Slashdot Mirror
Cool/Weird Stuff To Do On a Cluster?
Gori writes "I'm a researcher at a university. Our group mainly does Agent Based Modeling of interdisciplinary problems (think massive simulations where technology, policy, and economics meet). Recently, we managed to get a bunch of money for a High Performance Cluster to run our stuff on. The code is mostly written in Java. Our IT support people are very capable of setting up a stable cluster that will run Java perfectly. But where's the fun in that? What I'm trying to figure out are other, more far-out and interesting things to do with this machine — think 500+ Opteron cores, 2 GB RAM per core, a gigabit interconnect with some badass switches, a massive storage array, plus a bunch of UltraSPARC boxes. So at times when there's no stuff to crunch, I'd like to boot the thing up with a 'weird' system image and geek around in the name of science. Try fancy ways of building models, dynamically adding all sorts of hardware to it, etc. Have different schedulers compete for resources. Imagine a Matlab vs. Boinc vs. ProActive shootout. Maybe run plan9 on it? Most of us are not CE/CS people, but we are geeky enough. So, what would be the coolest and most far out thing you would do with this kind of hardware ?"
And save the environment a little bit?
I'd be interested to see how quickly you could fold@home@work on that cluster.
I think that would be an ideal setup to run Vista on. I heard that with SP1 you might only need half of the equipment you currently have.
that it will be fast enough to run Duke Nukem Forever when it gets released.
"Prefiero morir de pie que vivir siempre arrodillado!"
a beowulf cluster of these .. .
Humor from a Genetically Molested Mind
Quit playing around and run something that will actually help another person. (Plenty of grid clients out there).
meh
"So, what would be the coolest and most far out thing you would do with this kind of hardware?"
Instead of pissing around with stuff that may not go anywhere other than a few giggles over lunch.
Why not just rent, or lend it out to people who don't have the funding or equipment that could use this cluster for a better purpose than "playing around"?
Just saying...
Because Gentoo is just hours of fun....
compiling.
Well, you could try something that no modern computer has been able to achieve, and they think it'll take something on the order of Deep Thought to get it done -- run Windows Vista at a reasonable speed.
McCain/Palin '08. Now THAT's hope and change!
:-)
power it off and go get a blow job. You might like it.
You have a high-performance cluster, and you're running Java? I bet the OS in windows, too.
Have an open framework for members of the open source community to enhance and create new cluster/multicore optimized technologies. Allow us to do render farms or computation of nodes to do whatever sounds cool at the time. Of course the projects have to be approved, and their may be a small fee unless the project looks interesting or you wish to claim it against a donation of resources.
Crysis for the pc, if your lucky, you'll get 30 fps.
Get it to play a game of Tic-tac-Toe against itself. Give us some WOPR love!
"The price good men pay for indifference to public affairs is to be ruled by evil men." ~Plato (427-347 BC)
Being massively parallel it could be interesting to do some AI research. Like chess algorithms or something more fun perhaps a good automated tech support system via chat. Or trying to decode, capatacha. Map optimizations... a bunch of fun stuff. At least it would be for me.
If something is so important that you feel the need to post it on the internet... It probably isn't that important.
I run distributed answer set and SAT solvers on them and use these to do things like compose music, optimise machine code, (hopefully soon) find integer overflow bugs in code. Drop me a line if you're interested (mjb in the computer science department, University of Bath).
Or you could run an Eternity 2 ( http://www.eternityii.com/ ) solver...
You know you want to. Or you could evolve a bunch of virtual creatures on it: http://www.karlsims.com/evolved-virtual-creatures.html http://www.stellaralchemy.com/lee/vce3d_related_projects.html
Brute force random sizes of pe code or image code based off of known patterns or headers or signatures and see what interesting new things can be created.
Instead of random, how about have algorithm of the hour and show what seeding or using it can do.
Chess
Poker
Fighter Combat
Guerrilla Engagement
Desert Warefare
Air-to-Ground Actions
Theaterwide Tactical Warfare
Theaterwide Biotoxic and Chemical Warfare
Global Thermonuclear War
??
Write a program that creates every possible 255x255px bitmap possible, and then right an algorithm to go through and figure out which ones are rubbish and which ones are actually recognizable pictures.
Logic dictates that one of the resulting pictures would have to be of John Lennon kicking George W Bush in the nuts, find that picture and post it on failblog.
Voila.
