mirror of
https://github.com/hashcat/hashcat
synced 2024-11-20 23:27:31 +01:00
Add files via upload
This commit is contained in:
TROUNCE
GitHub
parent
15bf8b7302
commit
9646f8c4e6
926
OpenCL/m05000_a0-optimized.cl
Normal file
926
OpenCL/m05000_a0-optimized.cl
Normal file
@ -0,0 +1,926 @@
|
||||
/**
|
||||
* 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_sha1.cl"
|
||||
#endif
|
||||
|
||||
#if VECT_SIZE == 1
|
||||
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
|
||||
#elif VECT_SIZE == 2
|
||||
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
|
||||
#elif VECT_SIZE == 4
|
||||
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
|
||||
#elif VECT_SIZE == 8
|
||||
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
|
||||
#elif VECT_SIZE == 16
|
||||
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
|
||||
#endif
|
||||
|
||||
KERNEL_FQ void m05000_m04 (KERN_ATTR_RULES ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
const u64 lsz = get_local_size (0);
|
||||
|
||||
/**
|
||||
* bin2asc table
|
||||
*/
|
||||
|
||||
LOCAL_VK u32 l_bin2asc[256];
|
||||
|
||||
for (u32 i = lid; i < 256; i += lsz)
|
||||
{
|
||||
const u32 i0 = (i >> 0) & 15;
|
||||
const u32 i1 = (i >> 4) & 15;
|
||||
|
||||
l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
|
||||
| ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
|
||||
}
|
||||
|
||||
SYNC_THREADS ();
|
||||
|
||||
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;
|
||||
|
||||
/**
|
||||
* salt
|
||||
*/
|
||||
|
||||
u32 salt_buf0[4];
|
||||
u32 salt_buf1[4];
|
||||
u32 salt_buf2[4];
|
||||
u32 salt_buf3[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];
|
||||
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];
|
||||
salt_buf2[0] = salt_bufs[SALT_POS].salt_buf[ 8];
|
||||
salt_buf2[1] = salt_bufs[SALT_POS].salt_buf[ 9];
|
||||
salt_buf2[2] = salt_bufs[SALT_POS].salt_buf[10];
|
||||
salt_buf2[3] = salt_bufs[SALT_POS].salt_buf[11];
|
||||
salt_buf3[0] = salt_bufs[SALT_POS].salt_buf[12];
|
||||
salt_buf3[1] = salt_bufs[SALT_POS].salt_buf[13];
|
||||
salt_buf3[2] = salt_bufs[SALT_POS].salt_buf[14];
|
||||
salt_buf3[3] = salt_bufs[SALT_POS].salt_buf[15];
|
||||
|
||||
const u32 salt_len = salt_bufs[SALT_POS].salt_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_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
|
||||
|
||||
/**
|
||||
* prepend salt
|
||||
*/
|
||||
|
||||
const u32x out_salt_len = out_len + salt_len;
|
||||
|
||||
switch_buffer_by_offset_le_VV (w0, w1, w2, w3, salt_len);
|
||||
|
||||
w0[0] |= salt_buf0[0];
|
||||
w0[1] |= salt_buf0[1];
|
||||
w0[2] |= salt_buf0[2];
|
||||
w0[3] |= salt_buf0[3];
|
||||
w1[0] |= salt_buf1[0];
|
||||
w1[1] |= salt_buf1[1];
|
||||
w1[2] |= salt_buf1[2];
|
||||
w1[3] |= salt_buf1[3];
|
||||
w2[0] |= salt_buf2[0];
|
||||
w2[1] |= salt_buf2[1];
|
||||
w2[2] |= salt_buf2[2];
|
||||
w2[3] |= salt_buf2[3];
|
||||
w3[0] |= salt_buf3[0];
|
||||
w3[1] |= salt_buf3[1];
|
||||
w3[2] |= salt_buf3[2];
|
||||
w3[3] |= salt_buf3[3];
|
||||
|
||||
/**
|
||||
* append salt
|
||||
*/
|
||||
|
||||
u32x s0[4];
|
||||
u32x s1[4];
|
||||
u32x s2[4];
|
||||
u32x s3[4];
|
||||
|
||||
s0[0] = salt_buf0[0];
|
||||
s0[1] = salt_buf0[1];
|
||||
s0[2] = salt_buf0[2];
|
||||
s0[3] = salt_buf0[3];
|
||||
s1[0] = salt_buf1[0];
|
||||
s1[1] = salt_buf1[1];
|
||||
s1[2] = salt_buf1[2];
|
||||
s1[3] = salt_buf1[3];
|
||||
s2[0] = salt_buf2[0];
|
||||
s2[1] = salt_buf2[1];
|
||||
s2[2] = salt_buf2[2];
|
||||
s2[3] = salt_buf2[3];
|
||||
s3[0] = salt_buf3[0];
|
||||
s3[1] = salt_buf3[1];
|
||||
s3[2] = salt_buf3[2];
|
||||
s3[3] = salt_buf3[3];
|
||||
|
||||
switch_buffer_by_offset_le_VV (s0, s1, s2, s3, out_salt_len);
|
||||
|
||||
w0[0] |= s0[0];
|
||||
w0[1] |= s0[1];
|
||||
w0[2] |= s0[2];
|
||||
w0[3] |= s0[3];
|
||||
w1[0] |= s1[0];
|
||||
w1[1] |= s1[1];
|
||||
w1[2] |= s1[2];
|
||||
w1[3] |= s1[3];
|
||||
w2[0] |= s2[0];
|
||||
w2[1] |= s2[1];
|
||||
w2[2] |= s2[2];
|
||||
w2[3] |= s2[3];
|
||||
w3[0] |= s3[0];
|
||||
w3[1] |= s3[1];
|
||||
w3[2] |= s3[2];
|
||||
w3[3] |= s3[3];
|
||||
|
||||
const u32x salt_out_salt_len = salt_len + out_len + salt_len;
|
||||
|
||||
append_0x80_4x4_VV (w0, w1, w2, w3, salt_out_salt_len);
|
||||
|
||||
/**
|
||||
* sha1
|
||||
*/
|
||||
|
||||
u32x w0_t = hc_swap32 (w0[0]);
|
||||
u32x w1_t = hc_swap32 (w0[1]);
|
||||
u32x w2_t = hc_swap32 (w0[2]);
|
||||
u32x w3_t = hc_swap32 (w0[3]);
|
||||
u32x w4_t = hc_swap32 (w1[0]);
|
||||
u32x w5_t = hc_swap32 (w1[1]);
|
||||
u32x w6_t = hc_swap32 (w1[2]);
|
||||
u32x w7_t = hc_swap32 (w1[3]);
|
||||
u32x w8_t = hc_swap32 (w2[0]);
|
||||
u32x w9_t = hc_swap32 (w2[1]);
|
||||
u32x wa_t = hc_swap32 (w2[2]);
|
||||
u32x wb_t = hc_swap32 (w2[3]);
|
||||
u32x wc_t = hc_swap32 (w3[0]);
|
||||
u32x wd_t = hc_swap32 (w3[1]);
|
||||
u32x we_t = 0;
|
||||
u32x wf_t = salt_out_salt_len * 8;
|
||||
|
||||
u32x a = SHA1M_A;
|
||||
u32x b = SHA1M_B;
|
||||
u32x c = SHA1M_C;
|
||||
u32x d = SHA1M_D;
|
||||
u32x e = SHA1M_E;
|
||||
|
||||
#undef K
|
||||
#define K SHA1C00
|
||||
|
||||
SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
|
||||
SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
|
||||
SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
|
||||
SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
|
||||
SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
|
||||
SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
|
||||
SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
|
||||
SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
|
||||
SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
|
||||
SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
|
||||
SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
|
||||
SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
|
||||
SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
|
||||
SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
|
||||
SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
|
||||
SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
|
||||
w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
|
||||
w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
|
||||
w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
|
||||
w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
|
||||
|
||||
#undef K
|
||||
#define K SHA1C01
|
||||
|
||||
w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
|
||||
