD5_STEP (MD5_Fo, c, d, a, b, t2[2], MD5C0a, MD5S02); + MD5_STEP (MD5_Fo, b, c, d, a, t2[3], MD5C0b, MD5S03); + MD5_STEP (MD5_Fo, a, b, c, d, t3[0], MD5C0c, MD5S00); + MD5_STEP (MD5_Fo, d, a, b, c, t3[1], MD5C0d, MD5S01); + MD5_STEP (MD5_Fo, c, d, a, b, t3[2], MD5C0e, MD5S02); + MD5_STEP (MD5_Fo, b, c, d, a, t3[3], MD5C0f, MD5S03); + + MD5_STEP (MD5_Go, a, b, c, d, t0[1], MD5C10, MD5S10); + MD5_STEP (MD5_Go, d, a, b, c, t1[2], MD5C11, MD5S11); + MD5_STEP (MD5_Go, c, d, a, b, t2[3], MD5C12, MD5S12); + MD5_STEP (MD5_Go, b, c, d, a, t0[0], MD5C13, MD5S13); + MD5_STEP (MD5_Go, a, b, c, d, t1[1], MD5C14, MD5S10); + MD5_STEP (MD5_Go, d, a, b, c, t2[2], MD5C15, MD5S11); + MD5_STEP (MD5_Go, c, d, a, b, t3[3], MD5C16, MD5S12); + MD5_STEP (MD5_Go, b, c, d, a, t1[0], MD5C17, MD5S13); + MD5_STEP (MD5_Go, a, b, c, d, t2[1], MD5C18, MD5S10); + MD5_STEP (MD5_Go, d, a, b, c, t3[2], MD5C19, MD5S11); + MD5_STEP (MD5_Go, c, d, a, b, t0[3], MD5C1a, MD5S12); + MD5_STEP (MD5_Go, b, c, d, a, t2[0], MD5C1b, MD5S13); + MD5_STEP (MD5_Go, a, b, c, d, t3[1], MD5C1c, MD5S10); + MD5_STEP (MD5_Go, d, a, b, c, t0[2], MD5C1d, MD5S11); + MD5_STEP (MD5_Go, c, d, a, b, t1[3], MD5C1e, MD5S12); + MD5_STEP (MD5_Go, b, c, d, a, t3[0], MD5C1f, MD5S13); + + u32x t; + + MD5_STEP (MD5_H1, a, b, c, d, t1[1], MD5C20, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, t2[0], MD5C21, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, t2[3], MD5C22, MD5S22); + MD5_STEP (MD5_H2, b, c, d, a, t3[2], MD5C23, MD5S23); + MD5_STEP (MD5_H1, a, b, c, d, t0[1], MD5C24, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, t1[0], MD5C25, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, t1[3], MD5C26, MD5S22); + MD5_STEP (MD5_H2, b, c, d, a, t2[2], MD5C27, MD5S23); + MD5_STEP (MD5_H1, a, b, c, d, t3[1], MD5C28, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, t0[0], MD5C29, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, t0[3], MD5C2a, MD5S22); + MD5_STEP (MD5_H2, b, c, d, a, t1[2], MD5C2b, MD5S23); + MD5_STEP (MD5_H1, a, b, c, d, t2[1], MD5C2c, MD5S20); + MD5_STEP (MD5_H2, d, a, b, c, t3[0], MD5C2d, MD5S21); + MD5_STEP (MD5_H1, c, d, a, b, t3[3], MD5C2e, MD5S22); + MD5_STEP (MD5_H2, b, c, d, a, t0[2], MD5C2f, MD5S23); + + MD5_STEP (MD5_I , a, b, c, d, t0[0], MD5C30, MD5S30); + MD5_STEP (MD5_I , d, a, b, c, t1[3], MD5C31, MD5S31); + MD5_STEP (MD5_I , c, d, a, b, t3[2], MD5C32, MD5S32); + MD5_STEP (MD5_I , b, c, d, a, t1[1], MD5C33, MD5S33); + MD5_STEP (MD5_I , a, b, c, d, t3[0], MD5C34, MD5S30); + MD5_STEP (MD5_I , d, a, b, c, t0[3], MD5C35, MD5S31); + MD5_STEP (MD5_I , c, d, a, b, t2[2], MD5C36, MD5S32); + MD5_STEP (MD5_I , b, c, d, a, t0[1], MD5C37, MD5S33); + MD5_STEP (MD5_I , a, b, c, d, t2[0], MD5C38, MD5S30); + MD5_STEP (MD5_I , d, a, b, c, t3[3], MD5C39, MD5S31); + MD5_STEP (MD5_I , c, d, a, b, t1[2], MD5C3a, MD5S32); + MD5_STEP (MD5_I , b, c, d, a, t3[1], MD5C3b, MD5S33); + MD5_STEP (MD5_I , a, b, c, d, t1[0], MD5C3c, MD5S30); + MD5_STEP (MD5_I , d, a, b, c, t2[3], MD5C3d, MD5S31); + MD5_STEP (MD5_I , c, d, a, b, t0[2], MD5C3e, MD5S32); + MD5_STEP (MD5_I , b, c, d, a, t2[1], MD5C3f, MD5S33); + + a += MD5M_A; + b += MD5M_B; + c += MD5M_C; + d += MD5M_D; + + u16 t_abcd = ((a & 0xff) + ((a >> 8) & 0xff)); + u8 a_12 = (t_abcd % 0x3e); + + t_abcd = (((a >> 16 )& 0xff) + ((a >> 24) & 0xff)); + u8 a_34 = (t_abcd % 0x3e); + + t_abcd = ((b & 0xff) + ((b >> 8) & 0xff)); + u8 b_12 = (t_abcd % 0x3e); + + t_abcd = (((b >> 16) & 0xff) + ((b >> 24) & 0xff)); + u8 b_34 = (t_abcd % 0x3e); + + t_abcd = ((c & 0xff) + ((c >> 8) & 0xff)); + u8 c_12 = (t_abcd % 0x3e); + + t_abcd = (((c >> 16 )& 0xff) + ((c >> 24) & 0xff)); + u8 c_34 = (t_abcd % 0x3e); + + t_abcd = ((d & 0xff) + ((d >> 8) & 0xff)); + u8 d_12 = (t_abcd % 0x3e); + + t_abcd = (((d >> 16) & 0xff) + ((d >> 24) & 0xff)); + u8 d_34 = (t_abcd % 0x3e); + + a = (sof_lut[a_12]) + (sof_lut[a_34] << 8) + (sof_lut[b_12] << 16) + (sof_lut[b_34] << 24); + b = (sof_lut[c_12]) + (sof_lut[c_34] << 8) + (sof_lut[d_12] << 16) + (sof_lut[d_34] << 24); + + u32x z = 0; + + COMPARE_S_SIMD (a, b, z, z); + } +} + +KERNEL_FQ void m24900_m04 (KERN_ATTR_BASIC ()) +{ + /** + * base + */ + + const u64 gid = get_global_id (0); + + if (gid >= gid_max) return; + + u32 w0[4]; + + w0[0] = pws[gid].i[ 0]; + w0[1] = pws[gid].i[ 1]; + w0[2] = pws[gid].i[ 2]; + w0[3] = pws[gid].i[ 3]; + + u32 w1[4]; + + w1[0] = 0; + w1[1] = 0; + w1[2] = 0; + w1[3] = 0; + + u32 w2[4]; + + w2[0] = 0; + w2[1] = 0; + w2[2] = 0; + w2[3] = 0; + + u32 w3[4]; + + w3[0] = 0; + w3[1] = 0; + w3[2] = 0; + w3[3] = 0; + + const u32 pw_len = pws[gid].pw_len & 63; + + /** + * main + */ + + m24900m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, pws_pos, gid_max); +} + +KERNEL_FQ void m24900_m08 (KERN_ATTR_BASIC ()) +{ + /** + * base + */ + + const u64 gid = get_global_id (0); + + if (gid >= gid_max) return; + + u32 w0[4]; + + w0[0] = pws[gid].i[ 0]; + w0[1] = pws[gid].i[ 1]; + w0[2] = pws[gid].i[ 2]; + w0[3] = pws[gid].i[ 3]; + + u32 w1[4]; + + w1[0] = pws[gid].i[ 4]; + w1[1] = pws[gid].i[ 5]; + w1[2] = pws[gid].i[ 6]; + w1[3] = pws[gid].i[ 7]; + + u32 w2[4]; + + w2[0] = 0; + w2[1] = 0; + w2[2] = 0; + w2[3] = 0; + + u32 w3[4]; + + w3[0] = 0; + w3[1] = 0; + w3[2] = 0; + w3[3] = 0; + + const u32 pw_len = pws[gid].pw_len & 63; + + /** + * main + */ + + m24900m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, pws_pos, gid_max); +} + +KERNEL_FQ void m24900_m16 (KERN_ATTR_BASIC ()) +{ + /** + * base + */ + + const u64 gid = get_global_id (0); + + if (gid >= gid_max) return; + + u32 w0[4]; + + w0[0] = pws[gid].i[ 0]; + w0[1] = pws[gid].i[ 1]; + w0[2] = pws[gid].i[ 2]; + w0[3] = pws[gid].i[ 