Impressive GPU Numbers From Folding@Home 201
ludd1t3 writes, "The Folding@Home project has put forth some impressive performance numbers with the GPU client that's designed to work with the ATI X1900. According to the client statistics, there are 448 registered GPUs that produce 29 TFLOPS. Those 448 GPUs outperform the combined 25,050 CPUs registered by the Linux and Mac OS clients. Ouch! Are ASICs really that much better than general-purpose circuits? If so, does that mean that IBM was right all along with their AS/400, iSeries product which makes heavy use of ASICs?"
Lopsided Alright.. (Score:2, Interesting)
Those 448 GPUs outperform the combined 282,111 CPUs registered by the Linux and Mac OS clients. Ouch! Are ASICs really that much better than general-purpose circuits? If so, does that mean that IBM was right all along with their AS/400, iSeries product which makes heavy use of ASICs?"
That's pretty lopsided, but I suppose some of it could be explained away by GPU's not chewing through OS code and having to play nice for memory, so they'd be a bit more efficient. Could be most of those Linux and MacOS s
Re:Lopsided Alright.. (Score:4, Insightful)
Re: (Score:2)
Re: (Score:2)
Re:Lopsided Alright.. (Score:5, Informative)
Unless you are saying all CPUs are pegged at 99.9% use, or the GPU has memory three orders of magnitude faster then you're just looking at a effects that make a few percent difference here and there. The simple fact is the GPU is insanely faster at solving specific problems (3D processing) while it simply cannot ever run an operating system.
Re: (Score:2)
i'm guessing that the better parallelization in the GPU together with the fact that the average GPU participating in Folding is much more mo
Re:Lopsided Alright.. (Score:5, Insightful)
Re: (Score:2)
Re:Lopsided Alright.. (Score:4, Interesting)
1. GPU: 65.463
2. Linux: 1.219
3. Windows: 0.948
4. Mac: 0.511
Of course, GPU beating the hell out of CPU in such tests is no surprise. It's pretty much a massive parallel vector engine. I'm more interested in seeing how PS3 holds agains all other guys when it comes out. They have a folding client for PS3 already.
Re: (Score:2)
Re: (Score:2)
But these are not general purpose processors - in
Re: (Score:2)
The differences come in the quantity, not the kind. A CPU gives over a lot of transistors to caches and complex logic units. A GPU does not care much about logic and lacks caches.
Re: (Score:2)
Re: (Score:3, Funny)
"I can think of many, many things at once. As long as they are the same type of thing."
So obvious... (Score:2)
Re:So obvious... (Score:5, Funny)
Re: (Score:2, Funny)
- No, that's what consoles are for.
Re:So obvious... (Score:5, Funny)
Are ASICs really that much better? (Score:5, Funny)
Generally ASICs are much better than general-purpose circuits except in general cases.
Re: (Score:2)
Re: (Score:3, Funny)
You realize that somebody is bound to write a word processor that runs on a GPU now, just to prove it can be done?
Re: Are ASICs really that much better? (Score:4, Insightful)
Re: Are ASICs really that much better? (Score:5, Interesting)
Re: (Score:3, Funny)
Re: (Score:2)
GPUs are designed to perform floating point operations on 4x4 arrays of floating point numbers. This allows them to do the math required to scale, rotate, and project 3d vectors onto a 2d surface. Follow so far? These circuits not only have fast memory ties and huge parallelism, the are also hard wired to perform some of the exact same operations required by FAH in only a few clock cycles instead of 44 (on the P4, 14 on the Opteron).
Being massively para
Less specifically speaking: (Score:2)
The more specifically you can narrow down the problem set you're trying to solve, the faster you can solve it. The more specific your tool, the better it will work on that problem
IBM right all along, or obvious? (Score:3, Funny)
Distributed amongst home users (Score:5, Funny)
Solomon
Re:Distributed amongst home users (Score:5, Interesting)
Re: (Score:3, Funny)
Re: (Score:2)
And clearly, attempting to cure cancer and other such diseases is merely a waste of electricity.
