Technological leap or marketing necessity?
Where are the beasts? Where are the monolithic giants of graphical technology that make us go moist in the geek glands? Too long have we waited, frustrated at the less than satisfying make-do cards thrown our way like scraps from the table of the tech gods. AMD has tried to placate us with the vast scale of the HD3870 X2, a multi-core behemoth that demands half the space and practically all the power your PC can muster, but what of NVIDIA's top-end cards?
Just over two years ago, the much-heralded age of the DirectX 10-capable graphics card dawned with the supreme G80-powered GeForce 8800GTX. Then a year ago came the updated 8800 Ultra, a card that has remained NVIDIA's top end offering... until now. We've had to wait 12 long months for the refresh, during which we've been treated to a mass of mid-range cards. Admittedly, this included the excellent G92 8800GT; its first 65nm core, but still it's been a long time coming for the 9800GTX and GX2.
Both new cards are powered by the same 65nm G92, a core that is now one year old, and represents the first time that either AMD or NVIDIA have released a brand new family of top-end cards based on old architecture. Replacing the 8800GTX and Ultra is a necessity as far as furthering the NVIDIA brand is concerned, competition-wise though it's less of an issue. AMD still hasn't managed to create anything to seriously outperform these year-old cards. So is the lack of a new core an acknowledgment that NVIDIA only has to turn up to the race to win?
Promises, Promises
Towards the end of the year we are promised the GT200, the current nomenclature of NVIDIA's next chip, with a core designed to power the 9900 family of cards. With this in mind it was necessary for the green side of the graphics market to produce a range of cards to cover the high-end, and so the stop-gap measure of the 9800 cards have been born.
The GTX model is a straight, beefed up version of the G92 with higher clock speeds across the board. While it shares the same number of Raster Operators (ROPs) as the 8800GT, it has the old GTX's complement of shader units at 128, giving it the necessary speed boost. The GX2 follows the example of the old 7950GX2, strapping two G92-stuffed PCBs together, except this time they both face into the same heatsink, housed in a vaguely coffin-like surround. The clock speeds are slightly slower than the GTX, but a fair dose of optimizing has gone into making this single card SLI offering an impressive piece of engineering.
The first difference you'll notice when comparing the specs of the two new cards with the versions they're replacing is the change in memory capacity. Both the 8800GTX and Ultra had a 384-bit memory bus with 768MB of GDDR3, while the 98005 make do with the same 256-bit 512MB of memory that resides on the GTS and GT iterations of the G92-based 8800s.
ROP rules?
Due to its two cores the GX2 comes out tops in the memory bandwidth stakes at 128Gbps compared with the Ultra's 103.7Gbps, but the 9800GTX lags well behind the older cards. What this all means, in real terms, is that at the higher resolutions, and most especially with full screen anti-aliasing turned on, the new cards take quite a hit at the levels we were hoping these big-panel pixel pushers would excel at.
The differences between the GTX and GX2, and indeed the 8800GT, are slight; the GX2 simply relying on the brute force effect of the single card SLI factor. Where the difference between the two new G92 parts is most obvious though is the number of ROPs. The GTX is still hobbling along with 16, less than both the 8800GTX and Ultra at 24, but due to the doubling up the GX2 has 32. The difficulty is in knowing how much of a benefit this multi-CPU's extra ROPs actually gives as opposed to the single card with 24.
The question is: where do we find ourselves with the two new top-end cards? Well, mostly in the same place we were before, to be brutally honest. There's very little difference between this new set and the old, with the 9800GTX being the biggest disappointment.
Bigger, Faster, Stronger?
The 9800GX2 struggles to find any space between itself and the 8800GTX, it's supposed to be replacing, and there's also the fact that you can still pick up the older card - with the extra memory, bandwidth and ROPs - for less than $600. In some places you can save yourself around $100 and come out with an equivalent and, in some cases, faster card. The march of progress seems to have stomped right past this iteration of the 9800 without saluting.
NVIDIA then had to go down the multi-GPU route, not just to prove they could produce a functional version like AMD, but also to create a card that they could legitimately call the fastest graphics card around. Still, the memory constraints hold the GX2 back from being the superlative, stand out, top-end card de jour.
On the lower-res panels, without the silicon-melting anti-aliasing it speeds ahead of the competition, yet with all the bells and whistles cranked up to a deafening roar it struggles to break even with the old 8800 Ultra. Again, if you shop around you can pick up an Ultra for around $500, and be fairly sure that your card will have drivers mature enough to cater for whatever you throw down its tubes.
Essentially, if you've got yourself an 8800GTX or Ultra and felt that twinge of envy at the announcement of this new generation of top-end cards, then quit your worrying right now. In fact, you can probably be downright smug as your slightly geriatric cards are still more than capable of holding their own against these youngbloods. Till the GT200 that is.
CrossfireX and SLI: Platform Choices
One thing that hybrid Crossfire or SLI configurations may be useful for is taking the strain of physics off the CPU.How to Interpret Female Body Language
Understand female body language and you can have almost any woman you desire. Many men fail because they fail to read what a woman wants and say the wrong things that will impress her.Crossfire X vs SLI
New cards means another new round in the ongoing multi-GPU battle.