3]; + + u32 w1[4]; + + w1[0] = pws[gid].i[ 4]; + w1[1] = pws[gid].i[ 5]; + w1[2] = pws[gid].i[ 6]; + w1[3] = pws[gid].i[ 7]; + + u32 w2[4]; + + w2[0] = pws[gid].i[ 8]; + w2[1] = pws[gid].i[ 9]; + w2[2] = pws[gid].i[10]; + w2[3] = pws[gid].i[11]; + + u32 w3[4]; + + w3[0] = pws[gid].i[12]; + w3[1] = pws[gid].i[13]; + w3[2] = 0; + w3[3] = 0; + + const u32 pw_len = pws[gid].pw_len & 63; + + /** + * main + */ + + m24900m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, pws_pos, gid_max); +} + +KERNEL_FQ void m24900_s04 (KERN_ATTR_BASIC ()) +{ + /** + * base + */ + + const u64 gid = get_global_id (0); + + if (gid >= gid_max) return; + + u32 w0[4]; + + w0[0] = pws[gid].i[ 0]; + w0[1] = pws[gid].i[ 1]; + w0[2] = pws[gid].i[ 2]; + w0[3] = pws[gid].i[ 3]; + + u32 w1[4]; + + w1[0] = 0; + w1[1] = 0; + w1[2] = 0; + w1[3] = 0; + + u32 w2[4]; + + w2[0] = 0; + w2[1] = 0; + w2[2] = 0; + w2[3] = 0; + + u32 w3[4]; + + w3[0] = 0; + w3[1] = 0; + w3[2] = 0; + w3[3] = 0; + + const u32 pw_len = pws[gid].pw_len & 63; + + /** + * main + */ + + m24900s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, pws_pos, gid_max); +} + +KERNEL_FQ void m24900_s08 (KERN_ATTR_BASIC ()) +{ + /** + * base + */ + + const u64 gid = get_global_id (0); + + if (gid >= gid_max) return; + + u32 w0[4]; + + w0[0] = pws[gid].i[ 0]; + w0[1] = pws[gid].i[ 1]; + w0[2] = pws[gid].i[ 2]; + w0[3] = pws[gid].i[ 3]; + + u32 w1[4]; + + w1[0] = pws[gid].i[ 4]; + w1[1] = pws[gid].i[ 5]; + w1[2] = pws[gid].i[ 6]; + w1[3] = pws[gid].i[ 7]; + + u32 w2[4]; + + w2[0] = 0; + w2[1] = 0; + w2[2] = 0; + w2[3] = 0; + + u32 w3[4]; + + w3[0] = 0; + w3[1] = 0; + w3[2] = 0; + w3[3] = 0; + + const u32 pw_len = pws[gid].pw_len & 63; + + /** + * main + */ + + m24900s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, pws_pos, gid_max); +} + +KERNEL_FQ void m24900_s16 (KERN_ATTR_BASIC ()) +{ + /** + * base + */ + + const u64 gid = get_global_id (0); + + if (gid >= gid_max) return; + + u32 w0[4]; + + w0[0] = pws[gid].i[ 0]; + w0[1] = pws[gid].i[ 1]; + w0[2] = pws[gid].i[ 2]; + w0[3] = pws[gid].i[ 3]; + + u32 w1[4]; + + w1[0] = pws[gid].i[ 4]; + w1[1] = pws[gid].i[ 5]; + w1[2] = pws[gid].i[ 6]; + w1[3] = pws[gid].i[ 7]; + + u32 w2[4]; + + w2[0] = pws[gid].i[ 8]; + w2[1] = pws[gid].i[ 9]; + w2[2] = pws[gid].i[10]; + w2[3] = pws[gid].i[11]; + + u32 w3[4]; + + w3[0] = pws[gid].i[12]; + w3[1] = pws[gid].i[13]; + w3[2] = 0; + w3[3] = 0; + + const u32 pw_len = pws[gid].pw_len & 63; + + /** + * main + */ + + m24900s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, pws_pos, gid_max); +} diff --git a/docs/changes.txt b/docs/changes.txt index 387941f96..cc63abd57 100644 --- a/docs/changes.txt +++ b/docs/changes.txt @@ -14,6 +14,7 @@ - Added hash-mode: RAR3-p (Uncompressed) - Added hash-mode: RSA/DSA/EC/OPENSSH Private Keys - Added hash-mode: sha1(sha1($pass).