1
0
mirror of https://github.com/hashcat/hashcat.git synced 2024-11-12 18:59:03 +00:00
hashcat/OpenCL/m00030_a3.cl
jsteube 0bf4e3c34a - Dropped all vector code since new GPU's are all scalar, makes the code much easier
- Some performance on low-end GPU may drop because of that, but only for a few hash-modes
- Dropped scalar code (aka warp) since we do not have any vector datatypes anymore
- Renamed C++ overloading functions memcat32_9 -> memcat_c32_w4x4_a3x4
- Still need to fix kernels to new function names, needs to be done manually
- Temperature Management needs to be rewritten partially because of conflicting datatypes names
- Added code to create different codepaths for NV on AMD in runtime in host (see data.vendor_id)
- Added code to create different codepaths for NV on AMD in runtime in kernels (see IS_NV and IS_AMD)
- First tests working for -m 0, for example
- Great performance increases in general for NV so far
- Tested amp_* and markov_* kernel
- Migrated special NV optimizations for rule processor
2015-12-15 12:04:22 +01:00

738 lines
30 KiB
Common Lisp

/**
* Author......: Jens Steube <jens.steube@gmail.com>
* License.....: MIT
*/
#define _MD5_
#include "include/constants.h"
#include "include/kernel_vendor.h"
#define DGST_R0 0
#define DGST_R1 3
#define DGST_R2 2
#define DGST_R3 1
#include "include/kernel_functions.c"
#include "types_ocl.c"
#include "common.c"
#define COMPARE_S "check_single_comp4.c"
#define COMPARE_M "check_multi_comp4.c"
#define MD5_STEP_REV(f,a,b,c,d,x,t,s) \
{ \
a -= b; \
a = rotr32 (a, s); \
a -= f (b, c, d); \
a -= x; \
a -= t; \
}
#define MD5_STEP_REV1(f,a,b,c,d,x,t,s) \
{ \
a -= b; \
a = rotr32 (a, s); \
a -= x; \
a -= t; \
}
static void m00030m (u32 w[16], const u32 pw_len, __global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32 * words_buf_r, __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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset)
{
/**
* modifier
*/
const u32 gid = get_global_id (0);
const u32 lid = get_local_id (0);
/**
* salt
*/
u32 salt_buf0[4];
salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
u32 salt_buf1[4];
salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
u32 salt_buf2[4];
salt_buf2[0] = salt_bufs[salt_pos].salt_buf[ 8];
salt_buf2[1] = 0;
salt_buf2[2] = 0;
salt_buf2[3] = 0;
u32 salt_buf3[4];
salt_buf3[0] = 0;
salt_buf3[1] = 0;
salt_buf3[2] = 0;
salt_buf3[3] = 0;
switch_buffer_by_offset (salt_buf0, salt_buf1, salt_buf2, salt_buf3, pw_len);
w[ 0] |= salt_buf0[0];
w[ 1] |= salt_buf0[1];
w[ 2] |= salt_buf0[2];
w[ 3] |= salt_buf0[3];
w[ 4] |= salt_buf1[0];
w[ 5] |= salt_buf1[1];
w[ 6] |= salt_buf1[2];
