AMD ATI Radeon HD 4850 Crossfire

Team AMD in da house

You guys probably remembered early last year when NVIDIA dominated the mainstream market with a relatively poor GeForce 8600 GT. Once AMD released the series 3000 Radeon products I was just thrilled. They moved onwards to a 256-bit memory bus in the midrange segment and presented the Radeon HD 3850 & 3870 initially as the leading mainstream products. The 3000 series just butchered the GeForce 8600 GT in both price and performance. It literally took NVIDIA a while to properly react to that, and initially we noticed price drops in the 8600 range, then the 8800 GT drastically dropped in price to counteract the Radeon 3000 series and finally the competing product as we still see it today was released, the GeForce 9600 GT. Over the past six months or so the best bang for buck performing products actually were just that, the GeForce 9600 GT, the Radeon HD 3850 and of course the Radeon HD 3870.

These three products are still showing leading performance in the mid-range segment, until today that is. Though not touching the niche high-range market, AMD is doubling up that performance for you at nearly the same price. Quite an achievement. With that little intro let's talk a little about the GPU and the differences between the two models released today.

So I spilled the beans already a little on the frontpage. Today AMD brings you products based on the new RV770 based chipset. They put nearly a billion transistors into that GPU, which is now built upon a 55-nm production. The number of transistors for a midrange product like this is quite extreme and typically it's best to directly relate that to the number of shader processors to get a better understanding. Now please understand that ATI used different shader processors opposed to NVIDIA, so do not compare the two in that manner; but the new Radeon 4850/4870 have 800 shader cores. Effectively this product can poop out 1000/1200 GigaFLOPs of performance. Depending on how that is measured of course. But still, with an entry product at 199 USD, that's just an awful lot of computing power.

Next to internal efficiency improvements we also stumble into an updated UVD engine (HD video decoder/enhancer) which we'll talk about in a second.

PhysX - Much like NVIDIA just announced with the help of CUDA, ATI (AMD) recently announced cooperation with Intel's HAVOC engine. Though currently far less substantial, PhysX calculations over the GPU are in the work. As it works right now (example debris/cloth) physics calculations are computed over the CPU with games that support the HAVOK API. AMD is working on moving these functions to the GPU. Thus have the stream processors (shade engine) compute these functions. It's work in progress and during a recent press-briefing we asked when we can expect driver support for GPU HAVOK physics. The answer was unfortunately a bit cold. It could be a matter of two months, yet also easily be the end of the year. Fact remains though that the Series 4000 do support the feature and AMD is working on it.

NVIDIA recently expanded the way we need to think about the GPU. There are many other things you can do with the GPU other than rendering games. GPGPU is AMDs project on this, I call it parallel processing. AMD has opened up the GPU as well to be used for stream computing. Very coincidentally on a press-briefing all of a sudden a video transcoding example was given. 3rd party vendors can open up their API and use the GPU for, for example transcoding a high-def video stream to a smaller definiton on for your IPOD etc etc. Unfortunately for ATI, NVIDIA has the CUDA platform which has much more reach and is easier to use and program. So while the new series 4000 products without a doubt can handle stream processing very well for a multitude of applications, chances are pretty slim that consumers will actually see anything of it as it needs to be developed by software vendors who need to open up the code through CAL (Compute Abstraction Layer), for those interested AMD does have a nice SDK available on that.