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

  • ol1bit - Thursday, April 01, 2010 - link

    I thought it was a fare review. They talked about the heat issues, etc.

    You can't compare a 2 GPU card to a single GPU card. If they ever make a 2 core GF100, I'm sure Anandtech will do a review.
    Reply
  • IceDread - Tuesday, April 06, 2010 - link

    You are wrong. You can and you should compare single gpu cards with multi gpu cards. It does not matter if a card has one or 30 gpu's on the card. It's the performance / price that matters.

    These nvidia cards are very expensive in performance / price compared to the ATI cards, simple as that. It's obvious that nvidia dropped the ball with their new flagship. You even need 2 cards to be able to use 3 screens.

    This is bad for us customers, we are not getting any price pressure at all. These nvidia cards does not improve the market since they can not compete with the ATI card, only nvidia fans will purchase these cards or possibly some working with graphics.

    I hope nvidia will do better with their next series or cards and I hope that won't take to long because ATI will most likely release a new series in half a year or so.
    Reply
  • xxtypersxx - Sunday, March 28, 2010 - link

    I will be interested in seeing the performance gains that will likely come from revised Nvidia drivers in a month or two. In some of the tests the gtx470 is trading blows with the gtx285 despite having nearly double the compute power...I think there is a lot of room for optimization.

    I am no fanboy and even owned a 4850 for a while, but Nvidia's drivers have always been a big decision factor for me. I don't get any of the random issues that were common on catalyst and aside from the occasional hiccup (196.67 G92 fan bug) I don't worry about upgrades breaking things. I admit I don't know if all the 5xxx series driver issues have been fixed yet but I do look forward to driver parity, until then I think raw performance is only part of the equation.
    Reply
  • GourdFreeMan - Sunday, March 28, 2010 - link

    Ryan, have you checked performance and/or clocks to see if any of the cards you are testing are throttling under FurMark? I recall you mentioning in your 58xx review that ATi cards can throttle under FurMark to prevent damage, and while most of the power numbers look normal, I notice a few of the cards are consuming less power under FurMark than Crysis, unlike the majority of the cards which consume considerably more power running FurMark than Crysis... Reply
  • MojaMonkey - Sunday, March 28, 2010 - link

    I can turn off one light in my house and remove the power consumption difference between the GTX480 and the 5870.

    I thought this was an enthusiast site?

    I lol irl when people talk about saving 100 watts and buying a 5870. So saving 100 watts but building a 700 watt system? Are you saving the planet or something?

    I think nVidia is smart, if you fold or use cuda or need real time 3d performance from a quadro you will buy this card. That probably is a large enough market for a niche high end product like this.

    PS: 5870 is the best gaming card for the money!
    Reply
  • Paladin1211 - Sunday, March 28, 2010 - link

    No, the 5850 is.

    p/s: I misclicked the Report instead of Reply button, so pls ignore it T_T
    Reply
  • kallogan - Sunday, March 28, 2010 - link

    Seriously i wonder who'd want gpus that power angry, noisy and hot...Nvidia is out both on mobile and desktop market...The only pro for Nvidia i can see is the 3D support. Reply
  • beginner99 - Sunday, March 28, 2010 - link

    This is kind of bad for consumers. 0 pressure on ATI to do anything from lower price to anything else. they can just lay back and work on the next gen.
    Well, that at least made my decision easy. build now or wait for sandybridge. I will wait. hoepfully gpu marekt will be nicer then too (hard to be worse actually).
    Reply
  • C5Rftw - Sunday, March 28, 2010 - link

    I was waiting for the fermi cards to come out before my next high end build( looking for price drops), but I actually did not expect this card to be this fast. The GTX480 is ~15% faster than the 5870, but for $100 more, and it is just gonna be a Nvidia loyal card, and the 5870 will probably drop just a little if at all.. The 5850 and and 5830 should drop $25-50, hopefully more(2x5850 at ~250$ each would be FTW). Now, would I like to have a fermi?, well yeah for sure, but I would much rather have a 5870 and down the road add another. A GTX 480 uses the same, if not more power than (2) 5870's. Now this reminds me of the last gen of the P4's. or as we know em, the Preshots. Basically, Nvidia's idea of a huge chip approach, with yes impressive performance, was just the wrong approach. I mean, their next-gen, if based on this same "doubling" SPs, cuda cores, would draw 300w+ easily and almost require water cooling because the next TSMC process is going to be 32nm and that will not allow them to "cut the chip in half." ATI's theory started with the 4000 series has proven to be a much better/efficient design. I think they could make a 6870 using 40nm TSMC right now, but ofcourse it would be a hot chip. Now when they get the 32 TSMC FABs running, Nvidia has got to re-design their chips.. And with how hot the GTX 480 is, I dont see how they could make a GTX 495. Also, the 5890 is right around the corner and that should give the final punch to KO Nvidia in this GPU generation. On a side note, Thank " " that there is some healthy competion or AMD might pull what Nvidia did and rebrand the 8800 5 or 6 times. Reply
  • Belard - Sunday, March 28, 2010 - link

    Keep in mind, the GeForce 480 (GTX means nothing, see any GTX210 or GT 285?) is already the most power hungry card on the market, just under 300watts under full load.... if the GF480 had all 512 Cuda Cores running and clocked higher... the card will easily surpass 300watts!

