Final Words

To wrap things up, let’s start with the obvious: NVIDIA has reclaimed their crown – they have the fastest single-GPU card. The GTX 480 is between 10 and 15% faster than the Radeon 5870 depending on the resolution, giving it a comfortable lead over AMD’s best single-GPU card.

With that said, we have to take pause for a wildcard: AMD’s 2GB Radeon 5870, which will be launching soon. We know the 1GB 5870 is RAM-limited at times, and while it’s unlikely more RAM on its own will be enough to make up the performance difference, we can’t fully rule that out until we have the benchmarks we need. If the GTX 480 doesn’t continue to end up being the fastest single-GPU card out there, we’ll be surprised.

The best news in this respect is that you’ll have time to soak in the information. With a retail date of April 12th, if AMD launches their card within the next couple of weeks you’ll have a chance to look at the performance of both cards and decide which to get without getting blindsided.

On a longer term note, we’re left wondering just how long NVIDIA can maintain this lead. If a 2GB Radeon isn’t enough to break the GTX 480, how about a higher clocked 5800 series part? AMD has had 6 months to refine and respin as necessary; with their partners already producing factory overclocked cards up to 900MHz, it’s too early to count AMD out if they really want to do some binning in order to come up with a faster Radeon 5800.

Meanwhile let’s talk about the other factors: price, power, and noise. At $500 the GTX 480 is the world’s fastest single-GPU card, but it’s not a value proposition. The price gap between it and the Radeon 5870 is well above the current performance gap, but this has always been true about the high-end. Bigger than price though is the tradeoff for going with the GTX 480 and its much bigger GPU – it’s hotter, it’s noisier, and it’s more power hungry, all for 10-15% more performance. If you need the fastest thing you can get then the choice is clear, otherwise you’ll have some thinking to decide what you want and what you’re willing to live with in return.

Moving on, we have the GTX 470 to discuss. It’s not NVIDIA’s headliner so it’s easy to get lost in the shuffle. With a price right between the 5850 and 5870, it delivers performance right where you’d expect it to be. At 5-10% slower than the 5870 on average, it’s actually a straightforward value proposition: you get 90-95% of the performance for around 87% of the price. It’s not a huge bargain, but it’s competitively priced against the 5870. Against the 5850 this is less true where it’s a mere 2-8% faster, but this isn’t unusual for cards above $300 – the best values are rarely found there. The 5850 is the bargain hunter’s card, otherwise if you can spend more pick a price and you’ll find your card. Just keep in mind that the GTX 470 is still going to be louder/hotter than any 5800 series card, so there are tradeoffs to make, and we imagine most people would err towards the side of the cooler Radeon cards.

With that out of the way, let’s take a moment to discuss Fermi’s future prospects. Fermi’s compute-heavy and tessellation-heavy design continues to interest us but home users won’t find an advantage to that design today. This is a card that bets on the future and we don’t have our crystal ball. With some good consumer-oriented GPGPU programs and developers taking up variable tessellation NVIDIA could get a lot out of this card, or if that fails to happen they could get less than they hoped for. All we can do is sit and watch – it’s much too early to place our bets.

As for NVIDIA’s ecosystem, the situation hasn’t changed much from 2009. NVIDIA continues to offer interesting technologies like PhysX, 3D Vision, and CUDA’s wider GPGPU application library. But none of these are compelling enough on their own, they’re merely the icing on the cake. But if you’re already in NVIDIA’s ecosystem then the choice seems clear: NVIDIA has a DX11 card ready to go that lets you have your cake and eat it too.

Finally, as we asked in the title, was it worth the wait? No, probably not. A 15% faster single-GPU card is appreciated and we’re excited to see both AMD and NVIDIA once again on competitive footing with each other, but otherwise with much of Fermi’s enhanced abilities still untapped, we’re going to be waiting far longer for a proper resolution anyhow. For now we’re just happy to finally have Fermi, so that we can move on to the next step.