Protein folding really helps us biologists A LOT, so please run it. http://folding.stanford.edu/
There was this one incident when me and this girl turned a cabinet over on it's side and used it as a surface for sex play. That was different. It didn't get weird until she insisted that I tie her wrists with some Cat 5 though.
I'm doing computational condensed matter physics for my PhD. If you give me an account, I can keep your cluster at full load while you're not using it. :) The type of stuff I run can span hundreds of processors over (sorry to say it) slow interconnects like GigE.
If you let me use it, I'll acknowledge you in all publications AND I'll make you some pretty pictures (materials under extreme conditions make for cool figures).
Anyone else think a 2^16 vs. 2^16 Team Fortress game would be pretty cool?
Corollary to Hanlon's razor: Any significantly advanced stupidity is indistinguishable from malice.
as some have said, donate the time to people would like to buy it but can't, or on odd days turn up 1000 SETI@home processes and see how far it gets?
Create a reverse Google bomb - Index every link to say 'george bush' from Google, read each page into memory hash the words, assigning value by count amongst all the pages, and then post the top ten words on GW that are not 'the' 'a' 'was' etc.
Perhaps comparing this to the same process on Paris Hilton would be a report that sparks SkyNet to life. I don't know. Seriously, if those two have 6 of the top ten words in common it would have to mean something.
If you have all that cpu sitting idle, that is the kind of weird shit nobody else would do, but also couldn't not read the report either. Perhaps you'll start something new for Google Trends? :)
Support NYCountryLawyer RIAA vs People
I do burn-in testing on a lot of the machines we get at work, using hardware I can't personally afford.
My favorite test is to find scenes to render with a raytracer.. yafray is my favorite, runs on all major platforms. But not just any scene, it has to have all the details turned up to 11, contain extremely high detail (polygon counts drive up memory usage), and write out an absurdly large image.
Kind of whimsical but it's hard to not be impressed by an image 20,000 pixels square with perfectly accurate reflections. Who cares if I can only fit a fraction of it on my monitor. ;)
Generate public access rainbow tables with optimized databases that always grows when idle and provide access to user's. Do different algorithms and use multiple length strings. Reverse engineer the encryption used in viruses to steal blackmail people. Create one hell of a neural net to process as many captcha systems as possible.
Rosetta @ home or fold.it
Or you could try to thermally load them in patterns that produced different tones on the fans (or maybe an AM radio) record it then speed it up. Maybe you could make it sound like a baluga whale.
Or maybe you could implement a virtual machine cluster of 250 cores. The repeat the process till you see how many virtual machines you can stack on top of each other till it has the same speed as a single processor.
While this might sound stupid this would give us a rough estimate of how many watts per virtual world it takes and from that we could figure out how many layers deep in the simulation we actually live assuming the top level one is powered by something less than 1 sol of power.
or work out all possible moves in N-space tic-tac-toe. The only smart move is not to play.
Some drink at the fountain of knowledge. Others just gargle.
Play the original Tetris game one the most powerful computer it's ever been played on. That's the first thing I would do.
I'd do some serious folding@home!
[[ DmD ]]
Just because you can.
Do it!
"So, what would be the coolest and most far out thing you would do with this kind of hardware ?"
Get Rails to scale?
I (Mat) work at Vanderbilt University's supercomputing center. Our university supercomputing center was originally a joint venture between the proteomics and high-energy physics departments, but they decided to make it a independent university-wide initiative to bring HPC tools to all users.
Before we founded the center, there were a lot of groups that required computing on campus, but it was highly inefficient. Their local clusters had lots of free cycles (low return on asset) that they couldn't effectively share with other users, the clusters were down quite often (grad students and postdocs are poor sysadmins, plus they should be doing actual research anyway). Several other problems related to either pooling of resources or pooling of knowledge, you get the idea...
I highly recommend setting up a batch scheduler such as Torque/Maui and opening your cluster to all researchers on campus. You'd be surprised how much demand is out there. We have all the usual math/science/engineering/biomedical users, plus users in more esoteric fields (nursing, accounting, music, psychology). You can always give your group a higher job priority if needed. It gives a higher return on asset and gets lots of goodwill on campus (and, potentially, at funding agencies). You can charge users for support, storage, etc for cost recovery, or even use it as a revenue source if your grants allow.
Having different types of users also allows cross-pollination of ideas. We have a large number of biomedical researchers who are now using a high-energy physics software (geant), biomedial people who are teaching other users how to program in R, etc. These are avenues for research/discovery that didn't exist before.