$salt) +- Added hash-mode: Dahua Authentication MD5 ## ## Bugs diff --git a/docs/readme.txt b/docs/readme.txt index 21fec6f19..38b7fe300 100644 --- a/docs/readme.txt +++ b/docs/readme.txt @@ -336,6 +336,7 @@ NVIDIA GPUs require "NVIDIA Driver" (440.64 or later) and "CUDA Toolkit" (9.0 or - Django (SHA-1) - Web2py pbkdf2-sha512 - TOTP (HMAC-SHA1) +- Dahua Authentication MD5 ## ## Attack-Modes diff --git a/src/modules/module_24900.c b/src/modules/module_24900.c new file mode 100644 index 000000000..436060dc3 --- /dev/null +++ b/src/modules/module_24900.c @@ -0,0 +1,184 @@ +/** + * Author......: See docs/credits.txt + * License.....: MIT + */ + +#include "common.h" +#include "types.h" +#include "modules.h" +#include "bitops.h" +#include "convert.h" +#include "shared.h" + +static const u32 ATTACK_EXEC = ATTACK_EXEC_INSIDE_KERNEL; +static const u32 DGST_POS0 = 0; +static const u32 DGST_POS1 = 1; +static const u32 DGST_POS2 = 2; +static const u32 DGST_POS3 = 3; +static const u32 DGST_SIZE = DGST_SIZE_4_4; +static const u32 HASH_CATEGORY = HASH_CATEGORY_RAW_HASH; +static const char *HASH_NAME = "Dahua Authentication MD5"; +static const u64 KERN_TYPE = 24900; +static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE + | OPTI_TYPE_PRECOMPUTE_INIT + | OPTI_TYPE_MEET_IN_MIDDLE + | OPTI_TYPE_NOT_ITERATED + | OPTI_TYPE_NOT_SALTED + | OPTI_TYPE_RAW_HASH; +static const u64 OPTS_TYPE = OPTS_TYPE_PT_GENERATE_LE + | OPTS_TYPE_PT_ADD80 + | OPTS_TYPE_PT_ADDBITS14; +static const u32 SALT_TYPE = SALT_TYPE_NONE; +static const char *ST_PASS = "hashcat"; +static const char *ST_HASH = "GRuHbyVp"; + +u32 module_attack_exec (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ATTACK_EXEC; } +u32 module_dgst_pos0 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS0; } +u32 module_dgst_pos1 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS1; } +u32 module_dgst_pos2 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS2; } +u32 module_dgst_pos3 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS3; } +u32 module_dgst_size (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_SIZE; } +u32 module_hash_category (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_CATEGORY; } +const char *module_hash_name (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_NAME; } +u64 module_kern_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return KERN_TYPE; } +u32 module_opti_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTI_TYPE; } +u64 module_opts_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTS_TYPE; } +u32 module_salt_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return SALT_TYPE; } +const char *module_st_hash (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_HASH; } +const char *module_st_pass (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_PASS; } + +int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED void *digest_buf, MAYBE_UNUSED salt_t *salt, MAYBE_UNUSED void *esalt_buf, MAYBE_UNUSED void *hook_salt_buf, MAYBE_UNUSED hashinfo_t *hash_info, const char *line_buf, MAYBE_UNUSED const int line_len) +{ + u32 *digest = (u32 *) digest_buf; + + token_t token; + + token.token_cnt = 1; + + token.len_min[0] = 8; + token.len_max[0] = 8; + token.attr[0] = TOKEN_ATTR_VERIFY_LENGTH; + + const int rc_tokenizer = input_tokenizer ((const u8 *) line_buf, line_len, &token); + + if (rc_tokenizer != PARSER_OK) return (rc_tokenizer); + + u8 temp_hex_buf[17] = { 0 }; + + const u8 *hash_pos = token.buf[0]; + + hex_encode ((u8 *) hash_pos, 8, temp_hex_buf); + + digest[0] = hex_to_u32 (temp_hex_buf + 0); + digest[1] = hex_to_u32 (temp_hex_buf + 8); + digest[2] = 0; + digest[3] = 0; + + return (PARSER_OK); +} + +int module_hash_encode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const void *digest_buf, MAYBE_UNUSED const salt_t *salt, MAYBE_UNUSED const void *esalt_buf, MAYBE_UNUSED const void *hook_salt_buf, MAYBE_UNUSED const hashinfo_t *hash_info, char *line_buf, MAYBE_UNUSED const int line_size) +{ + const u32 *digest = (const u32 *) digest_buf; + + // we can not change anything in the original buffer, otherwise destroying sorting + // therefore create some local buffer + + u32 tmp[4]; + + tmp[0] = digest[0]; + tmp[1] = digest[1]; + tmp[2] = 0; + tmp[3] = 0; + + u8 *out_buf = (u8 *) line_buf; + + u8 ht_buf[17] = { 0 }; + + u32_to_hex (tmp[0], ht_buf + 0); + u32_to_hex (tmp[1], ht_buf + 8); + + hex_decode (ht_buf, 16, (u8 *) out_buf); + + const int out_len = 8; + + return out_len; +} + +void module_init (module_ctx_t *module_ctx) +{ + module_ctx->module_context_size = MODULE_CONTEXT_SIZE_CURRENT; + module_ctx->module_interface_version = MODULE_INTERFACE_VERSION_CURRENT; + + module_ctx->module_attack_exec = module_attack_exec; + module_ctx->module_benchmark_esalt = MODULE_DEFAULT; + module_ctx->module_benchmark_hook_salt = MODULE_DEFAULT; + module_ctx->module_benchmark_mask = MODULE_DEFAULT; + module_ctx->module_benchmark_salt = MODULE_DEFAULT; + module_ctx->module_build_plain_postprocess = MODULE_DEFAULT; + module_ctx->module_deep_comp_kernel = MODULE_DEFAULT; + module_ctx->module_dgst_pos0 = module_dgst_pos0; + module_ctx->module_dgst_pos1 = module_dgst_pos1; + module_ctx->module_dgst_pos2 = module_dgst_pos2; + module_ctx->module_dgst_pos3 = module_dgst_pos3; + module_ctx->module_dgst_size = module_dgst_size; + module_ctx->module_dictstat_disable = MODULE_DEFAULT; + module_ctx->module_esalt_size = MODULE_DEFAULT; + module_ctx->module_extra_buffer_size = MODULE_DEFAULT; + module_ctx->module_extra_tmp_size = MODULE_DEFAULT; + module_ctx->module_forced_outfile_format = MODULE_DEFAULT; + module_ctx->module_hash_binary_count = MODULE_DEFAULT; + module_ctx->module_hash_binary_parse = MODULE_DEFAULT; + module_ctx->module_hash_binary_save = MODULE_DEFAULT; + module_ctx->module_hash_decode_potfile = MODULE_DEFAULT; + module_ctx->module_hash_decode_zero_hash = MODULE_DEFAULT; + module_ctx->module_hash_decode = module_hash_decode; + module_ctx->module_hash_encode_status = MODULE_DEFAULT; + module_ctx->module_hash_encode_potfile = MODULE_DEFAULT; + module_ctx->module_hash_encode = module_hash_encode; + module_ctx->module_hash_init_selftest = MODULE_DEFAULT; + module_ctx->module_hash_mode = MODULE_DEFAULT; + module_ctx->module_hash_category = module_hash_category; + module_ctx->module_hash_name = module_hash_name; + module_ctx->module_hashes_count_min = MODULE_DEFAULT; + module_ctx->module_hashes_count_max = MODULE_DEFAULT; + module_ctx->module_hlfmt_disable = MODULE_DEFAULT; + module_ctx->module_hook_extra_param_size = MODULE_DEFAULT; + module_ctx->module_hook_extra_param_init = MODULE_DEFAULT; + module_ctx->module_hook_extra_param_term = MODULE_DEFAULT; + module_ctx->module_hook12 = MODULE_DEFAULT; + module_ctx->module_hook23 = MODULE_DEFAULT; + module_ctx->module_hook_salt_size = MODULE_DEFAULT; + module_ctx->module_hook_size = MODULE_DEFAULT; + module_ctx->module_jit_build_options = MODULE_DEFAULT; + module_ctx->module_jit_cache_disable = MODULE_DEFAULT; + module_ctx->module_kernel_accel_max = MODULE_DEFAULT; + module_ctx->module_kernel_accel_min = MODULE_DEFAULT; + module_ctx->module_kernel_loops_max = MODULE_DEFAULT; + module_ctx->module_kernel_loops_min = MODULE_DEFAULT; + module_ctx->module_kernel_threads_max = MODULE_DEFAULT; + module_ctx->module_kernel_threads_min = MODULE_DEFAULT; + module_ctx->module_kern_type = module_kern_type; + module_ctx->module_kern_type_dynamic = MODULE_DEFAULT; + module_ctx->module_opti_type = module_opti_type; + module_ctx->module_opts_type = module_opts_type; + module_ctx->module_outfile_check_disable = MODULE_DEFAULT; + module_ctx->module_outfile_check_nocomp = MODULE_DEFAULT; + module_ctx->module_potfile_custom_check = MODULE_DEFAULT; + module_ctx->module_potfile_disable = MODULE_DEFAULT; + module_ctx->module_potfile_keep_all_hashes = MODULE_DEFAULT; + module_ctx->module_pwdump_column = MODULE_DEFAULT; + module_ctx->module_pw_max = MODULE_DEFAULT; + module_ctx->module_pw_min = MODULE_DEFAULT; + module_ctx->module_salt_max = MODULE_DEFAULT; + module_ctx->module_salt_min = MODULE_DEFAULT; + module_ctx->module_salt_type = module_salt_type; + module_ctx->module_separator = MODULE_DEFAULT; + module_ctx->module_st_hash = module_st_hash; + module_ctx->module_st_pass = module_st_pass; + module_ctx->module_tmp_size = MODULE_DEFAULT; + module_ctx->module_unstable_warning = MODULE_DEFAULT; + module_ctx->module_warmup_disable = MODULE_DEFAULT; +} + +