Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

NVIDIA and AMD Launch New High-End Workstation, Virtualization, and HPC GPUs

Unknown Lamer posted about 2 years ago | from the doubles-as-a-space-heater dept.

Graphics 95

MojoKid writes "Nvidia is taking the wraps off a new GPU targeted at HPC and as expected, it's a monster. The Nvidia K20, based on the GK110 GPU, weighs in at 7.1B transistors, double the previous gen GK104's 3.54B. The GK110 is capable of pairing double-precision operations with other instructions (Fermi and GK104 couldn't) and the number of registers each thread can access has been quadrupled, from 63 to 255. Threads within a warp are now capable of sharing data. K20 also supports a greater number of atomic operations and brings new features to the table including Dynamic Parallelism. Meanwhile, AMD has announced a new FirePro graphics card at SC12 today, and it's aimed at server workloads and data center deployment. Rumors of a dual-core Radeon 7990 have floated around since before the HD 7000 series debuted, but this is the first time we've seen such a card in the wild. On paper, AMD's new FirePro S10000 is a serious beast. Single and double-precision rates at 5.9 TFLOPS and 1.48 TFLOPS respectively are higher than anything from Intel or Nvidia, as is the card's memory bandwidth. The flip side to these figures, however, is the eye-popping power draw. At 375W, the S10000 needs a pair of eight-pin PSU connectors. The S10000 is aimed at the virtualization market with its dual-GPUs on a single-card offering a good way to improve GPU virtualization density inside a single server." My entire computer uses less power than one of these cards.

cancel ×

95 comments

Sorry! There are no comments related to the filter you selected.

Intel's Xeon Phi is also out (2)

symbolset (646467) | about 2 years ago | (#41964361)

Here is the spin from El Reg [theregister.co.uk] .

How long is the wait ? (4, Interesting)

Taco Cowboy (5327) | about 2 years ago | (#41964453)

Right now they are all too expensive, and consume too much juice.

How long would the wait be before these things get to have pricetag that average Joe (well, advance version of average Joe) can afford ?

Re:How long is the wait ? (1)

symbolset (646467) | about 2 years ago | (#41964565)

About three years, I think. China is doing some good work with MIPS cores these days.

Re:How long is the wait ? (1)

LordLimecat (1103839) | about 2 years ago | (#41966363)

3 years is right, considering theyre about 3 generations behind AMD and Intel.

Re:How long is the wait ? (2)

hairyfeet (841228) | about 2 years ago | (#41965661)

I've found if you stay a couple of generations behind you can get excellent bang for the buck without breaking your wallet. For example I've had the HD4850 for a couple of years now, paid a grand total of $75 for a 256bit card that was nearly $300 when first released. Come Feb I'll be moving to an HD6850, it'll be around $90-$100 by then and again 256bit only with GDDR 5 instead of 3 and I have no doubt it'll be good for a couple of years if not longer.

Re:How long is the wait ? (-1, Troll)

Life2Death (801594) | about 2 years ago | (#41966071)

I just purchased 4 of said 6850 for about $105 a pop. What rocks do you live under good sir?

Re:How long is the wait ? (0)

Anonymous Coward | about 2 years ago | (#41966295)

I just purchased 4 of said 6850 for about $105 a pop. What rocks do you live under good sir?

So you are saying that, at $105, it's not quite yet in the $90-$100 range that he said he expects it to be in by Feb. Not sure what your point is, or what living under a rock has to do with anything.

I am confused. (0)

Anonymous Coward | about 2 years ago | (#41964383)

The S10000 is aimed at the virtualization market with its dual-GPUs on a single-card offering a good way to improve GPU virtualization density inside a single server.

I know this may be a stupid question, but I have a hard time imagining how a GPU could be of practical use on a VM, outside of GPGPU stuff (where it seems like using a VM would still be less efficient, if performance is so important).

Re:I am confused. (0)

Anonymous Coward | about 2 years ago | (#41964399)

even one VM can start bogging down fairly standard issue gamer issue cards, imagine a dozen running at once

Re:I am confused. (2)

Martin Blank (154261) | about 2 years ago | (#41964681)

I'm hoping for a consumer-level version so I can run Linux as my primary and Windows as a secondary gaming OS and still get full GPU performance on both platforms.

Re:I am confused. (1)

Anonymous Coward | about 2 years ago | (#41965561)

You can already do this. Search for "PCIe passthrough" "VGA passthrough" "Xen passthrough" etc. Requires a processor that supports AMD-V or Intel VT-d.

Desktop Virtualization does graphics on a server (5, Informative)

billstewart (78916) | about 2 years ago | (#41964535)

Server virtualization doesn't really need this - running web servers or databases or name servers, which are all essentially fancy timesharing.

