NVIDIA's GeForce GTX 580: Fermi Refined
by Ryan Smith on November 9, 2010 9:00 AM ESTFinal Thoughts
Even though NVIDIA is only launching a single card today there’s a lot to digest, so let’s get to it.
Since the GeForce GTX 580 arrived in our hands last week, we’ve been mulling over how to approach it. It boils down to two schools of thought: 1) Do we praise NVIDIA for delivering a high performance single GPU card that strikes the right balance of performance and temperature/noise, or 2) Do we give an indifferent thumbs-up to NVIDIA for only finally delivering the card that we believe the GTX 480 should have been.
The answer we’ve decided is one of mild, but well earned praise. The GTX 580 is not the true next-generation successor to the GTX 480; it’s the GTX 480 having gone back in the womb for 7 months of development. Much like AMD, NVIDIA faced a situation where they were going to do a new product without a die shrink, and had limited options as a result. NVIDIA chose wisely, and came back with a card that is both decently faster and a refined GTX 480 at the same time.
With the GTX 480 we could recognize it as being the fastest single GPU card on the market, but only by recognizing the fact that it was hot and loud at the same time. For buyers the GTX 480 was a tradeoff product – sure it’s fast, but is it too hot/too loud for me? The GTX 580 requires no such tradeoff. We can never lose sight of the fact that it’s a high-end card and is going to be more power hungry, louder, and hotter than many other cards on the market, but it’s not the awkward card that the GTX 480 was. For these reasons our endorsement of the GTX 580 is much more straightforward, at least as long as we make it clear that GTX 580 is less an upgrade for GTX 480, and more a better upgrade for the GTX 285 and similar last-generation cards.
What we’re left with today is something much closer to the “traditional” state of the GPU market: NVIDIA has the world’s fastest single-GPU card, while AMD is currently nipping at their heels with multi-GPU products. Both the Radeon HD 5970 and Radeon HD 6870 CF are worthy competitors to the GTX 580 – they’re faster and in the case of the 6870 CF largely comparable in terms of power/temperature/noise. If you have a board capable of supporting a pair of 6870s and don’t mind the extra power it’s hard to go wrong, but only if you’re willing to put up with the limitations of a multi-GPU setup. It’s a very personal choice – we’d be willing to trade the performance for the simplicity of avoiding a multi-GPU setup, but we can’t speak for everyone.
So what’s next? A few different things. From the NVIDIA camp, NVIDIA is promising a quick launch of the rest of the GeForce 500 series. Given the short development cycles for NVIDIA we’d expect more refined GF10x parts, but this is very much a shot in the dark. Much more likely is a 3GB GTX 580, seeing as how NVIDIA's official product literature calls the GTX 580 the "GeForce GTX 580 1.5GB", a distinction that was never made for the GTX 480.
More interesting however will be what NVIDIA does with GF110 since it’s a more capable part than GF100 in every way. The GF100 based Quadros and Teslas were only launched in the last few months, but they’re already out of date. With NVIDIA’s power improvements in particular, this seems like a shoo-in for at least one improved Quadro and Tesla card. We also expect 500 series replacements for some of the GF100-based cards (with the GTX 465 likely going away permanently).
Meanwhile the AMD camp is gearing up for their own launches. The 6900 series is due to launch before the year is out, bringing with it AMD’s new Cayman GPU. There’s little we know or can say at this point, but as a part positioned above the 6800 series we’re certainly hoping for a slugfest. At $500 the GTX 580 is pricey (much like the GTX 480 before it), and while this isn’t unusual for the high-end market we wouldn’t mind seeing NVIDIA and AMD bring a high-intensity battle to the high-end, something that we’ve been sorely missing for the last year. Until we see the 6900 series we wouldn’t make any bets, but we can certainly look forward to it later this year.