w[ 7] |= salt_buf1[3];
w[ 8] |= salt_buf2[0];
w[ 9] |= salt_buf2[1];
w[10] |= salt_buf2[2];
w[11] |= salt_buf2[3];
w[12] |= salt_buf3[0];
w[13] |= salt_buf3[1];
w[14] |= salt_buf3[2];
w[15] |= salt_buf3[3];
const u32 salt_len = salt_bufs[salt_pos].salt_len;
const u32 pw_salt_len = pw_len + salt_len;
w[14] = pw_salt_len * 8;
/**
* base
*/
const u32 F_w0c00 = 0 + MD5C00;
const u32 F_w1c01 = w[ 1] + MD5C01;
const u32 F_w2c02 = w[ 2] + MD5C02;
const u32 F_w3c03 = w[ 3] + MD5C03;
const u32 F_w4c04 = w[ 4] + MD5C04;
const u32 F_w5c05 = w[ 5] + MD5C05;
const u32 F_w6c06 = w[ 6] + MD5C06;
const u32 F_w7c07 = w[ 7] + MD5C07;
const u32 F_w8c08 = w[ 8] + MD5C08;
const u32 F_w9c09 = w[ 9] + MD5C09;
const u32 F_wac0a = w[10] + MD5C0a;
const u32 F_wbc0b = w[11] + MD5C0b;
const u32 F_wcc0c = w[12] + MD5C0c;
const u32 F_wdc0d = w[13] + MD5C0d;
const u32 F_wec0e = w[14] + MD5C0e;
const u32 F_wfc0f = w[15] + MD5C0f;
const u32 G_w1c10 = w[ 1] + MD5C10;
const u32 G_w6c11 = w[ 6] + MD5C11;
const u32 G_wbc12 = w[11] + MD5C12;
const u32 G_w0c13 = 0 + MD5C13;
const u32 G_w5c14 = w[ 5] + MD5C14;
const u32 G_wac15 = w[10] + MD5C15;
const u32 G_wfc16 = w[15] + MD5C16;
const u32 G_w4c17 = w[ 4] + MD5C17;
const u32 G_w9c18 = w[ 9] + MD5C18;
const u32 G_wec19 = w[14] + MD5C19;
const u32 G_w3c1a = w[ 3] + MD5C1a;
const u32 G_w8c1b = w[ 8] + MD5C1b;
const u32 G_wdc1c = w[13] + MD5C1c;
const u32 G_w2c1d = w[ 2] + MD5C1d;
const u32 G_w7c1e = w[ 7] + MD5C1e;
const u32 G_wcc1f = w[12] + MD5C1f;
const u32 H_w5c20 = w[ 5] + MD5C20;
const u32 H_w8c21 = w[ 8] + MD5C21;
const u32 H_wbc22 = w[11] + MD5C22;
const u32 H_wec23 = w[14] + MD5C23;
const u32 H_w1c24 = w[ 1] + MD5C24;
const u32 H_w4c25 = w[ 4] + MD5C25;
const u32 H_w7c26 = w[ 7] + MD5C26;
const u32 H_wac27 = w[10] + MD5C27;
const u32 H_wdc28 = w[13] + MD5C28;
const u32 H_w0c29 = 0 + MD5C29;
const u32 H_w3c2a = w[ 3] + MD5C2a;
const u32 H_w6c2b = w[ 6] + MD5C2b;
const u32 H_w9c2c = w[ 9] + MD5C2c;
const u32 H_wcc2d = w[12] + MD5C2d;
const u32 H_wfc2e = w[15] + MD5C2e;
const u32 H_w2c2f = w[ 2] + MD5C2f;
const u32 I_w0c30 = 0 + MD5C30;
const u32 I_w7c31 = w[ 7] + MD5C31;
const u32 I_wec32 = w[14] + MD5C32;
const u32 I_w5c33 = w[ 5] + MD5C33;
const u32 I_wcc34 = w[12] + MD5C34;
const u32 I_w3c35 = w[ 3] + MD5C35;
const u32 I_wac36 = w[10] + MD5C36;
const u32 I_w1c37 = w[ 1] + MD5C37;
const u32 I_w8c38 = w[ 8] + MD5C38;
const u32 I_wfc39 = w[15] + MD5C39;
const u32 I_w6c3a = w[ 6] + MD5C3a;
const u32 I_wdc3b = w[13] + MD5C3b;
const u32 I_w4c3c = w[ 4] + MD5C3c;
const u32 I_wbc3d = w[11] + MD5C3d;
const u32 I_w2c3e = w[ 2] + MD5C3e;
const u32 I_w9c3f = w[ 9] + MD5C3f;
/**
* loop
*/