w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
|
||||
w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
|
||||
w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
|
||||
w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
|
||||
w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
|
||||
wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
|
||||
wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
|
||||
wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
|
||||
wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
|
||||
we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
|
||||
wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
|
||||
w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
|
||||
w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
|
||||
w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
|
||||
w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
|
||||
w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
|
||||
w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
|
||||
w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
|
||||
w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
|
||||
|
||||
#undef K
|
||||
#define K SHA1C02
|
||||
|
||||
w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
|
||||
w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
|
||||
wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
|
||||
wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
|
||||
wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
|
||||
wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
|
||||
we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
|
||||
wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
|
||||
w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
|
||||
w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
|
||||
w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
|
||||
w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
|
||||
w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
|
||||
w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
|
||||
w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
|
||||
w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
|
||||
w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
|
||||
w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
|
||||
wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
|
||||
wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
|
||||
|
||||
#undef K
|
||||
#define K SHA1C03
|
||||
|
||||
wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
|
||||
wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
|
||||
we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
|
||||
wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
|
||||
w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
|
||||
w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
|
||||
w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
|
||||
w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
|
||||
w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
|
||||
w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
|
||||
w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
|
||||
w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
|
||||
w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
|
||||
w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
|
||||
wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
|
||||
wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
|
||||
wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
|
||||
wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
|
||||
we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
|
||||
wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
|
||||
|
||||
a += SHA1M_A;
|
||||
b += SHA1M_B;
|
||||
c += SHA1M_C;
|
||||
d += SHA1M_D;
|
||||
e += SHA1M_E;
|
||||
|
||||
/**
|
||||
* 2nd SHA1
|
||||
*/
|
||||
|
||||
w0_t = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
|
||||
w1_t = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
|
||||
w2_t = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
|
||||
w3_t = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
|
||||
w4_t = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
|
||||
w5_t = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
|
||||
w6_t = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
|
||||
w7_t = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
|
||||
w8_t = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
|
||||
w9_t = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
|
||||
|
||||
wa_t = 0x80000000;
|
||||
wb_t = 0;
|
||||
wc_t = 0;
|
||||
wd_t = 0;
|
||||
we_t = 0;
|
||||
wf_t = 40 * 8;
|
||||
|
||||
a = SHA1M_A;
|
||||
b = SHA1M_B;
|
||||
c = SHA1M_C;
|
||||
d = SHA1M_D;
|
||||
e = SHA1M_E;
|
||||
|
||||
#undef K
|
||||
#define K SHA1C00
|
||||
|
||||
SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
|
||||
SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
|
||||
SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
|
||||
SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
|
||||
SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
|
||||
SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
|
||||
SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
|
||||
SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
|
||||
SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
|
||||
SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
|
||||
SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
|
||||
SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
|
||||
SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
|
||||
SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
|
||||
SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
|
||||
SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
|
||||
w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
|
||||
w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
|
||||
w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
|
||||
w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
|
||||
|
||||
#undef K
|
||||
#define K SHA1C01
|
||||
|
||||
w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
|
||||
w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
|
||||
w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
|
||||
w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