Facebook
Twitter
RSS
160 Comments
View All Comments
chizow - Tuesday, November 9, 2010 - link
There's 2 ways they can go with the GTX 570, either more disabled SM than just 1 (2-3) and similar clockspeed to the GTX 580, or fewer disabled SM but much lower clockspeed. Both would help to reduce TDP but with more disabled SM that would also help Nvidia unload the rest of their chip yield. I have a feeling they'll disable 2-3 SM with higher clocks similar to the 580 so that the 470 is still slightly slower than the 480.I'm thinking along the same lines as you though for the GTX 560, it'll most likely be the full-fledged GF104 we've been waiting for with all 384SP enabled, probably slightly higher clockspeeds and not much more than that, but definitely a faster card than the original GF104.
vectorm12 - Tuesday, November 9, 2010 - link
I'd really love to see the raw crunching power of the 480/580 vs. 5870/6870.I've found ighashgpu to be a great too to determine that and it can be found at http://www.golubev.com/
Please consider it for future tests as it's very well optimized for both CUDA and Stream
spigzone - Tuesday, November 9, 2010 - link
The performance advantage of a single GPU vs CF or SLI is steadily diminishing and approaching a point of near irrelevancy.6870 CF beats out the 580 in nearly every parameter, often substantially on performance benchmarks, and per current newegg prices, comes in at $80 cheaper.
But I think the real sweet spot would be a 6850 CF setup with AMD Overdrive applied 850Mz clocks, which any 6850 can achieve at stock voltages with minimal thermal/power/noise costs (and minimal 'tinkering'), and from the few 6850 CF benchmarks that showed up would match or even beat the GTX580 on most game benchmarks and come in at $200 CHEAPER.
That's an elbow from the sky in my book.
smookyolo - Tuesday, November 9, 2010 - link
You seem to be forgetting the minimum framerates... those are so much more important than average/maximum.Sihastru - Tuesday, November 9, 2010 - link
Agreed, CF scales very badly when it comes to minumum framerates. It is even below the minimum framerates of one of the cards in the CF setup. It is very anoying when you're doing 120FPS in a game and from time to time your framerates drop to an unplayable and very noticable 20FPS.chizow - Tuesday, November 9, 2010 - link
Nice job on the review as usual Ryan,Would've liked to have seen some expanded results however, but somewhat understandable given your limited access to hardware atm. It sounds like you plan on having some SLI results soon.
I would've really liked to have seen clock-for-clock comparisons though to the original GTX 480 though to isolate the impact of the refinements between GF100 and GF110. To be honest, taking away the ~10% difference in clockspeeds, what we're left with seems to be ~6-10% from those missing 6% functional units (32 SM and 4 TMUs).
I would've also liked to have seen some preliminary overclocking results with the GF110 to see how much the chip revision and cooling refinements increased clockspeed overhead, if at all. Contrary to somewhat popular belief, the GTX 480 did overclock quite well, and while that also increased heat and noise it'll be hard for someone with an overclocked 480 to trade it in for a 580 if it doesn't clock much better than the 480.
I know you typically have follow-up articles once the board partners send you more samples, so hopefully you consider these aspects in your next review, thanks!
PS: On page 4, I believe this should be a supposed GTX 570 mentioned in this excerpt and not GTX 470: "At 244W TDP the card draws too much for 6+6, but you can count on an eventual GTX 470 to fill that niche."
mapesdhs - Tuesday, November 9, 2010 - link
"I would've also liked to have seen some preliminary overclocking results ..."
Though obviously not a true oc'ing revelation, I note with interest there's already
a factory oc'd 580 listed on seller sites (Palit Sonic), with an 835 core and 1670
shader. The pricing is peculiar though, with one site pricing it the same as most
reference cards, another site pricing it 30 UKP higher. Of course though, none
of them show it as being in stock yet. :D
Anyway, thanks for the writeup! At least the competition for the consumer finally
looks to be entering a more sensible phase, though it's a shame the naming
schemes are probably going to fool some buyers.
Ian.
Ryan Smith - Wednesday, November 10, 2010 - link
You're going to have to wait until I have some more cards for some meaningful overclocking results. However clock-for-clock comparisons I can do.http://www.anandtech.com/show/4012/nvidias-geforce...
JimmiG - Tuesday, November 9, 2010 - link
Well technically, this is not a 512-SP card at 772 MHz. This is because if you ever find a way to put all 512 processors at 100% load, the throttling mechanism will kick in.That's like saying you managed to overclock your CPU to 4.7 GHz.. sure, it might POST, but as soon as you try to *do* anything, it instantly crashes.
Ryan Smith - Tuesday, November 9, 2010 - link
Based on the performance of a number of games and compute applications, I am confident that power throttling is not kicking in for anything besides FurMark and OCCT.