u32 w0l = w[0];
for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
{
const u32 w0r = words_buf_r[il_pos];
const u32 w0 = w0l | w0r;
u32 tmp2;
u32 a = MD5M_A;
u32 b = MD5M_B;
u32 c = MD5M_C;
u32 d = MD5M_D;
MD5_STEP (MD5_Fo, a, b, c, d, w0, F_w0c00, MD5S00);
MD5_STEP0(MD5_Fo, d, a, b, c, F_w1c01, MD5S01);
MD5_STEP0(MD5_Fo, c, d, a, b, F_w2c02, MD5S02);
MD5_STEP0(MD5_Fo, b, c, d, a, F_w3c03, MD5S03);
MD5_STEP0(MD5_Fo, a, b, c, d, F_w4c04, MD5S00);
MD5_STEP0(MD5_Fo, d, a, b, c, F_w5c05, MD5S01);
MD5_STEP0(MD5_Fo, c, d, a, b, F_w6c06, MD5S02);
MD5_STEP0(MD5_Fo, b, c, d, a, F_w7c07, MD5S03);
MD5_STEP0(MD5_Fo, a, b, c, d, F_w8c08, MD5S00);
MD5_STEP0(MD5_Fo, d, a, b, c, F_w9c09, MD5S01);
MD5_STEP0(MD5_Fo, c, d, a, b, F_wac0a, MD5S02);
MD5_STEP0(MD5_Fo, b, c, d, a, F_wbc0b, MD5S03);
MD5_STEP0(MD5_Fo, a, b, c, d, F_wcc0c, MD5S00);
MD5_STEP0(MD5_Fo, d, a, b, c, F_wdc0d, MD5S01);
MD5_STEP0(MD5_Fo, c, d, a, b, F_wec0e, MD5S02);
MD5_STEP0(MD5_Fo, b, c, d, a, F_wfc0f, MD5S03);
MD5_STEP0(MD5_Go, a, b, c, d, G_w1c10, MD5S10);
MD5_STEP0(MD5_Go, d, a, b, c, G_w6c11, MD5S11);
MD5_STEP0(MD5_Go, c, d, a, b, G_wbc12, MD5S12);
MD5_STEP (MD5_Go, b, c, d, a, w0, G_w0c13, MD5S13);
MD5_STEP0(MD5_Go, a, b, c, d, G_w5c14, MD5S10);
MD5_STEP0(MD5_Go, d, a, b, c, G_wac15, MD5S11);
MD5_STEP0(MD5_Go, c, d, a, b, G_wfc16, MD5S12);
MD5_STEP0(MD5_Go, b, c, d, a, G_w4c17, MD5S13);
MD5_STEP0(MD5_Go, a, b, c, d, G_w9c18, MD5S10);
MD5_STEP0(MD5_Go, d, a, b, c, G_wec19, MD5S11);
MD5_STEP0(MD5_Go, c, d, a, b, G_w3c1a, MD5S12);
MD5_STEP0(MD5_Go, b, c, d, a, G_w8c1b, MD5S13);
MD5_STEP0(MD5_Go, a, b, c, d, G_wdc1c, MD5S10);
MD5_STEP0(MD5_Go, d, a, b, c, G_w2c1d, MD5S11);
MD5_STEP0(MD5_Go, c, d, a, b, G_w7c1e, MD5S12);
MD5_STEP0(MD5_Go, b, c, d, a, G_wcc1f, MD5S13);
MD5_STEP0(MD5_H1, a, b, c, d, H_w5c20, MD5S20);
MD5_STEP0(MD5_H2, d, a, b, c, H_w8c21, MD5S21);
MD5_STEP0(MD5_H1, c, d, a, b, H_wbc22, MD5S22);
MD5_STEP0(MD5_H2, b, c, d, a, H_wec23, MD5S23);
MD5_STEP0(MD5_H1, a, b, c, d, H_w1c24, MD5S20);
MD5_STEP0(MD5_H2, d, a, b, c, H_w4c25, MD5S21);
MD5_STEP0(MD5_H1, c, d, a, b, H_w7c26, MD5S22);
MD5_STEP0(MD5_H2, b, c, d, a, H_wac27, MD5S23);
MD5_STEP0(MD5_H1, a, b, c, d, H_wdc28, MD5S20);
MD5_STEP (MD5_H2, d, a, b, c, w0, H_w0c29, MD5S21);
MD5_STEP0(MD5_H1, c, d, a, b, H_w3c2a, MD5S22);
MD5_STEP0(MD5_H2, b, c, d, a, H_w6c2b, MD5S23);
MD5_STEP0(MD5_H1, a, b, c, d, H_w9c2c, MD5S20);
MD5_STEP0(MD5_H2, d, a, b, c, H_wcc2d, MD5S21);
MD5_STEP0(MD5_H1, c, d, a, b, H_wfc2e, MD5S22);
MD5_STEP0(MD5_H2, b, c, d, a, H_w2c2f, MD5S23);
MD5_STEP (MD5_I , a, b, c, d, w0, I_w0c30, MD5S30);
MD5_STEP0(MD5_I , d, a, b, c, I_w7c31, MD5S31);
