Slashdot Mirror
NVIDIA's New Flagship GeForce GTX 580 Tested
MojoKid writes "Even before NVIDIA's GF100 GPU-based GeForce GTX 480 officially arrived, there were a myriad of reports claiming the cards would be hot, loud, and consume a lot of power. Of course, NVIDIA knew that well before the first card ever hit store shelves, so the company got to work on a revision of the GPU and card itself that would attempt to address these concerns. Today the company has launched the GeForce GTX 580 and as its name suggests, it's a next-gen product, but the GF110 GPU powering the card is largely unchanged from the GF100 in terms of its features. However, refinements have been made to the design and manufacturing of the chip, along with its cooling solution and PCB. In short, the GeForce GTX 580 turned out to be the fastest, single-GPU on the market currently. It can put up in-game benchmark scores between 30% and 50% faster than AMD's current flagship single-GPU, the Radeon HD 5870. Take synthetic tests like Unigine into account and the GTX 580 can be up to twice as fast."
http://www.pcper.com/article.php?aid=1034
http://www.hardocp.com/article/2010/11/09/nvidia_geforce_gtx_580_video_card_review
http://www.anandtech.com/show/4008/nvidias-geforce-gtx-580
http://www.legitreviews.com/article/1461/1/
http://www.techreport.com/articles.x/19934
http://www.bit-tech.net/hardware/graphics/2010/11/09/nvidia-geforce-gtx-580-review/1
I am very glad to see the performance crown handed back and forth.
Now if only this was happening in the CPU market...
At what point are Nvidia and AMD going to supplant the need for an Intel or AMD cpu? This (graphics) processor in a card is blazingly fast.
Its not really driving down the cost of the old cards as much as they used to, how much does this thing cost, and why does a 8800GTX still cost tween 200$ and 400$ and its not uncommon to see GTX280's for nearly 500 bucks
yes I know they have cheaper cards, I have a GTS250 but still
This GTX580 is a 3 billion transistor chip(not counting the RAM on the same card, just the GPU die itself). Does anybody know what year the number of transistors on the entire planet reached the number on this die?
I'm more mystified by the form factors of these things with every new release - I really miss being able to actually see the PCB on my new hardware. At what point is it going to be more expedient for me to simply place my GPU in its' own little box outside the case to expedite cooling, perhaps a dedicated power supply, of course lots of fans... A Graphics Appliance if you will.
...ought to be enough for anybody.
He who knows best knows how little he knows. - Thomas Jefferson
So, this card is about as fast, and consumes about the same power as a 480, but it's "next gen" anyway ?
That looks like a 480 with the 4 replaced by a 5. Hardly a revolution.
Just watercool the 480, it's how it's supposed to be used.
What may happen, what AMD would like to see happen, is for GPU functions to become a part of the CPU, that GPUs go away because CPUs can do it. However that'll be because CPUs have GPU like logic in addition to their own. GPUs are great and blazingly fast... But only at some things. I've written up the list before and don't feel like doing it again but more or less you find that some things run great on a GPU, others run for shit. More or less it has to be floating point, massively parallel, and have very little branching. Some things meet that criteria, others don't.
CPUs are CPUs because they are good at everything. They can do any task well. GPUs are specialized processors, they do only certain tasks, but do them much better. You can go a step further to ASICs, Application Specific Integrated Circuits. They do one and only one thing, but are amazing at it. ASICs are how a tiny, cheap, 5 watt switch can forward 16gb/sec of traffic. Try having a computer do that and you'd need a beefy system to process all of it but a tiny ASIC on the switch can handle it. However it does nothing but switch packets, it is completely inflexible in its design.
Does anyone assume that the synthetic benchmarks achieved by either AMD or NVIDIA are representative of anything more than these companies' efforts to tweak their driver sets against the pre-existing criteria for getting a "good score"?
Both companies I believe have been accused over the years of doing just that and pointing the finger at the other as taking part in shennaniganism"
I went to battle M.C. Escher, but drew a blank.
everyone knows if it's an NVIDIA it's gotta be good....wink..wink.