Play a digital version of hide and seek. Flip a certain register on only one of the memory chips and have competitions on who can find it the first.
Sounds like an xkcd title.
See what it takes to make the processors burn.
Try to think of something that will most benefit humanity as a whole.
It is pitch black. You are likely to be eaten by a grue.
What to do with it? Thats easy. Build a hot chick like they did in Weird Science then GPL the code.
really I'll give you a maya license!
Doooo iiiiiiiit!
Try figuring out a new prime number, perhaps win some money too mersenne.org if you can figure out the first 10 Million Digit Prime.
http://www.opensciencegrid.org/
That way you can backfill the resource with jobs from VOs (Virtual Organizations, think projects/groups) you choose. It is similar to BOINC in the sense you can pick what science to support.
The idea is that the sharing will go both ways. You will give spare cycles to other users on OSG, and in return, you will be able to use spare cycles on other resources.
Spend some time on the OSG website reading the things under "Learn About Us". Also check out the research highlights to see what kind of science is being done on OSG resources:
http://www.opensciencegrid.org/About/Research_Using_OSG/Research_Highlights/Research_Highlights_Archive
(Shameless plug - I'm part of this team) The good news is that OSG have an ongoing effort to help you join your resource to OSG, and help your users get going on the grid:
https://twiki.grid.iu.edu/twiki/bin/view/Engagement/WebHome
void party()
{
while(fork()) {
fork()
}
}
Someone already did, about 20 threads up from this one.
Well, as you say, it's slashdot after all...
+1 IDisagreeSoHeMustBeATrollOrAnAstroturferOrAShill
xkcd Network
Some cool things to try
- AI / Math stuff: think solving rubick's cube, etc :P
- Fractals: try an arbitrary precision library and zooming in very deeply on a fractal
- make -j (yes, -j, not -j something) on a linux kernel
- Genetic programming
how long until
Instead of randomly generating pictures or something as someone suggested above, why not make it generate say a 64k program, keep iterating through this until you get an executable that will actually RUN (Without crashing) and see what happens.
+1 IDisagreeSoHeMustBeATrollOrAnAstroturferOrAShill
Would be to run a VR simulation of you interacting with female simulacra in social situations while simultaneously running a parallel statistical model of the chances of you getting laid based on your interactions with the simulacra.
Sig this!
Finish Duke Nukem Forever
Calculate the Stupidity of GWB
How many licks it takes to get to the center of a tootsie pop.
Compile Linux Kernel (and all modules) for every processor ever known to man. Perhaps Gentoo for every Processor.
Agent K: A *person* is smart. People are dumb, stupid, panicky animals, and you know it.
Construct some scenarios to test emergence. Like the game of Life, with the potential to form much more complex outcomes. There'd be some software writing involved to get the project off the ground, after that it's a matter of coming up with different rules for interactions, or different properties for the 'organisms'.
I think it'd be really interesting to see what complex structures evolve out of different sets of simple rules and interactions. Who knows, you may even discover something incredible in the process.
Murphey's fighting Occam, and we're in the stands.
You can try to launch a really big and nasty simulation of the universe. Those produce really nice pictures and eat up all your processor power. Just don't let this kind of power unused, it is a waste :)
EULA : By reading the above message, you agree that I now own your soul.
CWI has ran their own attempts at various large composite numbers with their software, and it would be a good read. Since you're part of an Academic institution, you should be able to get access to their code. You could contact them through CWI's website if you want.
Give Kerry Conran another shot.
Oliver's law of assumed responsibility: If you're seen fixing it, you will be blamed for breaking it.
In my experience as a sysadmin, when you have a resource, your users want it to be "up" all the time, no matter what. If it's interactive, they'll leave VNC sessions or xterms or screen sessions running on it and want them to be there when they come back. If it's noninteractive (ie: a queue/batch system), your users want to be able to submit jobs now, without waiting for the sysadmin to come in and fire it all up and make it run.
Without some serious organizational political capital, it's pretty hard to pull off powering down the compute resources. It can be done, but it's going to leave a lot of people unhappy.
How about simulating tentacles physics for future 3D hentai games?
Sure, fractal exploration programs are nothing new. But what about building the deepest image of the Mandelbrot set out there, or some other set?