But "Desktop Virtualization" emulates your entire desktop as a virtual machine on a shared server, graphics and all, and just ships the rendered screens back to your desktop, accessible from anywhere, with RDP or VNC or whatever, kind of like a clumsy version of X Windows except you get to do full-scale graphics acceleration at the server farm instead of at your desktop. The mainframe IT crowd like it, because the PC on your desk can be dumb and low-powered, and the server back in the server farm they get to maintain can be big and fancy, and they can have better control over it than over your desktop, don't need to keep every bit of software up to date on everybody's remote PC, and it's generally easier to manage. And if you're logging into your work desktop from Starbucks, they don't have to protect it as thoroughly from everybody else there, and you can access your work Windows desktop from your personal iPad or your kid's gaming machine or whatever, and the company data's not very vulnerable because there's really nothing running on the remote machine.

And using this chip, they've got a lot more graphics horsepower available for rendering desktops, so for instance they can provide you with adequate performance for video editing, not just for email and word processing .

Re:Desktop Virtualization does graphics on a serve (2, Interesting)

Anonymous Coward | about 2 years ago | (#41964759)

I think you missed the point here. Even if the card is capable of doing super high res rendering, the network traffic would be the weak point. The graphics card is much much better off being put in the client than rendering to a bitmap that has to be transferred. (And remote desktop protocols try to compare what has actually changed in order to send the least amount of data, which will cause high processing load when you run something at a high FPS).

I think is for using GPUs for processing (Password cracking, protein folding, etc.), as many specialized computational software packages do.

Re:Desktop Virtualization does graphics on a serve (1)

billstewart (78916) | about 2 years ago | (#41964863)

I didn't say I'm convinced that Desktop Virtualization is a good thing, as opposed to a scam for selling hardware to IT departments. But this chip could very well make it better. It seems to be especially popular in environments where everybody has an actual desk they sit in front of, but it's also starting to address the BYOD market.

Re:Desktop Virtualization does graphics on a serve (2)

gubon13 (2695335) | about 2 years ago | (#41965033)

The problem with virtualized desktop infrastructure (VDI) display technology rarely has anything to do with graphic limitations of the server.

The problem almost always has everything to do with the technologies that exist to send screen data to the zero/thin/thick client over anything less than a sub-5ms, 1Gbps+ LAN. RDP is trash, VNC is trash, PCoIP is slightly less poopy trash.

Now, could this GPU have some sort of application for, say, the video editing industry, where these client/server systems are quite advanced (but always on said sub-5ms, 1Gbps+ LAN)? Sure.

But a BYOD application? Probably never...

Re:Desktop Virtualization does graphics on a serve (0)

Anonymous Coward | about 2 years ago | (#41966221)

The problem almost always has everything to do with the technologies that exist to send screen data to the zero/thin/thick client over anything less than a sub-5ms, 1Gbps+ LAN. RDP is trash, VNC is trash, PCoIP is slightly less poopy trash.

That's funny since I can use RDP over 2-3 mbps connections just fine.

Re:Desktop Virtualization does graphics on a serve (2)

Luckyo (1726890) | about 2 years ago | (#41966775)

"Can use" =! "works well".

Re:Desktop Virtualization does graphics on a serve (1)

billstewart (78916) | about 2 years ago | (#41975481)

My standard desktop environment at work uses RDP on a 10 Mbps LAN through an old slow firewall to connect to a jump server in my lab; when I'm at home I use SSL VPN over 3 Mbps DSL to get to the company network gateway location, and then run RDP over that through the firewall in my lab. (We do computer security development in our underground laboratory, so we can't simply connect it to the office LAN because it has a direct internet connection with various mean nasty ugly stuff on it.) The jump server used to be an actual machine; now it's a VM image of Win2008 or something similar.

So a standard office desktop kind of environment works ok there - I can surf the web on the jump server, run lightweight Flash or Java animation, drag windows around, etc. I can even use VMware tools to access the consoles of other VMs. Theoretically I can run video on it, but at least YouTube in a browser is badly jumpy, and audio is actively painful, even if I'm at the office. I haven't bothered to track down the bottlenecks, because there are too many of them in between me and the application; if I really need to watch animation on one of the lab boxes, I can connect my laptop directly to the lab-net cable instead of using RDP.

I'd expect that PCoIP on an adequately tuned network would work better, because some of the people they sell it to need to do need to watch video or listen to audio at work (and because we haven't bothered tuning ours.) And the BYOD market has become seriously important to business - too many people want to use their iPads or shiny Mac laptops to access their work environments, and Virtual Desktop provides a way to do that without the IT department having to make all the corporate applications work on all the target platforms.

