mirror of https://github.com/hashcat/hashcat.git
commit
f016deaa76
@ -0,0 +1,57 @@
|
||||
---
|
||||
name: Bug report
|
||||
about: Something is not working as expected
|
||||
title: ''
|
||||
labels: bug
|
||||
assignees: ''
|
||||
|
||||
---
|
||||
|
||||
**GitHub is for bugs and features - not for support**
|
||||
For support, please use the hashcat forums https://hashcat.net/forum/
|
||||
|
||||
**Check the FAQ**
|
||||
Some items that might appear to be issues are not issues. Please review the hashcat FAQ https://hashcat.net/wiki/doku.php?id=frequently_asked_questions before submitting a bug report.
|
||||
|
||||
**Describe the bug**
|
||||
A clear and concise description of what the bug is.
|
||||
|
||||
**To Reproduce**
|
||||
Please provide us with all files required to reproduce the bug locally on our development systems. For instance: hash files, wordlists, rule files, ...
|
||||
|
||||
**Expected behavior**
|
||||
A clear and concise description of what you expected to happen.
|
||||
|
||||
**Hardware/Compute device (please complete the following information):**
|
||||
- Compute device name: [e.g. RTX2080Ti]
|
||||
- OpenCL/CUDA driver name: [e.g. NVIDIA DRIVER]
|
||||
- OpenCL/CUDA driver version: [e.g. 465.21]
|
||||
- OpenCL/CUDA driver source: [e.g. runtime installer/.exe installer]
|
||||
|
||||
**Hashcat version (please complete the following information):**
|
||||
- OS: [e.g. Linux]
|
||||
- Distribution: [e.g. Ubuntu 18.04]
|
||||
- Version: [e.g. 6.2.0]
|
||||
|
||||
**Diagnostic output compute devices:**
|
||||
|
||||
|
||||
```
|
||||
For NV: Post nvidia-smi output. This tool also exist on Windows
|
||||
For AMD ROCm: Post rocm-smi and rocminfo output
|
||||
```
|
||||
|
||||
```
|
||||
Post clinfo output
|
||||
```
|
||||
|
||||
```
|
||||
Post hashcat -I output
|
||||
```
|
||||
|
||||
```
|
||||
On Linux: post lspci output
|
||||
```
|
||||
|
||||
**Additional context**
|
||||
Add any other context about the problem here. For instance, it was working with hashcat version X.X.X (also please post output from older versions).
|
@ -0,0 +1,32 @@
|
||||
---
|
||||
name: Feature Request - Add new algorithm
|
||||
about: Add support for new hash-mode (-m)
|
||||
title: ''
|
||||
labels: new algorithm
|
||||
assignees: ''
|
||||
|
||||
---
|
||||
|
||||
**Is your request based on a publicly know cryptographic schema and where can we find information about?**
|
||||
For instance:
|
||||
- The hashing function XY is a public known hash algorithm on Wikipedia.
|
||||
- The password protection for the application XY was made by public by security researcher XY and there's a paper called ...
|
||||
- The cryptographic schema used in protocol XY can be found in the OSS code on it's GitHub repository.
|
||||
|
||||
**Describe alternatives you've considered**
|
||||
A clear and concise description of any alternative solutions or features you've considered. For instance, other standalone crackers which already support this algorithm.
|
||||
|
||||
**Provide an example hash/database/file and a known correct password**
|
||||
The most easy way to produce this is to simply generate a new one using the application itself.
|
||||
|
||||
**Explain how the cryptographic schema is implemented**
|
||||
The best way is with a proof of concept code in any computer language or pseudo code you like.
|
||||
|
||||
**Describe the known limitations of the algorithm**
|
||||
Many applications limit the password and/or salt to a specific minimum and maximum length.
|
||||
|
||||
**Where do you typically find the algorithm**
|
||||
In case you are requesting a cryptographic primitive, name some of the Applications/OS in which it is being used.
|
||||
|
||||
**Additional context**
|
||||
Add any other context or screenshots about the feature request here.
|
@ -0,0 +1,306 @@
|
||||
/**
|
||||
* Author......: See docs/credits.txt
|
||||
* License.....: MIT
|
||||
*/
|
||||
|
||||
#include "inc_vendor.h"
|
||||
#include "inc_types.h"
|
||||
#include "inc_platform.h"
|
||||
#include "inc_common.h"
|
||||
#include "inc_cipher_aes.h"
|
||||
#include "inc_cipher_aes-gcm.h"
|
||||
|
||||
DECLSPEC void AES_GCM_inc32 (u32 *block)
|
||||
{
|
||||
block[3] += 1;
|
||||
}
|
||||
|
||||
DECLSPEC void AES_GCM_xor_block (u32 *dst, const u32 *src)
|
||||
{
|
||||
dst[0] ^= src[0];
|
||||
dst[1] ^= src[1];
|
||||
dst[2] ^= src[2];
|
||||
dst[3] ^= src[3];
|
||||
}
|
||||
|
||||
DECLSPEC void AES_GCM_gf_mult (const u32 *x, const u32 *y, u32 *z)
|
||||
{
|
||||
z[0] = 0;
|
||||
z[1] = 0;
|
||||
z[2] = 0;
|
||||
z[3] = 0;
|
||||
|
||||
u32 t[4];
|
||||
|
||||
t[0] = y[0];
|
||||
t[1] = y[1];
|
||||
t[2] = y[2];
|
||||
t[3] = y[3];
|
||||
|
||||
for (int i = 0; i < 4; i++)
|
||||
{
|
||||
const u32 tv = x[i];
|
||||
|
||||
for (int j = 0; j < 32; j++)
|
||||
{
|
||||
if ((tv >> (31 - j)) & 1)
|
||||
{
|
||||
z[0] ^= t[0];
|
||||
z[1] ^= t[1];
|
||||
z[2] ^= t[2];
|
||||
z[3] ^= t[3];
|
||||
}
|
||||
|
||||
const int m = t[3] & 1; // save lost bit
|
||||
|
||||
t[3] = (t[2] << 31) | (t[3] >> 1);
|
||||
t[2] = (t[1] << 31) | (t[2] >> 1);
|
||||
t[1] = (t[0] << 31) | (t[1] >> 1);
|
||||
t[0] = 0 | (t[0] >> 1);
|
||||
|
||||
t[0] ^= m * 0xe1000000;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
DECLSPEC void AES_GCM_ghash (const u32 *subkey, const u32 *in, int in_len, u32 *out)
|
||||
{
|
||||
int i;
|
||||
int j;
|
||||
|
||||
for (i = 0, j = 0; i < in_len - 15; i += 16, j += 4)
|
||||
{
|
||||
u32 t2[4];
|
||||
|
||||
t2[0] = in[j + 0];
|
||||
t2[1] = in[j + 1];
|
||||
t2[2] = in[j + 2];
|
||||
t2[3] = in[j + 3];
|
||||
|
||||
AES_GCM_xor_block (out, t2);
|
||||
|
||||
u32 tmp[4];
|
||||
|
||||
AES_GCM_gf_mult (out, subkey, tmp);
|
||||
|
||||
out[0] = tmp[0];
|
||||
out[1] = tmp[1];
|
||||
out[2] = tmp[2];
|
||||
out[3] = tmp[3];
|
||||
}
|
||||
|
||||
const int left = in_len - i;
|
||||
|
||||
if (left > 0)
|
||||
{
|
||||
u32 t2[4];
|
||||
|
||||
t2[0] = (left > 0) ? in[j + 0] : 0;
|
||||
t2[1] = (left > 4) ? in[j + 1] : 0;
|
||||
t2[2] = (left > 8) ? in[j + 2] : 0;
|
||||
t2[3] = (left > 12) ? in[j + 3] : 0;
|
||||
|
||||
AES_GCM_xor_block (out, t2);
|
||||
|
||||
u32 tmp[4];
|
||||
|
||||
AES_GCM_gf_mult (out, subkey, tmp);
|
||||
|
||||
out[0] = tmp[0];
|
||||
out[1] = tmp[1];
|
||||
out[2] = tmp[2];
|
||||
out[3] = tmp[3];
|
||||
}
|
||||
}
|
||||
|
||||
DECLSPEC void AES_GCM_ghash_global (const u32 *subkey, GLOBAL_AS const u32 *in, int in_len, u32 *out)
|
||||
{
|
||||
int i;
|
||||
int j;
|
||||
|
||||
for (i = 0, j = 0; i < in_len - 15; i += 16, j += 4)
|
||||
{
|
||||
u32 t2[4];
|
||||
|
||||
t2[0] = in[j + 0];
|
||||
t2[1] = in[j + 1];
|
||||
t2[2] = in[j + 2];
|
||||
t2[3] = in[j + 3];
|
||||
|
||||
AES_GCM_xor_block (out, t2);
|
||||
|
||||
u32 tmp[4];
|
||||
|
||||
AES_GCM_gf_mult (out, subkey, tmp);
|
||||
|
||||
out[0] = tmp[0];
|
||||
out[1] = tmp[1];
|
||||
out[2] = tmp[2];
|
||||
out[3] = tmp[3];
|
||||
}
|
||||
|
||||
const int left = in_len - i;
|
||||
|
||||
if (left > 0)
|
||||
{
|
||||
u32 t2[4];
|
||||
|
||||
t2[0] = (left > 0) ? in[j + 0] : 0;
|
||||
t2[1] = (left > 4) ? in[j + 1] : 0;
|
||||
t2[2] = (left > 8) ? in[j + 2] : 0;
|
||||
t2[3] = (left > 12) ? in[j + 3] : 0;
|
||||
|
||||
AES_GCM_xor_block (out, t2);
|
||||
|
||||
u32 tmp[4];
|
||||
|
||||
AES_GCM_gf_mult (out, subkey, tmp);
|
||||
|
||||
out[0] = tmp[0];
|
||||
out[1] = tmp[1];
|
||||
out[2] = tmp[2];
|
||||
out[3] = tmp[3];
|
||||
}
|
||||
}
|
||||
|
||||
DECLSPEC void AES_GCM_Init (const u32 *ukey, int key_len, u32 *key, u32 *subkey, SHM_TYPE u32 *s_te0, SHM_TYPE u32 *s_te1, SHM_TYPE u32 *s_te2, SHM_TYPE u32 *s_te3, SHM_TYPE u32 *s_te4)
|
||||
{
|
||||
if (key_len == 128)
|
||||
{
|
||||
AES128_set_encrypt_key (key, ukey, s_te0, s_te1, s_te2, s_te3);
|
||||
|
||||
AES192_encrypt (key, subkey, subkey, s_te0, s_te1, s_te2, s_te3, s_te4);
|
||||
}
|
||||
else if (key_len == 192)
|
||||
{
|
||||
AES192_set_encrypt_key (key, ukey, s_te0, s_te1, s_te2, s_te3);
|
||||
|
||||
AES192_encrypt (key, subkey, subkey, s_te0, s_te1, s_te2, s_te3, s_te4);
|
||||
}
|
||||
else if (key_len == 256)
|
||||
{
|
||||
AES256_set_encrypt_key (key, ukey, s_te0, s_te1, s_te2, s_te3);
|
||||
|
||||
AES256_encrypt (key, subkey, subkey, s_te0, s_te1, s_te2, s_te3, s_te4);
|
||||
}
|
||||
}
|
||||
|
||||
DECLSPEC void AES_GCM_Prepare_J0 (const u32 *iv, int iv_len, const u32 *subkey, u32 *J0)
|
||||
{
|
||||
if (iv_len == 12)
|
||||
{
|
||||
J0[0] = iv[0];
|
||||
J0[1] = iv[1];
|
||||
J0[2] = iv[2];
|
||||
J0[3] = 0x00000001;
|
||||
}
|
||||
else
|
||||
{
|
||||
AES_GCM_gf_mult (iv, subkey, J0);
|
||||
|
||||
u32 len_buf[4] = { 0 };
|
||||
|
||||
len_buf[3] = iv_len * 8;
|
||||
|
||||
AES_GCM_xor_block (len_buf, J0);
|
||||
|
||||
AES_GCM_gf_mult (len_buf, subkey, J0);
|
||||
}
|
||||
}
|
||||
|
||||
DECLSPEC void AES_GCM_gctr (const u32 *key, const u32 *iv, const u32 *in, int in_len, u32 *out, SHM_TYPE u32 *s_te0, SHM_TYPE u32 *s_te1, SHM_TYPE u32 *s_te2, SHM_TYPE u32 *s_te3, SHM_TYPE u32 *s_te4)
|
||||
{
|
||||
const u32 *xpos = in;
|
||||
|
||||
u32 *ypos = out;
|
||||
|
||||
u32 iv_buf[4];
|
||||
|
||||
iv_buf[0] = iv[0];
|
||||
iv_buf[1] = iv[1];
|
||||
iv_buf[2] = iv[2];
|
||||
iv_buf[3] = iv[3];
|
||||
|
||||
const int n = in_len / 16;
|
||||
|
||||
for (u32 i = 0; i < n; i++)
|
||||
{
|
||||
AES256_encrypt (key, iv_buf, ypos, s_te0, s_te1, s_te2, s_te3, s_te4);
|
||||
|
||||
AES_GCM_xor_block (ypos, xpos);
|
||||
|
||||
xpos += 4;
|
||||
ypos += 4;
|
||||
|
||||
AES_GCM_inc32 (iv_buf);
|
||||
}
|
||||
|
||||
// this is not byte accurate but 4-byte accurate. needs fix?
|
||||
|
||||
int last = in + (in_len/4) - xpos;
|
||||
|
||||
if (last)
|
||||
{
|
||||
u32 tmp[4] = { 0 };
|
||||
|
||||
AES256_encrypt (key, iv_buf, tmp, s_te0, s_te1, s_te2, s_te3, s_te4);
|
||||
|
||||
if (last >= 1) *ypos++ = *xpos++ ^ tmp[0];
|
||||
if (last >= 2) *ypos++ = *xpos++ ^ tmp[1];
|
||||
if (last >= 3) *ypos++ = *xpos++ ^ tmp[2];
|
||||
}
|
||||
}
|
||||
|
||||
DECLSPEC void AES_GCM_GCTR (u32 *key, u32 *J0, const u32 *in, int in_len, u32 *out, SHM_TYPE u32 *s_te0, SHM_TYPE u32 *s_te1, SHM_TYPE u32 *s_te2, SHM_TYPE u32 *s_te3, SHM_TYPE u32 *s_te4)
|
||||
{
|
||||
u32 J0_incr[4];
|
||||
|
||||
J0_incr[0] = J0[0];
|
||||
J0_incr[1] = J0[1];
|
||||
J0_incr[2] = J0[2];
|
||||
J0_incr[3] = J0[3];
|
||||
|
||||
AES_GCM_gctr (key, J0_incr, in, in_len, out, s_te0, s_te1, s_te2, s_te3, s_te4);
|
||||
}
|
||||
|
||||
DECLSPEC void AES_GCM_GHASH (const u32 *subkey, const u32 *aad_buf, int aad_len, const u32 *enc_buf, int enc_len, u32 *out)
|
||||
{
|
||||
out[0] = 0;
|
||||
out[1] = 0;
|
||||
out[2] = 0;
|
||||
out[3] = 0;
|
||||
|
||||
AES_GCM_ghash (subkey, aad_buf, aad_len, out);
|
||||
|
||||
AES_GCM_ghash (subkey, enc_buf, enc_len, out);
|
||||
|
||||
u32 len_buf[4];
|
||||
|
||||
len_buf[0] = aad_len * 8;
|
||||
len_buf[1] = 0;
|
||||
len_buf[2] = 0;
|
||||
len_buf[3] = enc_len * 8;
|
||||
|
||||
AES_GCM_ghash (subkey, len_buf, 16, out);
|
||||
}
|
||||
|
||||
DECLSPEC void AES_GCM_GHASH_GLOBAL (const u32 *subkey, const u32 *aad_buf, int aad_len, GLOBAL_AS const u32 *enc_buf, int enc_len, u32 *out)
|
||||
{
|
||||
out[0] = 0;
|
||||
out[1] = 0;
|
||||
out[2] = 0;
|
||||
out[3] = 0;
|
||||
|
||||
AES_GCM_ghash (subkey, aad_buf, aad_len, out);
|
||||
|
||||
AES_GCM_ghash_global (subkey, enc_buf, enc_len, out);
|
||||
|
||||
u32 len_buf[4];
|
||||
|
||||
len_buf[0] = aad_len * 8;
|
||||
len_buf[1] = 0;
|
||||
len_buf[2] = 0;
|
||||
len_buf[3] = enc_len * 8;
|
||||
|
||||
AES_GCM_ghash (subkey, len_buf, 16, out);
|
||||
}
|
@ -0,0 +1,21 @@
|
||||
/**
|
||||
* Author......: See docs/credits.txt
|
||||
* License.....: MIT
|
||||
*/
|
||||
|
||||
#ifndef _INC_CIPHER_AES_GCM_H
|
||||
#define _INC_CIPHER_AES_GCM_H
|
||||
|
||||
DECLSPEC void AES_GCM_inc32 (u32 *block);
|
||||
DECLSPEC void AES_GCM_xor_block (u32 *dst, const u32 *src);
|
||||
DECLSPEC void AES_GCM_gf_mult (const u32 *x, const u32 *y, u32 *z);
|
||||
DECLSPEC void AES_GCM_ghash (const u32 *subkey, const u32 *in, int in_len, u32 *out);
|
||||
DECLSPEC void AES_GCM_ghash_global (const u32 *subkey, GLOBAL_AS const u32 *in, int in_len, u32 *out);
|
||||
DECLSPEC void AES_GCM_Init (const u32 *ukey, int key_len, u32 *key, u32 *subkey, SHM_TYPE u32 *s_te0, SHM_TYPE u32 *s_te1, SHM_TYPE u32 *s_te2, SHM_TYPE u32 *s_te3, SHM_TYPE u32 *s_te4);
|
||||
DECLSPEC void AES_GCM_Prepare_J0 (const u32 *iv, int iv_len, const u32 *subkey, u32 *J0);
|
||||
DECLSPEC void AES_GCM_gctr (const u32 *key, const u32 *iv, const u32 *in, int in_len, u32 *out, SHM_TYPE u32 *s_te0, SHM_TYPE u32 *s_te1, SHM_TYPE u32 *s_te2, SHM_TYPE u32 *s_te3, SHM_TYPE u32 *s_te4);
|
||||
DECLSPEC void AES_GCM_GCTR (u32 *key, u32 *J0, const u32 *in, int in_len, u32 *out, SHM_TYPE u32 *s_te0, SHM_TYPE u32 *s_te1, SHM_TYPE u32 *s_te2, SHM_TYPE u32 *s_te3, SHM_TYPE u32 *s_te4);
|
||||
DECLSPEC void AES_GCM_GHASH (const u32 *subkey, const u32 *aad_buf, int aad_len, const u32 *enc_buf, int enc_len, u32 *out);
|
||||
DECLSPEC void AES_GCM_GHASH_GLOBAL (const u32 *subkey, const u32 *aad_buf, int aad_len, GLOBAL_AS const u32 *enc_buf, int enc_len, u32 *out);
|
||||
|
||||
#endif // _INC_CIPHER_AES_GCM_H
|
@ -0,0 +1,269 @@
|
||||
#include "inc_vendor.h"
|
||||
#include "inc_types.h"
|
||||
#include "inc_platform.h"
|
||||
#include "inc_common.h"
|
||||
#include "inc_cipher_rc4.h"
|
||||
|
||||
#ifdef IS_CPU
|
||||
|
||||
// Pattern linear
|
||||
|
||||
DECLSPEC u8 GET_KEY8 (LOCAL_AS u32 *S, const u8 k)
|
||||
{
|
||||
LOCAL_AS u8 *S8 = (LOCAL_AS u8 *) S;
|
||||
|
||||
return S8[k];
|
||||
}
|
||||
|
||||
DECLSPEC void SET_KEY8 (LOCAL_AS u32 *S, const u8 k, const u8 v)
|
||||
{
|
||||
LOCAL_AS u8 *S8 = (LOCAL_AS u8 *) S;
|
||||
|
||||
S8[k] = v;
|
||||
}
|
||||
|
||||
DECLSPEC void SET_KEY32 (LOCAL_AS u32 *S, const u8 k, const u32 v)
|
||||
{
|
||||
S[k] = v;
|
||||
}
|
||||
|
||||
#else
|
||||
|
||||
// The goal of this pattern is to have the minimum shared memory bank conflicts as possible.
|
||||
// Bank conflicts force the device to serialize the bank access and this results in performance drops.
|
||||
//
|
||||
// Good to know:
|
||||
// NV and AMD GPU both have exactly 32 shared memory banks (at least on all modern GPU).
|
||||
// These banks can't be addressed directly, but indirectly.
|
||||
// Each of the 32 banks add some space to the total LOCAL buffer.
|
||||
// But this space is not simply appended, but in chunks of 4 bytes:
|
||||
// Bank 0 provides bytes 0..3, Bank 1 provides bytes 4..7, Bank 2 provides 8..11, and so on..
|
||||
//
|
||||
// We design the memory structure that each thread ID aligns with the corresponding bank ID.
|
||||
// If a thread always access the same bank, then there are no bank conflicts and we reach our goal.
|
||||
//
|
||||
// Since we have 32 banks, we ideally operate on 32 threads.
|
||||
// For NV GPU this aligns perfectly, because native threads = 32.
|
||||
// For AMD GPU it does not, because native threads = 64. But we can reduce it to only 1 bank conflict per thread.
|
||||
//
|
||||
// The size for the S[] buffer for each thread is 256 byte, basically just the RC4 sbox.
|
||||
// We want to assign 1 thread to 1 bank, so for 32 banks the total size is 8192 bytes (256 * 32 = 8192):
|
||||
// LOCAL_VK u32 S[64 * FIXED_LOCAL_SIZE];
|
||||
// Note that sizeof (u32) * 64 = 256 and then multiplied with the thread count.
|
||||
//
|
||||
// Addressing:
|
||||
//
|
||||
// This is the first major offset and is relevant for thread ID >= 32 (AMD or non-native thread count on NV):
|
||||
// (t / 32) * 8192
|
||||
// The first 8192 bytes of S[] are accessed from threads 0..31 and the next 8192 bytes from threads 32..63
|
||||
// We could also use more than 64 threads but we need to make sure it's a multiple of 32.
|
||||
//
|
||||
// Inside this window of 8192 bytes we select the bank id from the thread id:
|
||||
// (t & 31) * 4
|
||||
// We need to do the * 4 because of the 4 byte chunks (see top)
|
||||
//
|
||||
// Because of the indirect bank ID addressing we can't write from left to right, we write from top to bottom.
|
||||
// To ensure each thread stays to its assigned bank id from the previous calculation we could simply do k * 128,
|
||||
// because 128 = 4 (bank chunk size) * 32 (banks).
|
||||
//
|
||||
// However, it's not that easy. We need to find a way to enforce a chunk size of 4.