Re: (Score:3, Insightful)
Obvious? (Score:2, Insightful)
Maybe I'm missing some subtlety in the OP somewhere, but if GPUs weren't better at what they're doing than CPUs, there wouldn't be a point in having a GPU in the first place.
...and if you have a problem that can be expressed in terms of the problem space the GPU is designed to handle, then that problem is going to run faster on the gpu than on the CPU.
Re: (Score:2)
Re: (Score:2)
Except that the operations used for folding are a subset of the operations performed for 3D graphics.
In a word, folding is a subset of 3D graphics processing and rendering, which does make the conclusion obvious.
Re: (Score:2, Offtopic)
Except you can Windows on a Mac now, so it can play games. So Macintosh hardware can do everything a Mac can do and everything a PC can do, making the Mac the superior hardware choice.
Re: (Score:2)
Re: (Score:2)
...until you realize that Asus computers can't run Mac OS (legally, stablely (is that a word?), conveniently, etc.), which tips the balance back in favor of the Apple.
Re: (Score:2)
Mac IS NOT the superior hardware choice for games (Score:2)
The top of the line iMac comes with a 7300GT Nvidia card. You can up it to a mid range 7600GT card at most. Now with Windows installed, do you think that the 7600GT would drive the 24" monitor as well as oh say a dual 7900GT SLI setup?
Oh, get a Mac Pro you say. Well except that you still have no SLI or Crossfire support and extremely limited choices of video cards. And it costs an arm and a leg. Sure it's cheap for a dual Xeon workstation - but if you just want to play games
For which purpose? (Score:2)
GPUs are Specialized Parallel Computers (Score:5, Insightful)
Making a general purpose parallel computer is very, very hard. It just so happens that you can use things like shaders for more than just graphics processing, and so via OpenGL and DirectX you can make GPUs do some nifty things.
In theory, and indeed often in practice, parallel computers are much, much faster than their serial counterparts. Hence the reason a GPU that costs $200 can render incredible 3D scenes that a $1000 CPU wouldn't have a prayer trying to render.
Re:GPUs are Specialized Parallel Computers (Score:5, Informative)
Here's a Wikipedia article [wikipedia.org] on general purpose GPU processing.
Folding is what's know as a rediculously parallel problem. That is, it can be broken up in to small subproblems that can be distributed among many processors with a minimal amount of communication among processors. It also benefits from not requiring a lot of branching (if/switch statements and such), which GPUs generally do not handle well.
Many problems, (I'd argue MOST problems) do not cater well to these kinds of restrictions. So, while a GPU is well suited to crunching away on pieces of the folding problem, it's going to be lousy at doing the day-to-day stuff you do with your computer.
Re:GPUs are Specialized Parallel Computers (Score:5, Informative)
This is the perfect time... (Score:3, Interesting)
I actually installed boinc with seti on several of my machines last night and it worked quite well to heat part of the house (us Canadians need to turn the heater on earlier). Took a bit of time to get started, but it was nice and toasty in the morning.
Does anyone know if this method is less efficient in generating heat than using a apace heater? Slower perhaps...
If you're going to use energy by turning on the wall heater anyways, why not use it to crunch some numbers?
Re: (Score:2)
It probably depends on the technology your space heater uses to generate heat. If it's old-fashion resistive coils, it's probably about as efficient. The newer ceramic-element heaters I'm not sure about.
For the most efficient electric heating, you should be using a whole-house heat pump.
Re: (Score:2)
I'm not sure if you meant to exclude heat pumps from this statement, but if not, heat pumps can achieve 3-4 times the efficiency of resistance heaters. Here's a handy link [gsu.edu] that explains it in layman's terms.
But yo
Re:This is the perfect time... (Score:5, Insightful)
Using your CPU as a space heater is not a bad idea. It is 100% efficient. Every watt it consumes gets turned into heat. Before someone says "but the cooling fans are wasteful" let me remind you that the air moved by those cooling fans will eventually come to a stop (inside your house) as a result of friction, releasing its energy as heat in the process.