MD5_STEP0(MD5_I , c, d, a, b, I_wec32, MD5S32);
MD5_STEP0(MD5_I , b, c, d, a, I_w5c33, MD5S33);
MD5_STEP0(MD5_I , a, b, c, d, I_wcc34, MD5S30);
MD5_STEP0(MD5_I , d, a, b, c, I_w3c35, MD5S31);
MD5_STEP0(MD5_I , c, d, a, b, I_wac36, MD5S32);
MD5_STEP0(MD5_I , b, c, d, a, I_w1c37, MD5S33);
MD5_STEP0(MD5_I , a, b, c, d, I_w8c38, MD5S30);
MD5_STEP0(MD5_I , d, a, b, c, I_wfc39, MD5S31);
MD5_STEP0(MD5_I , c, d, a, b, I_w6c3a, MD5S32);
MD5_STEP0(MD5_I , b, c, d, a, I_wdc3b, MD5S33);
MD5_STEP0(MD5_I , a, b, c, d, I_w4c3c, MD5S30);
MD5_STEP0(MD5_I , d, a, b, c, I_wbc3d, MD5S31);
MD5_STEP0(MD5_I , c, d, a, b, I_w2c3e, MD5S32);
MD5_STEP0(MD5_I , b, c, d, a, I_w9c3f, MD5S33);
const u32 r0 = a;
const u32 r1 = d;
const u32 r2 = c;
const u32 r3 = b;
#include COMPARE_M
}
}
static void m00030s (u32 w[16], const u32 pw_len, __global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32 * words_buf_r, __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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset)
{
/**
* modifier
*/
const u32 gid = get_global_id (0);
const u32 lid = get_local_id (0);
/**
* base
*/
const u32 F_w0c00 = 0 + MD5C00;
const u32 F_w1c01 = w[ 1] + MD5C01;
const u32 F_w2c02 = w[ 2] + MD5C02;
const u32 F_w3c03 = w[ 3] + MD5C03;
const u32 F_w4c04 = w[ 4] + MD5C04;
const u32 F_w5c05 = w[ 5] + MD5C05;
const u32 F_w6c06 = w[ 6] + MD5C06;
const u32 F_w7c07 = w[ 7] + MD5C07;
const u32 F_w8c08 = w[ 8] + MD5C08;
const u32 F_w9c09 = w[ 9] + MD5C09;
const u32 F_wac0a = w[10] + MD5C0a;
const u32 F_wbc0b = w[11] + MD5C0b;
const u32 F_wcc0c = w[12] + MD5C0c;
const u32 F_wdc0d = w[13] + MD5C0d;
const u32 F_wec0e = w[14] + MD5C0e;
const u32 F_wfc0f = w[15] + MD5C0f;
const u32 G_w1c10 = w[ 1] + MD5C10;
const u32 G_w6c11 = w[ 6] + MD5C11;
const u32 G_wbc12 = w[11] + MD5C12;
const u32 G_w0c13 = 0 + MD5C13;
const u32 G_w5c14 = w[ 5] + MD5C14;
const u32 G_wac15 = w[10] + MD5C15;
const u32 G_wfc16 = w[15] + MD5C16;
const u32 G_w4c17 = w[ 4] + MD5C17;
const u32 G_w9c18 = w[ 9] + MD5C18;
const u32 G_wec19 = w[14] + MD5C19;
const u32 G_w3c1a = w[ 3] + MD5C1a;
const u32 G_w8c1b = w[ 8] + MD5C1b;
const u32 G_wdc1c = w[13] + MD5C1c;
const u32 G_w2c1d = w[ 2] + MD5C1d;
const u32 G_w7c1e = w[ 7] + MD5C1e;
const u32 G_wcc1f = w[12] + MD5C1f;
const u32 H_w5c20 = w[ 5] + MD5C20;
const u32 H_w8c21 = w[ 8] + MD5C21;
const u32 H_wbc22 = w[11] + MD5C22;
const u32 H_wec23 = w[14] + MD5C23;
const u32 H_w1c24 = w[ 1] + MD5C24;
const u32 H_w4c25 = w[ 4] + MD5C25;
const u32 H_w7c26 = w[ 7] + MD5C26;
const u32 H_wac27 = w[10] + MD5C27;
const u32 H_wdc28 = w[13] + MD5C28;
const u32 H_w0c29 = 0 + MD5C29;
const u32 H_w3c2a = w[ 3] + MD5C2a;