Seriously, though, if you guys do "massive simulations where technology, policy, and economics meet", I'd like to see some simulations of the global economic and environmental consequences of rapidly rising energy prices, or calculations of how much waste heat contributes to climate change.
Prize money in the $100K and up ranges are available for primes that are found above 10 million digits. If you can get the cluster to search for a 10 million digit prime and you end up finding it, you'd earn your Department a cool $100,000 in extra funding. I haven't read the exact rules for the Prime95 program invlovement, but you'd still get a good grant for your Dept. from just crunching 1s and 0s on your idle processes.
It'll be right here waiting for you.
/. is way to mature on this topic.
I'd set to work simulating the perfect pair of breasts on a trampoline.
I'm a CS (Anthro minor) undergrad student working with "Agent Based Modeling of interdisciplinary problems" looking for a place to go to grad school. What university is this with the nice cluster and the group of people working on the problems I want to help solve?
Mine is Good
I like encryptions. I'd play with cracking them, just to say I did.
Take my tagline on for your first challenge. :)
Serious? Seriousness is well above my pay grade.
As someone else said... AI research...
See if you can get it to deduce the existence of rice pudding and income tax...
If it can do that, it's on the way to solving the ultimate question. Then we could see if douglas was right.
Would that not be an interesting task? develop a powersaving scalling system that turns all but one of the machines off when the system isnt in use but will still look "up" to anybody trying to use it. perhaps even use standby and WOL on the last machine so the power usage drops to almost zero.
IranAir Flight 655 never forget!
SETI at home is pointless, wait 10 years and well be able to see planets and will just get a single supercomputer to watch those solar systems. There are useful BONIC projects
IranAir Flight 655 never forget!
Well, you could always make a virus farm
But seriously though, let your physics department know that you have idle time on such a cluster, they will come begging at you for some cicles. I've tried running a simulation of some quantum systems from first principles, using Monte Carlo methods (my software), and it would never get anywhere on small clusters. On a big one I managed to see something, but after days of processing.
entropy happens
Couldn't you be doing something yourself to save the environment right now - something like turning off YOUR computer instead of browsing slashdot? Oh, wait - that would require YOU to do something. That kind of environmental activism is never as much fun as simply preaching to other people what THEY should be doing. Hypocrisy is SO much fun - carry on!
A variant on the rendering theme: Instead of simulating rays, simulate light wavelets and the modern theory of light. You should have enough compute power there to render reasonable scenes using such a technique.
Fluid dynamics: This is a popular one, and NASA offer source codes for free for subsonic, supersonic and even hypersonic flows. In fact, they offer quite a number of subsonic ones. They're also not the only source. There's several open-source CFD packages, ranging from river simulations to aircraft simulations.
Supernovae simulation: There are packages (freeish, rather restricted in access) that allow you to simulate thermonuclear and supernovae explosions within stars. The restrictions are for rather obvious reasons, even though the odds of anyone nasty obtaining a star is, well, unlikely.
COLOSSUS: There are still a couple of ENIGMA ciphers that have never been broken, which can be obtained along with the algorithm Colossus used in World War II to crack such codes. You could complete the set and maybe discover some lost secret (yeah, right).
BLAST: Other posters have suggested renting out the computer time, but that just transfers the problem of what to run, rather than solving it. BLAST, or one of the MPI-based variants thereof, is an exceedingly popular tool for examining nucleotide sequences, but as the databases grow ever-larger, the demand for ever-more information also increases, creating a need for significant compute power to produce the volume of results desired.
It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
Skynet.
Moderator hint: a comment is neither "Flamebait" nor "Troll" if it is true.
...but I could see myself throwing a HUGE party for it. Put a little hat on it, and tape a drink (isopropyl of course) to a paper hand for it.
If it were a really, really good party I would look over at it during the 'trying hard to stay quiet, amidst the passed out drunkards' sex and give it the thumbs up!
I may regret posting this, but that's the first 'Crazy/Weird' thing that came to mind... :P
Bullshit. No way, no how is C++ ten times faster than Java. You're smoking crack.
ZFS: because love is never having to say fsck
Obviously they need to upgrade their equipment.
IP address, username, and password please?
What would be the fun in that?
Dealing with lawyers would be a lot less tedious if they all looked like Casey Novak.
That actually does sound interesting!
Even with one node on all the time... you could pretty reasonably pull that off with the rest of the nodes. You could even have it dynamically scale the "awake" part of the cluster to match the number of jobs in the queue or the utilization of the awake parts. Just imagining going from 200W to 30-40kW and back automatically, on demand... yeah, that'd be handy.