    This in turn means MORE heat, more power, more noise. There are videos on the 480/470s & ATI cards... the 480's fan is running very fast and loud to keep it under 100c, about 2~3 times hotter than a typical CPU.

    We will see the ATI 6000 series on 40nm, but it may not be with TSMC.

    If the upcoming 5890 is 15% faster and can sell for $400~450, that would put some hurt on the GF480.

    Not sure how/why ATI would do re-branding. The 4670 is almost like a 3870, but is easily a more advanced and cheaper GPU. The bottom end GPUs have all changed. 2400 / 3450, 4350, 5450 - all different.

    Nvidia has been doing re-branding for quite a long time. The GF2mx was re-branded as the GF2MX 400 (These were bottom end $150~190 cards in 2001) and then for some bone-head reason, during the GF6 era - they brought back the GF2MX but added DX8. Huh? Add a function to an OLD bottom end GPU?

    The GF2-TI came out when GF3-TI series was launched... they wanted "TI" branding. The GF2-TI was a rebranded GF2-Pro with a slight clock upgrade.

    Then came the first big-branding/feature fiasco with Nvidia. The GF8 was the first DX8 cards. Then the GF 4 series came out. The GF4ti were the high end models. But the MX series were nothing more than GF2 (DX7) with optional DVI... to take care of the low end and shove the letter names to the front.

    GF4 mx420 = GF2mx, but a bit slower.
    GF4 mx440 = GF2 Pro/TI
    GF4 mx460 = ... faster DX7 card, but it was about $20~35 cheaper than the GF4-TI4200, a DX8 card. The Ti4200 was a #1 seller at about $200. Some of the 440se & 8x models may have 64 or 128bit RAM... ugh.

    Then they had fun with the TI series when AGP 8x came out... NEW models! Either thou the cards couldn't max out the AGP 4x bus. Even the future ATI 9800Pro only ran 1~3% faster with AGP 8x.

    GF4 Ti 4200 > GF4 Ti 4200 8x
    GF4 Ti 4400 > GF4 Ti 4800 SE
    GF4 Ti 4600 > GF4 Ti 4800

    Yep, same GPUs... new names. Some people would upgrade to nothing or worse. Some even went from the 4600 to the 4800SE which was a downgrade!

    GF5 5500 = 5200

    Since the GF5... er "FX" series, Nvidia kept the DX# and feature set within the series. All GF5 cards are DX9.

    But the 5200s were a joke. By the time they hit the market at $120, the Ti4200s were also $120 and the 4mx were reduced to $30~60. But the 5200 was HALF the performance of a 4200. People actually thought they were upgrading... returns happened.

    Funny thing once. A person bought a "5200" at walmart and was confused by the POST display of "4200". Luckily he had posted to us on the interent. We laughed our butts off...! What happened? Batch & switch... someone bought a 5200, took it home - switched cards, took it back to Walmart for a refund. hey, its usually a brick or a dead card, etc. he got used card, but a much better product.

    Like the ATI 5450 is too slow for gaming today for DX11, the GF5200 was horrible back in 2003 for DX9! The 5200 is still sold today, the only thing left.

    Pretty much the entire GF5 series was utter garbage. 4 versions of the GF5600 ($150~200) were slower than the previous $100 Ti 4200. It was sick. This allowed ATI to gain respect and marketshare with their ATI 9600 & 9700 cards. The GF 5700 series (2 out of 5 types) were good Ti4200 replacements. The 5900 went up against the ATI 9800. I've owned both.

    Since then, ATI pretty much had the upper hand in performance throughout the GF6 & GF7 era. AMD buys out ATI, then the GF8 and core2 wipes out ATI/AMD with faster products.

    While ATI had the faster cards during DX9.0c (really MS? Couldn't make 6.1, 6.2?) era over the GF6/7... Nvidia *HAD* the lower end market. The GF6600 and 7600GT were $150~200 products... ATI products in that price range were either too slow or cost too much.

    With GF 8800 & 8600s, ATI had lost high & mid-range markets. The HD 2000 series = too expensive, too hot and not fast enough... (sound familiar). The ATI 3000 series brought ATI back to competitive position where it counted. Meanwhile, Nvidia milked the G92~96 for the past 2+ years. They are code-name & model number crazy happy.

    As long as ATI continues doing engineering and management this way, nVidia will continue to be in trouble for a long time unless they get their act together or count on the server market to stay in business.

    End of short history lesson :0
    Reply

Log in

Don't have an account? Sign up now