Depending on what type of space heater you use, and the construction of your house, your computer can be more efficient than many other electric space heaters. Since none of the energy "consumed" by your CPU/GPU is converted to visible light, none of it has the opportunity to leave your house through your window panes (assuming you have IR reflective glass). Contrast this to quartz and halogen space heaters which produce a fair amount of visible light.
In much the same way, incandescent bulbs match the efficiency of compact fluorescents during the winter months. Every watt "wasted" as heat during the summer is now performing useful work heating your house. (Before someone says "you called a quartz/halogen space heater inefficient because of its waste light, and now an incandescent efficient because of its waste heat!' let me say that the space heater's light is not useful light, while the bulb's heat is useful heat (during the cool months.))
Re: (Score:2)
(And before you tell me that some percentage of my fur
Re:This is the perfect time... (Score:4, Insightful)
Natural gas is (cdn)$0.278287 per cubic meter, and electricity is 0.058
At 96% efficiency, natural gas works out to 0.027331 / kwh, (3413 btu in 1 kwh) or 47% of the cost of electricity at today's prices in Toronto.
So 1/3 was a bit of hyperbole, but not too much.
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
The guy just doesn't take in account the fact that heat pumps move calories from point A to point B.
Usually, when such people try to compute the "efficiency" of a heat pump", they take two things: the power draw from the electrical outlet (which is the energy loss), and the heat that comes in (the energy gain). This pretty much always yield an efficiency > 1 in good conditions (won't work in siberia for example), but the part missing is that the heat pumps don't generate heat from the electricity they d
Re: (Score:2)
http://en.wikipedia.org/wiki/Heat_pump [wikipedia.org]
http://en.wikipedia.org/wiki/Coefficient_of_perfor mance [wikipedia.org]
Re: (Score:2)
Re: (Score:2)
It's for t
Re:This is the perfect time... (Score:4, Informative)
Not true. You aren't taking into account Power Factor at all... Not that I'm surprised, as most people don't understand it.
With switching power supplies, it's common to see PF in the range of 0.4, as opposed to fully-resistive electric space-heaters (and incandesent lightbulbs) with a perfect 1.0 PF.
Residential customers are lucky, in that they don't get charged for PF losses by the power company, while companies certainly do. However, it's still highly ineffecient, even if you aren't paying for it directly.
And besides that, electric heating is almost always more expensive than conventional heating, like natural gas, or electric heatpumps.
PF losses are not losses in any real sense (Score:2)
Re: (Score:3, Informative)
Electricity isn't water, you can't return it to the source.
With a lower power factor, you're either forcing the power company to install huge banks of capacitors, or making the generators work that much harder for fewer watts actually delivered/used. That's practically the definition of "inefficent".
Re: (Score:3, Informative)
Re: (Score:2)
Both run on DC, so they don't even count. The switching power supply, which converts the AC to DC, is the only thing that counts.
This sentence makes no sense at all. You clearly have no understanding of PF.
Not really. (Score:4, Insightful)
>Using your CPU as a space heater is not a bad idea. It is 100% efficient.
Not really. Consider exergy [wikipedia.org]. Yes, your CPU is just as efficient as any electric space heater. However, consider that the alternative is probably burning natural gas or oil in a furnace. If you burn fuel for heat, 90%+ of the chemical energy goes to producing heat (the rest is lost as unburnt hydrocarbons in the exhaust). If you burn fuel to spin a turbine at a power plant, only about 40% goes to electrical energy, and unless it's a cogeneration plant which uses the waste heat for industrial purposes, the rest is lost as heat up the smokestacks. So, starting from the fossil-fuel source, electrical heating is less than half as efficient as burning fuel for heat. If you do need to heat using electric power, it's much more efficient to use that electricity to pump heat in from a lower temperature outside than it is to turn that electricity itself into heat.
If you are stuck with electric (non-heat-pump) heating in your house, however, you are correct: There is absolutely no reason not to run your CPU or any other electrical appliance full tilt.
