We’ve recently updated Elcomsoft Distributed Password Recovery, adding enhanced GPU-assisted recovery for many supported formats. In a word, the new release adds GPU-accelerated recovery for OS X keychain, triples BitLocker recovery speeds, improves W-Fi password recovery and enhances GPU acceleration support for Internet Key Exchange (IKE).
Posts Tagged ‘Nvidia’
Elcomsoft Distributed Password Recovery Updated with OS X Keychain Support and Enhanced GPU AccelerationThursday, November 26th, 2015
If you care about password cracking, hardware acceleration or Wi-Fi protection this interview with our friend Sethioz is certainly for you. Being currently a freelance security tester Sethioz kindly shared his experience in cracking passwords using video cards, which in its turn derived from his gaming interest in cards. His personal experience may be very helpful to those whose concern about password cracking is not trivial.
How did it all start or what was the reason to try to find a Wi-Fi password?
There is no short answer to this, if there would be, I guess it would be “curiosity”. I think I got my first computer somewhere in 2002-2003 (my own PC) and ever since I’ve been interested in everything that is not “normal”, such as reverse engineering, debugging, hacking games, cracking password etc. (more…)
We have just released a long-awaited update to one of our flagship products, Elcomsoft Distributed Password Recovery. While you can learn more about what’s been added and changed from our official announcement, in this post we’d like to share some insight about the path we took to design this update. (more…)
Elcomsoft Phone Breaker Update: Improved iCloud Acquisition, Two-Factor Authentication and Stronger Brute ForceWednesday, December 17th, 2014
We are excited to announce an update to one of our oldest mobile forensic tools, Elcomsoft Phone Breaker. In this release we mostly targeted iCloud acquisition, although we’ve made some changes to the password recovery algorithm targeting iOS offline backups. All in all, the new tool can be used under a wider range of circumstances, squeezes more juice of your existing acceleration hardware and adds support for newest and greatest AMD and NVIDIA boards.
We have just updated Advanced Office Password Recovery and Distributed Password Recovery with NVIDIA Tesla K20 support, enabling world’s fastest password recovery with NVIDIA’s latest supercomputing platform. Elcomsoft Advanced Office Password Recovery removes document restrictions and recovers passwords protecting Microsoft Office documents, while Elcomsoft Distributed Password Recovery can quickly break a wide range of passwords on multiple workstations with near zero scalability overhead.
GPU-accelerated password recovery dramatically reduces the time required to break long and complex passwords, offering more than 20-fold performance gain over CPU-only operations (compared to a quad-core Intel i7 CPU). NVIDIA’s latest Tesla K20 platform further increases the performance, delivering a nearly 1.5x performance increase compared to the use of a dual-core NVIDIA GeForce GTX 690 board.
A workstation equipped with an NVIDIA Tesla K20 unit can crunch as many as 27500 Office 2007 passwords per second, or 13500 passwords per second in the case of Microsoft Office 2010. In comparison, the next-best solution, a dual-core GeForce GTX 690 board, can try some 19000 Office 2007 or 9000 Office 2010 passwords per second.
The updated Elcomsoft Advanced Office Password Recovery and Elcomsoft Distributed Password Recovery now fully support the latest NVIDIA supercomputing hardware, enabling users to gain unrestricted access to many types of documents in far less time.
ElcomSoft has recently announced the switch to OpenCL, an open cross-platform architecture offering universal, future-proof accessibility to a wide range of acceleration hardware. We’re actively using GPU acceleration for breaking passwords faster. No issues with NVIDIA hardware, but working with AMD devices has always been a trouble.
So we jumped in, embedding OpenCL support into Elcomsoft Phone Password Breaker and Wireless Security Auditor. As an immediate benefit, we were able to add long-awaited support for AMD’s latest generation of graphic accelerators, the AMD Radeon™ HD 7000 Series currently including AMD Radeon™ HD 7750, 7770, 7950, and 7970 models. Headache-free support for future generations of acceleration hardware is icing on the cake.
After switching to OpenCL, we further optimized acceleration code for AMD hardware, squeezing up to 50% more speed out of the same boards. This isn’t something to sniff at, as even a few per cents of performance can save hours when breaking long, complex passwords.
OpenCL vs. CUDA
AMD goes OpenCL. What about NVIDIA? Technically, we could have handled NVIDIA accelerators the same way, via OpenCL (it’s a cross-platform architecture, remember?) In that case, we would be getting a simpler, easier to maintain product line with a single acceleration technology to support.