Re:Desktop Virtualization does graphics on a serve (1)

GNious (953874) | about 2 years ago | (#41966005)

Use the GPU for heavy compression of bitmap data? :)

Re:Desktop Virtualization does graphics on a serve (2, Informative)

Anonymous Coward | about 2 years ago | (#41965463)

I've done several Virtual Desktop projects for "scientific users" using GPU based acceleration on the physical server hosting the VDIs. The benefits of a powerful GPU are many:

1) You can provide GPU accelerated applications to all or some VDI users (I'm talking about GPU for calculation, not necessarily rendering graphics).
2) You can provide accelerated rendering by pairing server-GPU with whatever GPU is on the endpoint desktop for a better user experience (especially over limited network bandwidth), using technologies like HDX-3D Pro.
3) You can share out that GPU in the server to tens or potentially hundreds of users at once, so getter a better return on your capital investment in such a high-price item.

Since I can have 3 or 4 GPUs in a single server, VDI projects tend to be limited more by memory (we use 1TB VMCo nodes, each can hold hundreds of desktops), or IOPS (rather, storage latency to be accurate), where we use a tier of solid state storage.

Whether its a good idea or not, there are still loads of scientific users out there who are graduating from using local tools on their local PC (rather than a dedicated compute/rendering farm/cluster) and they like to continue working that way. VDI+GPU+Big memory appliance+Solid State means they dont have to "re-train".

Re:Desktop Virtualization does graphics on a serve (1)

billstewart (78916) | about 2 years ago | (#41975589)

1) The orginal poster had said "except for GPGPU etc."; there's lots of obviously cool computational application for these things, if you need to do heavy calculation.

2) Thanks, I hadn't known about that! (I haven't really looked at Xen since Citrix bought it, though I'm starting to see people using it instead of VMware because of the Free Beer prices.)

3) This thing seems to be about 5-10 times the price of a typical medium-high-end video card, so you need a reasonably large group of users to make it pay off, but especially for scientific users who also want it for calculation it could be a good deal.

Re:Desktop Virtualization does graphics on a serve (1)

Life2Death (801594) | about 2 years ago | (#41966099)

Its too bad that GPU acceleration on the VM world is so infantile right now. Hyper-V and VMWare can sorta do it OK but again, it has its issues and problems such as overhead or just not running all together (certain apps want certain cards.)

No one in a business is going to drop $4000 on a card to render kitty videos faster for the accounting department, no, these are for CAD and design engineers who want to go thin client.

Re:Desktop Virtualization does graphics on a serve (0)

Anonymous Coward | about 2 years ago | (#41966473)

Many database internal operations are intrinsically parallel. GPUs can accelerate Joins, Sorts, Query planning, and Stored Procedures.
Speeding databases allows new computationally intensive applications like image queries, 3D CMS, data mining, ...

My entire house uses less power than one of these (1)

fustakrakich (1673220) | about 2 years ago | (#41964387)

Well, it's good to see AMD keeping with tradition, a blessing for those in the frozen north..

Re:My entire house uses less power than one of the (0)

Anonymous Coward | about 2 years ago | (#41964425)

no it doesn't, a standard refrigerator uses more at 10x the voltage, quit being a dink

Re:My entire house uses less power than one of the (1)

fustakrakich (1673220) | about 2 years ago | (#41964439)

Voltage isn't power..

Re:My entire house uses less power than one of the (-1)

Anonymous Coward | about 2 years ago | (#41964515)

so 375 watts at 12 volts is the same as 375 watts at 120 volts?

well fuck me, everything should run at 1 volt and save the earth

Re:My entire house uses less power than one of the (2, Informative)

Anonymous Coward | about 2 years ago | (#41964557)

so 375 watts at 12 volts is the same as 375 watts at 120 volts?

Yes, unless you're talking 375 amps at 12 volts vs 375 amps at 120 volts (which is quite a lot)

Re:My entire house uses less power than one of the (1)

Joce640k (829181) | about 2 years ago | (#41965373)

Ummm, but he isn't, he's talking watts...

Re:My entire house uses less power than one of the (1)

Dan9999 (679463) | about 2 years ago | (#41967271)

don't you mean watts he talking about?

Re:My entire house uses less power than one of the (1)

Joce640k (829181) | about 2 years ago | (#41965375)

Yes, unless you're talking 375 amps at 12 volts vs 375 amps at 120 volts (which is quite a lot)

Did somebody seriously mod that "informative"??? Sheesh.

(Right now it's modded "+2 infromative"...)

Re:My entire house uses less power than one of the (0)

Anonymous Coward | about 2 years ago | (#41965457)

Watts, volts... Just triggered the moderator's soundex algorithm (And mine too... And I am an Elec. engg)

Re:My entire house uses less power than one of the (2, Informative)

Anonymous Coward | about 2 years ago | (#41965711)

Ugh...