const u32 H_w6c2b = w[ 6] + MD5C2b;
const u32 H_w9c2c = w[ 9] + MD5C2c;
const u32 H_wcc2d = w[12] + MD5C2d;
const u32 H_wfc2e = w[15] + MD5C2e;
const u32 H_w2c2f = w[ 2] + MD5C2f;
const u32 I_w0c30 = 0 + MD5C30;
const u32 I_w7c31 = w[ 7] + MD5C31;
const u32 I_wec32 = w[14] + MD5C32;
const u32 I_w5c33 = w[ 5] + MD5C33;
const u32 I_wcc34 = w[12] + MD5C34;
const u32 I_w3c35 = w[ 3] + MD5C35;
const u32 I_wac36 = w[10] + MD5C36;
const u32 I_w1c37 = w[ 1] + MD5C37;
const u32 I_w8c38 = w[ 8] + MD5C38;
const u32 I_wfc39 = w[15] + MD5C39;
const u32 I_w6c3a = w[ 6] + MD5C3a;
const u32 I_wdc3b = w[13] + MD5C3b;
const u32 I_w4c3c = w[ 4] + MD5C3c;
const u32 I_wbc3d = w[11] + MD5C3d;
const u32 I_w2c3e = w[ 2] + MD5C3e;
const u32 I_w9c3f = w[ 9] + MD5C3f;
/**
* 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]
};
/**
* reverse
*/
u32 a_rev = digests_buf[digests_offset].digest_buf[0];
u32 b_rev = digests_buf[digests_offset].digest_buf[1];
u32 c_rev = digests_buf[digests_offset].digest_buf[2];
u32 d_rev = digests_buf[digests_offset].digest_buf[3];
MD5_STEP_REV (MD5_I, b_rev, c_rev, d_rev, a_rev, w[ 9], MD5C3f, MD5S33);
MD5_STEP_REV (MD5_I, c_rev, d_rev, a_rev, b_rev, w[ 2], MD5C3e, MD5S32);
MD5_STEP_REV (MD5_I, d_rev, a_rev, b_rev, c_rev, w[11], MD5C3d, MD5S31);
MD5_STEP_REV (MD5_I, a_rev, b_rev, c_rev, d_rev, w[ 4], MD5C3c, MD5S30);
MD5_STEP_REV (MD5_I, b_rev, c_rev, d_rev, a_rev, w[13], MD5C3b, MD5S33);
MD5_STEP_REV (MD5_I, c_rev, d_rev, a_rev, b_rev, w[ 6], MD5C3a, MD5S32);
MD5_STEP_REV (MD5_I, d_rev, a_rev, b_rev, c_rev, w[15], MD5C39, MD5S31);
MD5_STEP_REV (MD5_I, a_rev, b_rev, c_rev, d_rev, w[ 8], MD5C38, MD5S30);
MD5_STEP_REV (MD5_I, b_rev, c_rev, d_rev, a_rev, w[ 1], MD5C37, MD5S33);
MD5_STEP_REV (MD5_I, c_rev, d_rev, a_rev, b_rev, w[10], MD5C36, MD5S32);
MD5_STEP_REV (MD5_I, d_rev, a_rev, b_rev, c_rev, w[ 3], MD5C35, MD5S31);
MD5_STEP_REV (MD5_I, a_rev, b_rev, c_rev, d_rev, w[12], MD5C34, MD5S30);
MD5_STEP_REV (MD5_I, b_rev, c_rev, d_rev, a_rev, w[ 5], MD5C33, MD5S33);
MD5_STEP_REV (MD5_I, c_rev, d_rev, a_rev, b_rev, w[14], MD5C32, MD5S32);
MD5_STEP_REV (MD5_I, d_rev, a_rev, b_rev, c_rev, w[ 7], MD5C31, MD5S31);
MD5_STEP_REV (MD5_I, a_rev, b_rev, c_rev, d_rev, 0, MD5C30, MD5S30);
const u32 pre_cd = c_rev ^ d_rev;
MD5_STEP_REV1(MD5_H, b_rev, c_rev, d_rev, a_rev, w[ 2], MD5C2f, MD5S23);
MD5_STEP_REV1(MD5_H, c_rev, d_rev, a_rev, b_rev, w[15], MD5C2e, MD5S22);
/**
* loop
*/
u32 w0l = w[0];
for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
{
const u32 w0r = words_buf_r[il_pos];
const u32 w0 = w0l | w0r;
const u32 pre_d = d_rev;
const u32 pre_a = a_rev - w0;
const u32 pre_b = b_rev - (pre_a ^ pre_cd);
