Prologue

Because designing GPUs this big is "[redacted] hard"

-NVIDIA’s VP of Product Marketing Ujesh Desai on GF100

Fermi/GF100/GTX400 has been a long time coming. For an industry where the major players are usually in lockstep with each other in some fashion, this latest cycle has been distinctly out of sync. In September of 2009 we saw AMD launch their Radeon 5000 series, and spend the next 6 months as the performance leader for the discrete graphics market for virtually every price point. NVIDIA on the other hand missed the latest cycle by a mile, and when AMD was delivering 5000 series cards NVIDIA could only talk about the High Performance Computing applications of their next GPU, Fermi. It would be the next big thing, both figuratively and literally.

In January we got the next piece of the Fermi story at CES, when NVIDIA was willing to talk about the gaming-oriented hardware and applications of the first Fermi GPU: GF100. We found out it would be significantly different from the GT200 GPU powering NVIDIA’s GTX200 series, that NVIDIA was going to break up the traditional fixed-function pipeline and at the same time take a particularly keen interest in tessellation. What we didn’t find out is when it would ship.

Much of this has been in NVIDIA’s hands – some of it has not. What’s indisputable is that TSMC, the chip foundry used by both AMD and NVIDIA, was not delivering the kind of yields on their 40nm process that AMD and NVIDIA were expecting. Both of them suffered for it. AMD could not get enough viable chips to meet demand for their 5000 series part, leaving a wake of disappointed gamers who could not get AMD’s latest wonder, and limiting AMD’s ability to profit from one of the few times in AMD/ATI’s history where the company had a clear lead over NVIDIA, and if you ask AMD also limiting their ability to control prices. NVIDIA meanwhile had to deal with the fact that they were trying to produce a very large chip on a low-yielding process, a combination for disaster given that size is the enemy of high yields.

What’s also indisputable is that this 6 month wait has benefited few people. For the observers of an industry where the competition is cut-throat we saw GPU prices rise, when in the last generation AMD and NVIDIA knocked upwards of hundreds of dollars off of each other’s prices practically overnight. It may have been good times overall for AMD, but for buyers the competitive marketplace is sorely missed.

That brings us to today. We can see the light at the end of the tunnel, the end of NVIDIA’s 6 month journey is near. We’ve told you about the compute applications of Fermi, we’ve told you about the gaming applications of Fermi, and now at long last we can tell you about the first products. It’s time to say hello to the GTX 400 series.

Meet the GTX 480 and GTX 470

 

  GTX 480 GTX 470 GTX 295 GTX 285 9800+ GTX
Stream Processors 480 448 2 x 240 240 128
Texture Address / Filtering 60/60 56/56 2 x 80 / 80 80 / 80 64 / 64
ROPs 48 40 2x 28 32 16
Core Clock 700MHz 607MHz 576MHz 648MHz 738MHz
Shader Clock 1401MHz 1215MHz 1242MHz 1476MHz 1836MHz
Memory Clock 924MHz (3696MHz data rate) GDDR5 837MHz (3348MHz data rate) GDDR5 999MHz (1998MHz data rate) GDDR3 1242MHz (2484MHz data rate) GDDR3 1100MHz (2200MHz data rate) GDDR3
Memory Bus Width 384-bit 320-bit 2 x 448-bit 512-bit 256-bit
Frame Buffer 1.5GB 1.25GB 2 x 896MB 1GB 512MB
Transistor Count 3B 3B 2 x 1.4B 1.4B 754M
Manufacturing Process TSMC 40nm TSMC 40nm TSMC 55nm TSMC 55nm TSMC 55nm
Price Point $499 $349 $500 $400 $150 - 200

Today NVIDIA is launching two cards: the GeForce GTX 480, and the GeForce GTX 470. Both of them are based on GF100, the first and largest member of the Fermi family. Right off the bat, we can tell you that neither card is a complete GF100 chip. We know from NVIDIA’s earlier announcements that a complete GF100 is a 512 SP/core part organized in a 4x16x32 fashion, but these first parts will not have all of GF100’s functional units activated. Instead we’ll be getting a 480 core part for the GTX 480, and a 448 core part for the GTX 470. Ultimately we will not be seeing the full power of GF100 right away, but you can be sure that somewhere down the line we’ll see a GTX 485 or GTX 490 with all of GF100’s functional units enabled.