|
||||
// (k / 4) * 128
|
||||
//
|
||||
// Finally we can select the actual target byte from (1 out of 4) from this chunk:
|
||||
// (k & 3)
|
||||
|
||||
#define KEY8(t,k) (((k) & 3) + (((k) / 4) * 128) + (((t) & 31) * 4) + (((t) / 32) * 8192))
|
||||
|
||||
DECLSPEC u8 GET_KEY8 (LOCAL_AS u32 *S, const u8 k)
|
||||
{
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
LOCAL_AS u8 *S8 = (LOCAL_AS u8 *) S;
|
||||
|
||||
return S8[KEY8 (lid, k)];
|
||||
}
|
||||
|
||||
DECLSPEC void SET_KEY8 (LOCAL_AS u32 *S, const u8 k, const u8 v)
|
||||
{
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
LOCAL_AS u8 *S8 = (LOCAL_AS u8 *) S;
|
||||
|
||||
S8[KEY8 (lid, k)] = v;
|
||||
}
|
||||
|
||||
#define KEY32(t,k) (((k) * 32) + ((t) & 31) + (((t) / 32) * 2048))
|
||||
|
||||
DECLSPEC void SET_KEY32 (LOCAL_AS u32 *S, const u8 k, const u32 v)
|
||||
{
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
S[KEY32 (lid, k)] = v;
|
||||
}
|
||||
|
||||
#undef KEY8
|
||||
#undef KEY32
|
||||
|
||||
#endif
|
||||
|
||||
DECLSPEC void rc4_init_40 (LOCAL_AS u32 *S, const u32 *key)
|
||||
{
|
||||
u32 v = 0x03020100;
|
||||
u32 a = 0x04040404;
|
||||
|
||||
#ifdef _unroll
|
||||
#pragma unroll
|
||||
#endif
|
||||
for (u8 i = 0; i < 64; i++)
|
||||
{
|
||||
SET_KEY32 (S, i, v); v += a;
|
||||
}
|
||||
|
||||
const u8 d0 = v8a_from_v32_S (key[0]);
|
||||
const u8 d1 = v8b_from_v32_S (key[0]);
|
||||
const u8 d2 = v8c_from_v32_S (key[0]);
|
||||
const u8 d3 = v8d_from_v32_S (key[0]);
|
||||
const u8 d4 = v8a_from_v32_S (key[1]);
|
||||
|
||||
u8 j = 0;
|
||||
|
||||
#ifdef _unroll
|
||||
#pragma unroll
|
||||
#endif
|
||||
for (u32 i = 0; i < 255; i += 5)
|
||||
{
|
||||
j += GET_KEY8 (S, i + 0) + d0; rc4_swap (S, i + 0, j);
|
||||
j += GET_KEY8 (S, i + 1) + d1; rc4_swap (S, i + 1, j);
|
||||
j += GET_KEY8 (S, i + 2) + d2; rc4_swap (S, i + 2, j);
|
||||
j += GET_KEY8 (S, i + 3) + d3; rc4_swap (S, i + 3, j);
|
||||
j += GET_KEY8 (S, i + 4) + d4; rc4_swap (S, i + 4, j);
|
||||
}
|
||||
|
||||
j += GET_KEY8 (S, 255) + d0; rc4_swap (S, 255, j);
|
||||
}
|
||||
|
||||
DECLSPEC void rc4_init_128 (LOCAL_AS u32 *S, const u32 *key)
|
||||
{
|
||||
u32 v = 0x03020100;
|
||||
u32 a = 0x04040404;
|
||||
|
||||
#ifdef _unroll
|
||||
#pragma unroll
|
||||
#endif
|
||||
for (u8 i = 0; i < 64; i++)
|
||||
{
|
||||
SET_KEY32 (S, i, v); v += a;
|
||||
}
|
||||
|
||||
u8 j = 0;
|
||||
|
||||
for (u32 i = 0; i < 16; i++)
|
||||
{
|
||||
u8 idx = i * 16;
|
||||
|
||||
u32 v;
|
||||
|
||||
v = key[0];
|
||||
|
||||
j += GET_KEY8 (S, idx) + v8a_from_v32_S (v); rc4_swap (S, idx, j); idx++;
|
||||
j += GET_KEY8 (S, idx) + v8b_from_v32_S (v); rc4_swap (S, idx, j); idx++;
|
||||
j += GET_KEY8 (S, idx) + v8c_from_v32_S (v); rc4_swap (S, idx, j); idx++;
|
||||
j += GET_KEY8 (S, idx) + v8d_from_v32_S (v); rc4_swap (S, idx, j); idx++;
|
||||
|
||||
v = key[1];
|
||||
|
||||
j += GET_KEY8 (S, idx) + v8a_from_v32_S (v); rc4_swap (S, idx, j); idx++;
|
||||
j += GET_KEY8 (S, idx) + v8b_from_v32_S (v); rc4_swap (S, idx, j); idx++;
|
||||
j += GET_KEY8 (S, idx) + v8c_from_v32_S (v); rc4_swap (S, idx, j); idx++;
|
||||
j += GET_KEY8 (S, idx) + v8d_from_v32_S (v); rc4_swap (S, idx, j); idx++;
|
||||
|
||||
v = key[2];
|
||||
|
||||
j += GET_KEY8 (S, idx) + v8a_from_v32_S (v); rc4_swap (S, idx, j); idx++;
|
||||
j += GET_KEY8 (S, idx) + v8b_from_v32_S (v); rc4_swap (S, idx, j); idx++;
|
||||
j += GET_KEY8 (S, idx) + v8c_from_v32_S (v); rc4_swap (S, idx, j); idx++;
|
||||
j += GET_KEY8 (S, idx) + v8d_from_v32_S (v); rc4_swap (S, idx, j); idx++;
|
||||
|
||||
v = key[3];
|
||||
|
||||
j += GET_KEY8 (S, idx) + v8a_from_v32_S (v); rc4_swap (S, idx, j); idx++;
|
||||
j += GET_KEY8 (S, idx) + v8b_from_v32_S (v); rc4_swap (S, idx, j); idx++;
|
||||
j += GET_KEY8 (S, idx) + v8c_from_v32_S (v); rc4_swap (S, idx, j); idx++;
|
||||
j += GET_KEY8 (S, idx) + v8d_from_v32_S (v); rc4_swap (S, idx, j); idx++;
|
||||
}
|
||||
}
|
||||
|
||||
DECLSPEC void rc4_swap (LOCAL_AS u32 *S, const u8 i, const u8 j)
|
||||
{
|
||||
u8 tmp;
|
||||
|
||||
tmp = GET_KEY8 (S, i);
|
||||
SET_KEY8 (S, i, GET_KEY8 (S, j));
|
||||
SET_KEY8 (S, j, tmp);
|
||||
}
|
||||
|
||||
DECLSPEC u8 rc4_next_16 (LOCAL_AS u32 *S, const u8 i, const u8 j, const u32 *in, u32 *out)
|
||||
{
|
||||
u8 a = i;
|
||||
u8 b = j;
|
||||
|
||||
#ifdef _unroll
|
||||
#pragma unroll
|
||||
#endif
|
||||
for (int k = 0; k < 4; k++)
|
||||
{
|
||||
u32 xor4 = 0;
|
||||
|
||||
u32 tmp;
|
||||
|
||||
u8 idx;
|
||||
|
||||
a += 1;
|
||||
b += GET_KEY8 (S, a);
|
||||
|
||||
rc4_swap (S, a, b);
|
||||
|
||||
idx = GET_KEY8 (S, a) + GET_KEY8 (S, b);
|
||||
|
||||
tmp = GET_KEY8 (S, idx);
|
||||
|
||||
xor4 |= tmp << 0;
|
||||
|
||||
a += 1;
|
||||
b += GET_KEY8 (S, a);
|
||||
|
||||
rc4_swap (S, a, b);
|
||||
|
||||
idx = GET_KEY8 (S, a) + GET_KEY8 (S, b);
|
||||
|
||||
tmp = GET_KEY8 (S, idx);
|
||||
|
||||
xor4 |= tmp << 8;
|
||||
|
||||
a += 1;
|
||||
b += GET_KEY8 (S, a);
|
||||
|
||||
rc4_swap (S, a, b);
|
||||
|
||||
idx = GET_KEY8 (S, a) + GET_KEY8 (S, b);
|
||||
|
||||
tmp = GET_KEY8 (S, idx);
|
||||
|
||||
xor4 |= tmp << 16;
|
||||
|
||||
a += 1;
|
||||
b += GET_KEY8 (S, a);
|
||||
|
||||
rc4_swap (S, a, b);
|
||||
|
||||
idx = GET_KEY8 (S, a) + GET_KEY8 (S, b);
|
||||
|
||||
tmp = GET_KEY8 (S, idx);
|
||||
|
||||
xor4 |= tmp << 24;
|
||||
|
||||
out[k] = in[k] ^ xor4;
|
||||
}
|
||||
|
||||
return b;
|
||||
}
|
@ -0,0 +1,18 @@
|
||||
/**
|
||||
* Author......: See docs/credits.txt
|
||||
* License.....: MIT
|
||||
*/
|
||||
|
||||
#ifndef _INC_CIPHER_RC4_H
|
||||
#define _INC_CIPHER_RC4_H
|
||||
|
||||
DECLSPEC u8 GET_KEY8 (LOCAL_AS u32 *S, const u8 k);
|
||||
DECLSPEC void SET_KEY8 (LOCAL_AS u32 *S, const u8 k, const u8 v);
|
||||
DECLSPEC void SET_KEY32 (LOCAL_AS u32 *S, const u8 k, const u32 v);
|
||||
|
||||
DECLSPEC void rc4_init_40 (LOCAL_AS u32 *S, const u32 *key);
|
||||
DECLSPEC void rc4_init_128 (LOCAL_AS u32 *S, const u32 *key);
|
||||
DECLSPEC void rc4_swap (LOCAL_AS u32 *S, const u8 i, const u8 j);
|
||||
DECLSPEC u8 rc4_next_16 (LOCAL_AS u32 *S, const u8 i, const u8 j, const u32 *in, u32 *out);
|
||||
|
||||
#endif // _INC_CIPHER_RC4_H
|
@ -0,0 +1,320 @@
|
||||
/**
|
||||
* Author......: See docs/credits.txt
|
||||
* License.....: MIT
|
||||
*/
|
||||
|
||||
#define NEW_SIMD_CODE
|
||||
|
||||
#ifdef KERNEL_STATIC
|
||||
#include "inc_vendor.h"
|
||||
#include "inc_types.h"
|
||||
#include "inc_platform.cl"
|
||||
#include "inc_common.cl"
|
||||
#include "inc_rp_optimized.h"
|
||||
#include "inc_rp_optimized.cl"
|
||||
#include "inc_simd.cl"
|
||||
#include "inc_hash_md5.cl"
|
||||
#endif
|
||||
|
||||
KERNEL_FQ void m00070_m04 (KERN_ATTR_RULES ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
u32 pw_buf0[4];
|
||||
u32 pw_buf1[4];
|
||||
|
||||
pw_buf0[0] = pws[gid].i[0];
|
||||
pw_buf0[1] = pws[gid].i[1];
|
||||
pw_buf0[2] = pws[gid].i[2];
|
||||
pw_buf0[3] = pws[gid].i[3];
|
||||
pw_buf1[0] = pws[gid].i[4];
|
||||
pw_buf1[1] = pws[gid].i[5];
|
||||
pw_buf1[2] = pws[gid].i[6];
|
||||
pw_buf1[3] = pws[gid].i[7];
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* 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);
|
||||
|
||||
make_utf16le (w1, w2, w3);
|
||||
make_utf16le (w0, w0, w1);
|
||||
|
||||
const u32x out_len2 = out_len * 2;
|
||||
|
||||
append_0x80_4x4_VV (w0, w1, w2, w3, out_len2);
|
||||
|
||||
w3[2] = out_len2 * 8;
|
||||
w3[3] = 0;
|
||||
|
||||
/**
|
||||
* md5
|
||||
*/
|
||||
|
||||
u32x a = MD5M_A;
|
||||
u32x b = MD5M_B;
|
||||
u32x c = MD5M_C;
|
||||
u32x d = MD5M_D;
|
||||
|
||||
MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
|
||||
MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
|
||||
MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
|
||||
MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
|
||||
MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
|
||||
MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
|
||||
MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
|
||||
MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
|
||||
MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
|
||||
MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
|
||||
MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
|
||||
MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
|
||||
MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
|
||||
MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
|
||||
MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
|
||||
MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
|
||||
|
||||
MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
|
||||
MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
|
||||
MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
|
||||
MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
|
||||
MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
|
||||
MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
|
||||
MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
|
||||
MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
|
||||
MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
|
||||
MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
|
||||
MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
|
||||
MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
|
||||
MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
|
||||
MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
|
||||
MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
|
||||
MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
|
||||
|
||||
u32x t;
|
||||
|
||||
MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
|
||||
MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
|
||||
MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
|
||||
MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
|
||||
MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
|
||||
MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
|
||||
MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
|
||||
MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
|
||||
MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
|
||||
MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
|
||||
MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
|
||||
MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
|
||||
MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
|
||||
MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
|
||||
MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
|
||||
MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
|
||||
|
||||
MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
|
||||
MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
|
||||
MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
|
||||
MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
|
||||
MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
|
||||
MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
|
||||
MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
|
||||
MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
|
||||
MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
|
||||
MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
|
||||
MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
|
||||
MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
|
||||
MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
|
||||
MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
|
||||
MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
|
||||
MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
|
||||
|
||||
COMPARE_M_SIMD (a, d, c, b);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00070_m08 (KERN_ATTR_RULES ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00070_m16 (KERN_ATTR_RULES ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00070_s04 (KERN_ATTR_RULES ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
u32 pw_buf0[4];
|
||||
u32 pw_buf1[4];
|
||||
|
||||
pw_buf0[0] = pws[gid].i[0];
|
||||
pw_buf0[1] = pws[gid].i[1];
|
||||
pw_buf0[2] = pws[gid].i[2];
|
||||
pw_buf0[3] = pws[gid].i[3];
|
||||
pw_buf1[0] = pws[gid].i[4];
|
||||
pw_buf1[1] = pws[gid].i[5];
|
||||
pw_buf1[2] = pws[gid].i[6];
|
||||
pw_buf1[3] = pws[gid].i[7];
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* digest
|
||||
*/
|
||||
|
||||
const u32 search[4] =
|
||||
{
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R0],
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R1],
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R2],
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R3]
|
||||
};
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
|
||||
{
|
||||
u32x w0[4] = { 0 };
|
||||
u32x w1[4] = { 0 };
|
||||
u32x w2[4] = { 0 };
|
||||
u32x w3[4] = { 0 };
|
||||
|
||||
const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
|
||||
|
||||
make_utf16le (w1, w2, w3);
|
||||
make_utf16le (w0, w0, w1);
|
||||
|
||||
const u32x out_len2 = out_len * 2;
|
||||
|
||||
append_0x80_4x4_VV (w0, w1, w2, w3, out_len2);
|
||||
|
||||
w3[2] = out_len2 * 8;
|
||||
w3[3] = 0;
|
||||
|
||||
/**
|
||||
* md5
|
||||
*/
|
||||
|
||||
u32x a = MD5M_A;
|
||||
u32x b = MD5M_B;
|
||||
u32x c = MD5M_C;
|
||||
u32x d = MD5M_D;
|
||||
|
||||
MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
|
||||
MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
|
||||
MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
|
||||
MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
|
||||
MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
|
||||
MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
|
||||
MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
|
||||
MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
|
||||
MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
|
||||
MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
|
||||
MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
|
||||
MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
|
||||
MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
|
||||
MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
|
||||
MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
|
||||
MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
|
||||
|
||||
MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
|
||||
MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
|
||||
MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
|
||||
MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
|
||||
MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
|
||||
MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
|
||||
MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
|
||||
MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
|
||||
MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
|
||||
MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
|
||||
MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
|
||||
MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
|
||||
MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
|
||||
MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
|
||||
MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
|
||||
MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
|
||||
|
||||
u32x t;
|
||||
|
||||
MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
|
||||
MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
|
||||
MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
|
||||
MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
|
||||
MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
|
||||
MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
|
||||
MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
|
||||
MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
|
||||
MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
|
||||
MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
|
||||
MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
|
||||
MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
|
||||
MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
|
||||
MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
|
||||
MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
|
||||
MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
|
||||
|
||||
MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
|
||||
MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
|
||||
MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
|
||||
MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
|
||||
MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
|
||||
MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
|
||||
MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
|
||||
MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
|
||||
MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
|
||||
MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
|
||||
MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
|
||||
MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
|
||||
MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
|
||||
|
||||
if (MATCHES_NONE_VS (a, search[0])) continue;
|
||||
|
||||
MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
|
||||
MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
|
||||
MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
|
||||
|
||||
COMPARE_S_SIMD (a, d, c, b);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00070_s08 (KERN_ATTR_RULES ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00070_s16 (KERN_ATTR_RULES ())
|
||||
{
|
||||
}
|
@ -0,0 +1,117 @@
|
||||
/**
|
||||
* 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_md5.cl"
|
||||
#endif
|
||||
|
||||
KERNEL_FQ void m00070_mxx (KERN_ATTR_RULES ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
COPY_PW (pws[gid]);
|
||||
|
||||
/**
|
||||
* 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);
|
||||
|
||||
md5_ctx_t ctx;
|
||||
|
||||
md5_init (&ctx);
|
||||
|
||||
md5_update_utf16le (&ctx, tmp.i, tmp.pw_len);
|
||||
|
||||
md5_final (&ctx);
|
||||
|
||||
const u32 r0 = ctx.h[DGST_R0];
|
||||
const u32 r1 = ctx.h[DGST_R1];
|
||||
const u32 r2 = ctx.h[DGST_R2];
|
||||
const u32 r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_M_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00070_sxx (KERN_ATTR_RULES ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
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]);
|
||||
|
||||
/**
|
||||
* 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);
|
||||
|
||||
md5_ctx_t ctx;
|
||||
|
||||
md5_init (&ctx);
|
||||
|
||||
md5_update_utf16le (&ctx, tmp.i, tmp.pw_len);
|
||||
|
||||
md5_final (&ctx);
|
||||
|
||||
const u32 r0 = ctx.h[DGST_R0];
|
||||
const u32 r1 = ctx.h[DGST_R1];
|
||||
const u32 r2 = ctx.h[DGST_R2];
|
||||
const u32 r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_S_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
@ -0,0 +1,438 @@
|
||||
/**
|
||||
* Author......: See docs/credits.txt
|
||||
* License.....: MIT
|
||||
*/
|
||||
|
||||
#define NEW_SIMD_CODE
|
||||
|
||||
#ifdef KERNEL_STATIC
|
||||
#include "inc_vendor.h"
|
||||
#include "inc_types.h"
|
||||
#include "inc_platform.cl"
|
||||
#include "inc_common.cl"
|
||||
#include "inc_simd.cl"
|
||||
#include "inc_hash_md5.cl"
|
||||
#endif
|
||||
|
||||
KERNEL_FQ void m00070_m04 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
u32 pw_buf0[4];
|
||||
u32 pw_buf1[4];
|
||||
|
||||
pw_buf0[0] = pws[gid].i[0];
|
||||
pw_buf0[1] = pws[gid].i[1];
|
||||
pw_buf0[2] = pws[gid].i[2];
|
||||
pw_buf0[3] = pws[gid].i[3];
|
||||
pw_buf1[0] = pws[gid].i[4];
|
||||
pw_buf1[1] = pws[gid].i[5];
|
||||
pw_buf1[2] = pws[gid].i[6];
|
||||
pw_buf1[3] = pws[gid].i[7];
|
||||
|
||||
const u32 pw_l_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
|
||||
{
|
||||
const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
|
||||
|
||||
const u32x pw_len = (pw_l_len + pw_r_len) & 63;
|
||||
|
||||
/**
|
||||
* concat password candidate
|
||||
*/
|
||||
|
||||
u32x wordl0[4] = { 0 };
|
||||
u32x wordl1[4] = { 0 };
|
||||
u32x wordl2[4] = { 0 };
|
||||
u32x wordl3[4] = { 0 };
|
||||
|
||||
wordl0[0] = pw_buf0[0];
|
||||
wordl0[1] = pw_buf0[1];
|
||||
wordl0[2] = pw_buf0[2];
|
||||
wordl0[3] = pw_buf0[3];
|
||||
wordl1[0] = pw_buf1[0];
|
||||
wordl1[1] = pw_buf1[1];
|
||||
wordl1[2] = pw_buf1[2];
|
||||
wordl1[3] = pw_buf1[3];
|
||||
|
||||
u32x wordr0[4] = { 0 };
|
||||
u32x wordr1[4] = { 0 };
|
||||
u32x wordr2[4] = { 0 };
|
||||
u32x wordr3[4] = { 0 };
|
||||
|
||||
wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
|
||||
wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
|
||||
wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
|
||||
wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
|
||||
wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
|
||||
wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
|
||||
wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
|
||||
wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
|
||||
|
||||
if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
|
||||
{
|
||||
switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
|
||||
}
|
||||
else
|
||||
{
|
||||
switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
|
||||
}
|
||||
|
||||
u32x w0[4];
|
||||
u32x w1[4];
|
||||
u32x w2[4];
|
||||
u32x w3[4];
|
||||
|
||||
w0[0] = wordl0[0] | wordr0[0];
|
||||
w0[1] = wordl0[1] | wordr0[1];
|
||||
w0[2] = wordl0[2] | wordr0[2];
|
||||
w0[3] = wordl0[3] | wordr0[3];
|
||||
w1[0] = wordl1[0] | wordr1[0];
|
||||
w1[1] = wordl1[1] | wordr1[1];
|
||||
w1[2] = wordl1[2] | wordr1[2];
|
||||
w1[3] = wordl1[3] | wordr1[3];
|
||||
w2[0] = wordl2[0] | wordr2[0];
|
||||
w2[1] = wordl2[1] | wordr2[1];
|
||||
w2[2] = wordl2[2] | wordr2[2];
|
||||
w2[3] = wordl2[3] | wordr2[3];
|
||||
w3[0] = wordl3[0] | wordr3[0];
|
||||
w3[1] = wordl3[1] | wordr3[1];
|
||||
w3[2] = wordl3[2] | wordr3[2];
|
||||
w3[3] = wordl3[3] | wordr3[3];
|
||||
|
||||
make_utf16le (w1, w2, w3);
|
||||
make_utf16le (w0, w0, w1);
|
||||
|
||||
const u32x pw_len2 = pw_len * 2;
|
||||
|
||||
append_0x80_4x4_VV (w0, w1, w2, w3, pw_len2);
|
||||
|
||||
w3[2] = pw_len2 * 8;
|
||||
w3[3] = 0;
|
||||
|
||||
/**
|
||||
* md5
|
||||
*/
|
||||
|
||||
u32x a = MD5M_A;
|
||||
u32x b = MD5M_B;
|
||||
u32x c = MD5M_C;
|
||||
u32x d = MD5M_D;
|
||||
|
||||
MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
|
||||
MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
|
||||
MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
|
||||
MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
|
||||
MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
|
||||
MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
|
||||
MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
|
||||
MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
|
||||
MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
|
||||
MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
|
||||
MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
|
||||
MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
|
||||
MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
|
||||
MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
|
||||
MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
|
||||
MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
|
||||
|
||||
MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
|
||||
MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
|
||||
MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
|
||||
MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
|
||||
MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
|
||||
MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
|
||||
MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
|
||||
MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
|
||||
MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
|
||||
MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
|
||||
MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
|
||||
MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
|
||||
MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
|
||||
MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
|
||||
MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
|
||||
MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
|
||||
|
||||
u32x t;
|
||||
|
||||
MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
|
||||
MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
|
||||
MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
|
||||
MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
|
||||
MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
|
||||
MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
|
||||
MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
|
||||
MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
|
||||
MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
|
||||
MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
|
||||
MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
|
||||
MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
|
||||
MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
|
||||
MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
|
||||
MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
|
||||
MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
|
||||
|
||||
MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
|
||||
MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
|
||||
MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
|
||||
MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
|
||||
MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
|
||||
MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
|
||||
MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
|
||||
MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
|
||||
MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
|
||||
MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
|
||||
MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
|
||||
MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
|
||||
MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
|
||||
MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
|
||||
MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
|
||||
MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
|
||||
|
||||
COMPARE_M_SIMD (a, d, c, b);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00070_m08 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00070_m16 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00070_s04 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
u32 pw_buf0[4];
|
||||
u32 pw_buf1[4];
|
||||
|
||||
pw_buf0[0] = pws[gid].i[0];
|
||||
pw_buf0[1] = pws[gid].i[1];
|
||||
pw_buf0[2] = pws[gid].i[2];
|
||||
pw_buf0[3] = pws[gid].i[3];
|
||||
pw_buf1[0] = pws[gid].i[4];
|
||||
pw_buf1[1] = pws[gid].i[5];
|
||||
pw_buf1[2] = pws[gid].i[6];
|
||||
pw_buf1[3] = pws[gid].i[7];
|
||||
|
||||
const u32 pw_l_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* digest
|
||||
*/
|
||||
|
||||
const u32 search[4] =
|
||||
{
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R0],
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R1],
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R2],
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R3]
|
||||
};
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
|
||||
{
|
||||
const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
|
||||
|
||||
const u32x pw_len = (pw_l_len + pw_r_len) & 63;
|
||||
|
||||
/**
|
||||
* concat password candidate
|
||||
*/
|
||||
|
||||
u32x wordl0[4] = { 0 };
|
||||
u32x wordl1[4] = { 0 };
|
||||
u32x wordl2[4] = { 0 };
|
||||
u32x wordl3[4] = { 0 };
|
||||
|
||||
wordl0[0] = pw_buf0[0];
|
||||
wordl0[1] = pw_buf0[1];
|
||||
wordl0[2] = pw_buf0[2];
|
||||
wordl0[3] = pw_buf0[3];
|
||||
wordl1[0] = pw_buf1[0];
|
||||
wordl1[1] = pw_buf1[1];
|
||||
wordl1[2] = pw_buf1[2];
|
||||
wordl1[3] = pw_buf1[3];
|
||||
|
||||
u32x wordr0[4] = { 0 };
|
||||
u32x wordr1[4] = { 0 };
|
||||
u32x wordr2[4] = { 0 };
|
||||
u32x wordr3[4] = { 0 };
|
||||
|
||||
wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
|
||||
wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
|
||||
wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
|
||||
wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
|
||||
wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
|
||||
wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
|
||||
wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
|
||||
wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
|
||||
|
||||
if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
|
||||
{
|
||||
switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
|
||||
}
|
||||
else
|
||||
{
|
||||
switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
|
||||
}
|
||||
|
||||
u32x w0[4];
|
||||
u32x w1[4];
|
||||
u32x w2[4];
|
||||
u32x w3[4];
|
||||
|
||||
w0[0] = wordl0[0] | wordr0[0];
|
||||
w0[1] = wordl0[1] | wordr0[1];
|
||||
w0[2] = wordl0[2] | wordr0[2];
|
||||
w0[3] = wordl0[3] | wordr0[3];
|
||||
w1[0] = wordl1[0] | wordr1[0];
|
||||
w1[1] = wordl1[1] | wordr1[1];
|
||||
w1[2] = wordl1[2] | wordr1[2];
|
||||
w1[3] = wordl1[3] | wordr1[3];
|
||||
w2[0] = wordl2[0] | wordr2[0];
|
||||
w2[1] = wordl2[1] | wordr2[1];
|
||||
w2[2] = wordl2[2] | wordr2[2];
|
||||
w2[3] = wordl2[3] | wordr2[3];
|
||||
w3[0] = wordl3[0] | wordr3[0];
|
||||
w3[1] = wordl3[1] | wordr3[1];
|
||||
w3[2] = wordl3[2] | wordr3[2];
|
||||
w3[3] = wordl3[3] | wordr3[3];
|
||||
|
||||
make_utf16le (w1, w2, w3);
|
||||
make_utf16le (w0, w0, w1);
|
||||
|
||||
const u32x pw_len2 = pw_len * 2;
|
||||
|
||||
append_0x80_4x4_VV (w0, w1, w2, w3, pw_len2);
|
||||
|
||||
w3[2] = pw_len2 * 8;
|
||||
w3[3] = 0;
|
||||
|
||||
/**
|
||||
* md5
|
||||
*/
|
||||
|
||||
u32x a = MD5M_A;
|
||||
u32x b = MD5M_B;
|
||||
u32x c = MD5M_C;
|
||||
u32x d = MD5M_D;
|
||||
|
||||
MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
|
||||
MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
|
||||
MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
|
||||
MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
|
||||
MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
|
||||
MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
|
||||
MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
|
||||
MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
|
||||
MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
|
||||
MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
|
||||
MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
|
||||
MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
|
||||
MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
|
||||
MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
|
||||
MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
|
||||
MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
|
||||
|
||||
MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
|
||||
MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
|
||||
MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
|
||||
MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
|
||||
MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
|
||||
MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
|
||||
MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
|
||||
MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
|
||||
MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
|
||||
MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
|
||||
MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
|
||||
MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
|
||||
MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
|
||||
MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
|
||||
MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
|
||||
MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
|
||||
|
||||
u32x t;
|
||||
|
||||
MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
|
||||
MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
|
||||
MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
|
||||
MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
|
||||
MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
|
||||
MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
|
||||
MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
|
||||
MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
|
||||
MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
|
||||
MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
|
||||
MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
|
||||
MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
|
||||
MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
|
||||
MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
|
||||
MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
|
||||
MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
|
||||
|
||||
MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
|
||||
MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
|
||||
MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
|
||||
MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
|
||||
MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
|
||||
MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
|
||||
MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
|
||||
MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
|
||||
MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
|
||||
MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
|
||||
MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
|
||||
MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
|
||||
MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
|
||||
|
||||
if (MATCHES_NONE_VS (a, search[0])) continue;
|
||||
|
||||
MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
|
||||
MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
|
||||
MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
|
||||
|
||||
COMPARE_S_SIMD (a, d, c, b);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00070_s08 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00070_s16 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
}
|
@ -0,0 +1,111 @@
|
||||
/**
|
||||
* 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_md5.cl"
|
||||
#endif
|
||||
|
||||
KERNEL_FQ void m00070_mxx (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
md5_ctx_t ctx0;
|
||||
|
||||
md5_init (&ctx0);
|
||||
|
||||
md5_update_global_utf16le (&ctx0, pws[gid].i, pws[gid].pw_len);
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
|
||||
{
|
||||
md5_ctx_t ctx = ctx0;
|
||||
|
||||
md5_update_global_utf16le (&ctx, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
|
||||
|
||||
md5_final (&ctx);
|
||||
|
||||
const u32 r0 = ctx.h[DGST_R0];
|
||||
const u32 r1 = ctx.h[DGST_R1];
|
||||
const u32 r2 = ctx.h[DGST_R2];
|
||||
const u32 r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_M_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00070_sxx (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
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
|
||||
*/
|
||||
|
||||
md5_ctx_t ctx0;
|
||||
|
||||
md5_init (&ctx0);
|
||||
|
||||
md5_update_global_utf16le (&ctx0, pws[gid].i, pws[gid].pw_len);
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
|
||||
{
|
||||
md5_ctx_t ctx = ctx0;
|
||||
|
||||
md5_update_global_utf16le (&ctx, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
|
||||
|
||||
md5_final (&ctx);
|
||||
|
||||
const u32 r0 = ctx.h[DGST_R0];
|
||||
const u32 r1 = ctx.h[DGST_R1];
|
||||
const u32 r2 = ctx.h[DGST_R2];
|
||||
const u32 r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_S_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
@ -0,0 +1,661 @@
|
||||
/**
|
||||
* Author......: See docs/credits.txt
|
||||
* License.....: MIT
|
||||
*/
|
||||
|
||||
#define NEW_SIMD_CODE
|
||||
|
||||
#ifdef KERNEL_STATIC
|
||||
#include "inc_vendor.h"
|
||||
#include "inc_types.h"
|
||||
#include "inc_platform.cl"
|
||||
#include "inc_common.cl"
|
||||
#include "inc_simd.cl"
|
||||
#include "inc_hash_md5.cl"
|
||||
#endif
|
||||
|
||||
#define MD5_STEP_REV(f,a,b,c,d,x,t,s) \
|
||||
{ \
|
||||
a -= b; \
|
||||
a = hc_rotr32_S (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 = hc_rotr32_S (a, s); \
|
||||
a -= x; \
|
||||
a -= t; \
|
||||
}
|
||||
|
||||
DECLSPEC void m00070m (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
w[14] = pw_len * 8;
|
||||
w[15] = 0;
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u32 F_w0c00 = 0u + 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 = 0u + 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 = 0u + 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 = 0u + 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 < il_cnt; il_pos += VECT_SIZE)
|
||||
{
|
||||
const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
|
||||
|
||||
const u32x w0 = w0l | w0r;
|
||||
|
||||
u32x a = MD5M_A;
|
||||
u32x b = MD5M_B;
|
||||
u32x c = MD5M_C;
|
||||
u32x d = MD5M_D;
|
||||
|
||||
MD5_STEP (MD5_Fo, a, b, c, d, w0, 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);
|
||||
|
||||
u32x t;
|
||||
|
||||
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);
|
||||
|
||||
COMPARE_M_SIMD (a, d, c, b);
|
||||
}
|
||||
}
|
||||
|
||||
DECLSPEC void m00070s (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u32 F_w0c00 = 0u + 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 = 0u + 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 = 0u + 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 = 0u + 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_S, b_rev, c_rev, d_rev, a_rev, w[ 9], MD5C3f, MD5S33);
|
||||
MD5_STEP_REV (MD5_I_S, c_rev, d_rev, a_rev, b_rev, w[ 2], MD5C3e, MD5S32);
|
||||
MD5_STEP_REV (MD5_I_S, d_rev, a_rev, b_rev, c_rev, w[11], MD5C3d, MD5S31);
|
||||
MD5_STEP_REV (MD5_I_S, a_rev, b_rev, c_rev, d_rev, w[ 4], MD5C3c, MD5S30);
|
||||
MD5_STEP_REV (MD5_I_S, b_rev, c_rev, d_rev, a_rev, w[13], MD5C3b, MD5S33);
|
||||
MD5_STEP_REV (MD5_I_S, c_rev, d_rev, a_rev, b_rev, w[ 6], MD5C3a, MD5S32);
|
||||
MD5_STEP_REV (MD5_I_S, d_rev, a_rev, b_rev, c_rev, w[15], MD5C39, MD5S31);
|
||||
MD5_STEP_REV (MD5_I_S, a_rev, b_rev, c_rev, d_rev, w[ 8], MD5C38, MD5S30);
|
||||
MD5_STEP_REV (MD5_I_S, b_rev, c_rev, d_rev, a_rev, w[ 1], MD5C37, MD5S33);
|
||||
MD5_STEP_REV (MD5_I_S, c_rev, d_rev, a_rev, b_rev, w[10], MD5C36, MD5S32);
|
||||
MD5_STEP_REV (MD5_I_S, d_rev, a_rev, b_rev, c_rev, w[ 3], MD5C35, MD5S31);
|
||||
MD5_STEP_REV (MD5_I_S, a_rev, b_rev, c_rev, d_rev, w[12], MD5C34, MD5S30);
|
||||
MD5_STEP_REV (MD5_I_S, b_rev, c_rev, d_rev, a_rev, w[ 5], MD5C33, MD5S33);
|
||||
MD5_STEP_REV (MD5_I_S, c_rev, d_rev, a_rev, b_rev, w[14], MD5C32, MD5S32);
|
||||
MD5_STEP_REV (MD5_I_S, d_rev, a_rev, b_rev, c_rev, w[ 7], MD5C31, MD5S31);
|
||||
MD5_STEP_REV (MD5_I_S, a_rev, b_rev, c_rev, d_rev, 0, MD5C30, MD5S30);
|
||||
|
||||
const u32 pre_cd = c_rev ^ d_rev;
|
||||
|
||||
MD5_STEP_REV1(MD5_H_S, b_rev, c_rev, d_rev, a_rev, w[ 2], MD5C2f, MD5S23);
|
||||
MD5_STEP_REV1(MD5_H_S, c_rev, d_rev, a_rev, b_rev, w[15], MD5C2e, MD5S22);
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
u32 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;
|
||||
|
||||
const u32x pre_d = d_rev;
|
||||
const u32x pre_a = a_rev - w0;
|
||||
const u32x pre_b = b_rev - (pre_a ^ pre_cd);
|
||||
const u32x pre_c = c_rev - (pre_a ^ pre_b ^ pre_d);
|
||||
|
||||
u32x a = MD5M_A;
|
||||
u32x b = MD5M_B;
|
||||
u32x c = MD5M_C;
|
||||
u32x d = MD5M_D;
|
||||
|
||||
MD5_STEP (MD5_Fo, a, b, c, d, w0, 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);
|
||||
|
||||
u32x t;
|
||||
|
||||
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);
|
||||
|
||||
if (MATCHES_NONE_VV (pre_c, c)) 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);
|
||||
|
||||
if (MATCHES_NONE_VV (pre_d, d)) 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);
|
||||
|
||||
COMPARE_S_SIMD (a, d, c, b);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00070_m04 (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 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 & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m00070m (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00070_m08 (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 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 & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m00070m (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00070_m16 (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 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 & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m00070m (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00070_s04 (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 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 & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m00070s (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00070_s08 (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 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 & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m00070s (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00070_s16 (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 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 & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m00070s (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
@ -0,0 +1,137 @@
|
||||
/**
|
||||
* Author......: See docs/credits.txt
|
||||
* License.....: MIT
|
||||
*/
|
||||
|
||||
#define NEW_SIMD_CODE
|
||||
|
||||
#ifdef KERNEL_STATIC
|
||||
#include "inc_vendor.h"
|
||||
#include "inc_types.h"
|
||||
#include "inc_platform.cl"
|
||||
#include "inc_common.cl"
|
||||
#include "inc_simd.cl"
|
||||
#include "inc_hash_md5.cl"
|
||||
#endif
|
||||
|
||||
KERNEL_FQ void m00070_mxx (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
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];
|
||||
}
|
||||
|
||||
/**
|
||||
* 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;
|
||||
|
||||
md5_ctx_vector_t ctx;
|
||||
|
||||
md5_init_vector (&ctx);
|
||||
|
||||
md5_update_vector_utf16le (&ctx, w, pw_len);
|
||||
|
||||
md5_final_vector (&ctx);
|
||||
|
||||
const u32x r0 = ctx.h[DGST_R0];
|
||||
const u32x r1 = ctx.h[DGST_R1];
|
||||
const u32x r2 = ctx.h[DGST_R2];
|
||||
const u32x r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_M_SIMD (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00070_sxx (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
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];
|
||||
}
|
||||
|
||||
/**
|
||||
* 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;
|
||||
|
||||
md5_ctx_vector_t ctx;
|
||||
|
||||
md5_init_vector (&ctx);
|
||||
|
||||
md5_update_vector_utf16le (&ctx, w, pw_len);
|
||||
|
||||
md5_final_vector (&ctx);
|
||||
|
||||
const u32x r0 = ctx.h[DGST_R0];
|
||||
const u32x r1 = ctx.h[DGST_R1];
|
||||
const u32x r2 = ctx.h[DGST_R2];
|
||||
const u32x r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_S_SIMD (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
@ -0,0 +1,408 @@
|
||||
/**
|
||||
* 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
|
||||
|
||||
KERNEL_FQ void m00170_m04 (KERN_ATTR_RULES ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
u32 pw_buf0[4];
|
||||
u32 pw_buf1[4];
|
||||
|
||||
pw_buf0[0] = pws[gid].i[0];
|
||||
pw_buf0[1] = pws[gid].i[1];
|
||||
pw_buf0[2] = pws[gid].i[2];
|
||||
pw_buf0[3] = pws[gid].i[3];
|
||||
pw_buf1[0] = pws[gid].i[4];
|
||||
pw_buf1[1] = pws[gid].i[5];
|
||||
pw_buf1[2] = pws[gid].i[6];
|
||||
pw_buf1[3] = pws[gid].i[7];
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* 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);
|
||||
|
||||
make_utf16le (w1, w2, w3);
|
||||
make_utf16le (w0, w0, w1);
|
||||
|
||||
const u32x out_len2 = out_len * 2;
|
||||
|
||||
append_0x80_4x4_VV (w0, w1, w2, w3, out_len2);
|
||||
|
||||
/**
|
||||
* 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 = out_len2 * 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);
|
||||
|
||||
COMPARE_M_SIMD (d, e, c, b);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00170_m08 (KERN_ATTR_RULES ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00170_m16 (KERN_ATTR_RULES ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00170_s04 (KERN_ATTR_RULES ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
u32 pw_buf0[4];
|
||||
u32 pw_buf1[4];
|
||||
|
||||
pw_buf0[0] = pws[gid].i[0];
|
||||
pw_buf0[1] = pws[gid].i[1];
|
||||
pw_buf0[2] = pws[gid].i[2];
|
||||
pw_buf0[3] = pws[gid].i[3];
|
||||
pw_buf1[0] = pws[gid].i[4];
|
||||
pw_buf1[1] = pws[gid].i[5];
|
||||
pw_buf1[2] = pws[gid].i[6];
|
||||
pw_buf1[3] = pws[gid].i[7];
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* digest
|
||||
*/
|
||||
|
||||
const u32 search[4] =
|
||||
{
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R0],
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R1],
|
||||
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);
|
||||
|
||||
make_utf16le (w1, w2, w3);
|
||||
make_utf16le (w0, w0, w1);
|
||||
|
||||
const u32x out_len2 = out_len * 2;
|
||||
|
||||
append_0x80_4x4_VV (w0, w1, w2, w3, out_len2);
|
||||
|
||||
/**
|
||||
* 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 = out_len2 * 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);
|
||||
|
||||
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 m00170_s08 (KERN_ATTR_RULES ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00170_s16 (KERN_ATTR_RULES ())
|
||||
{
|
||||
}
|
@ -0,0 +1,117 @@
|
||||
/**
|
||||
* 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
|
||||
|
||||