Temperature, Power, & Noise: Hot and Loud, but Not in the Good Way
POST A COMMENT

197 Comments

View All Comments

  • Headfoot - Monday, March 29, 2010 - link

    Unless you are an insider all of this "profitability" speculuation is just that, useless speculation.

    The reason they make both companies chips is more likely due to diversification, if one company does poorly one round then they are not going to go down with them. I'd hate to make ATI chips during the 2900XT era and i'd hate to make nVidia chips during the 5800 FX era
    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.
    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.
    Reply
  • iwodo - Saturday, March 27, 2010 - link

    If i remember correctly Nvidia makes nearly 30- 40% of their Profits from Telsa and Quadro. However Telsa and Quadro only occupies 10% of their Total GPU volume shipment. Or 20% if we only count desktop GPU.
    Which means Nvidia is selling those Perfect grade Fermi 512 Shader to the most profitable market. And they are just binning these chips to lower grade GTX 480 and GTX 470. While Fermi did not provide the explosion of HPC sales as we initially expected due to heat and power issues, but judging by pre-order numbers Nvidia still has quite a lot of orders to fulfill.

    The Best thing is we get another Die Shrink in late 2010 / early 2011 to 28nm. ( It is actually ready for volume production in 3Q 2010 ). This should bring Lower Power and Heat. Hopefully the next update will get us a much better Memory Controller, with 256Bit controller and may be 6Ghz+ GDDR5 should offer enough bandwidth while getting better yield then 384Bit Controller.

    Fermi may not be exciting now, but it will be in the future.
    Reply
  • swing848 - Saturday, March 27, 2010 - link

    We are not living in the future yet.

    When the future does arrive I expect there will also be newer, better hardware.
    Reply
  • Sunburn74 - Saturday, March 27, 2010 - link

    So how do you guys test temps? It's not specifically stated. Are you using a case? An open bench? Using readings from a temp meter? Or system readings from catalyst or nvidia control panel? Please enlighten. It's important because people will eventually have to extrapolate your results to their personal scenarios which involve cases of various designs. 94 degrees measured inside a case is completely different from 94 degrees measured on an open bench.

    Also, why are people saying all this stuff about switching sides and families? Just buy the best card available in your opinion. I mean it's not like ATI and Nvidia are feeding you guys and clothing your kids and paying your bills. They make gpus, something you plug into a case and forget about if it's working properly. I just don't get it :(
    Reply
  • Ryan Smith - Saturday, March 27, 2010 - link

    We're using a fully assembled and closed Thermaltake Spedo with a 120mm fan directing behind the video cards feeding them air. Temperatures are usually measured with GPU-Z unless for some reason it can't grab the temps from the driver. Reply
  • hybrid2d4x4 - Saturday, March 27, 2010 - link

    Thanks for elaborating on the temps as I was wondering about that myself. One other thing I'd like to know is how the VRM and RAM temps are on these cards. I'm assuming that the reported values are for just the core.
    The reason I ask is that on my 4870 with aftermarket cooling and the fan set pretty low, my core always stayed well below 65, while the RAM went all the way up to 115 and VRMs up to ~100 (I have obviously increased fan speeds as the RAM temps were way too hot for my liking- they now peak at ~90)
    Reply
  • Ryan Smith - Saturday, March 27, 2010 - link

    Correct, it's just the core. We don't have VRM temp data for Fermi. I would have to see if the Everest guys know how to read it, once they add support. Reply
  • shiggz - Friday, March 26, 2010 - link

    I just am not interested in a card with a TDP over 175W. When I upgraded from 8800gt to GTX 260 It was big jump in heat and noise and definitely at my tolerance limit during the summer months. I found myself under-clocking a card I had just bought.

    175W max though a 150W is preferred @ 250$ and I am ready to buy if NVIDIA wont make it then I will switch back to ATI.
    Reply

Log in

Don't have an account? Sign up now