However, we’re not making a full commitment just yet. While some of us love open-source, publicly maintained cross-platform solutions, these are not always the best thing to do in commercial apps. And for a moment here, we’re not talking about licensing issues. Instead, we’re talking sheer speed. While OpenCL is a great platform, offering future-proof, headache-free support of future acceleration hardware, it’s still an extra abstraction layer sitting between the hardware and our code. It’s great when we’re talking AMD, a company known for a rather inconsistent developer support for its latest hardware; there’s simply no alternative. If we wanted access to their latest state-of-the-art graphic accelerators such as AMD Radeon™ HD 7000 Series boards, it was OpenCL or nothing.
We didn’t have such issues with AMD’s main competitor, NVIDIA. NVIDIA was the first player on this arena, being the first to release graphical accelerators capable of fixed-point calculations. It was also the first to offer non-gaming developers access to sheer computational power of its GPU units by releasing CUDA, an application programming interface enabling developers use its hardware in non-graphical applications. From the very beginning and up to this day, CUDA maintains universal compatibility among the many generations of NVIDIA graphical accelerators. The same simply that can’t be said about AMD.
So is it the “if it ain’t broke, don’t fix it” approach? Partly, but that’s just one side of the coin. CUDA simply offers better performance than OpenCL. The speed benefit is slight, but it is there, and it’s significant enough to get noticed. We want to squeeze every last bit of performance out of our products and computers’ hardware, and that’s the real reason we’ll be staying with CUDA for as long as it’s supported – or until OpenCL offers performance that can match that of CUDA.
Did we make the switch half-heartedly? Nope. We’re enthusiastic about the future of OpenCL, looking forward to run our software on new acceleration platforms. But we don’t want to abandon our heritage code – especially if it performs better than its replacement!
There had been a long standing competition between NVIDIA and ATI which has lasted for years now. And there is no winner so far — just like with Windows vs. Linux or PC vs. Mac debate there are ones who prefer the former and others who prefer the latter. Kind of «religious» issue.
Some time ago we wrote about the smallest password cracking device. Not suitable for you? No problem, here is another one: not as small, but definitely more powerfull: Audi. Yes, it's a car. No, we're not kidding. Just read NVIDIA and Audi Marry Silicon Valley Technology with German Engineering press release from NVIDIA. Or if you need more information, The New MMI Generation from Audi might be also helpful. In brief: Audi A8 luxury sedan is equipped with an entertainment system that uses two GPUs from NVIDIA. We have no idea what are these chips (may be Fermi?) and is it technically possible to load our own code to them, but still funny, isn't it? 🙂
ATI is going to release Radeon HD 5000 cards (5850, 5870, 5870 X2) in October — well, hopefully. The top one (HD 5870X2: single-PCB, dual-GPU) will retail for $599.
As for NVIDIA’s new GT300, the specifications were revealed in April. In brief, it groups processing cores in sets of 32 (up from 24 in GT200) — up to 512 cores total for the high-end part. If the clocks remain the same as on GT200, that will double the overall performance. And there are other improvements as well: e.g. GT300 cores rely on MIMD-similar functions. Some fresh information about GT300 availability:
- Where is the nVidia GT300?
- nVidia plans GT300 demos for late September
- NVIDIA GeForce Drivers Include Details on GT300 GPU Series
You may ask — what about Intel? Well, new Core i5 and i7 (codename Lynnfield) now available. Nothing revolutionary new, just Intel P55 Express Chipset support: integrating both a 16-lane PCI Express 2 graphics port and two-channel memory controller on a single chip (previous chipsets required separate northbridge and southbridge), as well as several minor improvements. More information and some benchmarks at Intel Lynnfield; Core i5 750 and Core i7 870 Evaluation and New Intel Core i5, i7 Processors Product Matrix.
And still [almost] noting about Intel Larrabee, mostly just rumors:
Finally, funny article: NVIDIA to Intel: Your Days Are Numbered 🙂
Just about two weeks ago, ATI has introduced the fastest GPU yet: FirePro V8750. 800 shader engines, 115.2 GB/s memory bandwidth, 2 GB frame buffer memory (GDDR5), two DisplayPort outputs, one DVI output. Thinking about purchasing it? The cost is as high as $1,800. More details at Tom’s Hardware.
Want to compare ATI with NVIDIA? Then read ATI Stream vs. NVIDIA CUDA – GPGPU computing battle royale. Or you can use our Wireless Security Auditor (which supports cards from both manufacturers) for your own tests.