XSHA1 Reverser 1.1 - Tue, 17 Jan 2012 07:45:15 UTC
XSHA1 Reverser 1.1
Version 1.1 is out and has a huge speed increase almost 7 times faster than version 1.0.1. Also I basically removed the rate limit for the online version.
XSHA1 Reverser 1.0.1 - Fri, 13 Jan 2012 01:37:40 UTC
XSHA1 Reverser 1.0.1
Found and fixed two bugs while making it around 4 times faster (not done yet). This is just a bug fix release. Minor bug with -f|--output-not-found and half of all 13-16 character passwords (-c|--characters=16) and half of all 17-20 character passwords (-c|--characters=20) were not found because of copy and paste error with the mask in functions finishRev16() and finishRev20() in xsha1help.cpp.
XSHA1 Reverser 1.0 - Fri, 6 Jan 2012 01:56:43 UTC
XSHA1 Reverser 1.0
Reverses XSHA1 hashes of up to 16 character passwords in 0.1 second and up to 20 characters in 3.3 seconds. Now with friendly arguments. For people using Linux, if you want to use AVX or XOP you will need to compile it with a new-ish compiler like GCC 4.6.1. I only have GCC 4.4.4 :(.
XSHA1 Reverser 0.1 - Sat, 17 Dec 2011 02:16:03 UTC
XSHA1 Reverser 0.1
Here's the program and code for reversing XSHA1 hashes of up to 16 character passwords in 0.1 second and up to 20 characters in 10.8 seconds (right that's why I don't have benchmarks using SSE2 the function xsha1Reverse_20_sse2() has a bug that I never fixed. So don't modify the code to use that function instead use xsha1_rev_20() since that works but is slower).
DP Info (beta) - Sat, 17 Dec 2011 02:00:41 UTC
I've been working on DP stuff and I thought I'd share some results. It's going to be an interesting week... Hopefully. Also I moved the old beta (Rainbow table benchmark) to tools if you were wondering where that went.
Advanced RT Calc Updated - Fri, 18 Nov 2011 01:10:39 UTC
Advanced RT Calc
Added step generation, optimized for imperfect tables for IRT, support for imperfect tables for IPRT (I should really change that name since P stands for perfect... "DIRT" Destructive Indexed RT [maybe]), and calculations for the expected time spent checking for false alarms. Also fixed a few minor bugs.
Reverse XSHA1 to 0-16 Characters - Tue, 25 Oct 2011 04:59:15 UTC
Reverse XSHA1 to 0-16 characters in one second. I'll remove the rate limit once the SSE2 version is done. Hoping for 30 ms (+40 ms to launch a program). I need to find out how to make a PHP plugin.

10.8 seconds for 0-20 characters.
Guessing about an hour for 0-24 characters.
RT Benchmark (Now compiles with GCC 4.6.1) - Fri, 30 Sep 2011 00:16:01 UTC
RT benchmark

Took like 16 hours to compile GCC 4.6.1. I found another compiler bug this time in GCC, "static list<listHash*> s_hashes" didn't get initialized before hash classes started calling registerHash(). Hmmm "listHash" is probably the worst name I used it should really be "hashInfo". Anyway I got the benchmark to compile in GCC. Apparently GCC is better at optimizing the reduction function (9.5 - 10 MReduxes/s vs 7.4 - 8 MReduxes/s). Also hashing algorithms got a speed increase except SHA1 and MySQLSHA1, but overall links/second is higher in all cases.
RT Benchmark - Wed, 28 Sep 2011 04:09:55 UTC
RT benchmark

Core2Quad Q9300 2.5 GHz (one 32 bit thread):
Auto selects scalar, SSE2, SSSE3 (only for SHA1), AVX, or AVX_XOP.
Core2Quad Q9300 2.5 GHz (one 32 bit thread):
Cisco              5.64 MLinks/sec  7.48 MReduxes/sec  25.30 MHashes/sec [3xSSE2]
MD5                5.65 MLinks/sec  7.35 MReduxes/sec  26.13 MHashes/sec [3xSSE2]
Double Binary MD5  4.57 MLinks/sec  7.36 MReduxes/sec  12.95 MHashes/sec [3xSSE2]
Double MD5         4.54 MLinks/sec  7.40 MReduxes/sec  12.22 MHashes/sec [3xSSE2]
MD4/NTLM           6.07 MLinks/sec  7.40 MReduxes/sec  39.63 MHashes/sec [4xSSE2]
SHA1               4.54 MLinks/sec  8.00 MReduxes/sec  12.79 MHashes/sec [1xSSSE3]
MySQLSHA1/MySQL5   3.34 MLinks/sec  7.92 MReduxes/sec   6.35 MHashes/sec [1xSSSE3]
There's a simple speed up by just commenting out code in keyspace.cpp for ((m_charaterEncoding & (CE_UTF16_LE | CE_UTF16_BE)) != 0) and ((m_charaterEncoding & (CE_UTF32_LE | CE_UTF32_BE)) != 0) but then NTLM will break. Next update will have a few changes for speeding up the reduction function such as three classes keyspace8, keyspace16, and keyspace32. Also needs variable length character support for UTF-8 and UTF-16. The key space used for benchmarking is loweralpha#1-7. This code can use key spaces such as Omni-6.
Hash Benchmark :( I don't have AVX - Thu, 22 Sep 2011 20:48:50 UTC
Hash benchmark
These are all full hash functions for use with RTs and LHTs.

Core2Quad Q9300 2.5 GHz (one 32 bit thread):
Auto selects scalar, SSE2, SSSE3 (only for SHA1), AVX, or AVX_XOP.
                                               (WinRTGen speed info)
Cisco              [3xSSE2]  25.26 MHashes/sec (5.46x; 4.628 MHashes/sec)
MD5                [3xSSE2]  26.14 MHashes/sec (4.65x; 5.618 MHashes/sec)
Double Binary MD5  [3xSSE2]  12.90 MHashes/sec
Double MD5         [3xSSE2]  12.29 MHashes/sec
MD4/NTLM           [4xSSE2]  39.60 MHashes/sec (5.94x/10.88x; 6.667 MHashes/sec/3.641 MHashes/sec)
SHA1               [1xSSSE3] 12.82 MHashes/sec (5.38x; 2.383 MHashes/sec)
MySQLSHA1/MySQL5   [1xSSSE3]  6.37 MHashes/sec (3.52x; 1.810 MHashes/sec)
This is 3.52x to 10.88x (average 5.97x) faster than WinRTGen's hash speed. This is a little misleading since there's the reduction function. Hopefully it will have a link speed that is at least 2 times faster.
1 2 3 4