Re: (Score:2)
Re: (Score:2)
Do you ever think you might not know everything? 100% Efficient doesn't mean anything in this context. If it means anything, then everything that exists is 100% efficient at producing heat, due to the second law of thermodynamics. However, you are not considering the fact that CPU's produce RF and other radiation which escapes from the system you are trying to heat, and thus to get that 100% efficency you would have to mean that it
Re: (Score:2)
Re: (Score:2)
Re: (Score:3, Insightful)
I am spending $.10 for the extra kw hour roughly. In the summer I waste money on AC in the winter I save
gas money on heat. If I put my computer in 4watt S3 standby for 15 of those 20 hours, I can save a lot more.
FAH calculations do not depend on "free" "idle" computer power, they depend on users spending money to generate
the results.
Re: (Score:2)
I actually installed boinc with seti on several of my machines last night and it worked quite well to heat part of the house (us Canadians need to turn the heater on earlier). Took a bit of time to get started, but it was nice and toasty in the morning.
Does anyone know if this method is less efficient in generating heat than using a apace heater? Slower perhaps... If you're going to use energy by turning on the wall heater anyways, why not use it t
Re: (Score:3, Funny)
That makes it a little better... right?
Please?
Answers (Score:2)
Yes, that's why anyone would bother.
Q: If so, does that mean that IBM was right all along with their AS/400, iSeries product which makes heavy use of ASICs?
A: Yes and no. More relevant will Cell pave the way to good price/performance. The problem with the iSeries line is not so much performance, but price/performance For the same cost of an iSeries config you can cluster a bunch of xSeries and beat it through sheer brute force of CPUs. I
Re: (Score:2)
I run using both hardware types. xSeries can not complete in the shear thoughput of grunt data processing - Billions and Billions of records. Yes, 1000 PC can process billion of records, but then your cost pass that of 1 iSeries.
Now when you limit the processing to the type of computer that best handles that type of work:
xSeries is better in single/one off processes, like a web page request, or finding the Lat/Long of Address, where all the information is fresh look up each time. So s
Acutual Performance Figures? (Score:2)
For all we know the majority of those Linux and Mac clients are old P2s and G3s.
GPU != ASIC (Score:2)
Nvidia is less efficient? (Score:2)
Anyone care to explain?
Re: (Score:2)
Re: (Score:2)
And one big reason why it wouldnt fly on nvidea cards is that the latest ATI cards are MUCH MUCH faster when doing conditional stuff, which DOES happen in that kind of statement.
The raw throughput is irrelevant if one cards slows down an order of magnitude just because it cant handle an "if"...
Not a mystery (Score:3, Insightful)
Now, offer them a GPU-driven alternative. For the most part, the only people that will install and run it are those with a fancy-schmancy video card capable of running it, and for the most part, the only people that have a fancy-schmancy video card capable of running it have high-performance computers as well (or at least more recent computers that came with compatible cards.)
So let's say that's ten out of the hundred, and those ten are statistically likely to have had the highest-performing CPUs as well; so you've pulled the top ten performers out of the CPU-client pool, and thrown them in the GPU-client pool. Even if you didn't switch those ten people over to the GPU, you could probably isolate those computers' CPU-client performance numbers from the other 90 and find that they're disproportionally faster than a larger number of the slower computers.
There's still more to the story, of course, but you really are taking the highest-performing computers out of the CPU pool and into the GPU pool. The exception would be high-performance servers with lousy/no graphic cards, but those are likely working so hard to perform their normal business that Folding@Home isn't a priority.
Re:Not a mystery (Score:5, Insightful)
500 users out of 25000 means that you have at most taken the 2 percent highest performers out of the CPU pool. If we assume that those 2 percent have computers that are 5 times as powerful as the average computer, then we have lowered the average performance of the CPU pool by roughly 9%.
This 9% systematic effect will lower the reported performance superiority of around 5000% of the GPU vs. the CPU to something like 4500%. I.e. it doesnt change the result at all (which seems to be that GPUs kick ass for these applications).
Re: (Score:2)
Move the vector processor on-board? (Score:4, Interesting)
Couldn't we finally have graphics cards that only give output to the screen and separate vector processors with a standardized interface / instruction set?
Re: (Score:2)
Re: (Score:2)
There's already vector coprocessors on-board. The only problem is that on x86 they're cripplingly small.