const u32 pre_c = c_rev - (pre_a ^ pre_b ^ pre_d);
u32 tmp2;
u32 a = MD5M_A;
u32 b = MD5M_B;
u32 c = MD5M_C;
u32 d = MD5M_D;
MD5_STEP (MD5_Fo, a, b, c, d, w0, F_w0c00, MD5S00);
MD5_STEP0(MD5_Fo, d, a, b, c, F_w1c01, MD5S01);
MD5_STEP0(MD5_Fo, c, d, a, b, F_w2c02, MD5S02);
MD5_STEP0(MD5_Fo, b, c, d, a, F_w3c03, MD5S03);
MD5_STEP0(MD5_Fo, a, b, c, d, F_w4c04, MD5S00);
MD5_STEP0(MD5_Fo, d, a, b, c, F_w5c05, MD5S01);
MD5_STEP0(MD5_Fo, c, d, a, b, F_w6c06, MD5S02);
MD5_STEP0(MD5_Fo, b, c, d, a, F_w7c07, MD5S03);
MD5_STEP0(MD5_Fo, a, b, c, d, F_w8c08, MD5S00);
MD5_STEP0(MD5_Fo, d, a, b, c, F_w9c09, MD5S01);
MD5_STEP0(MD5_Fo, c, d, a, b, F_wac0a, MD5S02);
MD5_STEP0(MD5_Fo, b, c, d, a, F_wbc0b, MD5S03);
MD5_STEP0(MD5_Fo, a, b, c, d, F_wcc0c, MD5S00);
MD5_STEP0(MD5_Fo, d, a, b, c, F_wdc0d, MD5S01);
MD5_STEP0(MD5_Fo, c, d, a, b, F_wec0e, MD5S02);
MD5_STEP0(MD5_Fo, b, c, d, a, F_wfc0f, MD5S03);
MD5_STEP0(MD5_Go, a, b, c, d, G_w1c10, MD5S10);
MD5_STEP0(MD5_Go, d, a, b, c, G_w6c11, MD5S11);
MD5_STEP0(MD5_Go, c, d, a, b, G_wbc12, MD5S12);
MD5_STEP (MD5_Go, b, c, d, a, w0, G_w0c13, MD5S13);
MD5_STEP0(MD5_Go, a, b, c, d, G_w5c14, MD5S10);
MD5_STEP0(MD5_Go, d, a, b, c, G_wac15, MD5S11);
MD5_STEP0(MD5_Go, c, d, a, b, G_wfc16, MD5S12);
MD5_STEP0(MD5_Go, b, c, d, a, G_w4c17, MD5S13);
MD5_STEP0(MD5_Go, a, b, c, d, G_w9c18, MD5S10);
MD5_STEP0(MD5_Go, d, a, b, c, G_wec19, MD5S11);
MD5_STEP0(MD5_Go, c, d, a, b, G_w3c1a, MD5S12);
MD5_STEP0(MD5_Go, b, c, d, a, G_w8c1b, MD5S13);
MD5_STEP0(MD5_Go, a, b, c, d, G_wdc1c, MD5S10);
MD5_STEP0(MD5_Go, d, a, b, c, G_w2c1d, MD5S11);
MD5_STEP0(MD5_Go, c, d, a, b, G_w7c1e, MD5S12);
MD5_STEP0(MD5_Go, b, c, d, a, G_wcc1f, MD5S13);
MD5_STEP0(MD5_H1, a, b, c, d, H_w5c20, MD5S20);
MD5_STEP0(MD5_H2, d, a, b, c, H_w8c21, MD5S21);
MD5_STEP0(MD5_H1, c, d, a, b, H_wbc22, MD5S22);
MD5_STEP0(MD5_H2, b, c, d, a, H_wec23, MD5S23);
MD5_STEP0(MD5_H1, a, b, c, d, H_w1c24, MD5S20);
MD5_STEP0(MD5_H2, d, a, b, c, H_w4c25, MD5S21);
MD5_STEP0(MD5_H1, c, d, a, b, H_w7c26, MD5S22);
MD5_STEP0(MD5_H2, b, c, d, a, H_wac27, MD5S23);
MD5_STEP0(MD5_H1, a, b, c, d, H_wdc28, MD5S20);
MD5_STEP (MD5_H2, d, a, b, c, w0, H_w0c29, MD5S21);
MD5_STEP0(MD5_H1, c, d, a, b, H_w3c2a, MD5S22);
bool q_cond = allx (pre_c != c);
if (q_cond) continue;
MD5_STEP0(MD5_H2, b, c, d, a, H_w6c2b, MD5S23);
MD5_STEP0(MD5_H1, a, b, c, d, H_w9c2c, MD5S20);
MD5_STEP0(MD5_H2, d, a, b, c, H_wcc2d, MD5S21);
bool q_cond2 = allx (pre_d != d);
if (q_cond2) continue;
MD5_STEP0(MD5_H1, c, d, a, b, H_wfc2e, MD5S22);
MD5_STEP0(MD5_H2, b, c, d, a, H_w2c2f, MD5S23);
MD5_STEP (MD5_I , a, b, c, d, w0, I_w0c30, MD5S30);
MD5_STEP0(MD5_I , d, a, b, c, I_w7c31, MD5S31);