Repeat after me, Watt/hour = Amps/hours * Voltage

Amperage = Current over time
Wattage = Power over time

Current(Amp) != Power(Watt)

Btw, if you don't know, normal electrical devices are measured in hours, meaning X watt usage really means X watts over a period of an hour.

So 375 watts = total power
Higher voltage and lower current can equal the same power as lower current and higher voltage. Realistically, certain applications require certain voltages to work (high voltages for ovens as they are basically giant resistors). End result though, 375watts used in a device at 110v is the same as 375w used in say a 12v device. All that means is that the current draw is different.

Sincerely, a different AC who never bothered to create an account

Re:My entire house uses less power than one of the (1)

drakaan (688386) | about 2 years ago | (#41970459)

...Amperage = Current over time
Wattage = Power over time...

No.

Amperage is synonymous with current, wattage is synonymous with power...not current over time or power over time, that would be amp-hours or watt-hours if you're bringing time into the equation.

...Current(Amp) != Power(Watt)...

Correct.

...Btw, if you don't know, normal electrical devices are measured in hours, meaning X watt usage really means X watts over a period of an hour...

No.

Batteries and other electrical sources have capacities measured in watt-hours or amp-hours...electrical devices usually have specifications of required voltage and average, maximum, and minimum current draw at that voltage.

If you have a 4000mwh 6-volt battery and a device with a current draw of 250mw @6v, then you can tell how long your battery should last.

...So 375 watts = total power
Higher voltage and lower current can equal the same power as lower current and higher voltage. Realistically, certain applications require certain voltages to work (high voltages for ovens as they are basically giant resistors). End result though, 375watts used in a device at 110v is the same as 375w used in say a 12v device. All that means is that the current draw is different...

Correct.

Re:My entire house uses less power than one of the (1)

drakaan (688386) | about 2 years ago | (#41970951)

Have to correct myself, too...

...If you have a 4000mwh 6-volt battery and a device [with a current draw of] that uses 250mw @6v, then you can tell how long your battery should last...

Re:My entire house uses less power than one of the (3, Informative)

jones_supa (887896) | about 2 years ago | (#41965793)

so 375 watts at 12 volts is the same as 375 watts at 120 volts?

Yes, unless you're talking 375 amps at 12 volts vs 375 amps at 120 volts (which is quite a lot)

I think it's better to say 31 amps at 12 volts and 3 amps at 120 volts, both totaling to 375 watts.

Re:My entire house uses less power than one of the (1)

Tiger_Storms (769548) | about 2 years ago | (#41968843)

I think it's better to say 31 amps at 12 volts and 3 amps at 120 volts, both totaling to 375 watts.

Thank you for saying this, I think my head was about to explode from the people trying to figure out how it stuff works.

Re:My entire house uses less power than one of the (0)

Anonymous Coward | about 2 years ago | (#41977671)

Well, it's probably better to say it is 1/2 horsepower and imagine one half of a horse powering it... I guess the best would be to note it would take 3,226,666.66 of them to consume as much power as 1 flux capacitor.

Re:My entire house uses less power than one of the (1)

fustakrakich (1673220) | about 2 years ago | (#41964569)

Yep, 375 watts is 375 watts... Pretty amazing, isn't it?

Re:My entire house uses less power than one of the (1)

Anonymous Coward | about 2 years ago | (#41964581)

"Watts" are a unit of power, which is a measure of "energy" delivered per time. The technical notion of "energy" is actually fairly different from what a non-physicist probably thinks of when they say that word. "Voltage" or electric potential is closely related to energy, and is measure by the unit "volts." It is, however, not an energy. 375 Watts is a certain amount of energy delivered every second, in particular, 375 Joules. If this provided by an electrical current at 120 volts, or 12 volts, this is still the same amount of power. There is a relationship between delivered power, current, and voltage, P=IV, which involves another quantity, which I won't go into explaining. So, yes, in energetic terms, 375 watts is 375 watts. There is no reason that running something at 1 volt would save the earth any more than 120 volts. In fact, there is another effect, which I will not try to explain, that higher voltages tend to cause less lost energy due to resistance in wires.

Re:My entire house uses less power than one of the (2, Informative)

Anonymous Coward | about 2 years ago | (#41965157)

Volts = Difference in height between two water tanks
Amps = Flowrate in the hose connecting both tanks
Watts = Number of full water buckets * height difference you'd have to carry _per second_ to do the same
Energy = Total volume of water transfered * height difference

Re:My entire house uses less power than one of the (0)

Anonymous Coward | about 2 years ago | (#41965317)

Great analogy, thanks. Never could get past the "pressure and flow" comparisons, myself.