NVIDIA's GeForce GTX 480

What we’re starting out with today at the high-end is the GTX 480, a card based on a GF100 with 1 of the 16 SMs disabled that will sell for $499, making it the primary competitor for the Radeon 5870. The disabled SM has no affect on the ROPs which are part of a separate functional block, but it does cut down on the shading, texturing, and tessellation capabilities of the card compared to where a full GF100 card would be. This gives the GTX 480 the full 48 ROPs and 768KB of L2 cache of GF100, along with 60 texture units, 15 PolyMorph engines, and 480 cores. Although the architectural overhaul means we can’t compare the GTX 480 to the GTX 285 quite as easily as we could the Radeon 5000 series to the Radeon 4000 series, the GTX 480 is still in some ways a doubled-up GTX 285 from a shader standpoint.

The GTX 470 on the other hand is a further cut-down GF100-based product that will sell for $349. As we stated earlier it has only 448 cores, a product of NVIDIA disabling 2 of the 16 SMs. Along with disabling the SMs, NVIDIA also disabled 1 of the 6 ROP clusters, which disables 6 ROPs, 128KB of L2 cache, and 2 of the 32bit memory channels. This leaves us with 448 cores running alongside 40 ROPs, 640KB of L2 cache, all on a 320bit GDDR5 memory bus.


NVIDIA's GeForce GTX 470

As is usually the case for a harvested part, GTX 470 takes a clockspeed hit compared to GTX 480. The core clock falls 13% to 607MHz, and the shader clock falls the same distance to 1215MHz. The memory clock on the other hand only drops by 10% to 837MHz (3348MHz effective). Overall this gives the GTX 470 around 80% of the shading, texturing, and tessellation capabilities of the GTX 480 and 72% of the ROP capability and memory bandwidth.

One thing that caught our eye with all of this was that NVIDIA’s memory clocks are lower than we had been initially expecting. GDDR5 is readily available up to 5GHz while NVIDIA doesn’t go any higher than 3.7GHz; in fact between the smaller memory bus than the GTX 285 and the lower than expected memory clocks, the GTX 400 series doesn’t have all that much more bandwidth than the GTX 285 did. As it stands the GTX 480 only has 11% more memory bandwidth than the GTX 285, while the GTX 470 has 15% less than the GTX 285.

Given the 384-bit bus, we initially assumed NVIDIA was running in to even greater memory bus issues than AMD ran in to for the 5000 series, but as it turns out that’s not the case. When we asked NVIDIA about working with GDDR5, they told us that their biggest limitation wasn’t the bus like AMD but rather deficiencies in their own I/O controller, which in turn caused them to miss their targeted memory speeds. Unlike AMD who has been using GDDR5 for nearly 2 years, NVIDIA is still relatively new at using GDDR5 (their first product was the GT 240 late last year), so we can’t say we’re completely surprised here. If nothing else, this gives NVIDIA ample room to grow in the future if they can get a 384-bit memory bus up to the same speeds as AMD has gotten their 256-bit bus.

This leaves us with the other elephant in the room: yield on GF100. NVIDIA hasn’t commented specifically on the yields coming out of TSMC but we know even 6 months later that AMD still isn’t satisfied with things, so that should offer some guidance on the situation given NVIDIA’s larger die. As it stands NVIDIA chose to launch their highest end GF100 part with only 15 of 16 SMs in order to reach the “broadest availability”, which is a clear sign that NVIDIA isn’t getting enough full-yielding and high-clocking dies at this time to offer a proper unharvested part.

The power/heat situation also bears mentioning, since it often goes hand-in-hand with yield issues. With a 500mm2+ die on the 40nm process, it should come as no surprise that both the GTX 480 and GTX 470 are hot cards. NVIDIA has to pay the piper for having such a large die, and this is one of the places where they do so. The TDP for the GTX 480 is 250W while it’s 215W for the GTX 470; meanwhile the cards idle at 47W and 33W respectively. NVIDIA’s large die strategy usually leads to them having power-hungry parts, but from a historical perspective the GTX 480 is the hungriest yet for a single-GPU card; even the GTX280 wasn’t quite as high. We’ll get in to this more when we take a look at measured power consumption.