MD5_STEP0(MD5_I , c, d, a, b, I_wec32, MD5S32);
MD5_STEP0(MD5_I , b, c, d, a, I_w5c33, MD5S33);
MD5_STEP0(MD5_I , a, b, c, d, I_wcc34, MD5S30);
MD5_STEP0(MD5_I , d, a, b, c, I_w3c35, MD5S31);
MD5_STEP0(MD5_I , c, d, a, b, I_wac36, MD5S32);
MD5_STEP0(MD5_I , b, c, d, a, I_w1c37, MD5S33);
MD5_STEP0(MD5_I , a, b, c, d, I_w8c38, MD5S30);
MD5_STEP0(MD5_I , d, a, b, c, I_wfc39, MD5S31);
MD5_STEP0(MD5_I , c, d, a, b, I_w6c3a, MD5S32);
MD5_STEP0(MD5_I , b, c, d, a, I_wdc3b, MD5S33);
MD5_STEP0(MD5_I , a, b, c, d, I_w4c3c, MD5S30);
MD5_STEP0(MD5_I , d, a, b, c, I_wbc3d, MD5S31);
MD5_STEP0(MD5_I , c, d, a, b, I_w2c3e, MD5S32);
MD5_STEP0(MD5_I , b, c, d, a, I_w9c3f, MD5S33);
const u32 r0 = a;
const u32 r1 = d;
const u32 r2 = c;
const u32 r3 = b;
#include COMPARE_S
}
}
__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00030_m04 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32 * words_buf_r, __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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
/**
* base
*/
const u32 gid = get_global_id (0);
if (gid >= gid_max) return;
u32 w[16];
w[ 0] = pws[gid].i[ 0];
w[ 1] = pws[gid].i[ 1];
w[ 2] = pws[gid].i[ 2];
w[ 3] = pws[gid].i[ 3];
w[ 4] = 0;
w[ 5] = 0;
w[ 6] = 0;
w[ 7] = 0;
w[ 8] = 0;
w[ 9] = 0;
w[10] = 0;
w[11] = 0;
w[12] = 0;
w[13] = 0;
w[14] = pws[gid].i[14];
w[15] = 0;
const u32 pw_len = pws[gid].pw_len;
/**
* main
*/
m00030m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
}
__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00030_m08 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32 * words_buf_r, __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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
/**
* base
*/
const u32 gid = get_global_id (0);
if (gid >= gid_max) return;
u32 w[16];
w[ 0] = pws[gid].i[ 0];
w[ 1] = pws[gid].i[ 1];
w[ 2] = pws[gid].i[ 2];
w[ 3] = pws[gid].i[ 3];
w[ 4] = pws[gid].i[ 4];
w[ 5] = pws[gid].i[ 5];
w[ 6] = pws[gid].i[ 6];
w[ 7] = pws[gid].i[ 7];
w[ 8] = 0;
w[ 9] = 0;
w[10] = 0;
w[11] = 0;
w[12] = 0;
w[13] = 0;
w[14] = pws[gid].i[14];
w[15] = 0;
const u32 pw_len = pws[gid].pw_len;
/**
* main
*/
m00030m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
}
__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00030_m16 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32 * words_buf_r, __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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
/**
* base
*/
const u32 gid = get_global_id (0);
if (gid >= gid_max) return;
u32 w[16];
w[ 0] = pws[gid].i[ 0];
w[ 1] = pws[gid].i[ 1];
w[ 2] = pws[gid].i[ 2];
w[ 3] = pws[gid].i[ 3];
w[ 4] = pws[gid].i[ 4];