Re:My entire house uses less power than one of the (1)

LocoMosquito (1767862) | about 2 years ago | (#41969425)

1W=1J/s therefore 1Ws (Watt second) = 1J E=mc^2 => m=e/c^2 1gram=24GWh

Re:My entire house uses less power than one of the (4, Interesting)

epyT-R (613989) | about 2 years ago | (#41964629)

just wait until you wet your noodle on capacitive/inductive AC where watts is watts except when it's volt-amps, and efficiency is measured as a ratio between watts and volt-amps.

Re:My entire house uses less power than one of the (1)

spongman (182339) | about 2 years ago | (#41964889)

unreal!

Re:My entire house uses less power than one of the (3, Informative)

serviscope_minor (664417) | about 2 years ago | (#41965597)

and efficiency is measured as a ratio between watts and volt-amps.

No, efficiency is still measured as useful work out / Joule in.

You are referring to power factor, not efficiency.

The two are related, since electricity companies bill you on the number of Volt-Amps * Time used, not number of Joules, since it's much harder to do the latter, and the former determines the actual current which determines most of the expensive things, i.e. transmission losses, wire guage (infrastructure costs), etc.

If you're seriously screwey on your power factor, you can buy a power factor corrector and it will probably pay off quite quickly if you're a big user.

Re:My entire house uses less power than one of the (1)

inasity_rules (1110095) | about 2 years ago | (#41966319)

Power factor is a useless measure anyway. It is just a ratio. A bad power factor at 2W is not as bad as a bad power factor at 200kW. Use Vars instead. A much more useful value to have. Given the math of it I fail to understand why anyone is interested in PF. Source; I have designed PF correction systems (up to about 10MVars).

Re:My entire house uses less power than one of the (1)

ChrisMaple (607946) | about 2 years ago | (#41977111)

electricity companies bill you on the number of Volt-Amps * Time used

WRONG. Electric companies bill on watt-hours or other equivalent units of energy. Although large users of electricity may be charged penalties if the power factor is bad (V*A>>W), the basis is energy, not volt-amps*time.

Re:My entire house uses less power than one of the (1)

maxwell demon (590494) | about 2 years ago | (#41964991)

so 375 watts at 12 volts is the same as 375 watts at 120 volts?

In terms of power, it is.

well fuck me, everything should run at 1 volt and save the earth

The reason why this is a bad idea is that the currents you'd need then are extremely high (375 W at 12 V is 31.25 A, 375 W at 120 V is 3.125 A), and high currents means high losses in the electric line delivering the power (the losses grow quadratically with the current), which means you'd need thicker wires to compensate (the resistance is inversely proportional to the cross section), or can only use very short wires (the resistance is proportional to the length).

Re:My entire house uses less power than one of the (1)

serviscope_minor (664417) | about 2 years ago | (#41965603)

the resistance is inversely proportional to the cross section)

It's worse than that. At high currents, you need large cross sections. With AC, the skin effect will start to kick in eventually, which makes the resistance inversely proportional to the circumference of the wire, i.e. with the square root of the cross section.

Which is really annoying.

Re:My entire house uses less power than one of the (0)

Anonymous Coward | about 2 years ago | (#41968007)

Make it 0V and that would really save the Earth.

Re:My entire house uses less power than one of the (1)

TheSkepticalOptimist (898384) | about 2 years ago | (#41973301)

Would it be an Earth worth living in? What's the point of saving it if there is nothing to do.

Re:My entire house uses less power than one of the (0)

Anonymous Coward | about 2 years ago | (#41964787)

I see no references to voltage, only wattage.

Re:My entire house uses less power than one of the (0)

Anonymous Coward | about 2 years ago | (#41964467)

The typical fridge uses about 200 watts with the compressor running. Stop making stuff up.

Re:My entire house uses less power than one of the (0)

Anonymous Coward | about 2 years ago | (#41964485)

it uses 400 watts once its started, start up is much more

Re:My entire house uses less power than one of the (0)

Anonymous Coward | about 2 years ago | (#41965097)

woosh

oh, and you're a moron.

Quick! (1)

oldhack (1037484) | about 2 years ago | (#41964391)

Beowolf these mofos.

Re:Quick! (2)

Wonko the Sane (25252) | about 2 years ago | (#41964653)

Beowolf these mofos.

That's so last century.

These days it's, "imagine a Bitcoin mining rig of these"

Doesn't quite have the same cadence, though,

Re:Quick! (0)

Anonymous Coward | about 2 years ago | (#41965541)

It'll be Chris Poole anyways to waste these on bitcoin mining. The ASICs are coming.

And they have an 8-board FirePro system running (4, Interesting)

mozumder (178398) | about 2 years ago | (#41964397)

3.6 kilowatts, 16 GPUs:
http://fireuser.com/blog/8_amd_firepro_s10000s_16_gpus_achieve_8_tflops_real_world_double_precision_/ [fireuser.com]

and to think all this comes from video games.

