13 Years of GPU Acceleration with AMD and NVIDIA

It was exactly 13 years ago when we invented GPU acceleration. The encryption was getting stronger year over year, and the rate of trying the password combinations was (and still is) of great importance. It is the attack rate that determines how long and how complex the password can be discovered after a reasonable wait ranging from a few hours to several weeks.

The speed of a single CPU (or multiple CPUs if that matters) is not nearly enough to break today’s passwords. The hundreds of thousands or even millions hash iterations slow down the recovery to the crawl. In the end, the CPU becomes a bottleneck. 13 years ago, we saw the need for additional computation power. The solution was using the power of independent compute units found in common graphic cards.

With today’s proliferation of everything AI relying on GPU units our 13-year-old achievement seems obvious in retrospect. Back then, it was not only far from the obvious, but took us years to design and to implement. It was so innovative that it was covered in press.

Many things had change since then. CPUs have become more powerful, while AMD and NVIDIA video cards have become more powerful to a much greater degree. The encryption strength has also increased. At this time, we are striving to increase the absolute speed of password recovery while working on smarter attacks that dramatically reduce the number of passwords to try by targeting the human factor. Criminals are getting smarter and more cunning, encrypting everything they can. Our tools can break many hundred formats, most of which can be accelerated with a CPU.

See also