Page 1 of 1
Posted: Sat May 01, 2010 9:28 pm
oclHashcat is a free gpu supported hashcracking tool.
* Linux & Windows native binaries
* Uses OpenCL
* Fastest multihash MD5 cracker on NVidia cards
* Fastest multihash MD5 cracker on ATI 5xxx cards
* Supports wordlists (not limited to Brute-Force / Mask-Attack)
* Can mix wordlists with Mask-Attack to emulate Hybrid-Attacks
* Runs very cautious, you can still watch movies while cracking
* Number of workload can be configured (like -n in hashcat)
* Supports pause / resume
* Supports huge numbers of hashes (4 million and more)
* Able to work in a distributed environment
* Includes hashcats entire rule engine to modify wordlists on start
* ... and much more
* Windows XP 32bit
* Windows XP 64bit
* Windows Vista 64bit
* Windows 7 64bit
* Debian Lenny 32bit
* Ubuntu 9.02 64bit
* Ubuntu 9.10 64bit
Check the website to download it:
Posted: Sun May 02, 2010 3:13 pm
Nice work, looks great
Posted: Sun May 02, 2010 4:05 pm
1520-1600 Mhashes/s with ighashgpu v0.70.48.4
1980-2030 Mhashes/s with oclHashcat 0.18
according to speed that the softwares are stating with huge charset (108 chars) on 66.6k MD5 hashes on a o/c HD5970 (875/1225). Only bruteforce 8-8 - no Wordlist....
And ighashgpu uses GPU @ 90-98% on both GPUs - oclHashcat only 50-60 and 80-95% on the GPUs
But one bad thing: It seems it can't resume
(i mean after reboot or so) on this type of attack... so not useable for me until now. But maybe in 16 Days when my 8-8 job is done and i start with 9-9 a better Version is out.
here parameters i use:
ighashgpu.exe -uf:charset.txt -min:8 -max:8 -t:md5 -sf:"XKK'?e~/" hashes.txt
oclHashcat.exe -n 80 hashes.txt --custom-mask1=?s?u?d?säöüßÄÖÜ€§²³£© ?1?1?1?1 ?1?1?1?1?1
the strange thing is: that its 108 vs 109 chars.
according to --help ?s should be 33 chars. But it uses 34...
strange... what is the not shown char?
And after reboot and updates oclHashcat is even faster
But GPU usage is still going very much up and down and is overall not much..
Posted: Mon May 03, 2010 5:26 am
Could someone bench it on single hash on CUDA on some GTX2xx and compare to latest BarsWF?
Posted: Mon May 03, 2010 8:36 am
BarsWF is faster
Posted: Mon May 03, 2010 3:09 pm
BarsWF is faster
Need some numbers
I am in army and can't bench by myself (just 2.5 more weeks)
8800-9800GT would be fine too
Posted: Mon May 03, 2010 7:35 pm
Why such speed? Reversing isnt implemented in oclhc. It does not use CPU(only allowed on ATI/AMD with SSE3 enabled CPUs). It's not compiled with ICL.
It's a great tool for professionals.
Posted: Mon May 03, 2010 7:53 pm
Impressive, though I question the CUDA-Multiforcer compare - if you're using 0.7, I think the autotuner is broken (so non-optimal block/thread sizes are being used), and you should probably be using the '-l' switch for 500k MD5 hashes, as it improves speed on large hashlists dramatically. I may test it out if I feel like it, but I feel the comparison is not quite valid.
Posted: Tue May 04, 2010 4:43 am
Thanks for the bench.
I agree that it is very useful for real-world tasks.
Posted: Thu May 06, 2010 11:07 am
Updated to Catalyst 10.4
Now new Values.
ighasgpu is going very much up and down. (in this Version no more average speed but actual). Most time at 2700-2900 MHashes/s, but then every 4-8 Curspd Updates a dropin to 1000-1500 MHashes/s. (old 0.62 Version has around AVG 2300 MHashes/s after about 2 Minutes)
But over all i think both have now the same Speed @ around 2800 (!!!!) MHashes/s - I'm very very happy about the new speeds. now the 5970 is pretty as fast as i expected when i bought it.
Posted: Thu Jan 20, 2011 8:00 pm
The last version of hashcat is oclHashcat v0.24
changes v0.23 -> v0.24
Code: Select all
NVidia 8800gt, % applies to MD5
2 hashes: v0.23 = 302.9M/s, v0.24 = 311.3M/s
500.000 hashes: v0.23 = 295.6M/s, v0.24 = 302.5M/s
NVidia gtx465, % applies to SHA-1
2 hashes: v0.23 = 376.9M/s, v0.24 = 430.3M/s
500.000 hashes: v0.23 = 366.8M/s, v0.24 = 418.3M/s
It supports the following algorithms:
* Domain Cached Credentials
You can downlaod it here:
Posted: Mon Feb 21, 2011 4:17 pm
New update. World record for all listed algorithms.