Re:And they have an 8-board FirePro system running (0)

Anonymous Coward | about 2 years ago | (#41964489)

Total nerd porn, but really what are those power supplies in that machine? Did they just skip the "redundant" part and hardwire all three of them in?

Re:And they have an 8-board FirePro system running (1)

PhamNguyen (2695929) | about 2 years ago | (#41964959)

A thing of beauty indeed.

If you look carefully at the third picture you'll see that the graphics cards are hooked up to a green pcb like thing, and if you look at the first picture, you'll see that this green thing is plugged into the powers supply on the left. And in the second picture you see 3 power cords plugged into the power supply. I dunno where you buy this stuff (or if AMD built it themselves), but I really want one.

Re:And they have an 8-board FirePro system running (1)

Splab (574204) | about 2 years ago | (#41965181)

Looks like 3 sepperate PSUs, don't think thats too hard to come by.

Re:And they have an 8-board FirePro system running (1)

PhamNguyen (2695929) | about 2 years ago | (#41964977)

Update: The case is Colfax CXT8000 which has 3 1200W power supplies.

Re:And they have an 8-board FirePro system running (0)

Anonymous Coward | about 2 years ago | (#41977777)

The Colfax CTX8000 chassis is the OEM version of the following Tyan chassis if you want a whitebox version without the price overhead...

http://www.tyan.com/product_SKU_spec.aspx?ProductType=BB&pid=439&SKU=600000246

Re:And they have an 8-board FirePro system running (1)

Jayfield (2317990) | about 2 years ago | (#41964497)

Just look at those 8 cards crammed into that case! What are they called again? Oh yeah, FirePro!

Re:And they have an 8-board FirePro system running (1)

blahplusplus (757119) | about 2 years ago | (#41964591)

"and to think all this comes from video games."

The word "video games" just hides the fact that videogames are SIMULATIONS/Models (although simplified) of some aspect of the world. No one would be surprised since videogames are basically alternative world simulations and we're heading towards a time (eventually over the long term) where extremely complex behavior will be simulated.

OB: If I had a beowolf cluster of these.... (0)

Anonymous Coward | about 2 years ago | (#41964765)

Id have a shot at the top500... or mabye not.

Anway, Weighing in at 375W ( my current system is 90W),
Looks like I would need TWO EXTRA power supplies for two cards in SLI,

My semi-serious question: What comes with it in terms of cookware?
A ATI Skillet for frying eggs? an ATI spatula for scraping off frying journalists?
A Slashdot zapper?

Nice. I would like to see AutoCAD render on one of these aptly described beasts.

Re:OB: If I had a beowolf cluster of these.... (0)

Anonymous Coward | about 2 years ago | (#41965333)

Yep. I'd like to watch a render of 2 hours of high-def - or, even better, RED 4K footage

Re:And they have an 8-board FirePro system running (3, Interesting)

knarf (34928) | about 2 years ago | (#41965005)

Those 8 TFLOPS would have landed it somewhere at the top of the #500 supercomputer performance list in November, 2011 [top500.org] . ASCI White [top500.org] used 8192 375MHz Power3 cores to achieve this performance. It took up a fair bit of space [energy.gov] and used 3 MW to run the machine with a further 3 MW needed for cooling. It had a theoretical processing speed of 12.3 teraflops.

Re:And they have an 8-board FirePro system running (4, Informative)

knarf (34928) | about 2 years ago | (#41965017)

Of course that should read 'November 2001', not 'November 2011'...

Ya well there are some limits (1)

Sycraft-fu (314770) | about 2 years ago | (#41965903)

GPUs are powerful because they are more limited than CPUs. They are very good at what they do, but not as good at general operations. So, you can find things they are exceedingly good at, and thus way faster than CPUs, but also things they are bad at, and thus way slower.

1 TFlop on a video card isn't the same as a TFlop on a CPU in terms of the things you can do. A simple example of the limits are memory, the GPU relies on very fast local memory to do its work, but it is small, relatively speaking, under 10GB. So if your problem set is large, that is a problem as the data then has to go over the PCIe bus which is slow, from the GPU's perspective.

Don't get me wrong, they are dynamite for many kinds of problems, hence why they are popular, but you can't just compare them to a CPU.

ermahgerd (0)

Anonymous Coward | about 2 years ago | (#41964419)

"My entire computer uses less power than one of these cards." ....yeah. i just cried a little on the inside.

Re:ermahgerd (1)

Anonymous Coward | about 2 years ago | (#41965841)

Agreed, it was a bit silly analogue.