KERNEL_FQ void m00170_mxx (KERN_ATTR_RULES ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
COPY_PW (pws[gid]);
|
||||
|
||||
/**
|
||||
* 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;
|
||||
|
||||
sha1_init (&ctx);
|
||||
|
||||
sha1_update_utf16le_swap (&ctx, tmp.i, tmp.pw_len);
|
||||
|
||||
sha1_final (&ctx);
|
||||
|
||||
const u32 r0 = ctx.h[DGST_R0];
|
||||
const u32 r1 = ctx.h[DGST_R1];
|
||||
const u32 r2 = ctx.h[DGST_R2];
|
||||
const u32 r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_M_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00170_sxx (KERN_ATTR_RULES ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
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]);
|
||||
|
||||
/**
|
||||
* 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;
|
||||
|
||||
sha1_init (&ctx);
|
||||
|
||||
sha1_update_utf16le_swap (&ctx, tmp.i, tmp.pw_len);
|
||||
|
||||
sha1_final (&ctx);
|
||||
|
||||
const u32 r0 = ctx.h[DGST_R0];
|
||||
const u32 r1 = ctx.h[DGST_R1];
|
||||
const u32 r2 = ctx.h[DGST_R2];
|
||||
const u32 r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_S_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
@ -0,0 +1,522 @@
|
||||
/**
|
||||
* 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
|
||||
|
||||
KERNEL_FQ void m00170_m04 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
u32 pw_buf0[4];
|
||||
u32 pw_buf1[4];
|
||||
|
||||
pw_buf0[0] = pws[gid].i[0];
|
||||
pw_buf0[1] = pws[gid].i[1];
|
||||
pw_buf0[2] = pws[gid].i[2];
|
||||
pw_buf0[3] = pws[gid].i[3];
|
||||
pw_buf1[0] = pws[gid].i[4];
|
||||
pw_buf1[1] = pws[gid].i[5];
|
||||
pw_buf1[2] = pws[gid].i[6];
|
||||
pw_buf1[3] = pws[gid].i[7];
|
||||
|
||||
const u32 pw_l_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
|
||||
{
|
||||
const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
|
||||
|
||||
const u32x pw_len = (pw_l_len + pw_r_len) & 63;
|
||||
|
||||
/**
|
||||
* concat password candidate
|
||||
*/
|
||||
|
||||
u32x wordl0[4] = { 0 };
|
||||
u32x wordl1[4] = { 0 };
|
||||
u32x wordl2[4] = { 0 };
|
||||
u32x wordl3[4] = { 0 };
|
||||
|
||||
wordl0[0] = pw_buf0[0];
|
||||
wordl0[1] = pw_buf0[1];
|
||||
wordl0[2] = pw_buf0[2];
|
||||
wordl0[3] = pw_buf0[3];
|
||||
wordl1[0] = pw_buf1[0];
|
||||
wordl1[1] = pw_buf1[1];
|
||||
wordl1[2] = pw_buf1[2];
|
||||
wordl1[3] = pw_buf1[3];
|
||||
|
||||
u32x wordr0[4] = { 0 };
|
||||
u32x wordr1[4] = { 0 };
|
||||
u32x wordr2[4] = { 0 };
|
||||
u32x wordr3[4] = { 0 };
|
||||
|
||||
wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
|
||||
wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
|
||||
wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
|
||||
wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
|
||||
wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
|
||||
wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
|
||||
wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
|
||||
wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
|
||||
|
||||
if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
|
||||
{
|
||||
switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
|
||||
}
|
||||
else
|
||||
{
|
||||
switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
|
||||
}
|
||||
|
||||
u32x w0[4];
|
||||
u32x w1[4];
|
||||
u32x w2[4];
|
||||
u32x w3[4];
|
||||
|
||||
w0[0] = wordl0[0] | wordr0[0];
|
||||
w0[1] = wordl0[1] | wordr0[1];
|
||||
w0[2] = wordl0[2] | wordr0[2];
|
||||
w0[3] = wordl0[3] | wordr0[3];
|
||||
w1[0] = wordl1[0] | wordr1[0];
|
||||
w1[1] = wordl1[1] | wordr1[1];
|
||||
w1[2] = wordl1[2] | wordr1[2];
|
||||
w1[3] = wordl1[3] | wordr1[3];
|
||||
w2[0] = wordl2[0] | wordr2[0];
|
||||
w2[1] = wordl2[1] | wordr2[1];
|
||||
w2[2] = wordl2[2] | wordr2[2];
|
||||
w2[3] = wordl2[3] | wordr2[3];
|
||||
w3[0] = wordl3[0] | wordr3[0];
|
||||
w3[1] = wordl3[1] | wordr3[1];
|
||||
w3[2] = wordl3[2] | wordr3[2];
|
||||
w3[3] = wordl3[3] | wordr3[3];
|
||||
|
||||
make_utf16le (w1, w2, w3);
|
||||
make_utf16le (w0, w0, w1);
|
||||
|
||||
const u32x pw_len2 = pw_len * 2;
|
||||
|
||||
/**
|
||||
* 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 = pw_len2 * 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);
|
||||
|
||||
COMPARE_M_SIMD (d, e, c, b);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00170_m08 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00170_m16 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00170_s04 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
u32 pw_buf0[4];
|
||||
u32 pw_buf1[4];
|
||||
|
||||
pw_buf0[0] = pws[gid].i[0];
|
||||
pw_buf0[1] = pws[gid].i[1];
|
||||
pw_buf0[2] = pws[gid].i[2];
|
||||
pw_buf0[3] = pws[gid].i[3];
|
||||
pw_buf1[0] = pws[gid].i[4];
|
||||
pw_buf1[1] = pws[gid].i[5];
|
||||
pw_buf1[2] = pws[gid].i[6];
|
||||
pw_buf1[3] = pws[gid].i[7];
|
||||
|
||||
const u32 pw_l_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* 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)
|
||||
{
|
||||
const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
|
||||
|
||||
const u32x pw_len = (pw_l_len + pw_r_len) & 63;
|
||||
|
||||
/**
|
||||
* concat password candidate
|
||||
*/
|
||||
|
||||
u32x wordl0[4] = { 0 };
|
||||
u32x wordl1[4] = { 0 };
|
||||
u32x wordl2[4] = { 0 };
|
||||
u32x wordl3[4] = { 0 };
|
||||
|
||||
wordl0[0] = pw_buf0[0];
|
||||
wordl0[1] = pw_buf0[1];
|
||||
wordl0[2] = pw_buf0[2];
|
||||
wordl0[3] = pw_buf0[3];
|
||||
wordl1[0] = pw_buf1[0];
|
||||
wordl1[1] = pw_buf1[1];
|
||||
wordl1[2] = pw_buf1[2];
|
||||
wordl1[3] = pw_buf1[3];
|
||||
|
||||
u32x wordr0[4] = { 0 };
|
||||
u32x wordr1[4] = { 0 };
|
||||
u32x wordr2[4] = { 0 };
|
||||
u32x wordr3[4] = { 0 };
|
||||
|
||||
wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
|
||||
wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
|
||||
wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
|
||||
wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
|
||||
wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
|
||||
wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
|
||||
wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
|
||||
wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
|
||||
|
||||
if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
|
||||
{
|
||||
switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
|
||||
}
|
||||
else
|
||||
{
|
||||
switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
|
||||
}
|
||||
|
||||
u32x w0[4];
|
||||
u32x w1[4];
|
||||
u32x w2[4];
|
||||
u32x w3[4];
|
||||
|
||||
w0[0] = wordl0[0] | wordr0[0];
|
||||
w0[1] = wordl0[1] | wordr0[1];
|
||||
w0[2] = wordl0[2] | wordr0[2];
|
||||
w0[3] = wordl0[3] | wordr0[3];
|
||||
w1[0] = wordl1[0] | wordr1[0];
|
||||
w1[1] = wordl1[1] | wordr1[1];
|
||||
w1[2] = wordl1[2] | wordr1[2];
|
||||
w1[3] = wordl1[3] | wordr1[3];
|
||||
w2[0] = wordl2[0] | wordr2[0];
|
||||
w2[1] = wordl2[1] | wordr2[1];
|
||||
w2[2] = wordl2[2] | wordr2[2];
|
||||
w2[3] = wordl2[3] | wordr2[3];
|
||||
w3[0] = wordl3[0] | wordr3[0];
|
||||
w3[1] = wordl3[1] | wordr3[1];
|
||||
w3[2] = wordl3[2] | wordr3[2];
|
||||
w3[3] = wordl3[3] | wordr3[3];
|
||||
|
||||
make_utf16le (w1, w2, w3);
|
||||
make_utf16le (w0, w0, w1);
|
||||
|
||||
const u32x pw_len2 = pw_len * 2;
|
||||
|
||||
/**
|
||||
* 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 = pw_len2 * 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);
|
||||
|
||||
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 m00170_s08 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00170_s16 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
}
|
@ -0,0 +1,111 @@
|
||||
/**
|
||||
* 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
|
||||
|
||||
KERNEL_FQ void m00170_mxx (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
sha1_ctx_t ctx0;
|
||||
|
||||
sha1_init (&ctx0);
|
||||
|
||||
sha1_update_global_utf16le_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_utf16le_swap (&ctx, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
|
||||
|
||||
sha1_final (&ctx);
|
||||
|
||||
const u32 r0 = ctx.h[DGST_R0];
|
||||
const u32 r1 = ctx.h[DGST_R1];
|
||||
const u32 r2 = ctx.h[DGST_R2];
|
||||
const u32 r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_M_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00170_sxx (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
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
|
||||
*/
|
||||
|
||||
sha1_ctx_t ctx0;
|
||||
|
||||
sha1_init (&ctx0);
|
||||
|
||||
sha1_update_global_utf16le_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_utf16le_swap (&ctx, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
|
||||
|
||||
sha1_final (&ctx);
|
||||
|
||||
const u32 r0 = ctx.h[DGST_R0];
|
||||
const u32 r1 = ctx.h[DGST_R1];
|
||||
const u32 r2 = ctx.h[DGST_R2];
|
||||
const u32 r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_S_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
@ -0,0 +1,748 @@
|
||||
/**
|
||||
* 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
|
||||
|
||||
DECLSPEC void m00170m (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u32 c_16s = hc_rotl32_S ((w[13] ^ w[ 8] ^ w[ 2] ), 1u);
|
||||
const u32 c_17s = hc_rotl32_S ((w[14] ^ w[ 9] ^ w[ 3] ^ w[ 1]), 1u);
|
||||
const u32 c_18s = hc_rotl32_S ((w[15] ^ w[10] ^ w[ 4] ^ w[ 2]), 1u);
|
||||
const u32 c_19s = hc_rotl32_S ((c_16s ^ w[11] ^ w[ 5] ^ w[ 3]), 1u);
|
||||
const u32 c_20s = hc_rotl32_S ((c_17s ^ w[12] ^ w[ 6] ^ w[ 4]), 1u);
|
||||
const u32 c_21s = hc_rotl32_S ((c_18s ^ w[13] ^ w[ 7] ^ w[ 5]), 1u);
|
||||
const u32 c_22s = hc_rotl32_S ((c_19s ^ w[14] ^ w[ 8] ^ w[ 6]), 1u);
|
||||
const u32 c_23s = hc_rotl32_S ((c_20s ^ w[15] ^ w[ 9] ^ w[ 7]), 1u);
|
||||
const u32 c_24s = hc_rotl32_S ((c_21s ^ c_16s ^ w[10] ^ w[ 8]), 1u);
|
||||
const u32 c_25s = hc_rotl32_S ((c_22s ^ c_17s ^ w[11] ^ w[ 9]), 1u);
|
||||
const u32 c_26s = hc_rotl32_S ((c_23s ^ c_18s ^ w[12] ^ w[10]), 1u);
|
||||
const u32 c_27s = hc_rotl32_S ((c_24s ^ c_19s ^ w[13] ^ w[11]), 1u);
|
||||
const u32 c_28s = hc_rotl32_S ((c_25s ^ c_20s ^ w[14] ^ w[12]), 1u);
|
||||
const u32 c_29s = hc_rotl32_S ((c_26s ^ c_21s ^ w[15] ^ w[13]), 1u);
|
||||
const u32 c_30s = hc_rotl32_S ((c_27s ^ c_22s ^ c_16s ^ w[14]), 1u);
|
||||
const u32 c_31s = hc_rotl32_S ((c_28s ^ c_23s ^ c_17s ^ w[15]), 1u);
|
||||
const u32 c_32s = hc_rotl32_S ((c_29s ^ c_24s ^ c_18s ^ c_16s), 1u);
|
||||
const u32 c_33s = hc_rotl32_S ((c_30s ^ c_25s ^ c_19s ^ c_17s), 1u);
|
||||
const u32 c_34s = hc_rotl32_S ((c_31s ^ c_26s ^ c_20s ^ c_18s), 1u);
|
||||
const u32 c_35s = hc_rotl32_S ((c_32s ^ c_27s ^ c_21s ^ c_19s), 1u);
|
||||
const u32 c_36s = hc_rotl32_S ((c_33s ^ c_28s ^ c_22s ^ c_20s), 1u);
|
||||
const u32 c_37s = hc_rotl32_S ((c_34s ^ c_29s ^ c_23s ^ c_21s), 1u);
|
||||
const u32 c_38s = hc_rotl32_S ((c_35s ^ c_30s ^ c_24s ^ c_22s), 1u);
|
||||
const u32 c_39s = hc_rotl32_S ((c_36s ^ c_31s ^ c_25s ^ c_23s), 1u);
|
||||
const u32 c_40s = hc_rotl32_S ((c_37s ^ c_32s ^ c_26s ^ c_24s), 1u);
|
||||
const u32 c_41s = hc_rotl32_S ((c_38s ^ c_33s ^ c_27s ^ c_25s), 1u);
|
||||
const u32 c_42s = hc_rotl32_S ((c_39s ^ c_34s ^ c_28s ^ c_26s), 1u);
|
||||
const u32 c_43s = hc_rotl32_S ((c_40s ^ c_35s ^ c_29s ^ c_27s), 1u);
|
||||
const u32 c_44s = hc_rotl32_S ((c_41s ^ c_36s ^ c_30s ^ c_28s), 1u);
|
||||
const u32 c_45s = hc_rotl32_S ((c_42s ^ c_37s ^ c_31s ^ c_29s), 1u);
|
||||
const u32 c_46s = hc_rotl32_S ((c_43s ^ c_38s ^ c_32s ^ c_30s), 1u);
|
||||
const u32 c_47s = hc_rotl32_S ((c_44s ^ c_39s ^ c_33s ^ c_31s), 1u);
|
||||
const u32 c_48s = hc_rotl32_S ((c_45s ^ c_40s ^ c_34s ^ c_32s), 1u);
|
||||
const u32 c_49s = hc_rotl32_S ((c_46s ^ c_41s ^ c_35s ^ c_33s), 1u);
|
||||
const u32 c_50s = hc_rotl32_S ((c_47s ^ c_42s ^ c_36s ^ c_34s), 1u);
|
||||
const u32 c_51s = hc_rotl32_S ((c_48s ^ c_43s ^ c_37s ^ c_35s), 1u);
|
||||
const u32 c_52s = hc_rotl32_S ((c_49s ^ c_44s ^ c_38s ^ c_36s), 1u);
|
||||
const u32 c_53s = hc_rotl32_S ((c_50s ^ c_45s ^ c_39s ^ c_37s), 1u);
|
||||
const u32 c_54s = hc_rotl32_S ((c_51s ^ c_46s ^ c_40s ^ c_38s), 1u);
|
||||
const u32 c_55s = hc_rotl32_S ((c_52s ^ c_47s ^ c_41s ^ c_39s), 1u);
|
||||
const u32 c_56s = hc_rotl32_S ((c_53s ^ c_48s ^ c_42s ^ c_40s), 1u);
|
||||
const u32 c_57s = hc_rotl32_S ((c_54s ^ c_49s ^ c_43s ^ c_41s), 1u);
|
||||
const u32 c_58s = hc_rotl32_S ((c_55s ^ c_50s ^ c_44s ^ c_42s), 1u);
|
||||
const u32 c_59s = hc_rotl32_S ((c_56s ^ c_51s ^ c_45s ^ c_43s), 1u);
|
||||
const u32 c_60s = hc_rotl32_S ((c_57s ^ c_52s ^ c_46s ^ c_44s), 1u);
|
||||
const u32 c_61s = hc_rotl32_S ((c_58s ^ c_53s ^ c_47s ^ c_45s), 1u);
|
||||
const u32 c_62s = hc_rotl32_S ((c_59s ^ c_54s ^ c_48s ^ c_46s), 1u);
|
||||
const u32 c_63s = hc_rotl32_S ((c_60s ^ c_55s ^ c_49s ^ c_47s), 1u);
|
||||
const u32 c_64s = hc_rotl32_S ((c_61s ^ c_56s ^ c_50s ^ c_48s), 1u);
|
||||
const u32 c_65s = hc_rotl32_S ((c_62s ^ c_57s ^ c_51s ^ c_49s), 1u);
|
||||
const u32 c_66s = hc_rotl32_S ((c_63s ^ c_58s ^ c_52s ^ c_50s), 1u);
|
||||
const u32 c_67s = hc_rotl32_S ((c_64s ^ c_59s ^ c_53s ^ c_51s), 1u);
|
||||
const u32 c_68s = hc_rotl32_S ((c_65s ^ c_60s ^ c_54s ^ c_52s), 1u);
|
||||
const u32 c_69s = hc_rotl32_S ((c_66s ^ c_61s ^ c_55s ^ c_53s), 1u);
|
||||
const u32 c_70s = hc_rotl32_S ((c_67s ^ c_62s ^ c_56s ^ c_54s), 1u);
|
||||
const u32 c_71s = hc_rotl32_S ((c_68s ^ c_63s ^ c_57s ^ c_55s), 1u);
|
||||
const u32 c_72s = hc_rotl32_S ((c_69s ^ c_64s ^ c_58s ^ c_56s), 1u);
|
||||
const u32 c_73s = hc_rotl32_S ((c_70s ^ c_65s ^ c_59s ^ c_57s), 1u);
|
||||
const u32 c_74s = hc_rotl32_S ((c_71s ^ c_66s ^ c_60s ^ c_58s), 1u);
|
||||
const u32 c_75s = hc_rotl32_S ((c_72s ^ c_67s ^ c_61s ^ c_59s), 1u);
|
||||
const u32 c_76s = hc_rotl32_S ((c_73s ^ c_68s ^ c_62s ^ c_60s), 1u);
|
||||
const u32 c_77s = hc_rotl32_S ((c_74s ^ c_69s ^ c_63s ^ c_61s), 1u);
|
||||
const u32 c_78s = hc_rotl32_S ((c_75s ^ c_70s ^ c_64s ^ c_62s), 1u);
|
||||
const u32 c_79s = hc_rotl32_S ((c_76s ^ c_71s ^ c_65s ^ c_63s), 1u);
|
||||
|
||||
const u32 c_17sK = c_17s + SHA1C00;
|
||||
const u32 c_18sK = c_18s + SHA1C00;
|
||||
const u32 c_20sK = c_20s + SHA1C01;
|
||||
const u32 c_21sK = c_21s + SHA1C01;
|
||||
const u32 c_23sK = c_23s + SHA1C01;
|
||||
const u32 c_26sK = c_26s + SHA1C01;
|
||||
const u32 c_27sK = c_27s + SHA1C01;
|
||||
const u32 c_29sK = c_29s + SHA1C01;
|
||||
const u32 c_33sK = c_33s + SHA1C01;
|
||||
const u32 c_39sK = c_39s + SHA1C01;
|
||||
const u32 c_41sK = c_41s + SHA1C02;
|
||||
const u32 c_45sK = c_45s + SHA1C02;
|
||||
const u32 c_53sK = c_53s + SHA1C02;
|
||||
const u32 c_65sK = c_65s + SHA1C03;
|
||||
const u32 c_69sK = c_69s + SHA1C03;
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
u32 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;
|
||||
|
||||
const u32x w0s01 = hc_rotl32 (w0, 1u);
|
||||
const u32x w0s02 = hc_rotl32 (w0, 2u);
|
||||
const u32x w0s03 = hc_rotl32 (w0, 3u);
|
||||
const u32x w0s04 = hc_rotl32 (w0, 4u);
|
||||
const u32x w0s05 = hc_rotl32 (w0, 5u);
|
||||
const u32x w0s06 = hc_rotl32 (w0, 6u);
|
||||
const u32x w0s07 = hc_rotl32 (w0, 7u);
|
||||
const u32x w0s08 = hc_rotl32 (w0, 8u);
|
||||
const u32x w0s09 = hc_rotl32 (w0, 9u);
|
||||
const u32x w0s10 = hc_rotl32 (w0, 10u);
|
||||
const u32x w0s11 = hc_rotl32 (w0, 11u);
|
||||
const u32x w0s12 = hc_rotl32 (w0, 12u);
|
||||
const u32x w0s13 = hc_rotl32 (w0, 13u);
|
||||
const u32x w0s14 = hc_rotl32 (w0, 14u);
|
||||
const u32x w0s15 = hc_rotl32 (w0, 15u);
|
||||
const u32x w0s16 = hc_rotl32 (w0, 16u);
|
||||
const u32x w0s17 = hc_rotl32 (w0, 17u);
|
||||
const u32x w0s18 = hc_rotl32 (w0, 18u);
|
||||
const u32x w0s19 = hc_rotl32 (w0, 19u);
|
||||
const u32x w0s20 = hc_rotl32 (w0, 20u);
|
||||
const u32x w0s21 = hc_rotl32 (w0, 21u);
|
||||
const u32x w0s22 = hc_rotl32 (w0, 22U);
|
||||
|
||||
const u32x w0s04___w0s06 = w0s04 ^ w0s06;
|
||||
const u32x w0s04___w0s08 = w0s04 ^ w0s08;
|
||||
const u32x w0s08___w0s12 = w0s08 ^ w0s12;
|
||||
const u32x w0s04___w0s06___w0s07 = w0s04___w0s06 ^ w0s07;
|
||||
|
||||
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);
|
||||
SHA1_STEP (SHA1_F0o, e, a, b, c, d, w[ 1]);
|
||||
SHA1_STEP (SHA1_F0o, d, e, a, b, c, w[ 2]);
|
||||
SHA1_STEP (SHA1_F0o, c, d, e, a, b, w[ 3]);
|
||||
SHA1_STEP (SHA1_F0o, b, c, d, e, a, w[ 4]);
|
||||
SHA1_STEP (SHA1_F0o, a, b, c, d, e, w[ 5]);
|
||||
SHA1_STEP (SHA1_F0o, e, a, b, c, d, w[ 6]);
|
||||
SHA1_STEP (SHA1_F0o, d, e, a, b, c, w[ 7]);
|
||||
SHA1_STEP (SHA1_F0o, c, d, e, a, b, w[ 8]);
|
||||
SHA1_STEP (SHA1_F0o, b, c, d, e, a, w[ 9]);
|
||||
SHA1_STEP (SHA1_F0o, a, b, c, d, e, w[10]);
|
||||
SHA1_STEP (SHA1_F0o, e, a, b, c, d, w[11]);
|
||||
SHA1_STEP (SHA1_F0o, d, e, a, b, c, w[12]);
|
||||
SHA1_STEP (SHA1_F0o, c, d, e, a, b, w[13]);
|
||||
SHA1_STEP (SHA1_F0o, b, c, d, e, a, w[14]);
|
||||
SHA1_STEP (SHA1_F0o, a, b, c, d, e, w[15]);
|
||||
|
||||
SHA1_STEP (SHA1_F0o, e, a, b, c, d, (c_16s ^ w0s01));
|
||||
SHA1_STEPX(SHA1_F0o, d, e, a, b, c, (c_17sK));
|
||||
SHA1_STEPX(SHA1_F0o, c, d, e, a, b, (c_18sK));
|
||||
SHA1_STEP (SHA1_F0o, b, c, d, e, a, (c_19s ^ w0s02));
|
||||
|
||||
#undef K
|
||||
#define K SHA1C01
|
||||
|
||||
SHA1_STEPX(SHA1_F1 , a, b, c, d, e, (c_20sK));
|
||||
SHA1_STEPX(SHA1_F1 , e, a, b, c, d, (c_21sK));
|
||||
SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_22s ^ w0s03));
|
||||
SHA1_STEPX(SHA1_F1 , c, d, e, a, b, (c_23sK));
|
||||
SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_24s ^ w0s02));
|
||||
SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_25s ^ w0s04));
|
||||
SHA1_STEPX(SHA1_F1 , e, a, b, c, d, (c_26sK));
|
||||
SHA1_STEPX(SHA1_F1 , d, e, a, b, c, (c_27sK));
|
||||
SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_28s ^ w0s05));
|
||||
SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_29sK));
|
||||
SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_30s ^ w0s02 ^ w0s04));
|
||||
SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_31s ^ w0s06));
|
||||
SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_32s ^ w0s02 ^ w0s03));
|
||||
SHA1_STEPX(SHA1_F1 , c, d, e, a, b, (c_33sK));
|
||||
SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_34s ^ w0s07));
|
||||
SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_35s ^ w0s04));
|
||||
SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_36s ^ w0s04___w0s06));
|
||||
SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_37s ^ w0s08));
|
||||
SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_38s ^ w0s04));
|
||||
SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_39sK));
|
||||
|
||||
#undef K
|
||||
#define K SHA1C02
|
||||
|
||||
SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_40s ^ w0s04 ^ w0s09));
|
||||
SHA1_STEPX(SHA1_F2o, e, a, b, c, d, (c_41sK));
|
||||
SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_42s ^ w0s06 ^ w0s08));
|
||||
SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_43s ^ w0s10));
|
||||
SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_44s ^ w0s03 ^ w0s06 ^ w0s07));
|
||||
SHA1_STEPX(SHA1_F2o, a, b, c, d, e, (c_45sK));
|
||||
SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_46s ^ w0s04 ^ w0s11));
|
||||
SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_47s ^ w0s04___w0s08));
|
||||
SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_48s ^ w0s03 ^ w0s04___w0s08 ^ w0s05 ^ w0s10));
|
||||
SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_49s ^ w0s12));
|
||||
SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_50s ^ w0s08));
|
||||
SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_51s ^ w0s04___w0s06));
|
||||
SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_52s ^ w0s04___w0s08 ^ w0s13));
|
||||
SHA1_STEPX(SHA1_F2o, c, d, e, a, b, (c_53sK));
|
||||
SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_54s ^ w0s07 ^ w0s10 ^ w0s12));
|
||||
SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_55s ^ w0s14));
|
||||
SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_56s ^ w0s04___w0s06___w0s07 ^ w0s10 ^ w0s11));
|
||||
SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_57s ^ w0s08));
|
||||
SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_58s ^ w0s04___w0s08 ^ w0s15));
|
||||
SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_59s ^ w0s08___w0s12));
|
||||
|
||||
#undef K
|
||||
#define K SHA1C03
|
||||
|
||||
SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_60s ^ w0s04 ^ w0s08___w0s12 ^ w0s07 ^ w0s14));
|
||||
SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_61s ^ w0s16));
|
||||
SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_62s ^ w0s04___w0s06 ^ w0s08___w0s12));
|
||||
SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_63s ^ w0s08));
|
||||
SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_64s ^ w0s04___w0s06___w0s07 ^ w0s08___w0s12 ^ w0s17));
|
||||
SHA1_STEPX(SHA1_F1 , a, b, c, d, e, (c_65sK));
|
||||
SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_66s ^ w0s14 ^ w0s16));
|
||||
SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_67s ^ w0s08 ^ w0s18));
|
||||
SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_68s ^ w0s11 ^ w0s14 ^ w0s15));
|
||||
SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_69sK));
|
||||
SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_70s ^ w0s12 ^ w0s19));
|
||||
SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_71s ^ w0s12 ^ w0s16));
|
||||
SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_72s ^ w0s05 ^ w0s11 ^ w0s12 ^ w0s13 ^ w0s16 ^ w0s18));
|
||||
SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_73s ^ w0s20));
|
||||
SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_74s ^ w0s08 ^ w0s16));
|
||||
SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_75s ^ w0s06 ^ w0s12 ^ w0s14));
|
||||
SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_76s ^ w0s07 ^ w0s08___w0s12 ^ w0s16 ^ w0s21));
|
||||
SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_77s));
|
||||
SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_78s ^ w0s07 ^ w0s08 ^ w0s15 ^ w0s18 ^ w0s20));
|
||||
SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_79s ^ w0s08 ^ w0s22));
|
||||
|
||||
COMPARE_M_SIMD (d, e, c, b);
|
||||
}
|
||||
}
|
||||
|
||||
DECLSPEC void m00170s (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u32 c_16s = hc_rotl32_S ((w[13] ^ w[ 8] ^ w[ 2] ), 1u);
|
||||
const u32 c_17s = hc_rotl32_S ((w[14] ^ w[ 9] ^ w[ 3] ^ w[ 1]), 1u);
|
||||
const u32 c_18s = hc_rotl32_S ((w[15] ^ w[10] ^ w[ 4] ^ w[ 2]), 1u);
|
||||
const u32 c_19s = hc_rotl32_S ((c_16s ^ w[11] ^ w[ 5] ^ w[ 3]), 1u);
|
||||
const u32 c_20s = hc_rotl32_S ((c_17s ^ w[12] ^ w[ 6] ^ w[ 4]), 1u);
|
||||
const u32 c_21s = hc_rotl32_S ((c_18s ^ w[13] ^ w[ 7] ^ w[ 5]), 1u);
|
||||
const u32 c_22s = hc_rotl32_S ((c_19s ^ w[14] ^ w[ 8] ^ w[ 6]), 1u);
|
||||
const u32 c_23s = hc_rotl32_S ((c_20s ^ w[15] ^ w[ 9] ^ w[ 7]), 1u);
|
||||
const u32 c_24s = hc_rotl32_S ((c_21s ^ c_16s ^ w[10] ^ w[ 8]), 1u);
|
||||
const u32 c_25s = hc_rotl32_S ((c_22s ^ c_17s ^ w[11] ^ w[ 9]), 1u);