Meet the GTX 480 and GTX 470, Cont
POST A COMMENT

197 Comments

View All Comments

  • LuxZg - Tuesday, March 30, 2010 - link

    Like I've said before - if you want FASTEST (and that's usually what you want if you have money to throw away), you'll be buying HD5970. Or you'll be buying HD5970+water cooling as well.. Reply
  • ViRGE - Saturday, March 27, 2010 - link

    I'm not sure where you're getting that the HD5970 is a $600 card. In the US at least, that's a $700 card (or more) everywhere. Reply
  • wicko - Sunday, March 28, 2010 - link

    Honestly I don't even know if it should be mentioned at all even if it is 600, because there is almost no stock anywhere. Reply
  • LuxZg - Tuesday, March 30, 2010 - link

    Oh, don't make me laugh, please! :D In that case this review shouldn't be up at all, or it should be called "PREview".. or have you actually seen any stock of GTX470/480 arround? Reply
  • LuxZg - Sunday, March 28, 2010 - link

    It's AMD's & nVidia's recommended prices, and you can see them all in Anandtech's own articles:
    http://www.anandtech.com/video/showdoc.aspx?i=3783">http://www.anandtech.com/video/showdoc.aspx?i=3783 (nvidia prices)
    http://www.anandtech.com/video/showdoc.aspx?i=3746">http://www.anandtech.com/video/showdoc.aspx?i=3746 (ATI single-gpu cards)
    http://www.anandtech.com/video/showdoc.aspx?i=3679">http://www.anandtech.com/video/showdoc.aspx?i=3679 (ATI single/dual GPU cards)

    It is not my fault that your US shops bumped up the price in the complete absence of competition in the high end market. But US is not only market in the world either.

    You want to compare with real world prices? Here, prices from Croatia, Europe..

    HD5970 - 4290kn = 591€ (recommended is 599$, which is usually 599€ in EU)
    GTX480 - not listed, recommended is 499$/€
    HD5870 - 2530kn = 348€ (recommended is 399$/399€ in EU)
    GTX470 - not listed, recommended is 349$/€
    HD5850 - 1867kn = 257€ (recommended is 299$/299€ in EU)

    So let's say that European prices for GTX will be a bit lower than recommended ones, GTX480 would still be ~120-130€ pricier than HD5870, and HD5970 would be same ~120-130€ more expensive than GTX480.
    As for the lower priced nVidia card, it's again firmly in the middle between HD5850 & HD5870.

    Point is that there's no clear price comparision at the moment, and article's conclusion should be clear on that.
    Person that wants the FASTEST CARD will stretch for another 100$/€ to buy HD5970. Especially since this means lower noise, lower consumption, and lower heat. This all combined means you can save a few $/€ on PSU, case, cooling, and earplugs, throwing HD5970 in the arm reach of the GTX480 (price-wise) while allowing for better speeds.

    As for GTX470, again, lower consumption/heat/noise with ATI cards which means less expenses for PSU/cooling, and saving money on electrical bills. For me, well worth the 50€/$ difference in price, in fact, I'd rather spend 50$/€ more to buy HD5870 which is faster, less noisy, doesn't require me to buy new PSU (I own HD4890, which was overclocked for a while, so HD5870 would work fine just as well), and will save me 50W per hour of any game I play.. which will all make it CHEAPER than GTX470 in the long run.

    So let's talk again - why isn't conclusion made a bit more straightforward for end users, and why is HD5890 completely gone from the conclusion??
    Reply
  • Saiko Kila - Sunday, March 28, 2010 - link

    These MSRPs are not entirely, I mean historically correct... The first MSRP (list price) for HD 5850 was $259, and that was price you had to pay when buying on sites like newegg (there were some rebates, and some differences depending on manufacturer, but still you had to have a very potent hunting sense to get a card of any manufacturer, I got lucky twice). Shortly after launch (about one month, it was October) the MSRP (set by AMD) hiked to $279 and problems with supply not only continued but even worsened. Now, since November 2009, it's $299. HD 5870 followed generally similar path, though HD 5850 hiked more, which is no wonder. Note that this is for reference design only, some manufacturers had higher MSRPs, after all AMD or nvidia sell only chips and not gaming cards.

    If you believe anandtech, here you've got a link, the day the cards were announced:
    http://www.anandtech.com/video/showdoc.aspx?i=3643">http://www.anandtech.com/video/showdoc.aspx?i=3643

    The whole pricing things with HD 5xxx series is quite unusual (though not unexpected) since normally you'd anticipate the street price to be quite lower than MSRP, and then to drop even further, and you would be right. I remember buying EVGA GTX260 just after its launch and the price was good $20 lower than suggested price. That's why we need more competition, and for now the outlook isn't very bright, with nvidia not quite delivering...