Thread sharing data? (0)

Anonymous Coward | about 2 years ago | (#41964475)

"Threads within a warp are now capable of sharing data."

Woohoo... we discovered the keyword __shared__...

Re:Thread sharing data? (2)

darkain (749283) | about 2 years ago | (#41964981)

SHARING IS CARING!

Whoa, Nelly! (0)

Anonymous Coward | about 2 years ago | (#41964691)

More transistors on a chip than people on Earth.

*blinks*

Not for desktops and gaming (0)

Anonymous Coward | about 2 years ago | (#41964825)

These are for HPC (high performance computing). Basically these things will blow your mind if your work involved solving huge amounts of certain types of maths. Like matrices for example.

  So you can simulate forces in car accidents, simulate nuclear explosions, code cracking, pattern finding, data analysis etc. You know, real work.

  Good to see AMD in the game and fully committed. Now if only they can build the Opteron CPU's to match. Where is our FP performance you bastards! Not all of us are running web servers (spit spit) or virtualising office PC's (spit spit). Interger performance should be doubled up, and double your FPU. I want earth shattering FPU performance. I want Searing theaded interger performance. I want 10 or 12 cores on die, 20-24 cores per package..

  Give me give me...

375 W (4, Insightful)

timeOday (582209) | about 2 years ago | (#41964995)

Here is a dumb thing to say:

My entire computer uses less power than one of these cards.

Does the person who wrote this know how much a TFLOP actually is, let alone 5.9 TFLOPS (single precision) and 1.48 TFLOPS (double)? As an example, an Intel Core i7 980 XE does 109 GFLOPS double-precision. This is over 13 times that! It is really exciting to see the power of GPUs broadened to scientific computing in general. I doubt these cards would be cost-effective or are really intended for gaming.

Re:375 W (0)

Anonymous Coward | about 2 years ago | (#41965061)

you must be new here. this place crawls with amateurs and kids.

Re:375 W (1)

Neil Boekend (1854906) | about 2 years ago | (#41965179)

There is probably someone making a mod on some first person shooter to run it at 4 quadHD screens powered by an array of these cards. A couple of posts up someone already posted images of a system with 8 of these cards in it (because 1 wouldn't be awesome enough).

Re:375 W (1)

gman003 (1693318) | about 2 years ago | (#41965309)

Ironically, I don't think you can. At least, not at all easily.

The FirePro cards shows don't support multiple GPUs driving a single output. So you'd have to find some way to avoid treating the array of screens as a single screen, which is far easier said than done. At the very least, extensive reworking of the game's renderer seems in order, and any game open-source enough for a modder to do that is old or graphically-limited enough that you could drive quad QHD monitors using my laptop.

The Tesla and Xeon Phi don't support video output at all, and the drivers have no OpenGL or Direct3D support to my knowledge. So you would have to reimplement the entire graphics layer, then somehow pipe it out through another video card via shared memory.

And honestly, even then, I'm not sure you'd need a array of eight of these cards for any game on the market. I can max out nearly any game on my laptop, at full 1080p, using the mobile version of the GeForce 640. A mere 384 shader cores. The Tesla K20X is based on the same architecture, but scaled up to 7 times as many cores, and at a clock speed not significantly lower. So a gaming-oriented version of the K20X could max out any game on a three-by-two array of "Full HD" monitors (5760x2160). At four, you're running a three-by-two array of "Ultra HD" monitors (11520x4320) at 120+FPS. There is no way I can think of to feasibly require more from your hardware than this, and that's half the GPUs you proposed.

Re:375 W (0)

Anonymous Coward | about 2 years ago | (#41965625)

Not yet, but latest Crysis 3 benchmarks are showing 28 avg FPS (15 min FPS) for single GTX 690 [buzer.net] . With 1 screen setup.

Re:375 W (1)

timeOday (582209) | about 2 years ago | (#41976197)

Not yet, but latest Crysis 3 benchmarks are showing 28 avg FPS (15 min FPS) for single GTX 690. With 1 screen setup.

Well, that one screen is at 2560x1600. Not that many people have 30" screens. (Then again, Apple's "retina" display may start a long-overdue megapixel war in PC displays, if we are lucky).

Also this is "VHQ" quality. I see nothing wrong with releasing a new top title that cannot be played smoothly at max settings with current cards, so long as the game looks at least as good as any other game on current cards.

Re:375 W (0)

Anonymous Coward | about 2 years ago | (#41965205)

Here is a dumb thing to say:

My entire computer uses less power than one of these cards.

Does the person who wrote this know how much a TFLOP actually is, let alone 5.9 TFLOPS (single precision) and 1.48 TFLOPS (double)?
    As an example, an Intel Core i7 980 XE does 109 GFLOPS double-precision. This is over 13 times that! It is really exciting to see the power of GPUs broadened to scientific computing in general. I doubt these cards would be cost-effective or are really intended for gaming.