|
||||
const u32 c_26s = hc_rotl32_S ((c_23s ^ c_18s ^ w[12] ^ w[10]), 1u);
|
||||
const u32 c_27s = hc_rotl32_S ((c_24s ^ c_19s ^ w[13] ^ w[11]), 1u);
|
||||
const u32 c_28s = hc_rotl32_S ((c_25s ^ c_20s ^ w[14] ^ w[12]), 1u);
|
||||
const u32 c_29s = hc_rotl32_S ((c_26s ^ c_21s ^ w[15] ^ w[13]), 1u);
|
||||
const u32 c_30s = hc_rotl32_S ((c_27s ^ c_22s ^ c_16s ^ w[14]), 1u);
|
||||
const u32 c_31s = hc_rotl32_S ((c_28s ^ c_23s ^ c_17s ^ w[15]), 1u);
|
||||
const u32 c_32s = hc_rotl32_S ((c_29s ^ c_24s ^ c_18s ^ c_16s), 1u);
|
||||
const u32 c_33s = hc_rotl32_S ((c_30s ^ c_25s ^ c_19s ^ c_17s), 1u);
|
||||
const u32 c_34s = hc_rotl32_S ((c_31s ^ c_26s ^ c_20s ^ c_18s), 1u);
|
||||
const u32 c_35s = hc_rotl32_S ((c_32s ^ c_27s ^ c_21s ^ c_19s), 1u);
|
||||
const u32 c_36s = hc_rotl32_S ((c_33s ^ c_28s ^ c_22s ^ c_20s), 1u);
|
||||
const u32 c_37s = hc_rotl32_S ((c_34s ^ c_29s ^ c_23s ^ c_21s), 1u);
|
||||
const u32 c_38s = hc_rotl32_S ((c_35s ^ c_30s ^ c_24s ^ c_22s), 1u);
|
||||
const u32 c_39s = hc_rotl32_S ((c_36s ^ c_31s ^ c_25s ^ c_23s), 1u);
|
||||
const u32 c_40s = hc_rotl32_S ((c_37s ^ c_32s ^ c_26s ^ c_24s), 1u);
|
||||
const u32 c_41s = hc_rotl32_S ((c_38s ^ c_33s ^ c_27s ^ c_25s), 1u);
|
||||
const u32 c_42s = hc_rotl32_S ((c_39s ^ c_34s ^ c_28s ^ c_26s), 1u);
|
||||
const u32 c_43s = hc_rotl32_S ((c_40s ^ c_35s ^ c_29s ^ c_27s), 1u);
|
||||
const u32 c_44s = hc_rotl32_S ((c_41s ^ c_36s ^ c_30s ^ c_28s), 1u);
|
||||
const u32 c_45s = hc_rotl32_S ((c_42s ^ c_37s ^ c_31s ^ c_29s), 1u);
|
||||
const u32 c_46s = hc_rotl32_S ((c_43s ^ c_38s ^ c_32s ^ c_30s), 1u);
|
||||
const u32 c_47s = hc_rotl32_S ((c_44s ^ c_39s ^ c_33s ^ c_31s), 1u);
|
||||
const u32 c_48s = hc_rotl32_S ((c_45s ^ c_40s ^ c_34s ^ c_32s), 1u);
|
||||
const u32 c_49s = hc_rotl32_S ((c_46s ^ c_41s ^ c_35s ^ c_33s), 1u);
|
||||
const u32 c_50s = hc_rotl32_S ((c_47s ^ c_42s ^ c_36s ^ c_34s), 1u);
|
||||
const u32 c_51s = hc_rotl32_S ((c_48s ^ c_43s ^ c_37s ^ c_35s), 1u);
|
||||
const u32 c_52s = hc_rotl32_S ((c_49s ^ c_44s ^ c_38s ^ c_36s), 1u);
|
||||
const u32 c_53s = hc_rotl32_S ((c_50s ^ c_45s ^ c_39s ^ c_37s), 1u);
|
||||
const u32 c_54s = hc_rotl32_S ((c_51s ^ c_46s ^ c_40s ^ c_38s), 1u);
|
||||
const u32 c_55s = hc_rotl32_S ((c_52s ^ c_47s ^ c_41s ^ c_39s), 1u);
|
||||
const u32 c_56s = hc_rotl32_S ((c_53s ^ c_48s ^ c_42s ^ c_40s), 1u);
|
||||
const u32 c_57s = hc_rotl32_S ((c_54s ^ c_49s ^ c_43s ^ c_41s), 1u);
|
||||
const u32 c_58s = hc_rotl32_S ((c_55s ^ c_50s ^ c_44s ^ c_42s), 1u);
|
||||
const u32 c_59s = hc_rotl32_S ((c_56s ^ c_51s ^ c_45s ^ c_43s), 1u);
|
||||
const u32 c_60s = hc_rotl32_S ((c_57s ^ c_52s ^ c_46s ^ c_44s), 1u);
|
||||
const u32 c_61s = hc_rotl32_S ((c_58s ^ c_53s ^ c_47s ^ c_45s), 1u);
|
||||
const u32 c_62s = hc_rotl32_S ((c_59s ^ c_54s ^ c_48s ^ c_46s), 1u);
|
||||
const u32 c_63s = hc_rotl32_S ((c_60s ^ c_55s ^ c_49s ^ c_47s), 1u);
|
||||
const u32 c_64s = hc_rotl32_S ((c_61s ^ c_56s ^ c_50s ^ c_48s), 1u);
|
||||
const u32 c_65s = hc_rotl32_S ((c_62s ^ c_57s ^ c_51s ^ c_49s), 1u);
|
||||
const u32 c_66s = hc_rotl32_S ((c_63s ^ c_58s ^ c_52s ^ c_50s), 1u);
|
||||
const u32 c_67s = hc_rotl32_S ((c_64s ^ c_59s ^ c_53s ^ c_51s), 1u);
|
||||
const u32 c_68s = hc_rotl32_S ((c_65s ^ c_60s ^ c_54s ^ c_52s), 1u);
|
||||
const u32 c_69s = hc_rotl32_S ((c_66s ^ c_61s ^ c_55s ^ c_53s), 1u);
|
||||
const u32 c_70s = hc_rotl32_S ((c_67s ^ c_62s ^ c_56s ^ c_54s), 1u);
|
||||
const u32 c_71s = hc_rotl32_S ((c_68s ^ c_63s ^ c_57s ^ c_55s), 1u);
|
||||
const u32 c_72s = hc_rotl32_S ((c_69s ^ c_64s ^ c_58s ^ c_56s), 1u);
|
||||
const u32 c_73s = hc_rotl32_S ((c_70s ^ c_65s ^ c_59s ^ c_57s), 1u);
|
||||
const u32 c_74s = hc_rotl32_S ((c_71s ^ c_66s ^ c_60s ^ c_58s), 1u);
|
||||
const u32 c_75s = hc_rotl32_S ((c_72s ^ c_67s ^ c_61s ^ c_59s), 1u);
|
||||
|
||||
const u32 c_17sK = c_17s + SHA1C00;
|
||||
const u32 c_18sK = c_18s + SHA1C00;
|
||||
const u32 c_20sK = c_20s + SHA1C01;
|
||||
const u32 c_21sK = c_21s + SHA1C01;
|
||||
const u32 c_23sK = c_23s + SHA1C01;
|
||||
const u32 c_26sK = c_26s + SHA1C01;
|
||||
const u32 c_27sK = c_27s + SHA1C01;
|
||||
const u32 c_29sK = c_29s + SHA1C01;
|
||||
const u32 c_33sK = c_33s + SHA1C01;
|
||||
const u32 c_39sK = c_39s + SHA1C01;
|
||||
const u32 c_41sK = c_41s + SHA1C02;
|
||||
const u32 c_45sK = c_45s + SHA1C02;
|
||||
const u32 c_53sK = c_53s + SHA1C02;
|
||||
const u32 c_65sK = c_65s + SHA1C03;
|
||||
const u32 c_69sK = c_69s + SHA1C03;
|
||||
|
||||
/**
|
||||
* 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
|
||||
*/
|
||||
|
||||
u32 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;
|
||||
|
||||
const u32x w0s01 = hc_rotl32 (w0, 1u);
|
||||
const u32x w0s02 = hc_rotl32 (w0, 2u);
|
||||
const u32x w0s03 = hc_rotl32 (w0, 3u);
|
||||
const u32x w0s04 = hc_rotl32 (w0, 4u);
|
||||
const u32x w0s05 = hc_rotl32 (w0, 5u);
|
||||
const u32x w0s06 = hc_rotl32 (w0, 6u);
|
||||
const u32x w0s07 = hc_rotl32 (w0, 7u);
|
||||
const u32x w0s08 = hc_rotl32 (w0, 8u);
|
||||
const u32x w0s09 = hc_rotl32 (w0, 9u);
|
||||
const u32x w0s10 = hc_rotl32 (w0, 10u);
|
||||
const u32x w0s11 = hc_rotl32 (w0, 11u);
|
||||
const u32x w0s12 = hc_rotl32 (w0, 12u);
|
||||
const u32x w0s13 = hc_rotl32 (w0, 13u);
|
||||
const u32x w0s14 = hc_rotl32 (w0, 14u);
|
||||
const u32x w0s15 = hc_rotl32 (w0, 15u);
|
||||
const u32x w0s16 = hc_rotl32 (w0, 16u);
|
||||
const u32x w0s17 = hc_rotl32 (w0, 17u);
|
||||
const u32x w0s18 = hc_rotl32 (w0, 18u);
|
||||
const u32x w0s19 = hc_rotl32 (w0, 19u);
|
||||
const u32x w0s20 = hc_rotl32 (w0, 20u);
|
||||
|
||||
const u32x w0s04___w0s06 = w0s04 ^ w0s06;
|
||||
const u32x w0s04___w0s08 = w0s04 ^ w0s08;
|
||||
const u32x w0s08___w0s12 = w0s08 ^ w0s12;
|
||||
const u32x w0s04___w0s06___w0s07 = w0s04___w0s06 ^ w0s07;
|
||||
|
||||
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);
|
||||
SHA1_STEP (SHA1_F0o, e, a, b, c, d, w[ 1]);
|
||||
SHA1_STEP (SHA1_F0o, d, e, a, b, c, w[ 2]);
|
||||
SHA1_STEP (SHA1_F0o, c, d, e, a, b, w[ 3]);
|
||||
SHA1_STEP (SHA1_F0o, b, c, d, e, a, w[ 4]);
|
||||
SHA1_STEP (SHA1_F0o, a, b, c, d, e, w[ 5]);
|
||||
SHA1_STEP (SHA1_F0o, e, a, b, c, d, w[ 6]);
|
||||
SHA1_STEP (SHA1_F0o, d, e, a, b, c, w[ 7]);
|
||||
SHA1_STEP (SHA1_F0o, c, d, e, a, b, w[ 8]);
|
||||
SHA1_STEP (SHA1_F0o, b, c, d, e, a, w[ 9]);
|
||||
SHA1_STEP (SHA1_F0o, a, b, c, d, e, w[10]);
|
||||
SHA1_STEP (SHA1_F0o, e, a, b, c, d, w[11]);
|
||||
SHA1_STEP (SHA1_F0o, d, e, a, b, c, w[12]);
|
||||
SHA1_STEP (SHA1_F0o, c, d, e, a, b, w[13]);
|
||||
SHA1_STEP (SHA1_F0o, b, c, d, e, a, w[14]);
|
||||
SHA1_STEP (SHA1_F0o, a, b, c, d, e, w[15]);
|
||||
|
||||
SHA1_STEP (SHA1_F0o, e, a, b, c, d, (c_16s ^ w0s01));
|
||||
SHA1_STEPX(SHA1_F0o, d, e, a, b, c, (c_17sK));
|
||||
SHA1_STEPX(SHA1_F0o, c, d, e, a, b, (c_18sK));
|
||||
SHA1_STEP (SHA1_F0o, b, c, d, e, a, (c_19s ^ w0s02));
|
||||
|
||||
#undef K
|
||||
#define K SHA1C01
|
||||
|
||||
SHA1_STEPX(SHA1_F1 , a, b, c, d, e, (c_20sK));
|
||||
SHA1_STEPX(SHA1_F1 , e, a, b, c, d, (c_21sK));
|
||||
SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_22s ^ w0s03));
|
||||
SHA1_STEPX(SHA1_F1 , c, d, e, a, b, (c_23sK));
|
||||
SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_24s ^ w0s02));
|
||||
SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_25s ^ w0s04));
|
||||
SHA1_STEPX(SHA1_F1 , e, a, b, c, d, (c_26sK));
|
||||
SHA1_STEPX(SHA1_F1 , d, e, a, b, c, (c_27sK));
|
||||
SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_28s ^ w0s05));
|
||||
SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_29sK));
|
||||
SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_30s ^ w0s02 ^ w0s04));
|
||||
SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_31s ^ w0s06));
|
||||
SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_32s ^ w0s02 ^ w0s03));
|
||||
SHA1_STEPX(SHA1_F1 , c, d, e, a, b, (c_33sK));
|
||||
SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_34s ^ w0s07));
|
||||
SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_35s ^ w0s04));
|
||||
SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_36s ^ w0s04___w0s06));
|
||||
SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_37s ^ w0s08));
|
||||
SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_38s ^ w0s04));
|
||||
SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_39sK));
|
||||
|
||||
#undef K
|
||||
#define K SHA1C02
|
||||
|
||||
SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_40s ^ w0s04 ^ w0s09));
|
||||
SHA1_STEPX(SHA1_F2o, e, a, b, c, d, (c_41sK));
|
||||
SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_42s ^ w0s06 ^ w0s08));
|
||||
SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_43s ^ w0s10));
|
||||
SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_44s ^ w0s03 ^ w0s06 ^ w0s07));
|
||||
SHA1_STEPX(SHA1_F2o, a, b, c, d, e, (c_45sK));
|
||||
SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_46s ^ w0s04 ^ w0s11));
|
||||
SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_47s ^ w0s04___w0s08));
|
||||
SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_48s ^ w0s03 ^ w0s04___w0s08 ^ w0s05 ^ w0s10));
|
||||
SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_49s ^ w0s12));
|
||||
SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_50s ^ w0s08));
|
||||
SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_51s ^ w0s04___w0s06));
|
||||
SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_52s ^ w0s04___w0s08 ^ w0s13));
|
||||
SHA1_STEPX(SHA1_F2o, c, d, e, a, b, (c_53sK));
|
||||
SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_54s ^ w0s07 ^ w0s10 ^ w0s12));
|
||||
SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_55s ^ w0s14));
|
||||
SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_56s ^ w0s04___w0s06___w0s07 ^ w0s10 ^ w0s11));
|
||||
SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_57s ^ w0s08));
|
||||
SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_58s ^ w0s04___w0s08 ^ w0s15));
|
||||
SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_59s ^ w0s08___w0s12));
|
||||
|
||||
#undef K
|
||||
#define K SHA1C03
|
||||
|
||||
SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_60s ^ w0s04 ^ w0s08___w0s12 ^ w0s07 ^ w0s14));
|
||||
SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_61s ^ w0s16));
|
||||
SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_62s ^ w0s04___w0s06 ^ w0s08___w0s12));
|
||||
SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_63s ^ w0s08));
|
||||
SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_64s ^ w0s04___w0s06___w0s07 ^ w0s08___w0s12 ^ w0s17));
|
||||
SHA1_STEPX(SHA1_F1 , a, b, c, d, e, (c_65sK));
|
||||
SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_66s ^ w0s14 ^ w0s16));
|
||||
SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_67s ^ w0s08 ^ w0s18));
|
||||
SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_68s ^ w0s11 ^ w0s14 ^ w0s15));
|
||||
SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_69sK));
|
||||
SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_70s ^ w0s12 ^ w0s19));
|
||||
SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_71s ^ w0s12 ^ w0s16));
|
||||
SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_72s ^ w0s05 ^ w0s11 ^ w0s12 ^ w0s13 ^ w0s16 ^ w0s18));
|
||||
SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_73s ^ w0s20));
|
||||
SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_74s ^ w0s08 ^ w0s16));
|
||||
SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_75s ^ w0s06 ^ w0s12 ^ w0s14));
|
||||
|
||||
if (MATCHES_NONE_VS (e, e_rev)) continue;
|
||||
|
||||
const u32x c_76s = hc_rotl32 ((c_73s ^ c_68s ^ c_62s ^ c_60s), 1u);
|
||||
const u32x c_77s = hc_rotl32 ((c_74s ^ c_69s ^ c_63s ^ c_61s), 1u);
|
||||
const u32x c_78s = hc_rotl32 ((c_75s ^ c_70s ^ c_64s ^ c_62s), 1u);
|
||||
const u32x c_79s = hc_rotl32 ((c_76s ^ c_71s ^ c_65s ^ c_63s), 1u);
|
||||
|
||||
const u32x w0s21 = hc_rotl32 (w0, 21u);
|
||||
const u32x w0s22 = hc_rotl32 (w0, 22U);
|
||||
|
||||
SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_76s ^ w0s07 ^ w0s08___w0s12 ^ w0s16 ^ w0s21));
|
||||
SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_77s));
|
||||
SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_78s ^ w0s07 ^ w0s08 ^ w0s15 ^ w0s18 ^ w0s20));
|
||||
SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_79s ^ w0s08 ^ w0s22));
|
||||
|
||||
COMPARE_S_SIMD (d, e, c, b);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00170_m04 (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 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] = 0;
|
||||
w[15] = pws[gid].i[15];
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m00170m (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00170_m08 (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 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] = 0;
|
||||
w[15] = pws[gid].i[15];
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m00170m (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00170_m16 (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 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 & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m00170m (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00170_s04 (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 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] = 0;
|
||||
w[15] = pws[gid].i[15];
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m00170s (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00170_s08 (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 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] = 0;
|
||||
w[15] = pws[gid].i[15];
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m00170s (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00170_s16 (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 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 & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m00170s (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
@ -0,0 +1,137 @@
|
||||
/**
|
||||
* 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
|
||||
|
||||
KERNEL_FQ void m00170_mxx (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
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];
|
||||
}
|
||||
|
||||
/**
|
||||
* 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 (&ctx);
|
||||
|
||||
sha1_update_vector_utf16beN (&ctx, w, pw_len);
|
||||
|
||||
sha1_final_vector (&ctx);
|
||||
|
||||
const u32x r0 = ctx.h[DGST_R0];
|
||||
const u32x r1 = ctx.h[DGST_R1];
|
||||
const u32x r2 = ctx.h[DGST_R2];
|
||||
const u32x r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_M_SIMD (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m00170_sxx (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
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];
|
||||
}
|
||||
|
||||
/**
|
||||
* 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 (&ctx);
|
||||
|
||||
sha1_update_vector_utf16beN (&ctx, w, pw_len);
|
||||
|
||||
sha1_final_vector (&ctx);
|
||||
|
||||
const u32x r0 = ctx.h[DGST_R0];
|
||||
const u32x r1 = ctx.h[DGST_R1];
|
||||
const u32x r2 = ctx.h[DGST_R2];
|
||||
const u32x r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_S_SIMD (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
@ -0,0 +1,384 @@
|
||||
/**
|
||||
* 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_sha256.cl"
|
||||
#endif
|
||||
|
||||
#define SHA256_STEP_REV(a,b,c,d,e,f,g,h) \
|
||||
{ \
|
||||
u32 t2 = SHA256_S2_S(b) + SHA256_F0o(b,c,d); \
|
||||
u32 t1 = a - t2; \
|
||||
a = b; \
|
||||
b = c; \
|
||||
c = d; \
|
||||
d = e - t1; \
|
||||
e = f; \
|
||||
f = g; \
|
||||
g = h; \
|
||||
h = 0; \
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01470_m04 (KERN_ATTR_RULES ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
u32 pw_buf0[4];
|
||||
u32 pw_buf1[4];
|
||||
|
||||
pw_buf0[0] = pws[gid].i[0];
|
||||
pw_buf0[1] = pws[gid].i[1];
|
||||
pw_buf0[2] = pws[gid].i[2];
|
||||
pw_buf0[3] = pws[gid].i[3];
|
||||
pw_buf1[0] = pws[gid].i[4];
|
||||
pw_buf1[1] = pws[gid].i[5];
|
||||
pw_buf1[2] = pws[gid].i[6];
|
||||
pw_buf1[3] = pws[gid].i[7];
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* 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);
|
||||
|
||||
make_utf16le (w1, w2, w3);
|
||||
make_utf16le (w0, w0, w1);
|
||||
|
||||
const u32x out_len2 = out_len * 2;
|
||||
|
||||
append_0x80_4x4_VV (w0, w1, w2, w3, out_len2);
|
||||
|
||||
/**
|
||||
* sha256
|
||||
*/
|
||||
|
||||
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 = out_len2 * 8;
|
||||
|
||||
u32x a = SHA256M_A;
|
||||
u32x b = SHA256M_B;
|
||||
u32x c = SHA256M_C;
|
||||
u32x d = SHA256M_D;
|
||||
u32x e = SHA256M_E;
|
||||
u32x f = SHA256M_F;
|
||||
u32x g = SHA256M_G;
|
||||
u32x h = SHA256M_H;
|
||||
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
|
||||
|
||||
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
|
||||
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
|
||||
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
|
||||
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
|
||||
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
|
||||
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
|
||||
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
|
||||
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
|
||||
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
|
||||
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
|
||||
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
|
||||
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
|
||||
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
|
||||
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
|
||||
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
|
||||
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
|
||||
|
||||
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
|
||||
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
|
||||
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
|
||||
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
|
||||
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
|
||||
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
|
||||
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
|
||||
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
|
||||
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
|
||||
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
|
||||
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
|
||||
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
|
||||
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
|
||||
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
|
||||
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
|
||||
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
|
||||
|
||||
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
|
||||
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
|
||||
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
|
||||
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
|
||||
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
|
||||
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
|
||||
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
|
||||
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
|
||||
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
|
||||
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
|
||||
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
|
||||
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
|
||||
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
|
||||
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
|
||||
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
|
||||
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
|
||||
|
||||
COMPARE_M_SIMD (d, h, c, g);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01470_m08 (KERN_ATTR_RULES ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01470_m16 (KERN_ATTR_RULES ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01470_s04 (KERN_ATTR_RULES ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
u32 pw_buf0[4];
|
||||
u32 pw_buf1[4];
|
||||
|
||||
pw_buf0[0] = pws[gid].i[0];
|
||||
pw_buf0[1] = pws[gid].i[1];
|
||||
pw_buf0[2] = pws[gid].i[2];
|
||||
pw_buf0[3] = pws[gid].i[3];
|
||||
pw_buf1[0] = pws[gid].i[4];
|
||||
pw_buf1[1] = pws[gid].i[5];
|
||||
pw_buf1[2] = pws[gid].i[6];
|
||||
pw_buf1[3] = pws[gid].i[7];
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* digest
|
||||
*/
|
||||
|
||||
const u32 search[4] =
|
||||
{
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R0],
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R1],
|
||||
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];
|
||||
u32 e_rev = digests_buf[DIGESTS_OFFSET].digest_buf[4];
|
||||
u32 f_rev = digests_buf[DIGESTS_OFFSET].digest_buf[5];
|
||||
u32 g_rev = digests_buf[DIGESTS_OFFSET].digest_buf[6];
|
||||
u32 h_rev = digests_buf[DIGESTS_OFFSET].digest_buf[7];
|
||||
|
||||
SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
|
||||
SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
|
||||
SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
|
||||
SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
|
||||
|
||||
/**
|
||||
* 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);
|
||||
|
||||
make_utf16le (w1, w2, w3);
|
||||
make_utf16le (w0, w0, w1);
|
||||
|
||||
const u32x out_len2 = out_len * 2;
|
||||
|
||||
append_0x80_4x4_VV (w0, w1, w2, w3, out_len2);
|
||||
|
||||
/**
|
||||
* sha256
|
||||
*/
|
||||
|
||||
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 = out_len2 * 8;
|
||||
|
||||
u32x a = SHA256M_A;
|
||||
u32x b = SHA256M_B;
|
||||
u32x c = SHA256M_C;
|
||||
u32x d = SHA256M_D;
|
||||
u32x e = SHA256M_E;
|
||||
u32x f = SHA256M_F;
|
||||
u32x g = SHA256M_G;
|
||||
u32x h = SHA256M_H;
|
||||
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
|
||||
|
||||
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
|
||||
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
|
||||
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
|
||||
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
|
||||
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
|
||||
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
|
||||
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
|
||||
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
|
||||
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
|
||||
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
|
||||
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
|
||||
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
|
||||
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
|
||||
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
|
||||
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
|
||||
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
|
||||
