Cracking one billion passwords per second with NVIDIA video cards
The new release of Elcomsoft Distributed Password Recovery reaches the recovery speed of one billion passwords per second by employing several NVIDIA video accelerators. Today’s video cards such as NVIDIA GeForce GTX280 can process hundreds of billions fixed-point calculations per second. Add as much as 1 GB of onboard video memory and up to 240 processing units, multiply it by two by using a couple of NVIDIA cards, and enter the whole new world of super-parallel computational power for just a few hundred dollars. Unlike NVIDIA SLI mode, ElcomSoft has figured out how to unleash the computational power of several NVIDIA cards no matter whether or not they are of the same kind.
Until recently, the abundance of highly parallel, super-scalar processors in 3D graphic accelerators could only be used for gaming. Today, ElcomSoft has found a way to reach into the future. The company has figured out how to put computational power provided by several NVIDIA boards working together to crack many kinds of passwords.
In February 2007, NVIDIA launched CUDA, a developer’s kit that gives software developers access to the parallel processing power of the GPU. Modern NVIDIA GPUs act as powerful, highly parallel multiprocessors, with huge shared memory and cache.
Elcomsoft Distributed Password Recovery can recover a variety of system passwords such as NTLM and startup passwords, crack MD5 hashes, unlock password-protected documents created by Microsoft Office 97-2007, PDF files created by Adobe Acrobat, as well as PGP and UNIX and Oracle user passwords. With the newest GPU acceleration upgrade of Elcomsoft Distributed Password Recovery the passwords will be recovered up to 25 times faster than by using CPU-only mode.