You could also tie into environmental factors ... scaling back the cluster if the HVAC is underperforming and the room's getting warm. Or tying in power and cooling load balancing, powering up appropriate systems to keep the room from getting hot and cold spots.
This is so incredibly messy, BUT!!!
I heard there was no Java to C++ translator, but there is a Java to Python converter, and a Python to C++ compiler. Transliterate the C++ to either C or ObjC (not for any reason other than C++ is nasty) and insert some calls to ATI's programmable GPU and wham - your Java programme requiring a cluster of Teraflops can be outperformed by one desktop PC with a couple of middle-range GPUs.
Oh, it's a Government funded thing... Run atc from bsdgames on one CPU then Seti@Home on the rest, and take some meat to barbecue over the top of the exhausts ;)
That cluster could surely run enough web clients that you could create your own "Slashdot Effect".
Just put a front-end web page on it with a simple URL submission box.
Moderator hint: a comment is neither "Flamebait" nor "Troll" if it is true.
Huh? This kind of clueless drivel marked as "insightful"???
It is doubtful that there is significant amount of overhead. Fortran could be faster for specialized math tasks, for few select cases maybe an order of magnitude faster. C++ would just crash more often, without guaranteeing ANY speedup. Competently written java code, for agent-based simulations, should be up there with compiled languages.
Load up a FPS, and have everyone in the lab in a deathmatch- rendered through a ray tracer.
If an infinite number of monkeys......
Write a program that creates random code and tries to run it, then starts again. Eventually, we'll have the Singularity and not have to worry about finding cool things to do.
Stasis is death. Embrace change.
Instead of giving you ideas for cool things *you* can do - why not let us give it a shot? That might be cool for you - i dunno.
Release a set of user accounts to the public internet during downtimes, prevent the users from being able to change the passwords, and let them go nuts. Then observe.
You'll get to see them exploit every vulnerability in your system (good for security planning), run processes you've never seen before, and certainly exercise those processors. SPAM, Porn, Password hacking and cracking, the works. Observing, it might be like watching a train wreck.
It would be the biggest honeypot known to man.
I've always wanted to put a HUGE Server on the internet unprotected and watch what happens to it...
Lindsay Blanton
RadioReference.com
and maybe a few more battlestars, and render us a badass battle posted to Youtube during the hiatus.
I am very small, utmostly microscopic.
Try global thermonuclear war.
Create a google bomb for every word that is not 'the' 'a' 'was' etc.
Try and get the top ten results for everything point to pages with this embedded.
I don't therefore I'm not.
2^65025 / 2^41 = 2^64984 seconds. Divide by subtracting the index, e.g. 10^3/10^2=10^1
To divide by 2^25, just subtract 25 from the exponent, giving 2^64959 years, or 10^19555 years. But still much longer than the age of the universe.
You must be new here (I guess this one also qualifies as a classic)
Fire up a bunch of unpatched Windows virtual machines without virus scanners to seek out and run a bunch of random .exe files from BitTorrent. Another set of VMs aren't downloading but are wide open. Reboot everything at random intervals around 10 minutes. See how long it takes to make a system unbootable. It should take you just a few hours to set up and provide days of enjoyment.
tell us you actually shut down you home or work pc every time your not using it! Actually you wasted a lot of carbon by not only making that dumb comment but posting it so people took the 2.7 seconds to read it and now the 20.4 seconds for me to reply. ugh. you've now created a perpetual energy-eater!
Use all that power to fight aids: http://fightaidsathome.scripps.edu/
Hear that sound over your head?
That's the joke.
0x09F911029D74E35BD84156C5635688C0
Because people trust mediocre crypto way too much.
There's an open source Finite Element Analysis program. It has a client-server clustering capability. http://impact.sourceforge.net/ You can make it rain expensive sports-cars upon the pavement, if you want.
https://www.youtube.com/c/BrendaEM
Apparently it's very achievable -- CMSU came pretty close to claiming the $100,000 prize in late 2006.
I've worked with supercomputer class systems in the past, common question - "what can I do now?"
Two suggestions:
1. Set aside the first couple "downtime" sessions to run your crazy "OMG it actually worked" stuff out of the way. The stuff you'll brag about for years to come.
2. Every time thereafter, set it up with a grid computing client. Seriously. It may not take advantage of the interconnect fabric, but you will be doing your fellow humans a great service.