|
||||
w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
|
||||
w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
|
||||
wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
|
||||
wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
|
||||
wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
|
||||
wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
|
||||
we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
|
||||
wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
|
||||
w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
|
||||
w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
|
||||
w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
|
||||
w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
|
||||
w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
|
||||
w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
|
||||
w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
|
||||
w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
|
||||
|
||||
#undef K
|
||||
#define K SHA1C02
|
||||
|
||||
w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
|
||||
w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
|
||||
wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
|
||||
wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
|
||||
wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
|
||||
wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
|
||||
we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
|
||||
wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
|
||||
w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
|
||||
w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
|
||||
w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
|
||||
w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
|
||||
w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
|
||||
w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
|
||||
w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
|
||||
w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
|
||||
w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
|
||||
w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
|
||||
wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
|
||||
wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
|
||||
|
||||
#undef K
|
||||
#define K SHA1C03
|
||||
|
||||
wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
|
||||
wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
|
||||
we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
|
||||
wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
|
||||
w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
|
||||
w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
|
||||
w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
|
||||
w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
|
||||
w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
|
||||
w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
|
||||
w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
|
||||
w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
|
||||
w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
|
||||
w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
|
||||
wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
|
||||
wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
|
||||
wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
|
||||
wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
|
||||
we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
|
||||
wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
|
||||
|
||||
COMPARE_M_SIMD (d, e, c, b);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m05000_m08 (KERN_ATTR_RULES ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m05000_m16 (KERN_ATTR_RULES ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m05000_s04 (KERN_ATTR_RULES ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
const u64 lsz = get_local_size (0);
|
||||
|
||||
/**
|
||||
* bin2asc table
|
||||
*/
|
||||
|
||||
LOCAL_VK u32 l_bin2asc[256];
|
||||
|
||||
for (u32 i = lid; i < 256; i += lsz)
|
||||
{
|
||||
const u32 i0 = (i >> 0) & 15;
|
||||
const u32 i1 = (i >> 4) & 15;
|
||||
|
||||
l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
|
||||
| ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
|
||||
}
|
||||
|
||||
SYNC_THREADS ();
|
||||
|
||||
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;
|
||||
|
||||
/**
|
||||
* salt
|
||||
*/
|
||||
|
||||
u32 salt_buf0[4];
|
||||
u32 salt_buf1[4];
|
||||
u32 salt_buf2[4];
|
||||
u32 salt_buf3[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];
|
||||
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];
|
||||
salt_buf2[0] = salt_bufs[SALT_POS].salt_buf[ 8];
|
||||
salt_buf2[1] = salt_bufs[SALT_POS].salt_buf[ 9];
|
||||
salt_buf2[2] = salt_bufs[SALT_POS].salt_buf[10];
|
||||
salt_buf2[3] = salt_bufs[SALT_POS].salt_buf[11];
|
||||
salt_buf3[0] = salt_bufs[SALT_POS].salt_buf[12];
|
||||
salt_buf3[1] = salt_bufs[SALT_POS].salt_buf[13];
|
||||
salt_buf3[2] = salt_bufs[SALT_POS].salt_buf[14];
|
||||
salt_buf3[3] = salt_bufs[SALT_POS].salt_buf[15];
|
||||
|
||||
const u32 salt_len = salt_bufs[SALT_POS].salt_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]
|
||||
};
|
||||
|
||||
/**
|
||||
* reverse
|
||||
*/
|
||||
|
||||
const u32 e_rev = hc_rotl32_S (search[1], 2u);
|
||||
|
||||
/**
|
||||
* 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);
|
||||
|
||||
/**
|
||||
* prepend salt
|
||||
*/
|
||||
|
||||
const u32x out_salt_len = out_len + salt_len;
|
||||
|
||||
switch_buffer_by_offset_le_VV (w0, w1, w2, w3, salt_len);
|
||||
|
||||
w0[0] |= salt_buf0[0];
|
||||
w0[1] |= salt_buf0[1];
|
||||
w0[2] |= salt_buf0[2];
|
||||
w0[3] |= salt_buf0[3];
|
||||
w1[0] |= salt_buf1[0];
|
||||
w1[1] |= salt_buf1[1];
|
||||
w1[2] |= salt_buf1[2];
|
||||
w1[3] |= salt_buf1[3];
|
||||
w2[0] |= salt_buf2[0];
|
||||
w2[1] |= salt_buf2[1];
|
||||
w2[2] |= salt_buf2[2];
|
||||
w2[3] |= salt_buf2[3];
|
||||
w3[0] |= salt_buf3[0];
|
||||
w3[1] |= salt_buf3[1];
|
||||
w3[2] |= salt_buf3[2];
|
||||
w3[3] |= salt_buf3[3];
|
||||
|
||||
/**
|
||||
* append salt
|
||||
*/
|
||||
|
||||
u32x s0[4];
|
||||
u32x s1[4];
|
||||
u32x s2[4];
|
||||
u32x s3[4];
|
||||
|
||||
s0[0] = salt_buf0[0];
|
||||
s0[1] = salt_buf0[1];
|
||||
s0[2] = salt_buf0[2];
|
||||
s0[3] = salt_buf0[3];
|
||||
s1[0] = salt_buf1[0];