|
||||
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
|
||||
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
|
||||
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
|
||||
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
|
||||
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
|
||||
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
|
||||
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
|
||||
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
|
||||
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
|
||||
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
|
||||
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
|
||||
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
|
||||
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
|
||||
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
|
||||
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
|
||||
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
|
||||
|
||||
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
|
||||
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
|
||||
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
|
||||
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
|
||||
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
|
||||
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
|
||||
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
|
||||
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
|
||||
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
|
||||
|
||||
if (MATCHES_NONE_VS (h, d_rev)) continue;
|
||||
|
||||
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
|
||||
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
|
||||
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
|
||||
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
|
||||
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
|
||||
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
|
||||
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
|
||||
|
||||
COMPARE_S_SIMD (d, h, c, g);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01470_s08 (KERN_ATTR_RULES ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01470_s16 (KERN_ATTR_RULES ())
|
||||
{
|
||||
}
|
@ -0,0 +1,121 @@
|
||||
/**
|
||||
* 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_sha256.cl"
|
||||
#endif
|
||||
|
||||
KERNEL_FQ void m01470_mxx (KERN_ATTR_RULES ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
COPY_PW (pws[gid]);
|
||||
|
||||
sha256_ctx_t ctx0;
|
||||
|
||||
sha256_init (&ctx0);
|
||||
|
||||
/**
|
||||
* 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);
|
||||
|
||||
sha256_ctx_t ctx = ctx0;
|
||||
|
||||
sha256_update_utf16le_swap (&ctx, tmp.i, tmp.pw_len);
|
||||
|
||||
sha256_final (&ctx);
|
||||
|
||||
const u32 r0 = ctx.h[DGST_R0];
|
||||
const u32 r1 = ctx.h[DGST_R1];
|
||||
const u32 r2 = ctx.h[DGST_R2];
|
||||
const u32 r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_M_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01470_sxx (KERN_ATTR_RULES ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
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]);
|
||||
|
||||
sha256_ctx_t ctx0;
|
||||
|
||||
sha256_init (&ctx0);
|
||||
|
||||
/**
|
||||
* 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);
|
||||
|
||||
sha256_ctx_t ctx = ctx0;
|
||||
|
||||
sha256_update_utf16le_swap (&ctx, tmp.i, tmp.pw_len);
|
||||
|
||||
sha256_final (&ctx);
|
||||
|
||||
const u32 r0 = ctx.h[DGST_R0];
|
||||
const u32 r1 = ctx.h[DGST_R1];
|
||||
const u32 r2 = ctx.h[DGST_R2];
|
||||
const u32 r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_S_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
@ -0,0 +1,498 @@
|
||||
/**
|
||||
* 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_sha256.cl"
|
||||
#endif
|
||||
|
||||
#define SHA256_STEP_REV(a,b,c,d,e,f,g,h) \
|
||||
{ \
|
||||
u32 t2 = SHA256_S2_S(b) + SHA256_F0o(b,c,d); \
|
||||
u32 t1 = a - t2; \
|
||||
a = b; \
|
||||
b = c; \
|
||||
c = d; \
|
||||
d = e - t1; \
|
||||
e = f; \
|
||||
f = g; \
|
||||
g = h; \
|
||||
h = 0; \
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01470_m04 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
u32 pw_buf0[4];
|
||||
u32 pw_buf1[4];
|
||||
|
||||
pw_buf0[0] = pws[gid].i[0];
|
||||
pw_buf0[1] = pws[gid].i[1];
|
||||
pw_buf0[2] = pws[gid].i[2];
|
||||
pw_buf0[3] = pws[gid].i[3];
|
||||
pw_buf1[0] = pws[gid].i[4];
|
||||
pw_buf1[1] = pws[gid].i[5];
|
||||
pw_buf1[2] = pws[gid].i[6];
|
||||
pw_buf1[3] = pws[gid].i[7];
|
||||
|
||||
const u32 pw_l_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
|
||||
{
|
||||
const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
|
||||
|
||||
const u32x pw_len = (pw_l_len + pw_r_len) & 63;
|
||||
|
||||
/**
|
||||
* concat password candidate
|
||||
*/
|
||||
|
||||
u32x wordl0[4] = { 0 };
|
||||
u32x wordl1[4] = { 0 };
|
||||
u32x wordl2[4] = { 0 };
|
||||
u32x wordl3[4] = { 0 };
|
||||
|
||||
wordl0[0] = pw_buf0[0];
|
||||
wordl0[1] = pw_buf0[1];
|
||||
wordl0[2] = pw_buf0[2];
|
||||
wordl0[3] = pw_buf0[3];
|
||||
wordl1[0] = pw_buf1[0];
|
||||
wordl1[1] = pw_buf1[1];
|
||||
wordl1[2] = pw_buf1[2];
|
||||
wordl1[3] = pw_buf1[3];
|
||||
|
||||
u32x wordr0[4] = { 0 };
|
||||
u32x wordr1[4] = { 0 };
|
||||
u32x wordr2[4] = { 0 };
|
||||
u32x wordr3[4] = { 0 };
|
||||
|
||||
wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
|
||||
wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
|
||||
wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
|
||||
wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
|
||||
wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
|
||||
wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
|
||||
wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
|
||||
wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
|
||||
|
||||
if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
|
||||
{
|
||||
switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
|
||||
}
|
||||
else
|
||||
{
|
||||
switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
|
||||
}
|
||||
|
||||
u32x w0[4];
|
||||
u32x w1[4];
|
||||
u32x w2[4];
|
||||
u32x w3[4];
|
||||
|
||||
w0[0] = wordl0[0] | wordr0[0];
|
||||
w0[1] = wordl0[1] | wordr0[1];
|
||||
w0[2] = wordl0[2] | wordr0[2];
|
||||
w0[3] = wordl0[3] | wordr0[3];
|
||||
w1[0] = wordl1[0] | wordr1[0];
|
||||
w1[1] = wordl1[1] | wordr1[1];
|
||||
w1[2] = wordl1[2] | wordr1[2];
|
||||
w1[3] = wordl1[3] | wordr1[3];
|
||||
w2[0] = wordl2[0] | wordr2[0];
|
||||
w2[1] = wordl2[1] | wordr2[1];
|
||||
w2[2] = wordl2[2] | wordr2[2];
|
||||
w2[3] = wordl2[3] | wordr2[3];
|
||||
w3[0] = wordl3[0] | wordr3[0];
|
||||
w3[1] = wordl3[1] | wordr3[1];
|
||||
w3[2] = wordl3[2] | wordr3[2];
|
||||
w3[3] = wordl3[3] | wordr3[3];
|
||||
|
||||
make_utf16le (w1, w2, w3);
|
||||
make_utf16le (w0, w0, w1);
|
||||
|
||||
const u32x pw_len2 = pw_len * 2;
|
||||
|
||||
/**
|
||||
* sha256
|
||||
*/
|
||||
|
||||
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 = pw_len2 * 8;
|
||||
|
||||
u32x a = SHA256M_A;
|
||||
u32x b = SHA256M_B;
|
||||
u32x c = SHA256M_C;
|
||||
u32x d = SHA256M_D;
|
||||
u32x e = SHA256M_E;
|
||||
u32x f = SHA256M_F;
|
||||
u32x g = SHA256M_G;
|
||||
u32x h = SHA256M_H;
|
||||
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
|
||||
|
||||
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
|
||||
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
|
||||
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
|
||||
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
|
||||
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
|
||||
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
|
||||
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
|
||||
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
|
||||
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
|
||||
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
|
||||
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
|
||||
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
|
||||
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
|
||||
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
|
||||
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
|
||||
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
|
||||
|
||||
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
|
||||
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
|
||||
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
|
||||
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
|
||||
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
|
||||
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
|
||||
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
|
||||
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
|
||||
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
|
||||
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
|
||||
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
|
||||
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
|
||||
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
|
||||
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
|
||||
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
|
||||
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
|
||||
|
||||
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
|
||||
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
|
||||
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
|
||||
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
|
||||
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
|
||||
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
|
||||
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
|
||||
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
|
||||
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
|
||||
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
|
||||
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
|
||||
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
|
||||
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
|
||||
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
|
||||
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
|
||||
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
|
||||
|
||||
COMPARE_M_SIMD (d, h, c, g);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01470_m08 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01470_m16 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01470_s04 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
u32 pw_buf0[4];
|
||||
u32 pw_buf1[4];
|
||||
|
||||
pw_buf0[0] = pws[gid].i[0];
|
||||
pw_buf0[1] = pws[gid].i[1];
|
||||
pw_buf0[2] = pws[gid].i[2];
|
||||
pw_buf0[3] = pws[gid].i[3];
|
||||
pw_buf1[0] = pws[gid].i[4];
|
||||
pw_buf1[1] = pws[gid].i[5];
|
||||
pw_buf1[2] = pws[gid].i[6];
|
||||
pw_buf1[3] = pws[gid].i[7];
|
||||
|
||||
const u32 pw_l_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* 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];
|
||||
u32 e_rev = digests_buf[DIGESTS_OFFSET].digest_buf[4];
|
||||
u32 f_rev = digests_buf[DIGESTS_OFFSET].digest_buf[5];
|
||||
u32 g_rev = digests_buf[DIGESTS_OFFSET].digest_buf[6];
|
||||
u32 h_rev = digests_buf[DIGESTS_OFFSET].digest_buf[7];
|
||||
|
||||
SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
|
||||
SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
|
||||
SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
|
||||
SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
|
||||
{
|
||||
const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
|
||||
|
||||
const u32x pw_len = (pw_l_len + pw_r_len) & 63;
|
||||
|
||||
/**
|
||||
* concat password candidate
|
||||
*/
|
||||
|
||||
u32x wordl0[4] = { 0 };
|
||||
u32x wordl1[4] = { 0 };
|
||||
u32x wordl2[4] = { 0 };
|
||||
u32x wordl3[4] = { 0 };
|
||||
|
||||
wordl0[0] = pw_buf0[0];
|
||||
wordl0[1] = pw_buf0[1];
|
||||
wordl0[2] = pw_buf0[2];
|
||||
wordl0[3] = pw_buf0[3];
|
||||
wordl1[0] = pw_buf1[0];
|
||||
wordl1[1] = pw_buf1[1];
|
||||
wordl1[2] = pw_buf1[2];
|
||||
wordl1[3] = pw_buf1[3];
|
||||
|
||||
u32x wordr0[4] = { 0 };
|
||||
u32x wordr1[4] = { 0 };
|
||||
u32x wordr2[4] = { 0 };
|
||||
u32x wordr3[4] = { 0 };
|
||||
|
||||
wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
|
||||
wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
|
||||
wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
|
||||
wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
|
||||
wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
|
||||
wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
|
||||
wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
|
||||
wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
|
||||
|
||||
if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
|
||||
{
|
||||
switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
|
||||
}
|
||||
else
|
||||
{
|
||||
switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
|
||||
}
|
||||
|
||||
u32x w0[4];
|
||||
u32x w1[4];
|
||||
u32x w2[4];
|
||||
u32x w3[4];
|
||||
|
||||
w0[0] = wordl0[0] | wordr0[0];
|
||||
w0[1] = wordl0[1] | wordr0[1];
|
||||
w0[2] = wordl0[2] | wordr0[2];
|
||||
w0[3] = wordl0[3] | wordr0[3];
|
||||
w1[0] = wordl1[0] | wordr1[0];
|
||||
w1[1] = wordl1[1] | wordr1[1];
|
||||
w1[2] = wordl1[2] | wordr1[2];
|
||||
w1[3] = wordl1[3] | wordr1[3];
|
||||
w2[0] = wordl2[0] | wordr2[0];
|
||||
w2[1] = wordl2[1] | wordr2[1];
|
||||
w2[2] = wordl2[2] | wordr2[2];
|
||||
w2[3] = wordl2[3] | wordr2[3];
|
||||
w3[0] = wordl3[0] | wordr3[0];
|
||||
w3[1] = wordl3[1] | wordr3[1];
|
||||
w3[2] = wordl3[2] | wordr3[2];
|
||||
w3[3] = wordl3[3] | wordr3[3];
|
||||
|
||||
make_utf16le (w1, w2, w3);
|
||||
make_utf16le (w0, w0, w1);
|
||||
|
||||
const u32x pw_len2 = pw_len * 2;
|
||||
|
||||
/**
|
||||
* sha256
|
||||
*/
|
||||
|
||||
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 = pw_len2 * 8;
|
||||
|
||||
u32x a = SHA256M_A;
|
||||
u32x b = SHA256M_B;
|
||||
u32x c = SHA256M_C;
|
||||
u32x d = SHA256M_D;
|
||||
u32x e = SHA256M_E;
|
||||
u32x f = SHA256M_F;
|
||||
u32x g = SHA256M_G;
|
||||
u32x h = SHA256M_H;
|
||||
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
|
||||
|
||||
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
|
||||
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
|
||||
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
|
||||
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
|
||||
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
|
||||
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
|
||||
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
|
||||
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
|
||||
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
|
||||
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
|
||||
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
|
||||
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
|
||||
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
|
||||
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
|
||||
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
|
||||
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
|
||||
|
||||
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
|
||||
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
|
||||
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
|
||||
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
|
||||
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
|
||||
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
|
||||
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
|
||||
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
|
||||
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
|
||||
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
|
||||
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
|
||||
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
|
||||
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
|
||||
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
|
||||
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
|
||||
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
|
||||
|
||||
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
|
||||
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
|
||||
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
|
||||
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
|
||||
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
|
||||
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
|
||||
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
|
||||
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
|
||||
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
|
||||
|
||||
if (MATCHES_NONE_VS (h, d_rev)) continue;
|
||||
|
||||
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
|
||||
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
|
||||
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
|
||||
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
|
||||
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
|
||||
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
|
||||
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
|
||||
|
||||
COMPARE_S_SIMD (d, h, c, g);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01470_s08 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01470_s16 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
}
|
@ -0,0 +1,111 @@
|
||||
/**
|
||||
* 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_sha256.cl"
|
||||
#endif
|
||||
|
||||
KERNEL_FQ void m01470_mxx (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
sha256_ctx_t ctx0;
|
||||
|
||||
sha256_init (&ctx0);
|
||||
|
||||
sha256_update_global_utf16le_swap (&ctx0, pws[gid].i, pws[gid].pw_len);
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
|
||||
{
|
||||
sha256_ctx_t ctx = ctx0;
|
||||
|
||||
sha256_update_global_utf16le_swap (&ctx, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
|
||||
|
||||
sha256_final (&ctx);
|
||||
|
||||
const u32 r0 = ctx.h[DGST_R0];
|
||||
const u32 r1 = ctx.h[DGST_R1];
|
||||
const u32 r2 = ctx.h[DGST_R2];
|
||||
const u32 r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_M_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01470_sxx (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
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
|
||||
*/
|
||||
|
||||
sha256_ctx_t ctx0;
|
||||
|
||||
sha256_init (&ctx0);
|
||||
|
||||
sha256_update_global_utf16le_swap (&ctx0, pws[gid].i, pws[gid].pw_len);
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
|
||||
{
|
||||
sha256_ctx_t ctx = ctx0;
|
||||
|
||||
sha256_update_global_utf16le_swap (&ctx, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
|
||||
|
||||
sha256_final (&ctx);
|
||||
|
||||
const u32 r0 = ctx.h[DGST_R0];
|
||||
const u32 r1 = ctx.h[DGST_R1];
|
||||
const u32 r2 = ctx.h[DGST_R2];
|
||||
const u32 r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_S_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
@ -0,0 +1,634 @@
|
||||
/**
|
||||
* 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_sha256.cl"
|
||||
#endif
|
||||
|
||||
#define SHA256_STEP_REV(a,b,c,d,e,f,g,h) \
|
||||
{ \
|
||||
u32 t2 = SHA256_S2_S(b) + SHA256_F0o(b,c,d); \
|
||||
u32 t1 = a - t2; \
|
||||
a = b; \
|
||||
b = c; \
|
||||
c = d; \
|
||||
d = e - t1; \
|
||||
e = f; \
|
||||
f = g; \
|
||||
g = h; \
|
||||
h = 0; \
|
||||
}
|
||||
|
||||
DECLSPEC void m01470m (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
const u32 w0l = w0[0];
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
|
||||
{
|
||||
const u32x w0r = ix_create_bft (bfs_buf, il_pos);
|
||||
|
||||
const u32x w0lr = w0l | w0r;
|
||||
|
||||
u32x t0[4];
|
||||
u32x t1[4];
|
||||
u32x t2[4];
|
||||
u32x t3[4];
|
||||
|
||||
t0[0] = w0lr;
|
||||
t0[1] = w0[1];
|
||||
t0[2] = w0[2];
|
||||
t0[3] = w0[3];
|
||||
t1[0] = w1[0];
|
||||
t1[1] = w1[1];
|
||||
t1[2] = w1[2];
|
||||
t1[3] = w1[3];
|
||||
t2[0] = w2[0];
|
||||
t2[1] = w2[1];
|
||||
t2[2] = w2[2];
|
||||
t2[3] = w2[3];
|
||||
t3[0] = w3[0];
|
||||
t3[1] = w3[1];
|
||||
t3[2] = w3[2];
|
||||
t3[3] = w3[3];
|
||||
|
||||
/**
|
||||
* sha256
|
||||
*/
|
||||
|
||||
u32x w0_t = t0[0];
|
||||
u32x w1_t = t0[1];
|
||||
u32x w2_t = t0[2];
|
||||
u32x w3_t = t0[3];
|
||||
u32x w4_t = t1[0];
|
||||
u32x w5_t = t1[1];
|
||||
u32x w6_t = t1[2];
|
||||
u32x w7_t = t1[3];
|
||||
u32x w8_t = t2[0];
|
||||
u32x w9_t = t2[1];
|
||||
u32x wa_t = t2[2];
|
||||
u32x wb_t = t2[3];
|
||||
u32x wc_t = t3[0];
|
||||
u32x wd_t = t3[1];
|
||||
u32x we_t = 0;
|
||||
u32x wf_t = pw_len * 8;
|
||||
|
||||
u32x a = SHA256M_A;
|
||||
u32x b = SHA256M_B;
|
||||
u32x c = SHA256M_C;
|
||||
u32x d = SHA256M_D;
|
||||
u32x e = SHA256M_E;
|
||||
u32x f = SHA256M_F;
|
||||
u32x g = SHA256M_G;
|
||||
u32x h = SHA256M_H;
|
||||
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
|
||||
|
||||
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
|
||||
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
|
||||
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
|
||||
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
|
||||
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
|
||||
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
|
||||
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
|
||||
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
|
||||
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
|
||||
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
|
||||
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
|
||||
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
|
||||
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
|
||||
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
|
||||
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
|
||||
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
|
||||
|
||||
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
|
||||
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
|
||||
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
|
||||
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
|
||||
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
|
||||
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
|
||||
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
|
||||
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
|
||||
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
|
||||
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
|
||||
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
|
||||
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
|
||||
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
|
||||
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
|
||||
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
|
||||
