The Radeon HD 5970: Completing AMD's Takeover of the High End GPU Market
by Ryan Smith on November 18, 2009 12:00 AM EST- Posted in
- GPUs
40nm Supply Redux
If you have seen our Radeon 5800 supply article, then you know that AMD is currently trying to come to terms with a significant shortage of Cypress dice. Since the 5800 series launched in September, TSMC’s yields have taken a hit as the company ramps up 40nm production. And while this is resulting in more usable chips per week than when AMD started, it’s lower than it was supposed to be. Compounding matters is high demand for these cards thanks to their performance, features, and a lack of significant competition from NVIDIA at this time.
So when we were briefed about the 5970, we asked AMD point-blank whether it was a good idea to be launching another Cypress based card so soon, and at a time when they already don’t have enough chips to go around. Their answer was equally straightforward: why not?
The design is done and AMD is already capable of building the 5970. For AMD, there is no benefit in waiting; no matter what they do, anything with a Cypress chip in it today is going to sell out. Holding back may be slightly more egalitarian, but as the 5970 is a luxury part, it’s not a high-volume part anyhow, so its introduction isn’t going to significantly disrupt 5800 shipments even if it does use 2 GPUs per card. Ultimately I don’t think we would even be having this discussion unless the profit margin on the 5970 is higher than the 5870, so at some point this comes down to AMD doing what is most profitable for them.
At $600, AMD isn’t going to sell a ton of 5970s, and the launch numbers reflect this. While the 5800 series cards launched with tens-of-thousands of cards, the 5970 launch will simply be with thousands of cards. Even as a low-volume part, we’re expecting the 5970 to sell out just as fast as any 5800 card did. But depending on what AMD does with future chip shipments though and what TSMC’s yields do, this may be the first product line where demand finally gets met in the near future.
We also had a chance to talk to AMD about the overall 40nm supply situation. AMD of course isn’t very pleased with the situation, but this is something they’ve apparently planned for, after their first 40nm test chips came back as being less impressive than their 55nm and 65nm test chips were. Besides TSMC’s subpar yields, AMD is unable to get as many wafer starts as they’d like, which is compounding the issue.
Finally, we’re told that the TSMC situation is continuing to improve, and that AMD currently expects the Cypress chip supply to pick up in December. To what level of production “pick up” goes with we’re not sure, but it’s likely less than demand. In talking to AMD, they didn’t seem confident in being able to keep any Cypress-based products in stock through Christmas. Supplies will improve through the end of the year, but it sounds like it’s going to be 2010 before supply and demand finally balance out.
114 Comments
View All Comments
Lennie - Wednesday, November 18, 2009 - link
If so, then one could suspect it's the same issue with games due to VRMs of this particular card getting heated up and throttling the card. Perhaps not enough contact between VRM and HSF or a complete lack of TIM on VRM by accident. I would have reseated the HSF if I owned that card.Rajinder Gill - Wednesday, November 18, 2009 - link
I suspect it is VRM/heat related. The 'biggest' slaves Volterra currently supply are rated at 45 amps each afaik. Assuming ATI used the 45 amp slaves (which they must have), you've got around 135 amps on tap. Do the math for OCP or any related throttling effects kicking in. Essentially, 1.10VGPU puts you at 150w per GPU before things either shut down or need to be throttled (depends on how it's implemented as it nears peak). Any which way you look at it, ATI have used a high end VRM solution, but 4 slaves per GPU would have given a bit more leeway on some cards. I wonder what the variance is in terms of leakage from card to card as well. Seeing as there's not much current overhead in the VRM (or at least there does not appear to be), a small change in leakage would be enough to stop some cards from doing too much in terms of overclocking on the stock cooler.later
Raja
Silverforce11 - Wednesday, November 18, 2009 - link
It could be your PSU, some "single rail" PSU arent in fact using a single rail but several rails with a max limit on AMPs. Its deceptive.Guru3D uses 1200W PSU and manages 900 core, which is typically what a 5870 OC to on air. Essentially the chips are higher quality cypress, maybe you should retry it again with a different PSU then conclusions can be drawn.
Bolas - Wednesday, November 18, 2009 - link
Yep, there is certainly a market for 5970CF. Can't wait!tajmahal - Wednesday, November 18, 2009 - link
Big deal, another paper launch where only a tiny handful of people will be able to get one.LedHed - Tuesday, November 24, 2009 - link
My question is why do the OC the 5970 but not the 295...We all know the 295 is memory bottlenecked at resolutions at/over 2560x1600
But considering the GTX 295 is down below $450 and no one can find these cards in stock with a god awful price of $600 ($100 more than 295 at launch).
mschira - Wednesday, November 18, 2009 - link
newegg list 5 different models, they come and go quite fast.I managed to get one of them in my shopping card.
All it would need now is pay. (which I don't want to...).
So yea they are not exactly easy to get, but far from impossible.
So not a paper launch.
Be real, it's day two after the launch, and you CAN get them. That's not bad at all.
M.
MrPickins - Wednesday, November 18, 2009 - link
At the moment, Newegg shows two different 5970's in stock. A HIS and a Powercolor.tajmahal - Wednesday, November 18, 2009 - link
Listed, but not available. I guess newegg sold both of the ones they had available, and the 5850 and 5870 ?......... not available either.Silverforce11 - Wednesday, November 18, 2009 - link
Plenty of 5870s around at retails and etailers, what do you mean by "another paper launch"?