w[ 5] = pws[gid].i[ 5];
w[ 6] = pws[gid].i[ 6];
w[ 7] = pws[gid].i[ 7];
w[ 8] = pws[gid].i[ 8];
w[ 9] = pws[gid].i[ 9];
w[10] = pws[gid].i[10];
w[11] = pws[gid].i[11];
w[12] = pws[gid].i[12];
w[13] = pws[gid].i[13];
w[14] = pws[gid].i[14];
w[15] = pws[gid].i[15];
const u32 pw_len = pws[gid].pw_len;
/**
* main
*/
m00030m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
}
__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00030_s04 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32 * words_buf_r, __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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
/**
* base
*/
const u32 gid = get_global_id (0);
if (gid >= gid_max) return;
u32 w[16];
w[ 0] = pws[gid].i[ 0];
w[ 1] = pws[gid].i[ 1];
w[ 2] = pws[gid].i[ 2];
w[ 3] = pws[gid].i[ 3];
w[ 4] = 0;
w[ 5] = 0;
w[ 6] = 0;
w[ 7] = 0;
w[ 8] = 0;
w[ 9] = 0;
w[10] = 0;
w[11] = 0;
w[12] = 0;
w[13] = 0;
w[14] = pws[gid].i[14];
w[15] = 0;
const u32 pw_len = pws[gid].pw_len;
/**
* main
*/
m00030s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
}
__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00030_s08 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32 * words_buf_r, __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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
/**
* base
*/
const u32 gid = get_global_id (0);
if (gid >= gid_max) return;
u32 w[16];
w[ 0] = pws[gid].i[ 0];
w[ 1] = pws[gid].i[ 1];
w[ 2] = pws[gid].i[ 2];
w[ 3] = pws[gid].i[ 3];
w[ 4] = pws[gid].i[ 4];
w[ 5] = pws[gid].i[ 5];
w[ 6] = pws[gid].i[ 6];
w[ 7] = pws[gid].i[ 7];
w[ 8] = 0;
w[ 9] = 0;
w[10] = 0;
w[11] = 0;
w[12] = 0;
w[13] = 0;
w[14] = pws[gid].i[14];
w[15] = 0;
const u32 pw_len = pws[gid].pw_len;
/**
* main
*/
m00030s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
}
__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00030_s16 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32 * words_buf_r, __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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
/**
* base
*/
const u32 gid = get_global_id (0);
if (gid >= gid_max) return;
u32 w[16];
w[ 0] = pws[gid].i[ 0];
w[ 1] = pws[gid].i[ 1];
w[ 2] = pws[gid].i[ 2];
w[ 3] = pws[gid].i[ 3];
w[ 4] = pws[gid].i[ 4];
w[ 5] = pws[gid].i[ 5];
w[ 6] = pws[gid].i[ 6];
w[ 7] = pws[gid].i[ 7];
w[ 8] = pws[gid].i[ 8];
w[ 9] = pws[gid].i[ 9];
w[10] = pws[gid].i[10];
w[11] = pws[gid].i[11];
w[12] = pws[gid].i[12];
w[13] = pws[gid].i[13];
w[14] = pws[gid].i[14];
w[15] = pws[gid].i[15];
const u32 pw_len = pws[gid].pw_len;
/**
* main
*/
m00030s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
}