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
|
||||
|
||||
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
|
||||
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
|
||||
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
|
||||
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
|
||||
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
|
||||
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
|
||||
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
|
||||
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
|
||||
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
|
||||
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
|
||||
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
|
||||
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
|
||||
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
|
||||
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
|
||||
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
|
||||
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
|
||||
|
||||
COMPARE_M_SIMD (d, h, c, g);
|
||||
}
|
||||
}
|
||||
|
||||
DECLSPEC void m01470s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* digest
|
||||
*/
|
||||
|
||||
const u32 search[4] =
|
||||
{
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R0],
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R1],
|
||||
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];
|
||||
u32 e_rev = digests_buf[DIGESTS_OFFSET].digest_buf[4];
|
||||
u32 f_rev = digests_buf[DIGESTS_OFFSET].digest_buf[5];
|
||||
u32 g_rev = digests_buf[DIGESTS_OFFSET].digest_buf[6];
|
||||
u32 h_rev = digests_buf[DIGESTS_OFFSET].digest_buf[7];
|
||||
|
||||
SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
|
||||
SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
|
||||
SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
|
||||
SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
const u32 w0l = w0[0];
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
|
||||
{
|
||||
const u32x w0r = ix_create_bft (bfs_buf, il_pos);
|
||||
|
||||
const u32x w0lr = w0l | w0r;
|
||||
|
||||
u32x t0[4];
|
||||
u32x t1[4];
|
||||
u32x t2[4];
|
||||
u32x t3[4];
|
||||
|
||||
t0[0] = w0lr;
|
||||
t0[1] = w0[1];
|
||||
t0[2] = w0[2];
|
||||
t0[3] = w0[3];
|
||||
t1[0] = w1[0];
|
||||
t1[1] = w1[1];
|
||||
t1[2] = w1[2];
|
||||
t1[3] = w1[3];
|
||||
t2[0] = w2[0];
|
||||
t2[1] = w2[1];
|
||||
t2[2] = w2[2];
|
||||
t2[3] = w2[3];
|
||||
t3[0] = w3[0];
|
||||
t3[1] = w3[1];
|
||||
t3[2] = w3[2];
|
||||
t3[3] = w3[3];
|
||||
|
||||
/**
|
||||
* sha256
|
||||
*/
|
||||
|
||||
u32x w0_t = t0[0];
|
||||
u32x w1_t = t0[1];
|
||||
u32x w2_t = t0[2];
|
||||
u32x w3_t = t0[3];
|
||||
u32x w4_t = t1[0];
|
||||
u32x w5_t = t1[1];
|
||||
u32x w6_t = t1[2];
|
||||
u32x w7_t = t1[3];
|
||||
u32x w8_t = t2[0];
|
||||
u32x w9_t = t2[1];
|
||||
u32x wa_t = t2[2];
|
||||
u32x wb_t = t2[3];
|
||||
u32x wc_t = t3[0];
|
||||
u32x wd_t = t3[1];
|
||||
u32x we_t = 0;
|
||||
u32x wf_t = pw_len * 8;
|
||||
|
||||
u32x a = SHA256M_A;
|
||||
u32x b = SHA256M_B;
|
||||
u32x c = SHA256M_C;
|
||||
u32x d = SHA256M_D;
|
||||
u32x e = SHA256M_E;
|
||||
u32x f = SHA256M_F;
|
||||
u32x g = SHA256M_G;
|
||||
u32x h = SHA256M_H;
|
||||
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
|
||||
SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
|
||||
|
||||
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
|
||||
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
|
||||
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
|
||||
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
|
||||
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
|
||||
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
|
||||
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
|
||||
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
|
||||
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
|
||||
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
|
||||
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
|
||||
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
|
||||
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
|
||||
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
|
||||
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
|
||||
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
|
||||
|
||||
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
|
||||
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
|
||||
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
|
||||
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
|
||||
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
|
||||
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
|
||||
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
|
||||
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
|
||||
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
|
||||
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
|
||||
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
|
||||
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
|
||||
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
|
||||
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
|
||||
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
|
||||
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
|
||||
|
||||
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
|
||||
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
|
||||
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
|
||||
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
|
||||
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
|
||||
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
|
||||
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
|
||||
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
|
||||
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
|
||||
|
||||
if (MATCHES_NONE_VS (h, d_rev)) continue;
|
||||
|
||||
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
|
||||
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
|
||||
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
|
||||
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
|
||||
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
|
||||
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
|
||||
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
|
||||
|
||||
COMPARE_S_SIMD (d, h, c, g);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01470_m04 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
u32 w0[4];
|
||||
|
||||
w0[0] = pws[gid].i[ 0];
|
||||
w0[1] = pws[gid].i[ 1];
|
||||
w0[2] = pws[gid].i[ 2];
|
||||
w0[3] = pws[gid].i[ 3];
|
||||
|
||||
u32 w1[4];
|
||||
|
||||
w1[0] = 0;
|
||||
w1[1] = 0;
|
||||
w1[2] = 0;
|
||||
w1[3] = 0;
|
||||
|
||||
u32 w2[4];
|
||||
|
||||
w2[0] = 0;
|
||||
w2[1] = 0;
|
||||
w2[2] = 0;
|
||||
w2[3] = 0;
|
||||
|
||||
u32 w3[4];
|
||||
|
||||
w3[0] = 0;
|
||||
w3[1] = 0;
|
||||
w3[2] = 0;
|
||||
w3[3] = 0;
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m01470m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01470_m08 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
u32 w0[4];
|
||||
|
||||
w0[0] = pws[gid].i[ 0];
|
||||
w0[1] = pws[gid].i[ 1];
|
||||
w0[2] = pws[gid].i[ 2];
|
||||
w0[3] = pws[gid].i[ 3];
|
||||
|
||||
u32 w1[4];
|
||||
|
||||
w1[0] = pws[gid].i[ 4];
|
||||
w1[1] = pws[gid].i[ 5];
|
||||
w1[2] = pws[gid].i[ 6];
|
||||
w1[3] = pws[gid].i[ 7];
|
||||
|
||||
u32 w2[4];
|
||||
|
||||
w2[0] = 0;
|
||||
w2[1] = 0;
|
||||
w2[2] = 0;
|
||||
w2[3] = 0;
|
||||
|
||||
u32 w3[4];
|
||||
|
||||
w3[0] = 0;
|
||||
w3[1] = 0;
|
||||
w3[2] = 0;
|
||||
w3[3] = 0;
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m01470m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01470_m16 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
u32 w0[4];
|
||||
|
||||
w0[0] = pws[gid].i[ 0];
|
||||
w0[1] = pws[gid].i[ 1];
|
||||
w0[2] = pws[gid].i[ 2];
|
||||
w0[3] = pws[gid].i[ 3];
|
||||
|
||||
u32 w1[4];
|
||||
|
||||
w1[0] = pws[gid].i[ 4];
|
||||
w1[1] = pws[gid].i[ 5];
|
||||
w1[2] = pws[gid].i[ 6];
|
||||
w1[3] = pws[gid].i[ 7];
|
||||
|
||||
u32 w2[4];
|
||||
|
||||
w2[0] = pws[gid].i[ 8];
|
||||
w2[1] = pws[gid].i[ 9];
|
||||
w2[2] = pws[gid].i[10];
|
||||
w2[3] = pws[gid].i[11];
|
||||
|
||||
u32 w3[4];
|
||||
|
||||
w3[0] = pws[gid].i[12];
|
||||
w3[1] = pws[gid].i[13];
|
||||
w3[2] = 0;
|
||||
w3[3] = 0;
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m01470m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01470_s04 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
u32 w0[4];
|
||||
|
||||
w0[0] = pws[gid].i[ 0];
|
||||
w0[1] = pws[gid].i[ 1];
|
||||
w0[2] = pws[gid].i[ 2];
|
||||
w0[3] = pws[gid].i[ 3];
|
||||
|
||||
u32 w1[4];
|
||||
|
||||
w1[0] = 0;
|
||||
w1[1] = 0;
|
||||
w1[2] = 0;
|
||||
w1[3] = 0;
|
||||
|
||||
u32 w2[4];
|
||||
|
||||
w2[0] = 0;
|
||||
w2[1] = 0;
|
||||
w2[2] = 0;
|
||||
w2[3] = 0;
|
||||
|
||||
u32 w3[4];
|
||||
|
||||
w3[0] = 0;
|
||||
w3[1] = 0;
|
||||
w3[2] = 0;
|
||||
w3[3] = 0;
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m01470s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01470_s08 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
u32 w0[4];
|
||||
|
||||
w0[0] = pws[gid].i[ 0];
|
||||
w0[1] = pws[gid].i[ 1];
|
||||
w0[2] = pws[gid].i[ 2];
|
||||
w0[3] = pws[gid].i[ 3];
|
||||
|
||||
u32 w1[4];
|
||||
|
||||
w1[0] = pws[gid].i[ 4];
|
||||
w1[1] = pws[gid].i[ 5];
|
||||
w1[2] = pws[gid].i[ 6];
|
||||
w1[3] = pws[gid].i[ 7];
|
||||
|
||||
u32 w2[4];
|
||||
|
||||
w2[0] = 0;
|
||||
w2[1] = 0;
|
||||
w2[2] = 0;
|
||||
w2[3] = 0;
|
||||
|
||||
u32 w3[4];
|
||||
|
||||
w3[0] = 0;
|
||||
w3[1] = 0;
|
||||
w3[2] = 0;
|
||||
w3[3] = 0;
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m01470s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01470_s16 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
u32 w0[4];
|
||||
|
||||
w0[0] = pws[gid].i[ 0];
|
||||
w0[1] = pws[gid].i[ 1];
|
||||
w0[2] = pws[gid].i[ 2];
|
||||
w0[3] = pws[gid].i[ 3];
|
||||
|
||||
u32 w1[4];
|
||||
|
||||
w1[0] = pws[gid].i[ 4];
|
||||
w1[1] = pws[gid].i[ 5];
|
||||
w1[2] = pws[gid].i[ 6];
|
||||
w1[3] = pws[gid].i[ 7];
|
||||
|
||||
u32 w2[4];
|
||||
|
||||
w2[0] = pws[gid].i[ 8];
|
||||
w2[1] = pws[gid].i[ 9];
|
||||
w2[2] = pws[gid].i[10];
|
||||
w2[3] = pws[gid].i[11];
|
||||
|
||||
u32 w3[4];
|
||||
|
||||
w3[0] = pws[gid].i[12];
|
||||
w3[1] = pws[gid].i[13];
|
||||
w3[2] = 0;
|
||||
w3[3] = 0;
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m01470s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
@ -0,0 +1,145 @@
|
||||
/**
|
||||
* 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_sha256.cl"
|
||||
#endif
|
||||
|
||||
KERNEL_FQ void m01470_mxx (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
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];
|
||||
}
|
||||
|
||||
sha256_ctx_t ctx0;
|
||||
|
||||
sha256_init (&ctx0);
|
||||
|
||||
/**
|
||||
* 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;
|
||||
|
||||
sha256_ctx_vector_t ctx;
|
||||
|
||||
sha256_init_vector_from_scalar (&ctx, &ctx0);
|
||||
|
||||
sha256_update_vector_utf16beN (&ctx, w, pw_len);
|
||||
|
||||
sha256_final_vector (&ctx);
|
||||
|
||||
const u32x r0 = ctx.h[DGST_R0];
|
||||
const u32x r1 = ctx.h[DGST_R1];
|
||||
const u32x r2 = ctx.h[DGST_R2];
|
||||
const u32x r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_M_SIMD (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01470_sxx (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
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];
|
||||
}
|
||||
|
||||
sha256_ctx_t ctx0;
|
||||
|
||||
sha256_init (&ctx0);
|
||||
|
||||
/**
|
||||
* 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;
|
||||
|
||||
sha256_ctx_vector_t ctx;
|
||||
|
||||
sha256_init_vector_from_scalar (&ctx, &ctx0);
|
||||
|
||||
sha256_update_vector_utf16beN (&ctx, w, pw_len);
|
||||
|
||||
sha256_final_vector (&ctx);
|
||||
|
||||
const u32x r0 = ctx.h[DGST_R0];
|
||||
const u32x r1 = ctx.h[DGST_R1];
|
||||
const u32x r2 = ctx.h[DGST_R2];
|
||||
const u32x r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_S_SIMD (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
@ -0,0 +1,347 @@
|
||||
/**
|
||||
* 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_sha512.cl"
|
||||
#endif
|
||||
|
||||
DECLSPEC void sha512_transform_intern (const u32x *w0, const u32x *w1, const u32x *w2, const u32x *w3, u64x *digest)
|
||||
{
|
||||
u64x w0_t = hl32_to_64 (w0[0], w0[1]);
|
||||
u64x w1_t = hl32_to_64 (w0[2], w0[3]);
|
||||
u64x w2_t = hl32_to_64 (w1[0], w1[1]);
|
||||
u64x w3_t = hl32_to_64 (w1[2], w1[3]);
|
||||
u64x w4_t = hl32_to_64 (w2[0], w2[1]);
|
||||
u64x w5_t = hl32_to_64 (w2[2], w2[3]);
|
||||
u64x w6_t = hl32_to_64 (w3[0], w3[1]);
|
||||
u64x w7_t = 0;
|
||||
u64x w8_t = 0;
|
||||
u64x w9_t = 0;
|
||||
u64x wa_t = 0;
|
||||
u64x wb_t = 0;
|
||||
u64x wc_t = 0;
|
||||
u64x wd_t = 0;
|
||||
u64x we_t = 0;
|
||||
u64x wf_t = hl32_to_64 (w3[2], w3[3]);
|
||||
|
||||
u64x a = digest[0];
|
||||
u64x b = digest[1];
|
||||
u64x c = digest[2];
|
||||
u64x d = digest[3];
|
||||
u64x e = digest[4];
|
||||
u64x f = digest[5];
|
||||
u64x g = digest[6];
|
||||
u64x h = digest[7];
|
||||
|
||||
#define ROUND_EXPAND() \
|
||||
{ \
|
||||
w0_t = SHA512_EXPAND (we_t, w9_t, w1_t, w0_t); \
|
||||
w1_t = SHA512_EXPAND (wf_t, wa_t, w2_t, w1_t); \
|
||||
w2_t = SHA512_EXPAND (w0_t, wb_t, w3_t, w2_t); \
|
||||
w3_t = SHA512_EXPAND (w1_t, wc_t, w4_t, w3_t); \
|
||||
w4_t = SHA512_EXPAND (w2_t, wd_t, w5_t, w4_t); \
|
||||
w5_t = SHA512_EXPAND (w3_t, we_t, w6_t, w5_t); \
|
||||
w6_t = SHA512_EXPAND (w4_t, wf_t, w7_t, w6_t); \
|
||||
w7_t = SHA512_EXPAND (w5_t, w0_t, w8_t, w7_t); \
|
||||
w8_t = SHA512_EXPAND (w6_t, w1_t, w9_t, w8_t); \
|
||||
w9_t = SHA512_EXPAND (w7_t, w2_t, wa_t, w9_t); \
|
||||
wa_t = SHA512_EXPAND (w8_t, w3_t, wb_t, wa_t); \
|
||||
wb_t = SHA512_EXPAND (w9_t, w4_t, wc_t, wb_t); \
|
||||
wc_t = SHA512_EXPAND (wa_t, w5_t, wd_t, wc_t); \
|
||||
wd_t = SHA512_EXPAND (wb_t, w6_t, we_t, wd_t); \
|
||||
we_t = SHA512_EXPAND (wc_t, w7_t, wf_t, we_t); \
|
||||
wf_t = SHA512_EXPAND (wd_t, w8_t, w0_t, wf_t); \
|
||||
}
|
||||
|
||||
#define ROUND_STEP(i) \
|
||||
{ \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha512[i + 0]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha512[i + 1]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha512[i + 2]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha512[i + 3]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha512[i + 4]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha512[i + 5]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha512[i + 6]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha512[i + 7]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha512[i + 8]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha512[i + 9]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha512[i + 10]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha512[i + 11]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha512[i + 12]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha512[i + 13]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, we_t, k_sha512[i + 14]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha512[i + 15]); \
|
||||
}
|
||||
|
||||
ROUND_STEP (0);
|
||||
|
||||
#ifdef IS_CUDA
|
||||
ROUND_EXPAND (); ROUND_STEP (16);
|
||||
ROUND_EXPAND (); ROUND_STEP (32);
|
||||
ROUND_EXPAND (); ROUND_STEP (48);
|
||||
ROUND_EXPAND (); ROUND_STEP (64);
|
||||
#else
|
||||
#ifdef _unroll
|
||||
#pragma unroll
|
||||
#endif
|
||||
for (int i = 16; i < 80; i += 16)
|
||||
{
|
||||
ROUND_EXPAND (); ROUND_STEP (i);
|
||||
}
|
||||
#endif
|
||||
|
||||
/* rev
|
||||
digest[0] += a;
|
||||
digest[1] += b;
|
||||
digest[2] += c;
|
||||
digest[3] += d;
|
||||
digest[4] += e;
|
||||
digest[5] += f;
|
||||
digest[6] += g;
|
||||
digest[7] += h;
|
||||
*/
|
||||
|
||||
digest[0] = a;
|
||||
digest[1] = b;
|
||||
digest[2] = c;
|
||||
digest[3] = d;
|
||||
digest[4] = e;
|
||||
digest[5] = f;
|
||||
digest[6] = g;
|
||||
digest[7] = h;
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01770_m04 (KERN_ATTR_RULES ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
u32 pw_buf0[4];
|
||||
u32 pw_buf1[4];
|
||||
|
||||
pw_buf0[0] = pws[gid].i[0];
|
||||
pw_buf0[1] = pws[gid].i[1];
|
||||
pw_buf0[2] = pws[gid].i[2];
|
||||
pw_buf0[3] = pws[gid].i[3];
|
||||
pw_buf1[0] = pws[gid].i[4];
|
||||
pw_buf1[1] = pws[gid].i[5];
|
||||
pw_buf1[2] = pws[gid].i[6];
|
||||
pw_buf1[3] = pws[gid].i[7];
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* 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);
|
||||
|
||||
make_utf16le (w1, w2, w3);
|
||||
make_utf16le (w0, w0, w1);
|
||||
|
||||
const u32x out_len2 = out_len * 2;
|
||||
|
||||
append_0x80_4x4_VV (w0, w1, w2, w3, out_len2);
|
||||
|
||||
/**
|
||||
* sha512
|
||||
*/
|
||||
|
||||
u32x w0_t[4];
|
||||
u32x w1_t[4];
|
||||
u32x w2_t[4];
|
||||
u32x w3_t[4];
|
||||
|
||||
w0_t[0] = hc_swap32 (w0[0]);
|
||||
w0_t[1] = hc_swap32 (w0[1]);
|
||||
w0_t[2] = hc_swap32 (w0[2]);
|
||||
w0_t[3] = hc_swap32 (w0[3]);
|
||||
w1_t[0] = hc_swap32 (w1[0]);
|
||||
w1_t[1] = hc_swap32 (w1[1]);
|
||||
w1_t[2] = hc_swap32 (w1[2]);
|
||||
w1_t[3] = hc_swap32 (w1[3]);
|
||||
w2_t[0] = hc_swap32 (w2[0]);
|
||||
w2_t[1] = hc_swap32 (w2[1]);
|
||||
w2_t[2] = hc_swap32 (w2[2]);
|
||||
w2_t[3] = hc_swap32 (w2[3]);
|
||||
w3_t[0] = hc_swap32 (w3[0]);
|
||||
w3_t[1] = hc_swap32 (w3[1]);
|
||||
w3_t[2] = 0;
|
||||
w3_t[3] = out_len2 * 8;
|
||||
|
||||
u64x digest[8];
|
||||
|
||||
digest[0] = SHA512M_A;
|
||||
digest[1] = SHA512M_B;
|
||||
digest[2] = SHA512M_C;
|
||||
digest[3] = SHA512M_D;
|
||||
digest[4] = SHA512M_E;
|
||||
digest[5] = SHA512M_F;
|
||||
digest[6] = SHA512M_G;
|
||||
digest[7] = SHA512M_H;
|
||||
|
||||
sha512_transform_intern (w0_t, w1_t, w2_t, w3_t, digest);
|
||||
|
||||
const u32x r0 = l32_from_64 (digest[7]);
|
||||
const u32x r1 = h32_from_64 (digest[7]);
|
||||
const u32x r2 = l32_from_64 (digest[3]);
|
||||
const u32x r3 = h32_from_64 (digest[3]);
|
||||
|
||||
COMPARE_M_SIMD (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01770_m08 (KERN_ATTR_RULES ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01770_m16 (KERN_ATTR_RULES ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01770_s04 (KERN_ATTR_RULES ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
u32 pw_buf0[4];
|
||||
u32 pw_buf1[4];
|
||||
|
||||
pw_buf0[0] = pws[gid].i[0];
|
||||
pw_buf0[1] = pws[gid].i[1];
|
||||
pw_buf0[2] = pws[gid].i[2];
|
||||
pw_buf0[3] = pws[gid].i[3];
|
||||
pw_buf1[0] = pws[gid].i[4];
|
||||
pw_buf1[1] = pws[gid].i[5];
|
||||
pw_buf1[2] = pws[gid].i[6];
|
||||
pw_buf1[3] = pws[gid].i[7];
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* digest
|
||||
*/
|
||||
|
||||
const u32 search[4] =
|
||||
{
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R0],
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R1],
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R2],
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R3]
|
||||
};
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
|
||||
{
|
||||
u32x w0[4] = { 0 };
|
||||
u32x w1[4] = { 0 };
|
||||
u32x w2[4] = { 0 };
|
||||
u32x w3[4] = { 0 };
|
||||
|
||||
const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
|
||||
|
||||
make_utf16le (w1, w2, w3);
|
||||
make_utf16le (w0, w0, w1);
|
||||
|
||||
const u32x out_len2 = out_len * 2;
|
||||
|
||||
append_0x80_4x4_VV (w0, w1, w2, w3, out_len2);
|
||||
|
||||
/**
|
||||
* sha512
|
||||
*/
|
||||
|
||||
u32x w0_t[4];
|
||||
u32x w1_t[4];
|
||||
u32x w2_t[4];
|
||||
u32x w3_t[4];
|
||||
|
||||
w0_t[0] = hc_swap32 (w0[0]);
|
||||
w0_t[1] = hc_swap32 (w0[1]);
|
||||
w0_t[2] = hc_swap32 (w0[2]);
|
||||
w0_t[3] = hc_swap32 (w0[3]);
|
||||
w1_t[0] = hc_swap32 (w1[0]);
|
||||
w1_t[1] = hc_swap32 (w1[1]);
|
||||
w1_t[2] = hc_swap32 (w1[2]);
|
||||
w1_t[3] = hc_swap32 (w1[3]);
|
||||
w2_t[0] = hc_swap32 (w2[0]);
|
||||
w2_t[1] = hc_swap32 (w2[1]);
|
||||
w2_t[2] = hc_swap32 (w2[2]);
|
||||
w2_t[3] = hc_swap32 (w2[3]);
|
||||
w3_t[0] = hc_swap32 (w3[0]);
|
||||
w3_t[1] = hc_swap32 (w3[1]);
|
||||
w3_t[2] = 0;
|
||||
w3_t[3] = out_len2 * 8;
|
||||
|
||||
u64x digest[8];
|
||||
|
||||
digest[0] = SHA512M_A;
|
||||
digest[1] = SHA512M_B;
|
||||
digest[2] = SHA512M_C;
|
||||
digest[3] = SHA512M_D;
|
||||
digest[4] = SHA512M_E;
|
||||
digest[5] = SHA512M_F;
|
||||
digest[6] = SHA512M_G;
|
||||
digest[7] = SHA512M_H;
|
||||
|
||||
sha512_transform_intern (w0_t, w1_t, w2_t, w3_t, digest);
|
||||
|
||||
const u32x r0 = l32_from_64 (digest[7]);
|
||||
const u32x r1 = h32_from_64 (digest[7]);
|
||||
const u32x r2 = l32_from_64 (digest[3]);
|
||||
const u32x r3 = h32_from_64 (digest[3]);
|
||||
|
||||
COMPARE_S_SIMD (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01770_s08 (KERN_ATTR_RULES ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01770_s16 (KERN_ATTR_RULES ())
|
||||
{
|
||||
}
|
@ -0,0 +1,117 @@
|
||||
/**
|
||||
* 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_sha512.cl"
|
||||
#endif
|
||||
|
||||
KERNEL_FQ void m01770_mxx (KERN_ATTR_RULES ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
COPY_PW (pws[gid]);
|
||||
|
||||
/**
|
||||
* 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);
|
||||
|
||||
sha512_ctx_t ctx;
|
||||
|
||||
sha512_init (&ctx);
|
||||
|
||||
sha512_update_utf16le_swap (&ctx, tmp.i, tmp.pw_len);
|
||||
|
||||
sha512_final (&ctx);
|
||||
|
||||
const u32 r0 = l32_from_64_S (ctx.h[7]);
|
||||
const u32 r1 = h32_from_64_S (ctx.h[7]);
|
||||
const u32 r2 = l32_from_64_S (ctx.h[3]);
|
||||
const u32 r3 = h32_from_64_S (ctx.h[3]);
|
||||
|
||||
COMPARE_M_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01770_sxx (KERN_ATTR_RULES ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
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]);
|
||||
|
||||
/**
|
||||
* 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);
|
||||
|
||||
sha512_ctx_t ctx;
|
||||
|
||||
sha512_init (&ctx);
|
||||
|
||||
sha512_update_utf16le_swap (&ctx, tmp.i, tmp.pw_len);
|
||||
|
||||
sha512_final (&ctx);
|
||||
|
||||
const u32 r0 = l32_from_64_S (ctx.h[7]);
|
||||
const u32 r1 = h32_from_64_S (ctx.h[7]);
|
||||
const u32 r2 = l32_from_64_S (ctx.h[3]);
|
||||
const u32 r3 = h32_from_64_S (ctx.h[3]);
|
||||
|
||||
COMPARE_S_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
@ -0,0 +1,461 @@
|
||||
/**
|
||||
* 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_sha512.cl"
|
||||
#endif
|
||||
|
||||
DECLSPEC void sha512_transform_intern (const u32x *w0, const u32x *w1, const u32x *w2, const u32x *w3, u64x *digest)
|
||||
{
|
||||
u64x w0_t = hl32_to_64 (w0[0], w0[1]);
|
||||
u64x w1_t = hl32_to_64 (w0[2], w0[3]);
|
||||
u64x w2_t = hl32_to_64 (w1[0], w1[1]);
|
||||