I hope someone can figure out how to bypass the anti-overclocking tech. Otherwise, AMD is going to have an easier ride this round. Why are all manufacturers so damn evil? What's wrong with a little overclocking to boost speeds? When I'm spending this much money on a video card the least they could do is allow me to boost my speeds a little. They've also made water cooling the card pointless with their new current limiter. It's so easy to hate Nvidia. I'll buy from whichever company has the fastest card (without totally unreasonable pricing), but Nvidia's behavior is just so low. If anything they should be making it easier to overclock as the motherboard manufacturers do. An easy to adjust voltage control would be a much better feature than a current limiter. It would even give you the ability to undervolt to run quiet and cool.
Quite an experience to live in fear, isn't it? That's what it is to be a slave.
For one, there are a lot of motherboards that don't support it. Even new, reasonably high end boards. I have an Intel P35 board with a Core 2 Quad at home, but it has only 1 16x slot. At work, a Dell Precision T1500 with an i7, again only 1 16x slot. Crossfire/SLI cannot be done in these cases. You have to buy a single, heavier hitting, card if you want performance.
Also you need to do a bit more research if you think multi-card solutions work well all the time. They can, but they also can have some serious problems. Some games work great, others can't use a second card at all. There is something to be said for the simplicity of a single card that does what you need.
In terms of needing the speed? Well depends on what you have and your tastes. You certainly don't need it to play any game, all games are playable on less. However you might need it if you desire extremely high resolutions and high frame rates. If you have a 30" monitor and want to drive it at its native, beyond HD rez (2560x1600) you need some heavy hitting hardware to take care of that, particularly if you'd like the game to run nice and smooth, more around 60fps than around 30. You then need still more if you'd like to crank up anti-aliasing and so on.
Now that clearly isn't for everyone, but that's fine. There is no reason not to have a high end as well as a mid range. You should hate on people who want more performance than you do. In fact, you should thank them. Know why the 5770 is so cheap? Because the 5870 is not. That high end card financed the development of the new tech, it recouped a lot of the R&D costs, making an economical midrange card a reality.
This is why nobody seems to be able to break in and compete with nVidia and ATi in graphics. They target midrange or lower end, because development costs on high end stuff is so much. However nVidia and ATi have extremely solid mid and low range lineups, because they can take the tech on their high end cards, and scale it down.
Am I the only one not dumbfounded by how incredible these things are? And how much progress has been made with graphics cards and PC Gaming. You can get a graphics solution running Crysis at max settings at almost 60 fps for only $300 (GTX 460 SLI). With that, you can run every other game at max settings, 1900x1200, at like 100 FPS. I don't ever remember PC gaming giving this much bang-for-your-buck or making this much available.
I'm not knocking consoles, they have their places. But it just hurts to play any game at the low resolution of a console and its low graphics settings. And I find myself thinking Steam is even easier plug-and-play than the consoles are. And all the new advanced graphics features are in the new cards. I can't imagine the consoles ever catching up. And it wouldn't be economical for the console makers to do so. I think the future of gaming really may lie in the PC.
Just my opinion. Please, no flamewars here. I have both a PC and a 360 and I appreciate them both in different ways. I'm just floored at how far PC gaming have come in only 3 years.
P.S. I know the responses are coming, so I'll just put a disclaimer that I have my computer hooked up to my HDTV in my living room and yes I run most recent and current games at max or high graphics settings on an ancient 8800 GTS 512 with a Core 2 Duo and 2GB RAM.
Is it powerful enough to run Civilization V?
"The agriculture ministry is not in charge of Gundam" - Japanese ministry official.
The /. summary ends with:
It can put up in-game benchmark scores between 30% and 50% faster than AMD's current flagship single-GPU, the Radeon HD 5870.
But if you read the original article, the one flaw in the (otherwise good) nVidia card is that is still loses to the 5970 which is -- according to the article -- 'about a year old'. So why is that other article mentioned in the summary talking about the 5870 as if its the flagship? Clearly the 5970 is. Or am I missing something?
Wood Shavings!
- Godai
..never as long as Nvidia refuses to release even a hint of documentation and insists that GNU/Linux users accept their Binary Blob World Order. I don't really care if this new card is faster than the fastest AMD card, atleast I can (ab)use those for something. I still have a Nvidia PCI (not PCIe) card on some shelf which does NOT work with the Binary Blob under GNU/Linux, nor does it work with nouveau joke of a free driver.