    And these European prices - most if not all European countries have a heavy tax (VAT), this tax is always included and you have to pay it, there are other taxes too. In the US the sales tax is not included in the street price, and usually you can evade it after all (harder for Californians). Europeans usually get higher prices. Comparing US prices is thereby better, particularly in us dollars (most electronics deliveries are calculated in dollars in Europe). So the prices in the rest of the world were also boosted, even in Europe, despite weak dollar and other factors :)

    One note - HD5xxx cards are really very big and most of them have very unfriendly location of power sockets, so you'd expect to pay more for a proper, huge case. Also note that if you have a 600 W PSU or so you'd be smarter to keep it and not upgrade, unless REALLY necessary. The lower load means lower efficiency, especially when plugged to 115V/60Hz grid. So if you have a bigger PSU you pay more for electricity. And it seems that more gamers are concerned with that bill than in any time before... You couldn't blame them for that and it's sad in its own way.
    Reply
  • LuxZg - Tuesday, March 30, 2010 - link

    Well, current MSRP is like I wrote it above. If there is no competition and/or demand is very high, prices always tend to go up. We're just lucky it's not happening often because in IT competition is usually very good.

    As for European prices, what do taxes have to do with it? We've got 23% taxes here, but it's included in all prices, so if nVidia goes up 23% so do AMD cards as well. If I'm looking at prices in the same country (and city, and sometimes store as well), and if nVidia is 300$ and ATI is 100 and 500, than I just can't compare them and say "hey, nVidia is faster than this 100$ ATI card, I?ll buy that"... no, you can't compare like that. Only thing you can do in that case is say something like "OK, so I have 300$ and fastest I can afford is nVidia" .. or "I want fastest there is, and I don't mind the cost" and you'll take HD5970 than. Or you can't afford any of those. So again, I don't get why cards in this review are so rigidly compared one to another as if they have exact same price (or +/- 10$ difference). And at one hand they compare MORE expensive nVidia card to QUITE CHEAPER AMD card, but won't compare that same nVidia card to a more expensive AMD card.. WHY?

    And AMD cards are no bigger than nVidia ones, and last time I've checked bigger case is way way cheaper than a new PSU. And I'm running my computer on, get this, 450W PSU, so I'm not wasting any excessive power on inefficiences on low loads ;) And since this PSU keeps overclocked HD4890, it should work just fine with non-overclocked HD5870. While I'm pretty sure that GTX470 would already mean a new PSU, new PSU that costs ~100$/80€ .. So I'd pay more $ in total, and get a slower card.

    Again, I'm not getting why there's such a rigid idea of GTX470=HD5850 & GTX480=HD5870 ..
    Reply
  • LuxZg - Saturday, March 27, 2010 - link

    Just re-read the conclusion.. something lacks in this sentence:
    "If you need the fastest thing you can get then the choice is clear, .."
    Shouldn't it finish with "... choice is clear, HD5970..." ? That's what I'm saying, HD5970 wasn't mentioned in the entire conclusion. Past are the days of "single-GPU crown" .. That's just for nVidia to feel better. ATI Doesn't want "single GPU crown", they want the fastest graphics CARD. And they have it.. Serious lack in this article, serious.. And again, there is exact same amount of money dividing GTX480 and HD5870, as is between GTX480 and HD5970..
    Reply
  • blindbox - Saturday, March 27, 2010 - link

    I know this is going to take quite a bit of work, but can't you colour up the main cards and its competition in this review? By main cards, I mean GTX 470, 480 and 5850 and 5870. It's giving me a hard time to make comparison. I'm sure you guys did this before.. I think.

    It's funny how you guys only coloured the 480.

    PS: I'm sorry for the spam, my comments are not appearing, and I'm sorry for replying to this guy when it is completely off topic, lol.
    Reply
  • JarredWalton - Saturday, March 27, 2010 - link

    Yes, it did take a bit of work, but I did it for Ryan. The HD 5870/5970 results are in orange and the 5850 is in red. It makes more of a difference on crowded graphs, but it should help pick out the new parts and their competition. I'm guessing Ryan did it to save time, because frankly the graphing engine is a pain in the butt. Thankfully, the new engine should be up and running in the near future. :-) Reply

Log in

Don't have an account? Sign up now