|
||||
s1[1] = salt_buf1[1];
|
||||
s1[2] = salt_buf1[2];
|
||||
s1[3] = salt_buf1[3];
|
||||
s2[0] = salt_buf2[0];
|
||||
s2[1] = salt_buf2[1];
|
||||
s2[2] = salt_buf2[2];
|
||||
s2[3] = salt_buf2[3];
|
||||
s3[0] = salt_buf3[0];
|
||||
s3[1] = salt_buf3[1];
|
||||
s3[2] = salt_buf3[2];
|
||||
s3[3] = salt_buf3[3];
|
||||
|
||||
switch_buffer_by_offset_le_VV (s0, s1, s2, s3, out_salt_len);
|
||||
|
||||
w0[0] |= s0[0];
|
||||
w0[1] |= s0[1];
|
||||
w0[2] |= s0[2];
|
||||
w0[3] |= s0[3];
|
||||
w1[0] |= s1[0];
|
||||
w1[1] |= s1[1];
|
||||
w1[2] |= s1[2];
|
||||
w1[3] |= s1[3];
|
||||
w2[0] |= s2[0];
|
||||
w2[1] |= s2[1];
|
||||
w2[2] |= s2[2];
|
||||
w2[3] |= s2[3];
|
||||
w3[0] |= s3[0];
|
||||
w3[1] |= s3[1];
|
||||
w3[2] |= s3[2];
|
||||
w3[3] |= s3[3];
|
||||
|
||||
const u32x salt_out_salt_len = salt_len + out_len + salt_len;
|
||||
|
||||
append_0x80_4x4_VV (w0, w1, w2, w3, salt_out_salt_len);
|
||||
|
||||
/**
|
||||
* sha1
|
||||
*/
|
||||
|
||||
u32x w0_t = hc_swap32 (w0[0]);
|
||||
u32x w1_t = hc_swap32 (w0[1]);
|
||||
u32x w2_t = hc_swap32 (w0[2]);
|
||||
u32x w3_t = hc_swap32 (w0[3]);
|
||||
u32x w4_t = hc_swap32 (w1[0]);
|
||||
u32x w5_t = hc_swap32 (w1[1]);
|
||||
u32x w6_t = hc_swap32 (w1[2]);
|
||||
u32x w7_t = hc_swap32 (w1[3]);
|
||||
u32x w8_t = hc_swap32 (w2[0]);
|
||||
u32x w9_t = hc_swap32 (w2[1]);
|
||||
u32x wa_t = hc_swap32 (w2[2]);
|
||||
u32x wb_t = hc_swap32 (w2[3]);
|
||||
u32x wc_t = hc_swap32 (w3[0]);
|
||||
u32x wd_t = hc_swap32 (w3[1]);
|
||||
u32x we_t = 0;
|
||||
u32x wf_t = salt_out_salt_len * 8;
|
||||
|
||||
u32x a = SHA1M_A;
|
||||
u32x b = SHA1M_B;
|
||||
u32x c = SHA1M_C;
|
||||
u32x d = SHA1M_D;
|
||||
u32x e = SHA1M_E;
|
||||
|
||||
#undef K
|
||||
#define K SHA1C00
|
||||
|
||||
SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
|
||||
SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
|
||||
SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
|
||||
SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
|
||||
SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
|
||||
SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
|
||||
SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
|
||||
SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
|
||||
SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
|
||||
SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
|
||||
SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
|
||||
SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
|
||||
SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
|
||||
SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
|
||||
SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
|
||||
SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
|
||||
w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
|
||||
w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
|
||||
w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
|
||||
w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
|
||||
|
||||
#undef K
|
||||
#define K SHA1C01
|
||||
|
||||
w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
|
||||
w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
|
||||
w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
|
||||
w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
|
||||
w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
|
||||
w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
|
||||
wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
|
||||
wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
|
||||
wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
|
||||
wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
|
||||
we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
|
||||
wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
|
||||
w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
|
||||
w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
|
||||
w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
|
||||
w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
|
||||
w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
|
||||
w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
|
||||
w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
|
||||
w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
|
||||
|
||||
#undef K
|
||||
#define K SHA1C02
|
||||
|
||||
w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
|
||||
w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
|
||||
wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
|
||||
wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
|
||||
wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
|
||||
wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
|
||||
we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
|
||||
wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
|
||||
w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
|
||||
w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
|
||||
w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
|
||||
w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
|
||||
w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
|
||||
w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
|
||||
w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
|
||||
w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
|
||||
w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
|
||||
w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
|
||||
wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
|
||||
wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
|
||||
|
||||
#undef K
|
||||
#define K SHA1C03
|
||||
|
||||
wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
|
||||
wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
|
||||
we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
|
||||
wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
|
||||
w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
|
||||
w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
|
||||
w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
|
||||
w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
|
||||
w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
|
||||
w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
|
||||
w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
|
||||
w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
|
||||
w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