9/11: Never forget it was a false-flag operation
HardOCP is famous for their real gameplay ratings. They go and actually play through the game while testing performance. They then find the highest settings that the reviewer finds playable. Now while there is some subjectivity to it they do back it up with FPS numbers, and it is the same reviewer trying everything out. So it gives real, in game, actually playing, results. I find it maps nicely to what actually happens when I get a card and play games.
http://hardocp.com/article/2010/11/09/nvidia_geforce_gtx_580_video_card_review
The fastest single GPU consumer card available. TDP 244W! You can safely scrap your room heater now!
nvidia's previous flagship GTX480 uses more power at high loads and idle, competitor's ATi range 5xxx use more juice in idle, so it's definitely an improvement in all areas except price.
The name only suggests to me that they need a naming convention instead of just mashing the keyboard each release.
Looks like HardOCP hasn't been testing AMD's most recent flagship product, the Radeon HD 6xxx series, which a single card alone eats a 480GTX for breakfast.
Still waiting on Serviscope_minor to wake up to fucking reality and realize that Jessica Price isn't going to fuck him.
I am not in the market for a room heater! The HD68x0 ATIs take pretty much half that, at half the performance and a quarter of the price.
Again a showy card from Nvidia that basically only supports the ego of their lying boss and is otherwise a waste of money.
Most ACs are not even worth the keystrokes to insult them. Be generically insulted by this and ignored otherwise.
On a 30" monitor you have ~100 pixels per inch. At normal viewing distance that means they are a bit smaller than an most monitors, but still plenty visible. They are not as small as on many laptops, and not down to the level you need for them to completely vanish. That is probably in the realm of 300PPI or so. You might be able to get away with 200PPI, but then just leaning in might be enough that they aren't truly blended anymore.
So until the display is that high rez, AA is useful. We've got a long way to go to that point.
Also it still would probably be useful. As the other poster noted, you get a case of "pixel pop" with AA off. When you have a hard transition, a hard edge you notice it. In motion it can be seen as shimmer, even with small pixels. AA solves that quite nicely. Now perhaps with really small pixels this wouldn't be a problem, I don't know, I'd have to test, but they might have to be even smaller than you'd normally need.
Is that multi-GPU solutions are NOT the same as single GPU solutions just faster. In some cases, multi-GPU works great, you get nearly a doubling in speed. In other cases, it works ok you get more speed than single, though not double. In still other cases, it doesn't work at all, only one GPU is used. In yet other cases, shit goes really wrong and games won't work right unless you shut down a GPU. It depends on the game in question, the drivers you are using, and which company's GPUs you have. nVidia tends to be better, their SLI generally works better than ATi's Crossfire. However it still have problems in some cases.
Fast single GPU solutions are of interest because they work well. When you go multi-GPU, problems arise. In some cases, that's just fine, in particular if you are already using fast GPUs and only by going multiple can you go faster. However other people don't want the trouble. They'll pay extra for a single GPU that works.
Is you think nVidia's driver team should have to write good open source drivers all by themselves, since clearly the OSS community isn't nearly as good at graphics drivers as they pretended. I mean I remember the rhetoric: Just release the documentation, we've got legions of people who will crank out a driver that is better than any of the closed ones in a hurry. Ya well we see how that went. Here it is over a year later and you say it still can't stand up to ATi's closed driver, which is not nearly as good an nVidia's closed driver.
The problem I think is twofold:
1) The OSS heads didn't appreciate how damn complex a graphics driver is. You have people who'd written SCSI drivers or something and said "Well that isn't that hard." They forget that a binary SCSI driver is around 20k or something, you are dealing with a simple device. The main ATi Windows driver is 7.6MB and that is just the central driver, never mind all the support files it needs to work right. It is a major job, and the hardware changes fast.
2) The licensed stuff that the binary drivers have isn't for nothing. The companies license various technologies, parts of code, etc for a reason. None of those can go in the OSS drivers. They don't license it just for fun, there are reasons, and if that functionality has to be redone from scratch, well there you go.
So really I can't fault nVidia at all. They provide an extremely good binary driver. It is fast and have great feature support. They do not want to do the work to try and make an OSS driver that is as good (if it is even possible without the proprietary parts) for what is quite a small market. Also, the OSS community has quite well demonstrated with ATi that while they might have the will to help, they lack the ability to do so effectively. "Just give us the docs," was very clearly not enough.
So its been released now? Why then can I not purchase one?
Stupid distortion of the English Language :/
...