u64x w3_t = hl32_to_64 (w1[2], w1[3]);
|
||||
u64x w4_t = hl32_to_64 (w2[0], w2[1]);
|
||||
u64x w5_t = hl32_to_64 (w2[2], w2[3]);
|
||||
u64x w6_t = hl32_to_64 (w3[0], w3[1]);
|
||||
u64x w7_t = 0;
|
||||
u64x w8_t = 0;
|
||||
u64x w9_t = 0;
|
||||
u64x wa_t = 0;
|
||||
u64x wb_t = 0;
|
||||
u64x wc_t = 0;
|
||||
u64x wd_t = 0;
|
||||
u64x we_t = 0;
|
||||
u64x wf_t = hl32_to_64 (w3[2], w3[3]);
|
||||
|
||||
u64x a = digest[0];
|
||||
u64x b = digest[1];
|
||||
u64x c = digest[2];
|
||||
u64x d = digest[3];
|
||||
u64x e = digest[4];
|
||||
u64x f = digest[5];
|
||||
u64x g = digest[6];
|
||||
u64x h = digest[7];
|
||||
|
||||
#define ROUND_EXPAND() \
|
||||
{ \
|
||||
w0_t = SHA512_EXPAND (we_t, w9_t, w1_t, w0_t); \
|
||||
w1_t = SHA512_EXPAND (wf_t, wa_t, w2_t, w1_t); \
|
||||
w2_t = SHA512_EXPAND (w0_t, wb_t, w3_t, w2_t); \
|
||||
w3_t = SHA512_EXPAND (w1_t, wc_t, w4_t, w3_t); \
|
||||
w4_t = SHA512_EXPAND (w2_t, wd_t, w5_t, w4_t); \
|
||||
w5_t = SHA512_EXPAND (w3_t, we_t, w6_t, w5_t); \
|
||||
w6_t = SHA512_EXPAND (w4_t, wf_t, w7_t, w6_t); \
|
||||
w7_t = SHA512_EXPAND (w5_t, w0_t, w8_t, w7_t); \
|
||||
w8_t = SHA512_EXPAND (w6_t, w1_t, w9_t, w8_t); \
|
||||
w9_t = SHA512_EXPAND (w7_t, w2_t, wa_t, w9_t); \
|
||||
wa_t = SHA512_EXPAND (w8_t, w3_t, wb_t, wa_t); \
|
||||
wb_t = SHA512_EXPAND (w9_t, w4_t, wc_t, wb_t); \
|
||||
wc_t = SHA512_EXPAND (wa_t, w5_t, wd_t, wc_t); \
|
||||
wd_t = SHA512_EXPAND (wb_t, w6_t, we_t, wd_t); \
|
||||
we_t = SHA512_EXPAND (wc_t, w7_t, wf_t, we_t); \
|
||||
wf_t = SHA512_EXPAND (wd_t, w8_t, w0_t, wf_t); \
|
||||
}
|
||||
|
||||
#define ROUND_STEP(i) \
|
||||
{ \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha512[i + 0]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha512[i + 1]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha512[i + 2]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha512[i + 3]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha512[i + 4]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha512[i + 5]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha512[i + 6]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha512[i + 7]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha512[i + 8]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha512[i + 9]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha512[i + 10]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha512[i + 11]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha512[i + 12]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha512[i + 13]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, we_t, k_sha512[i + 14]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha512[i + 15]); \
|
||||
}
|
||||
|
||||
ROUND_STEP (0);
|
||||
|
||||
#ifdef IS_CUDA
|
||||
ROUND_EXPAND (); ROUND_STEP (16);
|
||||
ROUND_EXPAND (); ROUND_STEP (32);
|
||||
ROUND_EXPAND (); ROUND_STEP (48);
|
||||
ROUND_EXPAND (); ROUND_STEP (64);
|
||||
#else
|
||||
#ifdef _unroll
|
||||
#pragma unroll
|
||||
#endif
|
||||
for (int i = 16; i < 80; i += 16)
|
||||
{
|
||||
ROUND_EXPAND (); ROUND_STEP (i);
|
||||
}
|
||||
#endif
|
||||
|
||||
/* rev
|
||||
digest[0] += a;
|
||||
digest[1] += b;
|
||||
digest[2] += c;
|
||||
digest[3] += d;
|
||||
digest[4] += e;
|
||||
digest[5] += f;
|
||||
digest[6] += g;
|
||||
digest[7] += h;
|
||||
*/
|
||||
|
||||
digest[0] = a;
|
||||
digest[1] = b;
|
||||
digest[2] = c;
|
||||
digest[3] = d;
|
||||
digest[4] = e;
|
||||
digest[5] = f;
|
||||
digest[6] = g;
|
||||
digest[7] = h;
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01770_m04 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
u32 pw_buf0[4];
|
||||
u32 pw_buf1[4];
|
||||
|
||||
pw_buf0[0] = pws[gid].i[0];
|
||||
pw_buf0[1] = pws[gid].i[1];
|
||||
pw_buf0[2] = pws[gid].i[2];
|
||||
pw_buf0[3] = pws[gid].i[3];
|
||||
pw_buf1[0] = pws[gid].i[4];
|
||||
pw_buf1[1] = pws[gid].i[5];
|
||||
pw_buf1[2] = pws[gid].i[6];
|
||||
pw_buf1[3] = pws[gid].i[7];
|
||||
|
||||
const u32 pw_l_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
|
||||
{
|
||||
const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
|
||||
|
||||
const u32x pw_len = (pw_l_len + pw_r_len) & 63;
|
||||
|
||||
/**
|
||||
* concat password candidate
|
||||
*/
|
||||
|
||||
u32x wordl0[4] = { 0 };
|
||||
u32x wordl1[4] = { 0 };
|
||||
u32x wordl2[4] = { 0 };
|
||||
u32x wordl3[4] = { 0 };
|
||||
|
||||
wordl0[0] = pw_buf0[0];
|
||||
wordl0[1] = pw_buf0[1];
|
||||
wordl0[2] = pw_buf0[2];
|
||||
wordl0[3] = pw_buf0[3];
|
||||
wordl1[0] = pw_buf1[0];
|
||||
wordl1[1] = pw_buf1[1];
|
||||
wordl1[2] = pw_buf1[2];
|
||||
wordl1[3] = pw_buf1[3];
|
||||
|
||||
u32x wordr0[4] = { 0 };
|
||||
u32x wordr1[4] = { 0 };
|
||||
u32x wordr2[4] = { 0 };
|
||||
u32x wordr3[4] = { 0 };
|
||||
|
||||
wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
|
||||
wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
|
||||
wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
|
||||
wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
|
||||
wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
|
||||
wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
|
||||
wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
|
||||
wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
|
||||
|
||||
if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
|
||||
{
|
||||
switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
|
||||
}
|
||||
else
|
||||
{
|
||||
switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
|
||||
}
|
||||
|
||||
u32x w0[4];
|
||||
u32x w1[4];
|
||||
u32x w2[4];
|
||||
u32x w3[4];
|
||||
|
||||
w0[0] = wordl0[0] | wordr0[0];
|
||||
w0[1] = wordl0[1] | wordr0[1];
|
||||
w0[2] = wordl0[2] | wordr0[2];
|
||||
w0[3] = wordl0[3] | wordr0[3];
|
||||
w1[0] = wordl1[0] | wordr1[0];
|
||||
w1[1] = wordl1[1] | wordr1[1];
|
||||
w1[2] = wordl1[2] | wordr1[2];
|
||||
w1[3] = wordl1[3] | wordr1[3];
|
||||
w2[0] = wordl2[0] | wordr2[0];
|
||||
w2[1] = wordl2[1] | wordr2[1];
|
||||
w2[2] = wordl2[2] | wordr2[2];
|
||||
w2[3] = wordl2[3] | wordr2[3];
|
||||
w3[0] = wordl3[0] | wordr3[0];
|
||||
w3[1] = wordl3[1] | wordr3[1];
|
||||
w3[2] = wordl3[2] | wordr3[2];
|
||||
w3[3] = wordl3[3] | wordr3[3];
|
||||
|
||||
make_utf16le (w1, w2, w3);
|
||||
make_utf16le (w0, w0, w1);
|
||||
|
||||
const u32x pw_len2 = pw_len * 2;
|
||||
|
||||
/**
|
||||
* sha512
|
||||
*/
|
||||
|
||||
u32x w0_t[4];
|
||||
u32x w1_t[4];
|
||||
u32x w2_t[4];
|
||||
u32x w3_t[4];
|
||||
|
||||
w0_t[0] = hc_swap32 (w0[0]);
|
||||
w0_t[1] = hc_swap32 (w0[1]);
|
||||
w0_t[2] = hc_swap32 (w0[2]);
|
||||
w0_t[3] = hc_swap32 (w0[3]);
|
||||
w1_t[0] = hc_swap32 (w1[0]);
|
||||
w1_t[1] = hc_swap32 (w1[1]);
|
||||
w1_t[2] = hc_swap32 (w1[2]);
|
||||
w1_t[3] = hc_swap32 (w1[3]);
|
||||
w2_t[0] = hc_swap32 (w2[0]);
|
||||
w2_t[1] = hc_swap32 (w2[1]);
|
||||
w2_t[2] = hc_swap32 (w2[2]);
|
||||
w2_t[3] = hc_swap32 (w2[3]);
|
||||
w3_t[0] = hc_swap32 (w3[0]);
|
||||
w3_t[1] = hc_swap32 (w3[1]);
|
||||
w3_t[2] = 0;
|
||||
w3_t[3] = pw_len2 * 8;
|
||||
|
||||
u64x digest[8];
|
||||
|
||||
digest[0] = SHA512M_A;
|
||||
digest[1] = SHA512M_B;
|
||||
digest[2] = SHA512M_C;
|
||||
digest[3] = SHA512M_D;
|
||||
digest[4] = SHA512M_E;
|
||||
digest[5] = SHA512M_F;
|
||||
digest[6] = SHA512M_G;
|
||||
digest[7] = SHA512M_H;
|
||||
|
||||
sha512_transform_intern (w0_t, w1_t, w2_t, w3_t, digest);
|
||||
|
||||
const u32x r0 = l32_from_64 (digest[7]);
|
||||
const u32x r1 = h32_from_64 (digest[7]);
|
||||
const u32x r2 = l32_from_64 (digest[3]);
|
||||
const u32x r3 = h32_from_64 (digest[3]);
|
||||
|
||||
COMPARE_M_SIMD (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01770_m08 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01770_m16 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01770_s04 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
u32 pw_buf0[4];
|
||||
u32 pw_buf1[4];
|
||||
|
||||
pw_buf0[0] = pws[gid].i[0];
|
||||
pw_buf0[1] = pws[gid].i[1];
|
||||
pw_buf0[2] = pws[gid].i[2];
|
||||
pw_buf0[3] = pws[gid].i[3];
|
||||
pw_buf1[0] = pws[gid].i[4];
|
||||
pw_buf1[1] = pws[gid].i[5];
|
||||
pw_buf1[2] = pws[gid].i[6];
|
||||
pw_buf1[3] = pws[gid].i[7];
|
||||
|
||||
const u32 pw_l_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* digest
|
||||
*/
|
||||
|
||||
const u32 search[4] =
|
||||
{
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R0],
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R1],
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R2],
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R3]
|
||||
};
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
|
||||
{
|
||||
const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
|
||||
|
||||
const u32x pw_len = (pw_l_len + pw_r_len) & 63;
|
||||
|
||||
/**
|
||||
* concat password candidate
|
||||
*/
|
||||
|
||||
u32x wordl0[4] = { 0 };
|
||||
u32x wordl1[4] = { 0 };
|
||||
u32x wordl2[4] = { 0 };
|
||||
u32x wordl3[4] = { 0 };
|
||||
|
||||
wordl0[0] = pw_buf0[0];
|
||||
wordl0[1] = pw_buf0[1];
|
||||
wordl0[2] = pw_buf0[2];
|
||||
wordl0[3] = pw_buf0[3];
|
||||
wordl1[0] = pw_buf1[0];
|
||||
wordl1[1] = pw_buf1[1];
|
||||
wordl1[2] = pw_buf1[2];
|
||||
wordl1[3] = pw_buf1[3];
|
||||
|
||||
u32x wordr0[4] = { 0 };
|
||||
u32x wordr1[4] = { 0 };
|
||||
u32x wordr2[4] = { 0 };
|
||||
u32x wordr3[4] = { 0 };
|
||||
|
||||
wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
|
||||
wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
|
||||
wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
|
||||
wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
|
||||
wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
|
||||
wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
|
||||
wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
|
||||
wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
|
||||
|
||||
if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
|
||||
{
|
||||
switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
|
||||
}
|
||||
else
|
||||
{
|
||||
switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
|
||||
}
|
||||
|
||||
u32x w0[4];
|
||||
u32x w1[4];
|
||||
u32x w2[4];
|
||||
u32x w3[4];
|
||||
|
||||
w0[0] = wordl0[0] | wordr0[0];
|
||||
w0[1] = wordl0[1] | wordr0[1];
|
||||
w0[2] = wordl0[2] | wordr0[2];
|
||||
w0[3] = wordl0[3] | wordr0[3];
|
||||
w1[0] = wordl1[0] | wordr1[0];
|
||||
w1[1] = wordl1[1] | wordr1[1];
|
||||
w1[2] = wordl1[2] | wordr1[2];
|
||||
w1[3] = wordl1[3] | wordr1[3];
|
||||
w2[0] = wordl2[0] | wordr2[0];
|
||||
w2[1] = wordl2[1] | wordr2[1];
|
||||
w2[2] = wordl2[2] | wordr2[2];
|
||||
w2[3] = wordl2[3] | wordr2[3];
|
||||
w3[0] = wordl3[0] | wordr3[0];
|
||||
w3[1] = wordl3[1] | wordr3[1];
|
||||
w3[2] = wordl3[2] | wordr3[2];
|
||||
w3[3] = wordl3[3] | wordr3[3];
|
||||
|
||||
make_utf16le (w1, w2, w3);
|
||||
make_utf16le (w0, w0, w1);
|
||||
|
||||
const u32x pw_len2 = pw_len * 2;
|
||||
|
||||
/**
|
||||
* sha512
|
||||
*/
|
||||
|
||||
u32x w0_t[4];
|
||||
u32x w1_t[4];
|
||||
u32x w2_t[4];
|
||||
u32x w3_t[4];
|
||||
|
||||
w0_t[0] = hc_swap32 (w0[0]);
|
||||
w0_t[1] = hc_swap32 (w0[1]);
|
||||
w0_t[2] = hc_swap32 (w0[2]);
|
||||
w0_t[3] = hc_swap32 (w0[3]);
|
||||
w1_t[0] = hc_swap32 (w1[0]);
|
||||
w1_t[1] = hc_swap32 (w1[1]);
|
||||
w1_t[2] = hc_swap32 (w1[2]);
|
||||
w1_t[3] = hc_swap32 (w1[3]);
|
||||
w2_t[0] = hc_swap32 (w2[0]);
|
||||
w2_t[1] = hc_swap32 (w2[1]);
|
||||
w2_t[2] = hc_swap32 (w2[2]);
|
||||
w2_t[3] = hc_swap32 (w2[3]);
|
||||
w3_t[0] = hc_swap32 (w3[0]);
|
||||
w3_t[1] = hc_swap32 (w3[1]);
|
||||
w3_t[2] = 0;
|
||||
w3_t[3] = pw_len2 * 8;
|
||||
|
||||
u64x digest[8];
|
||||
|
||||
digest[0] = SHA512M_A;
|
||||
digest[1] = SHA512M_B;
|
||||
digest[2] = SHA512M_C;
|
||||
digest[3] = SHA512M_D;
|
||||
digest[4] = SHA512M_E;
|
||||
digest[5] = SHA512M_F;
|
||||
digest[6] = SHA512M_G;
|
||||
digest[7] = SHA512M_H;
|
||||
|
||||
sha512_transform_intern (w0_t, w1_t, w2_t, w3_t, digest);
|
||||
|
||||
const u32x r0 = l32_from_64 (digest[7]);
|
||||
const u32x r1 = h32_from_64 (digest[7]);
|
||||
const u32x r2 = l32_from_64 (digest[3]);
|
||||
const u32x r3 = h32_from_64 (digest[3]);
|
||||
|
||||
COMPARE_S_SIMD (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01770_s08 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01770_s16 (KERN_ATTR_BASIC ())
|
||||
{
|
||||
}
|
@ -0,0 +1,111 @@
|
||||
/**
|
||||
* 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_sha512.cl"
|
||||
#endif
|
||||
|
||||
KERNEL_FQ void m01770_mxx (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
sha512_ctx_t ctx0;
|
||||
|
||||
sha512_init (&ctx0);
|
||||
|
||||
sha512_update_global_utf16le_swap (&ctx0, pws[gid].i, pws[gid].pw_len);
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
|
||||
{
|
||||
sha512_ctx_t ctx = ctx0;
|
||||
|
||||
sha512_update_global_utf16le_swap (&ctx, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
|
||||
|
||||
sha512_final (&ctx);
|
||||
|
||||
const u32 r0 = l32_from_64_S (ctx.h[7]);
|
||||
const u32 r1 = h32_from_64_S (ctx.h[7]);
|
||||
const u32 r2 = l32_from_64_S (ctx.h[3]);
|
||||
const u32 r3 = h32_from_64_S (ctx.h[3]);
|
||||
|
||||
COMPARE_M_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01770_sxx (KERN_ATTR_BASIC ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 lid = get_local_id (0);
|
||||
const u64 gid = get_global_id (0);
|
||||
|
||||
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
|
||||
*/
|
||||
|
||||
sha512_ctx_t ctx0;
|
||||
|
||||
sha512_init (&ctx0);
|
||||
|
||||
sha512_update_global_utf16le_swap (&ctx0, pws[gid].i, pws[gid].pw_len);
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
|
||||
{
|
||||
sha512_ctx_t ctx = ctx0;
|
||||
|
||||
sha512_update_global_utf16le_swap (&ctx, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
|
||||
|
||||
sha512_final (&ctx);
|
||||
|
||||
const u32 r0 = l32_from_64_S (ctx.h[7]);
|
||||
const u32 r1 = h32_from_64_S (ctx.h[7]);
|
||||
const u32 r2 = l32_from_64_S (ctx.h[3]);
|
||||
const u32 r3 = h32_from_64_S (ctx.h[3]);
|
||||
|
||||
COMPARE_S_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
@ -0,0 +1,493 @@
|
||||
/**
|
||||
* 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_sha512.cl"
|
||||
#endif
|
||||
|
||||
DECLSPEC void sha512_transform_intern (const u32x *w0, const u32x *w1, const u32x *w2, const u32x *w3, u64x *digest)
|
||||
{
|
||||
u64x w0_t = hl32_to_64 (w0[0], w0[1]);
|
||||
u64x w1_t = hl32_to_64 (w0[2], w0[3]);
|
||||
u64x w2_t = hl32_to_64 (w1[0], w1[1]);
|
||||
u64x w3_t = hl32_to_64 (w1[2], w1[3]);
|
||||
u64x w4_t = hl32_to_64 (w2[0], w2[1]);
|
||||
u64x w5_t = hl32_to_64 (w2[2], w2[3]);
|
||||
u64x w6_t = hl32_to_64 (w3[0], w3[1]);
|
||||
u64x w7_t = 0;
|
||||
u64x w8_t = 0;
|
||||
u64x w9_t = 0;
|
||||
u64x wa_t = 0;
|
||||
u64x wb_t = 0;
|
||||
u64x wc_t = 0;
|
||||
u64x wd_t = 0;
|
||||
u64x we_t = 0;
|
||||
u64x wf_t = hl32_to_64 (w3[2], w3[3]);
|
||||
|
||||
u64x a = digest[0];
|
||||
u64x b = digest[1];
|
||||
u64x c = digest[2];
|
||||
u64x d = digest[3];
|
||||
u64x e = digest[4];
|
||||
u64x f = digest[5];
|
||||
u64x g = digest[6];
|
||||
u64x h = digest[7];
|
||||
|
||||
#define ROUND_EXPAND() \
|
||||
{ \
|
||||
w0_t = SHA512_EXPAND (we_t, w9_t, w1_t, w0_t); \
|
||||
w1_t = SHA512_EXPAND (wf_t, wa_t, w2_t, w1_t); \
|
||||
w2_t = SHA512_EXPAND (w0_t, wb_t, w3_t, w2_t); \
|
||||
w3_t = SHA512_EXPAND (w1_t, wc_t, w4_t, w3_t); \
|
||||
w4_t = SHA512_EXPAND (w2_t, wd_t, w5_t, w4_t); \
|
||||
w5_t = SHA512_EXPAND (w3_t, we_t, w6_t, w5_t); \
|
||||
w6_t = SHA512_EXPAND (w4_t, wf_t, w7_t, w6_t); \
|
||||
w7_t = SHA512_EXPAND (w5_t, w0_t, w8_t, w7_t); \
|
||||
w8_t = SHA512_EXPAND (w6_t, w1_t, w9_t, w8_t); \
|
||||
w9_t = SHA512_EXPAND (w7_t, w2_t, wa_t, w9_t); \
|
||||
wa_t = SHA512_EXPAND (w8_t, w3_t, wb_t, wa_t); \
|
||||
wb_t = SHA512_EXPAND (w9_t, w4_t, wc_t, wb_t); \
|
||||
wc_t = SHA512_EXPAND (wa_t, w5_t, wd_t, wc_t); \
|
||||
wd_t = SHA512_EXPAND (wb_t, w6_t, we_t, wd_t); \
|
||||
we_t = SHA512_EXPAND (wc_t, w7_t, wf_t, we_t); \
|
||||
wf_t = SHA512_EXPAND (wd_t, w8_t, w0_t, wf_t); \
|
||||
}
|
||||
|
||||
#define ROUND_STEP(i) \
|
||||
{ \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha512[i + 0]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha512[i + 1]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha512[i + 2]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha512[i + 3]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha512[i + 4]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha512[i + 5]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha512[i + 6]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha512[i + 7]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha512[i + 8]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha512[i + 9]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha512[i + 10]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha512[i + 11]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha512[i + 12]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha512[i + 13]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, we_t, k_sha512[i + 14]); \
|
||||
SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha512[i + 15]); \
|
||||
}
|
||||
|
||||
ROUND_STEP (0);
|
||||
|
||||
#ifdef IS_CUDA
|
||||
ROUND_EXPAND (); ROUND_STEP (16);
|
||||
ROUND_EXPAND (); ROUND_STEP (32);
|
||||
ROUND_EXPAND (); ROUND_STEP (48);
|
||||
ROUND_EXPAND (); ROUND_STEP (64);
|
||||
#else
|
||||
#ifdef _unroll
|
||||
#pragma unroll
|
||||
#endif
|
||||
for (int i = 16; i < 80; i += 16)
|
||||
{
|
||||
ROUND_EXPAND (); ROUND_STEP (i);
|
||||
}
|
||||
#endif
|
||||
|
||||
/* rev
|
||||
digest[0] += a;
|
||||
digest[1] += b;
|
||||
digest[2] += c;
|
||||
digest[3] += d;
|
||||
digest[4] += e;
|
||||
digest[5] += f;
|
||||
digest[6] += g;
|
||||
digest[7] += h;
|
||||
*/
|
||||
|
||||
digest[0] = a;
|
||||
digest[1] = b;
|
||||
digest[2] = c;
|
||||
digest[3] = d;
|
||||
digest[4] = e;
|
||||
digest[5] = f;
|
||||
digest[6] = g;
|
||||
digest[7] = h;
|
||||
}
|
||||
|
||||
DECLSPEC void m01770m (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
w[15] = pw_len * 8;
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
u32 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;
|
||||
|
||||
u32x w0_t[4];
|
||||
u32x w1_t[4];
|
||||
u32x w2_t[4];
|
||||
u32x w3_t[4];
|
||||
|
||||
w0_t[0] = w0;
|
||||
w0_t[1] = w[ 1];
|
||||
w0_t[2] = w[ 2];
|
||||
w0_t[3] = w[ 3];
|
||||
w1_t[0] = w[ 4];
|
||||
w1_t[1] = w[ 5];
|
||||
w1_t[2] = w[ 6];
|
||||
w1_t[3] = w[ 7];
|
||||
w2_t[0] = w[ 8];
|
||||
w2_t[1] = w[ 9];
|
||||
w2_t[2] = w[10];
|
||||
w2_t[3] = w[11];
|
||||
w3_t[0] = w[12];
|
||||
w3_t[1] = w[13];
|
||||
w3_t[2] = w[14];
|
||||
w3_t[3] = w[15];
|
||||
|
||||
u64x digest[8];
|
||||
|
||||
digest[0] = SHA512M_A;
|
||||
digest[1] = SHA512M_B;
|
||||
digest[2] = SHA512M_C;
|
||||
digest[3] = SHA512M_D;
|
||||
digest[4] = SHA512M_E;
|
||||
digest[5] = SHA512M_F;
|
||||
digest[6] = SHA512M_G;
|
||||
digest[7] = SHA512M_H;
|
||||
|
||||
sha512_transform_intern (w0_t, w1_t, w2_t, w3_t, digest);
|
||||
|
||||
const u32x r0 = l32_from_64 (digest[7]);
|
||||
const u32x r1 = h32_from_64 (digest[7]);
|
||||
const u32x r2 = l32_from_64 (digest[3]);
|
||||
const u32x r3 = h32_from_64 (digest[3]);
|
||||
|
||||
COMPARE_M_SIMD (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
|
||||
DECLSPEC void m01770s (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u64 gid = get_global_id (0);
|
||||
const u64 lid = get_local_id (0);
|
||||
|
||||
/**
|
||||
* digest
|
||||
*/
|
||||
|
||||
const u32 search[4] =
|
||||
{
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R0],
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R1],
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R2],
|
||||
digests_buf[DIGESTS_OFFSET].digest_buf[DGST_R3]
|
||||
};
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
u32 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;
|
||||
|
||||
u32x w0_t[4];
|
||||
u32x w1_t[4];
|
||||
u32x w2_t[4];
|
||||
u32x w3_t[4];
|
||||
|
||||
w0_t[0] = w0;
|
||||
w0_t[1] = w[ 1];
|
||||
w0_t[2] = w[ 2];
|
||||
w0_t[3] = w[ 3];
|
||||
w1_t[0] = w[ 4];
|
||||
w1_t[1] = w[ 5];
|
||||
w1_t[2] = w[ 6];
|
||||
w1_t[3] = w[ 7];
|
||||
w2_t[0] = w[ 8];
|
||||
w2_t[1] = w[ 9];
|
||||
w2_t[2] = w[10];
|
||||
w2_t[3] = w[11];
|
||||
w3_t[0] = w[12];
|
||||
w3_t[1] = w[13];
|
||||
w3_t[2] = w[14];
|
||||
w3_t[3] = w[15];
|
||||
|
||||
u64x digest[8];
|
||||
|
||||
digest[0] = SHA512M_A;
|
||||
digest[1] = SHA512M_B;
|
||||
digest[2] = SHA512M_C;
|
||||
digest[3] = SHA512M_D;
|
||||
digest[4] = SHA512M_E;
|
||||
digest[5] = SHA512M_F;
|
||||
digest[6] = SHA512M_G;
|
||||
digest[7] = SHA512M_H;
|
||||
|
||||
sha512_transform_intern (w0_t, w1_t, w2_t, w3_t, digest);
|
||||
|
||||
const u32x r0 = l32_from_64 (digest[7]);
|
||||
const u32x r1 = h32_from_64 (digest[7]);
|
||||
const u32x r2 = l32_from_64 (digest[3]);
|
||||
const u32x r3 = h32_from_64 (digest[3]);
|
||||
|
||||
COMPARE_S_SIMD (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01770_m04 (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 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] = 0;
|
||||
w[15] = pws[gid].i[15];
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m01770m (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01770_m08 (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 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] = 0;
|
||||
w[15] = pws[gid].i[15];
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m01770m (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01770_m16 (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 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 & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m01770m (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01770_s04 (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 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] = 0;
|
||||
w[15] = pws[gid].i[15];
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m01770s (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01770_s08 (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 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] = 0;
|
||||
w[15] = pws[gid].i[15];
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m01770s (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
||||
|
||||
KERNEL_FQ void m01770_s16 (KERN_ATTR_VECTOR ())
|
||||
{
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u64 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 & 63;
|
||||
|
||||
/**
|
||||
* main
|
||||
*/
|
||||
|
||||
m01770s (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_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, SALT_POS, loop_pos, loop_cnt, il_cnt, digests_cnt, DIGESTS_OFFSET, combs_mode, salt_repeat, pws_pos, gid_max);
|
||||
}
|
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in new issue