|
||||
w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
|
||||
wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
|
||||
wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
|
||||
wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
|
||||
wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
|
||||
we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
|
||||
wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
|
||||
|
||||
a += SHA1M_A;
|
||||
b += SHA1M_B;
|
||||
c += SHA1M_C;
|
||||
d += SHA1M_D;
|
||||
e += SHA1M_E;
|
||||
|
||||
/**
|
||||
* 2nd SHA1
|
||||
*/
|
||||
|
||||
w0_t = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
|
||||
w1_t = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
|
||||
w2_t = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
|
||||
w3_t = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
|
||||
w4_t = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
|
||||
w5_t = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
|
||||
w6_t = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
|
||||
w7_t = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
|
||||
w8_t = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
|
||||
w9_t = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
|
||||
|
||||
wa_t = 0x80000000;
|
||||
wb_t = 0;
|
||||
wc_t = 0;
|
||||
wd_t = 0;
|
||||
we_t = 0;
|
||||
wf_t = 40 * 8;
|
||||
|
||||
a = SHA1M_A;
|
||||
b = SHA1M_B;
|
||||
c = SHA1M_C;
|
||||
d = SHA1M_D;
|
||||
e = SHA1M_E;
|
||||
|
||||
#undef K
|
||||
#define K SHA1C00
|
||||
|
||||
SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
|
||||
SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
|
||||
SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
|
||||
SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
|
||||
SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
|
||||
SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
|
||||
SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
|
||||
SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
|
||||
SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
|
||||
SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
|
||||
SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
|
||||
SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
|
||||
SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
|
||||
SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
|
||||
SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
|
||||
SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
|
||||
w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
|
||||
w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
|
||||
w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
|
||||
w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
|
||||
|
||||
#undef K
|
||||
#define K SHA1C01
|
||||
|
||||
w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
|
||||
w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
|
||||
w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
|
||||
w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
|
||||
w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
|
||||
w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
|
||||
wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
|
||||
wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
|
||||
wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
|
||||
wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
|
||||
we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
|
||||
wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
|
||||
w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
|
||||
w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
|
||||
w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
|
||||
w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
|
||||
w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
|
||||
w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
|
||||
w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
|
||||
w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
|
||||
|
||||
#undef K
|
||||
#define K SHA1C02
|
||||
|
||||
w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
|
||||
w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
|
||||
wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
|
||||
wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
|
||||
wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
|
||||
wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
|
||||
we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
|
||||
wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
|
||||
w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
|
||||
w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
|
||||
w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
|
||||
w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
|
||||
w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
|
||||
w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
|
||||
w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
|
||||
w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
|
||||
w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
|
||||
w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
|
||||
wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
|
||||
wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
|
||||
|
||||
#undef K
|
||||
#define K SHA1C03
|
||||
|
||||
wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
|
||||
wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
|
||||
we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
|
||||
wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
|
||||
w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
|
||||
w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
|
||||
w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
|
||||
w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
|
||||
w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
|
||||
w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
|
||||
w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
|
||||
w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
|
||||
w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
|
||||
w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
|
||||
wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
|
||||
wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
|
||||
|
||||
if (MATCHES_NONE_VS (e, e_rev)) continue;
|
||||
|
||||
wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
|
||||
wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
|
||||
we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
|
||||
wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
|
||||
|
||||
COMPARE_S_SIMD (d, e, c, b);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m05000_s08 (KERN_ATTR_RULES ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m05000_s16 (KERN_ATTR_RULES ())
|
||||
{
|
||||
}
|
||||
265
OpenCL/m05000_a0-pure.cl
Normal file
265
OpenCL/m05000_a0-pure.cl
Normal file
@ -0,0 +1,265 @@
|
||||
/**
|
||||
* 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.h"
|
||||
#include "inc_rp.cl"
|
||||
#include "inc_scalar.cl"
|
||||
#include "inc_hash_sha1.cl"
|
||||
#endif
|
||||
|
||||
#if VECT_SIZE == 1
|
||||
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
|
||||
#elif VECT_SIZE == 2
|
||||
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
|
||||
#elif VECT_SIZE == 4
|
||||
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
|
||||
#elif VECT_SIZE == 8
|
||||
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
|
||||
#elif VECT_SIZE == 16
|
||||
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
|
||||
#endif
|
||||
|
||||
KERNEL_FQ void m05000_mxx (KERN_ATTR_RULES ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
const u64 lsz = get_local_size (0);
|
||||
|
||||
/**
|
||||
* bin2asc table
|
||||
*/
|
||||
|
||||
LOCAL_VK u32 l_bin2asc[256];
|
||||
|
||||
for (u32 i = lid; i < 256; i += lsz)
|
||||
{
|
||||
const u32 i0 = (i >> 0) & 15;
|
||||
const u32 i1 = (i >> 4) & 15;
|
||||
|
||||
l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
|
||||
| ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
|
||||
}
|
||||
|
||||
SYNC_THREADS ();
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
COPY_PW (pws[gid]);
|
||||
|
||||
const u32 salt_len = salt_bufs[SALT_POS].salt_len;
|
||||
|
||||
u32 s[64] = { 0 };
|
||||
|
||||
for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
|
||||
{
|
||||
s[idx] = hc_swap32_S (salt_bufs[SALT_POS].salt_buf[idx]);
|
||||
}
|
||||
|
||||
sha1_ctx_t ctx0;
|
||||
|
||||
sha1_init (&ctx0);
|
||||
|
||||
sha1_update (&ctx0, s, salt_len);
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
|
||||
{
|
||||
pw_t tmp = PASTE_PW;
|
||||
|
||||
tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
|
||||
|
||||
sha1_ctx_t ctx = ctx0;
|
||||
|
||||
sha1_update_swap (&ctx, tmp.i, tmp.pw_len);
|
||||
|
||||
sha1_update (&ctx, s, salt_len);
|
||||
|
||||
sha1_final (&ctx);
|
||||
|
||||
const u32 a = ctx.h[0];
|
||||
const u32 b = ctx.h[1];
|
||||
const u32 c = ctx.h[2];
|
||||
const u32 d = ctx.h[3];
|
||||
const u32 e = ctx.h[4];
|
||||
|
||||
sha1_ctx_t ctx1;
|
||||
|
||||
sha1_init (&ctx1);
|
||||
|
||||
ctx1.w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
|
||||
ctx1.w0[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
|
||||
ctx1.w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
|
||||
ctx1.w0[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
|
||||
ctx1.w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
|
||||
ctx1.w1[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
|
||||
ctx1.w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
|
||||
ctx1.w1[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
|
||||
ctx1.w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
|
||||
ctx1.w2[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
|
||||
|
||||
ctx1.len = 40;
|
||||
|
||||
sha1_final (&ctx1);
|
||||
|
||||
const u32 r0 = ctx1.h[DGST_R0];
|
||||
const u32 r1 = ctx1.h[DGST_R1];
|
||||
const u32 r2 = ctx1.h[DGST_R2];
|
||||
const u32 r3 = ctx1.h[DGST_R3];
|
||||
|
||||
COMPARE_M_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m05000_sxx (KERN_ATTR_RULES ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
const u64 lsz = get_local_size (0);
|
||||
|
||||
/**
|
||||
* bin2asc table
|
||||
*/
|
||||
|
||||
LOCAL_VK u32 l_bin2asc[256];
|
||||
|
||||
for (u32 i = lid; i < 256; i += lsz)
|
||||
{
|
||||
const u32 i0 = (i >> 0) & 15;
|
||||
const u32 i1 = (i >> 4) & 15;
|
||||
|
||||
l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
|
||||
| ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
|
||||
}
|
||||
|
||||
SYNC_THREADS ();
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
/**
|
||||
* 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]
|
||||
};
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
COPY_PW (pws[gid]);
|
||||
|
||||
const u32 salt_len = salt_bufs[SALT_POS].salt_len;
|
||||
|
||||
u32 s[64] = { 0 };
|
||||
|
||||
for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
|
||||
{
|
||||
s[idx] = hc_swap32_S (salt_bufs[SALT_POS].salt_buf[idx]);
|
||||
}
|
||||
|
||||
sha1_ctx_t ctx0;
|
||||
|
||||
sha1_init (&ctx0);
|
||||
|
||||
sha1_update (&ctx0, s, salt_len);
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
|
||||
{
|
||||
pw_t tmp = PASTE_PW;
|
||||
|
||||
tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
|
||||
|
||||
sha1_ctx_t ctx = ctx0;
|
||||
|
||||
sha1_update_swap (&ctx, tmp.i, tmp.pw_len);
|
||||
|
||||
sha1_update (&ctx, s, salt_len);
|
||||
|
||||
sha1_final (&ctx);
|
||||
|
||||
const u32 a = ctx.h[0];
|
||||
const u32 b = ctx.h[1];
|
||||
const u32 c = ctx.h[2];
|
||||
const u32 d = ctx.h[3];
|
||||
const u32 e = ctx.h[4];
|
||||
|
||||
sha1_ctx_t ctx1;
|
||||
|
||||
sha1_init (&ctx1);
|
||||
|
||||
ctx1.w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
|
||||
ctx1.w0[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
|
||||
ctx1.w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
|
||||
ctx1.w0[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
|
||||
ctx1.w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
|
||||
ctx1.w1[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
|
||||
ctx1.w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
|
||||
ctx1.w1[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
|
||||
ctx1.w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
|
||||
ctx1.w2[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
|
||||
|
||||
ctx1.len = 40;
|
||||
|
||||
sha1_final (&ctx1);
|
||||
|
||||
const u32 r0 = ctx1.h[DGST_R0];
|
||||
const u32 r1 = ctx1.h[DGST_R1];
|
||||
const u32 r2 = ctx1.h[DGST_R2];
|
||||