Re: (Score:2)
Re: (Score:2)
How about something like this: http://hardware.slashdot.org/article.pl?sid=06/04
Re: (Score:2)
Heck, put one on the CPU! (Score:2)
Re: (Score:2)
Re: (Score:2)
Good luck running your game on an off board GPU.
We have vector units on CPUs to help with the things that CPUs generally do. We have GPUs on video cards to do the things that video cards do. There are a few applications where the GPU is useful for things other than video, but not many. In fact, the vector u
wow (Score:2)
Even if, as i imagine, many of the linux clients aren't exactly top end CPUs. Usually it seems the top-end GPU is as complex as the top-end CPU of the time. I know the transistor count was close when i built my last complete setup. Surely my 1.6 P4 (soon-to-be-linux box) get trashed for complexity/throughput by a new video card by now
That and like others said a targeted client and screaming memory for the GPU is gonna rock. Would be closer if the CPU client was aimed at a parti
Remember: 1 GPU has more than one processor. (Score:5, Informative)
Standard CPU - 1 core (assuming dual cores get read as 2 CPUs).
448 GPUs x 56 = 25,088 effective processors all with on card memory.
25,050 CPUs x 1 core = 25,050 effective processors all dealing with system busses etc.
In short, if you're performing one simple task trillions of times, many very simple, highly optimized processors with dedicated memory do the job better than even a similar number of much more capable processors that have to play nice across a whole system.
And this ignores the number of old couple of hundred megahertz systems that people don't use anymore so hand over to the task vs. X1900s being the very high end of ATIs most recent line.
For massively parallel tasks like rendering pixels, folding proteins, compressing frames of a movie, etc. I'd absolutely love large quantities of a simple processor. For most other tasks, given present technology, I'd still side with fewer more able processors. Either way comparing 448 of something with 56 processors within it to 25,000 single processors and saying, "But 448 is SO much less than 25,000!" is an unfair comparrison.
Golly Beav.... (Score:2, Funny)
Actually Linux users have good hardware: (Score:4, Informative)
I took (TFlop/active cpu)*1000 to get a readable number --
or Gflops/cpu
Windows is
Mac is
Linux is 1.21
And GPU is 65!
The source:
http://fah-web.stanford.edu/cgi-bin/main.py?qtype
The average Linux user proably has a decent AMD Athlon,
The average Windoze user has a P4 Dell.
Athlons just crunch the math better.
Re: (Score:2)
I'm running it on my 1900xt (Score:2)
Not sure how my vid card will be in a month or so because i don't think they're designed to be in game play mode for more than 12 hours or so (can't think of anyone who plays more than 12hours at
Next they'll be telling us (Score:2)
Re: (Score:2)
I've worked with the S36/S38/AS400/iSeries/I5 for decades. The thing has always been rock solid. Not quite in the mainframe realm of up time, but in 20+ years I have only seen the machine down twice unplanned. Both cases due to hardware borking, fscking disks.
You can refresh all you like, no problem.
The downside is the lack of a decent gui, screen scrapers just don't cut it. IBM should make the X protocol or VNC protocol a
Re: (Score:2)
I use powerterm rather than CA but that's my preference. CA is big and clunky and doesn't give me the features I need.
The gui would not be for legacy apps although they could implment a screen scraper on the AS/400 if people wanted it. But rather for new apps.
Are you running win3.1 on those machines? (Score:2)
Sounds like you need virtual machines, run the old crap under a VM so it still works.
What could possibly those old systems do that you cannot replicate or recode on new systems, or at least have it recompiled with
wrapper apis, or is it that horendously badly coded.
i5 specs look good though - http://www-03.ibm.com/systems/i/hardware/ [ibm.com]
Re: (Score:2)
Ironic that macs use intel isnt it now (Score:2)
And before any one ays SPE cannot run general code, look at the instruction set, its as good if not better than the old
68k chips, infact much better as it has lots of cool math simd type instructions. Whats 90% of C/C++ code? lots of IFs and
variable assignments, and structure memcpys. Now if the whole OS would thread to all SPEs on demand it would fly.