" does 109 GFLOPS double-precision" - Can do is a better way of putting it as no real application will get anywhere near this limit. And similarly on the GPU. In fact in general peak flops is a fairly useless measure of computational power, except for marketing people to a gullible audience.

Much more interesting would be a comparison of performance on a realistic HPC workload, and by that I do NOT mean Linpack or matrix multiplies,

There is no "realistic HPC workload" (2)

S3D (745318) | about 2 years ago | (#41965445)

Specific algorithmic implementation and limitation imposed on it by hardware are wildly different. Some algorithms don't need If's and branch prediction, other do. Different algorithms have different memory access pattern, different complexity of the kernels(for GPGPUU) and different requirement to memory bandwidth. Even on GPGPU algorithms doing the same thing in CUDA and in OpenCL can have several times performance difference. And some algo consist of mostly matrix multiplication, and quite a number of useful methods reach peak GPGPU performance (for example PDE solution). You can't find consistent "average" HPC algorithm.

Re:375 W (2)

serviscope_minor (664417) | about 2 years ago | (#41965653)

Does the person who wrote this know how much a TFLOP actually is, let alone 5.9 TFLOPS (single precision) and 1.48 TFLOPS (double)? As an example, an Intel Core i7 980 XE does 109 GFLOPS double-precision. This is over 13 times that!

By way of comparison, the Opteron 6174 can hit a bit over 180GFlops in LINPACK. On a shared memory machine multi socket machine, the efficiency is very high, so a quad socket Opteron 6100 box would probably manage in the region of 700GFlops.

Anyway, plugging the numbers, the 6174 has a TDP of 175W, making the GPU about 4x better interms of FLOPs / Watt.

That's actually less than I was expecting.

Still can't beat the grunt and efficiency and density of GPUs yet, as long as you can program the little buggers. They're still very limited by access to memory.

Re:375 W (1)

EmagGeek (574360) | about 2 years ago | (#41965857)

Does the person even know that computer components are not sitting there consuming their tdp all the time?

The tdp is just a theoretical number that represents the maximum amount of heat energy the package is capable of dissipating without being damaged. It is NOT the amount of power the device will consume in normal operation. In practice, you will almost NEVER see a CPU or GPU consuming its tdp.

Re:375 W (1)

inasity_rules (1110095) | about 2 years ago | (#41966429)

I don't know hey. Given that these things dynamically overclock parts to when there is thermal/power headroom available, I would guess, yes, you would see it using tdp. Most processors under the right load should see tdp or close to it in the right loads. It might be tdp minus 2% or 3%, but close enough. If you have better cooling or a lower ambient, you might run into the power limit, which is generally set close to the rated tdp. But it all depends what your load is.

Re:375 W (2)

jeffb (2.718) (1189693) | about 2 years ago | (#41969589)

This. Remember the Cray-1 supercomputer? $5-10 million, 100KW power draw. The standard against which other systems were compared through the early 80's.

This card provides more than ten thousand times the computational power, using less than one-half percent the electrical power.

The future really is a cool place.

Nice! (1)

lennier1 (264730) | about 2 years ago | (#41966013)

With the adoption of GPU-based rendering in 3D graphics workstations for the entertainment industry it's great to see developments like that.

Rats. (1)

q043x (256014) | about 2 years ago | (#41966185)

I just, with this article, realise that my understanding of computer science may not be keeping up with reality. I am now old. Why would someone want to calculate zillions of floating point results on their PC? How can a GPU card have no graphical interface? And when did we start using Teraflops in desktops!??!?!

Re:Rats. (1)

Quince alPillan (677281) | about 2 years ago | (#41967463)

Your GPU card does more than just output video. The GPUs on these cards are designed for brute force calculations and chugging through numbers. They're designed for physics engines, running through protein folding calculations, and rendering high quality video in real time.

If you want to equate them to a design in the past, think of them as really really really powerful math co-processors. CPUs are designed for short command queues and calculations that are hard to predict the next step, while GPUs are designed for long command queues and easily predictable calculations.

...and we've been using teraflop scale on desktops since 2008. [amd.com]

Export restrictions (2)

hjf (703092) | about 2 years ago | (#41966193)

These things are regulated. Argentina tried to buy a few (5!) of their previous line, I think it was Tesla. The US government wouldn't allow it. Guess you have to be a NATO member to buy these.

For Editing? (0)

Anonymous Coward | about 2 years ago | (#41968109)

If one edits films would one of these cards make it a faster process from more typical home equipment or is playback the sole reason to purchase? If it helps with editing how much bang for the buck?

Check for New Comments
Slashdot Login

Need an Account?

Forgot your password?

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>