const u32 r3 = ctx1.h[DGST_R3];
|
||||
|
||||
COMPARE_S_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
1044
OpenCL/m05000_a1-optimized.cl
Normal file
1044
OpenCL/m05000_a1-optimized.cl
Normal file
File diff suppressed because it is too large
Load Diff
255
OpenCL/m05000_a1-pure.cl
Normal file
255
OpenCL/m05000_a1-pure.cl
Normal file
@ -0,0 +1,255 @@
|
||||
/**
|
||||
* 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_hash_sha1.cl"
|
||||
#endif
|
||||
|
||||
#if VECT_SIZE == 1
|
||||
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
|
||||
#elif VECT_SIZE == 2
|
||||
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
|
||||
#elif VECT_SIZE == 4
|
||||
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
|
||||
#elif VECT_SIZE == 8
|
||||
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
|
||||
#elif VECT_SIZE == 16
|
||||
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
|
||||
#endif
|
||||
|
||||
KERNEL_FQ void m05000_mxx (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
const u64 lsz = get_local_size (0);
|
||||
|
||||
/**
|
||||
* bin2asc table
|
||||
*/
|
||||
|
||||
LOCAL_VK u32 l_bin2asc[256];
|
||||
|
||||
for (u32 i = lid; i < 256; i += lsz)
|
||||
{
|
||||
const u32 i0 = (i >> 0) & 15;
|
||||
const u32 i1 = (i >> 4) & 15;
|
||||
|
||||
l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
|
||||
| ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
|
||||
}
|
||||
|
||||
SYNC_THREADS ();
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u32 salt_len = salt_bufs[SALT_POS].salt_len;
|
||||
|
||||
u32 s[64] = { 0 };
|
||||
|
||||
for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
|
||||
{
|
||||
s[idx] = hc_swap32_S (salt_bufs[SALT_POS].salt_buf[idx]);
|
||||
}
|
||||
|
||||
sha1_ctx_t ctx0;
|
||||
|
||||
sha1_init (&ctx0);
|
||||
|
||||
sha1_update (&ctx0, s, salt_len);
|
||||
|
||||
sha1_update_global_swap (&ctx0, pws[gid].i, pws[gid].pw_len);
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
|
||||
{
|
||||
sha1_ctx_t ctx = ctx0;
|
||||
|
||||
sha1_update_global_swap (&ctx, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
|
||||
|
||||
sha1_update (&ctx, s, salt_len);
|
||||
|
||||
sha1_final (&ctx);
|
||||
|
||||
const u32 a = ctx.h[0];
|
||||
const u32 b = ctx.h[1];
|
||||
const u32 c = ctx.h[2];
|
||||
const u32 d = ctx.h[3];
|
||||
const u32 e = ctx.h[4];
|
||||
|
||||
sha1_ctx_t ctx1;
|
||||
|
||||
sha1_init (&ctx1);
|
||||
|
||||
ctx1.w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
|
||||
ctx1.w0[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
|
||||
ctx1.w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
|
||||
ctx1.w0[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
|
||||
ctx1.w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
|
||||
ctx1.w1[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
|
||||
ctx1.w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
|
||||
ctx1.w1[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
|
||||
ctx1.w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
|
||||
ctx1.w2[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
|
||||
|
||||
ctx1.len = 40;
|
||||
|
||||
sha1_final (&ctx1);
|
||||
|
||||
const u32 r0 = ctx1.h[DGST_R0];
|
||||
const u32 r1 = ctx1.h[DGST_R1];
|
||||
const u32 r2 = ctx1.h[DGST_R2];
|
||||
const u32 r3 = ctx1.h[DGST_R3];
|
||||
|
||||
COMPARE_M_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m05000_sxx (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
const u64 lsz = get_local_size (0);
|
||||
|
||||
/**
|
||||
* bin2asc table
|
||||
*/
|
||||
|
||||
LOCAL_VK u32 l_bin2asc[256];
|
||||
|
||||
for (u32 i = lid; i < 256; i += lsz)
|
||||
{
|
||||
const u32 i0 = (i >> 0) & 15;
|
||||
const u32 i1 = (i >> 4) & 15;
|
||||
|
||||
l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
|
||||
| ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
|
||||
}
|
||||
|
||||
SYNC_THREADS ();
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
/**
|
||||
* 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]
|
||||
};
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u32 salt_len = salt_bufs[SALT_POS].salt_len;
|
||||
|
||||
u32 s[64] = { 0 };
|
||||
|
||||
for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
|
||||
{
|
||||
s[idx] = hc_swap32_S (salt_bufs[SALT_POS].salt_buf[idx]);
|
||||
}
|
||||
|
||||
sha1_ctx_t ctx0;
|
||||
|
||||
sha1_init (&ctx0);
|
||||
|
||||
sha1_update (&ctx0, s, salt_len);
|
||||
|
||||
sha1_update_global_swap (&ctx0, pws[gid].i, pws[gid].pw_len);
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
|
||||
{
|
||||
sha1_ctx_t ctx = ctx0;
|
||||
|
||||
sha1_update_global_swap (&ctx, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
|
||||
|
||||
sha1_update (&ctx, s, salt_len);
|
||||
|
||||
sha1_final (&ctx);
|
||||
|
||||
const u32 a = ctx.h[0];
|
||||
const u32 b = ctx.h[1];
|
||||
const u32 c = ctx.h[2];
|
||||
const u32 d = ctx.h[3];
|
||||
const u32 e = ctx.h[4];
|
||||
|
||||
sha1_ctx_t ctx1;
|
||||
|
||||
sha1_init (&ctx1);
|
||||
|
||||
ctx1.w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
|
||||
ctx1.w0[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
|
||||
ctx1.w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
|
||||
ctx1.w0[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
|
||||
ctx1.w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
|
||||
ctx1.w1[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
|
||||
ctx1.w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
|
||||
ctx1.w1[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
|
||||
ctx1.w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
|
||||
ctx1.w2[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
|
||||
|
||||
ctx1.len = 40;
|
||||
|
||||
sha1_final (&ctx1);
|
||||
|
||||
const u32 r0 = ctx1.h[DGST_R0];
|
||||
const u32 r1 = ctx1.h[DGST_R1];
|
||||
const u32 r2 = ctx1.h[DGST_R2];
|
||||
const u32 r3 = ctx1.h[DGST_R3];
|
||||
|
||||
COMPARE_S_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
1288
OpenCL/m05000_a3-optimized.cl
Normal file
1288
OpenCL/m05000_a3-optimized.cl
Normal file
File diff suppressed because it is too large
Load Diff
289
OpenCL/m05000_a3-pure.cl
Normal file
289
OpenCL/m05000_a3-pure.cl
Normal file
@ -0,0 +1,289 @@
|
||||
/**
|
||||
* 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_sha1.cl"
|
||||
#endif
|
||||
|
||||
#if VECT_SIZE == 1
|
||||
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
