facebook rss twitter

NVIDIA to bring GPU acceleration to everyday security software?

by Parm Mann on 7 October 2009, 11:43

Tags: NVIDIA (NASDAQ:NVDA)

Quick Link: HEXUS.net/qaudw

Add to My Vault: x

We know that NVIDIA has plans to slowly-but-surely conquer the world with GPU acceleration, but it's hoping to speed up the process with a usage scenario that could benefit millions; GPU-accelerated virus scanning.

According to Fudzilla.com, NVIDIA's General Manager of CUDA Sanford Russel claims the graphics giant is working on speeding up the virus-scan process. Due to the highly parallel nature of a virus scan, NVIDIA reckons the process could be quickened dramatically by offloading work to a GPU.

Trouble is, NVIDIA will need to find itself a security solutions provider willing to create anti-virus software based on CUDA - a C programming environment that enables developers to code algorithms to be executed on an NVIDIA GPU.

It's an interesting idea, and presumably one that NVIDIA feels will give its own GPUs an advantage over competing solutions - but let's not get ahead of ourselves, as GPU-acceleration isn't likely to alleviate the biggest burden on lengthy virus scans; the bottleneck created by hard drives.



HEXUS Forums :: 21 Comments

Login with Forum Account

Don't have an account? Register today!
Might not accelerate the whole system scan due to hard drive limitations, but it could go a long way to helping cure the percieved slowness that AV causes due on on-access and real time protection, scanning items in memory, websites etc…?
Beaten to it - isn't the bottle neck on a virus scan the HD?
Having seen the “huge” performance increases CUDA offers (say 0-1% on arithmetic PAR2 file checking) I wonder if this is worth the effort apart from to give nVidia free publicity…..
Methanoid
Having seen the “huge” performance increases CUDA offers (say 0-1% on arithmetic PAR2 file checking) I wonder if this is worth the effort apart from to give nVidia free publicity…..

Where is the bottleneck though?

Is it in the program itself, is it unsuited to CUDA, does CUDA have issues, is the HD being the limiting factor? and so on….

Offloading things to CUDA when appropriate and done correctly can give a huge increase in performance.

Are you using Par2cmdline? If so, remember that "This is the experimental CPU/GPU version. It may be useless to you."

Badaboom is a nice example of something that works well offloaded to CUDA.
Until i actually see this CUDA stuff benefiting the home user and being genuinely worthwhile its all just words. They seriosuly need to stop talking and slating other companies and just get on with doing things we can physically see.