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.
Facebook
Twitter
RSS
114 Comments
View All Comments
GourdFreeMan - Friday, November 20, 2009 - link
Having not bought MW2, I can say conversely that the lack of differentiation between console and PC features hurts game sales. According to news reports, in the UK PC sales of MW2 account for less than 3% of all sales. This is neither representative of the PC share of the gaming market (which should be ~25% of all "next-gen" sales based on quarterly reports of revenue from publishers), nor the size of the install base of modern graphics cards capable of running MW2 at a decent frame rate (which should be close to the size of the entire console market based on JPR figures). Admittedly the UK has a proportionately larger console share than the US or Germany, but I can't image MW2 sales of the PC version are much better globally.I am sure executives will be eager to blame piracy for the lack of PC sales, but their target market knows better...
cmdrdredd - Wednesday, November 18, 2009 - link
[quote]Unfortunately, since playing MW2, my question is: are there enough games that are sufficiently superior on the PC to justify the inital expense and power usage of this card? Maybe thats where eyefinity for AMD and PhysX for nVidia come in: they at least differentiate the PC experience from the console.I hate to say it, but to me there just do not seem to be enough games optimized for the PC to justify the price and power usage of this card, that is unless one has money to burn.[/quote]
Yes this is exactly my thoughts. They can tout DX11, fancy schmancy eyefinity, physx, everything except free lunch and it doesn't change the fact that the lineup for PC gaming is bland at best. It sucks, I love gaming on PC but it's pretty much a dead end at this time. No thanks to every 12 year old who curses at you on XBox Live.
The0ne - Wednesday, November 18, 2009 - link
My main reason to want this card would be to drive my 30" LCDs. I have two Dell's already and will get another one early next year. I don't actually play games much but I like having the desktop space for my work.-VM's at higher resolution
-more open windows without switching too much
-watch movie(s) while working
-bigger font size but maintaining the aspect ratio of programs :)
Currently have my main on one 30" and to my 73" TV. TV is only 1080P so space is a bit limited. Plus working on the TV sucks big time :/
shaolin95 - Wednesday, November 18, 2009 - link
I am glad ATI is able to keep competing as that helps keep prices at a "decent" level.Still, for all of you so amazed by eyefinity, do yourselves a favor and try 3D vision with a big screen DLP then you will laugh at what you thought was cool and "3D" before.
You can have 100 monitors but it is still just a flat world....time to join REAL 3D gaming guys!
Carnildo - Wednesday, November 18, 2009 - link
Back in college, I was the administrator for a CAVE system. It's a cube ten feet on a side, with displays on all surfaces. Combine that with head tracking, hand tracking, shutter glasses, and surround sound, and you've got a fully immersive 3D environment.It's designed for 3D visualization of large datasets, but people have ported a number of 3D shooters to the platform. You haven't lived until you've seen a life-sized opponent come around the corner and start blasting away at you.
7Enigma - Wednesday, November 18, 2009 - link
But Ryan, I feel you might need to edit a couple of your comparison comments between the 295 and this new card. Based on the comments in a several previous articles quite a few readers do not look at (or understand) the charts and instead rely on the commentary below the charts. Here's some examples:"Meanwhile the GTX 295 sees the first of many falls here. It falls behind the 5970 by 30%-40%. The 5870 gave it a run for its money, so this is no surprise."
This one for Stalker is clear and concise. I'd recommend you repeat this format for the rest of the games.
"As for the GTX 295, the lead is only 20%. This is one of the better scenarios for the GTX 295."
This comment was for Battleforge and IMO is confusing. To someone not reading the chart it could be viewed as saying the 295 has a 20% advantage. Again I'd stick with your Stalker comment.
"HAWX hasn’t yet reached a CPU ceiling, but it still gets incredibly high numbers. Overclocking the card gets 14% more, and the GTX 295 performance advantage is 26%."
Again, this could be seen as the 295 being 26% faster.
"Meanwhile overclocking the 5970 is good for another 9%, and the GTX 295 gap is 37%."
This one is less confusing as it doesn't mention an advantage but should just mention 37% slower.
Finally I think you made a typo in the conclusion where you said this:
"Overclock your 5970 to 5870 speeds if you can bear the extra power/heat/noise, but don’t expect 5970CF results."
I think you meant 5870CF results...
Overall, though, the article is really interesting as we've finally hit a performance bottleneck that is not so easily overcome (due to power draw and ATX specifications). I'm very pleased, however, that you mention first in the comments that this truly is a card meant for multi-monitor setups only, and even then, may be bottlenecked by design. The 5870 single card setup is almost overkill for a single display, and even then most people are not gaming on >24" monitors.
I've said it for the past 2 generations of cards but we've pretty much maxed out the need for faster cards (for GAMING purposes). Unless we start getting some super-hi res goggles that are reasonably priced, there just isn't much further to go due to display limitations. I mean honestly are those slightly fuzzy shadows worth the crazy perforamnce hit on a FPS? I honestly am having a VERY difficult time seeing a difference in the first set of pictures of the soldier's helmet. The pictures are taken slightly off angle from each other and even then I don't see what the arrow is pointing at. And if I can't see a significant difference in a STILL shot, how the heck am I to see a difference in-game!?
OK enough rant, thanks for the review. :)
Anand Lal Shimpi - Wednesday, November 18, 2009 - link
Thanks for the edits, I've made some corrections for Ryan that will hopefully make the statements more clear.I agree that the need for a faster GPU on the desktop is definitely minimized today. However I do believe in the "if you build it, they will come" philosophy. At some point, the amount of power you can get in a single GPU will be great enough that someone has to take advantage of it. Although we may need more of a paradigm shift to really bring about that sort of change. I wonder if Larrabee's programming model is all we'll need or if there's more necessary...
Take care,
Anand
7Enigma - Wednesday, November 18, 2009 - link
Thank you for the edits and the reply Anand.One of the main things I'd like to see GPU drivers implement is an artificial framerate cap option. These >100fps results in several of the tests at insane resolutions are not only pointless, but add unneccesary heat and stress to the system. Drop back down to normal resolutions that >90% of people have and it becomes even more wasteful to render 150fps.
I always enable V-sync in my games for my LCD (75Hz), but I don't know if this is actually throttling the gpu to not render greater than 75fps. My hunch is in the background it's rendering to its max but only showing on the screen the Hz limitation.
Zool - Wednesday, November 18, 2009 - link
I tryed out full screen furmark with vsync on and off (in 640*480) and the diference was 7 degre celsius. I have a custom cooler on the 4850 and a 20cm side fan on the case so thats quite lot.7Enigma - Thursday, November 19, 2009 - link
Thanks for the reply Zool, I was hoping that was the case. So it seems like if I ensure vsync is on I'm at least limiting the gpu to only displaying the refresh rate of the LCD. Awesome!