|
||||
#elif VECT_SIZE == 2
|
||||
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
|
||||
#elif VECT_SIZE == 4
|
||||
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
|
||||
#elif VECT_SIZE == 8
|
||||
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
|
||||
#elif VECT_SIZE == 16
|
||||
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
|
||||
#endif
|
||||
|
||||
KERNEL_FQ void m05000_mxx (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
const u64 lsz = get_local_size (0);
|
||||
|
||||
/**
|
||||
* bin2asc table
|
||||
*/
|
||||
|
||||
LOCAL_VK u32 l_bin2asc[256];
|
||||
|
||||
for (u32 i = lid; i < 256; i += lsz)
|
||||
{
|
||||
const u32 i0 = (i >> 0) & 15;
|
||||
const u32 i1 = (i >> 4) & 15;
|
||||
|
||||
l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
|
||||
| ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
|
||||
}
|
||||
|
||||
SYNC_THREADS ();
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len;
|
||||
|
||||
u32x w[64] = { 0 };
|
||||
|
||||
for (u32 i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
|
||||
{
|
||||
w[idx] = pws[gid].i[idx];
|
||||
}
|
||||
|
||||
const u32 salt_len = salt_bufs[SALT_POS].salt_len;
|
||||
|
||||
u32x s[64] = { 0 };
|
||||
|
||||
for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
|
||||
{
|
||||
s[idx] = hc_swap32 (salt_bufs[SALT_POS].salt_buf[idx]);
|
||||
}
|
||||
|
||||
sha1_ctx_t ctx0;
|
||||
|
||||
sha1_init (&ctx0);
|
||||
|
||||
sha1_update_global_swap (&ctx0, salt_bufs[SALT_POS].salt_buf, salt_bufs[SALT_POS].salt_len);
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
u32x w0l = w[0];
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
|
||||
{
|
||||
const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
|
||||
|
||||
const u32x w0 = w0l | w0r;
|
||||
|
||||
w[0] = w0;
|
||||
|
||||
sha1_ctx_vector_t ctx;
|
||||
|
||||
sha1_init_vector_from_scalar (&ctx, &ctx0);
|
||||
|
||||
sha1_update_vector_swap (&ctx, w, pw_len);
|
||||
|
||||
sha1_update_vector (&ctx, s, salt_len);
|
||||
|
||||
sha1_final_vector (&ctx);
|
||||
|
||||
const u32x a = ctx.h[0];
|
||||
const u32x b = ctx.h[1];
|
||||
const u32x c = ctx.h[2];
|
||||
const u32x d = ctx.h[3];
|
||||
const u32x e = ctx.h[4];
|
||||
|
||||
sha1_ctx_vector_t ctx1;
|
||||
|
||||
sha1_init_vector (&ctx1);
|
||||
|
||||
ctx1.w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
|
||||
ctx1.w0[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
|
||||
ctx1.w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
|
||||
ctx1.w0[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
|
||||
ctx1.w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
|
||||
ctx1.w1[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
|
||||
ctx1.w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
|
||||
ctx1.w1[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
|
||||
ctx1.w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
|
||||
ctx1.w2[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
|
||||
|
||||
ctx1.len = 40;
|
||||
|
||||
sha1_final_vector (&ctx1);
|
||||
|
||||
const u32x r0 = ctx1.h[DGST_R0];
|
||||
const u32x r1 = ctx1.h[DGST_R1];
|
||||
const u32x r2 = ctx1.h[DGST_R2];
|
||||
const u32x r3 = ctx1.h[DGST_R3];
|
||||
|
||||
COMPARE_M_SIMD (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m05000_sxx (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
const u64 lsz = get_local_size (0);
|
||||
|
||||
/**
|
||||
* bin2asc table
|
||||
*/
|
||||
|
||||
LOCAL_VK u32 l_bin2asc[256];
|
||||
|
||||
for (u32 i = lid; i < 256; i += lsz)
|
||||
{
|
||||
const u32 i0 = (i >> 0) & 15;
|
||||
const u32 i1 = (i >> 4) & 15;
|
||||
|
||||
l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
|
||||
| ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
|
||||
}
|
||||
|
||||
SYNC_THREADS ();
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
/**
|
||||
* 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]
|
||||
};
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len;
|
||||
|
||||
u32x w[64] = { 0 };
|
||||
|
||||
for (u32 i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
|
||||
{
|
||||
w[idx] = pws[gid].i[idx];
|
||||
}
|
||||
|
||||
const u32 salt_len = salt_bufs[SALT_POS].salt_len;
|
||||
|
||||
u32x s[64] = { 0 };
|
||||
|
||||
for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
|
||||
{
|
||||
s[idx] = hc_swap32 (salt_bufs[SALT_POS].salt_buf[idx]);
|
||||
}
|
||||
|
||||
sha1_ctx_t ctx0;
|
||||
|
||||
sha1_init (&ctx0);
|
||||
|
||||
sha1_update_global_swap (&ctx0, salt_bufs[SALT_POS].salt_buf, salt_bufs[SALT_POS].salt_len);
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
u32x w0l = w[0];
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
|
||||
{
|
||||
const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
|
||||
|
||||
const u32x w0 = w0l | w0r;
|
||||
|
||||
w[0] = w0;
|
||||
|
||||
sha1_ctx_vector_t ctx;
|
||||
|
||||
sha1_init_vector_from_scalar (&ctx, &ctx0);
|
||||
|
||||
sha1_update_vector_swap (&ctx, w, pw_len);
|
||||
|
||||
sha1_update_vector (&ctx, s, salt_len);
|
||||
|
||||
sha1_final_vector (&ctx);
|
||||
|
||||
const u32x a = ctx.h[0];
|
||||
const u32x b = ctx.h[1];
|
||||
const u32x c = ctx.h[2];
|
||||
const u32x d = ctx.h[3];
|
||||
const u32x e = ctx.h[4];
|
||||
|
||||
sha1_ctx_vector_t ctx1;
|
||||
|
||||
sha1_init_vector (&ctx1);
|
||||
|
||||
ctx1.w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
|
||||
ctx1.w0[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
|
||||
ctx1.w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
|
||||
ctx1.w0[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
|
||||
ctx1.w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
|
||||
ctx1.w1[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
|
||||
ctx1.w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
|
||||
ctx1.w1[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
|
||||
ctx1.w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
|
||||
ctx1.w2[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
|
||||
|
||||
ctx1.len = 40;
|
||||
|
||||
sha1_final_vector (&ctx1);
|
||||
|
||||
const u32x r0 = ctx1.h[DGST_R0];
|
||||
const u32x r1 = ctx1.h[DGST_R1];
|
||||
const u32x r2 = ctx1.h[DGST_R2];
|
||||
const u32x r3 = ctx1.h[DGST_R3];
|
||||
|
||||
COMPARE_S_SIMD (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
Loading…
Reference in New Issue
Block a user