Open Access to the GPU. Is this an open invitation to Malware?
Published in News

The average GPU is a pretty powerful computational device. The highly parallel design and efficient memory structure means that you can execute operations at a rate that puts most CPUs to shame. With the advent of Cuda and OpenCL the door was opened for developers to push workloads to the GPU and get back some pretty nice returns. Microsoft and many others joined in and began making access to the GPU simpler starting with DirectX 10.

The idea of GPU accelerated applications is one that has caught the attention of many developers over the years since we first heard about it. It is a great advancement in technology that allows you to use the parallel processing and faster memory of a GPU to perform complex tasks much faster than most CPUs can. This is great for software that needs that extra boost like AI, video or photo editing and… Malware. Yes it is also possible to develop malware that uses OpenCL and Cuda (NVIDIA’s flavor of GPU programing language.

16-Card-07Wow it looks like this month is the moth for leaks; we have seen early leaks on Intel’s Z77 chipset, nVidia’s mobile Kepler GPU and even early full reviews of Intel’s Ivy Bridge (this incident sent some at Intel over the edge). Now we have new leaks on nVidia’s Kepler. The first leak was a simple one that involved the early publishing of nVidia’s GTX 680 launch video. Apparently this was leaked on the eve of the launch (which if rumor is to be believed) is tomorrow some time.

Monday, 12 July 2010 13:52

Is AMD worried about the GTX 460?



GeForce_GTX_460_3qtrSo nVidia has dropped the GTX 460 on the world. Starting at midnight the reviews, press releases and all the usual brouhaha surrounding a new product launch began.  For us, as a new site we are not going to expect to see one of the new GF 104s for some time. Thankfully we have plenty to keep us busy as we get the site up to speed. No the thing that we wanted to go over is the interesting e-mails that we have seen from AMD.