Check out http://www.worldcommunitygrid.org/ for some ideas (from a big company whose sponsored code will not cause infinite loops on the nodes....).
SETI is IMNHO a complete waste of time.. if or when the aliens want to be found, it will probably be in Hollywood ID4 style and not some little green guy screetching "Can you hear me now?" on all frequencies and modulations.
Basically, you have a huge cluster and you want to do something fun.
Created a distributed controller application that spawns various systems and processes. When a group of controller nodes no longer detect one running... move it out of the group and reform another control node. Next, that group of nodes spawn another controller and move the address over to the new node.
Now, inject some random madness so nodes break on occassion. (Make it variable so you can pop nodes off left and right if wanted).
I say if you can perfect that then you can do something else with your randomly unreliable application cluster.
Who knows what kind of madness might spawn from that.
"You should always go to other people's funerals; otherwise, they won't come to yours." -- Yogi Berra
When not running it's purpose built program, let it run Electric Sheep! (The idea being that the cluster is "sleeping")
Why on earth are you running Java on a high performance cluster? Perhaps you could use all that horsepower to develop, say, some nice high performance software?
You might want to take a look at SAGE as a platform option for that cluster. Then you should be able to farm out jobs from Matlab, Mathematica etc.
"Nine times out of ten, starting a fire is not the best way to solve the problem." - my wife
If you can't come up with at least 5 things to do with it on your own, you have no business controlling such an expensive and valuable resource.
How about asking other research groups within your University or affiliated departments at other Universities if they need some CPU time? I'm certain there are people who would love to use it.
Just my $0.02
Do you even know anything about perl? -- AC Replying to Tom Christiansen post.
Folding@Home ;)
Preferably for team 33 ;)
"...Sleep comes like a drug in God's country Sad eyes, crooked crosses in God's country..."
By pass the DHD on a stargate as that needs a lot of cpu power to do.
I've always (well, for a while) wanted a supercomputer so i could run qemu recusively and see how many levels I could run and still have a usable system(or play an old game like quake.)
Doesn't using Java nullify/negate the power/usefulness of the cluster?
from 09 F9 11 02 9D 74 E3 5B D8 41 56 C5 63 56 88 C0
to 45 2F 6E 40 3C DF 10 71 4E 41 DF AA 25 7D 31 3F
Trying to answer the last question.
That's one of the new (and still experimental) features in the latest VI3 stuff from VMware. It migrates the VMs off the host when usage is low, then powers the host off. Something to play with one day.
...does it run Crysis?
Install some molecular dynamics simulation software, build a system to model a yeast cell in sugar solution. It would take a few thousand years in all atom mode, but you could do a coarse grained version faster.
Once done take your output files and animate them as the ultimate beer nerd film.
How about a distributed video encoder setup? Pop in your DVD and 5 minutes later it's super-duper H.264 with all the options, heck encode into the snow codec. At the bare minimum set up distcc on it and all the geeks will love you. See how long it takes to emerge everything in Gentoo with distcc.
Maybe run Electric Sheep?
Cwm, fjord-bank glyphs vext quiz
Run a program regarding the computation of pi in divide by zero, defined as the ratio of the circumference of the zero.
Pi can be obtained from a zero if its radius and area are known.
Numerical approximations of PI:
http://en.wikipedia.org/wiki/History_of_numerical_approximations_of_%CF%80
This should *produce* an ultra spark.
Seriously - run Plan 9 on your cluster, I want to read about this.
~hylas
Dash out a quickie pair of AIs to converse with each other, and decide what the best ultimate use of resources is, *then* load and run the *real* job?
It may no be science, but it's definitely geeky.
Let me second that. I work in NeuroImaging at Uchicago, and since we were given cluster and TeraGrid access we got neuroimaging folks using R and SWIFT (Grid parallel workflow language), and High Energy Physics folks implementing their signal analysis methods on neuroimaging data. They used to say that physical distance (in yards) is a good prediction of collaboration potential in academic departments. These days, sharing a computer cluster seems to achieve a similar thing. But, if you are asking how you can contribute, try setting up your system to load virtual machines on each node -- If you can get that going you'll find many potential users that couldn't bother with adapting their code to the cluster, but would be glad to load an image and run a job in it.
How many points you can rack up in the Folding contest.
That's the most interesting thing you can do with this cluster.
Reading Slashdot dulls creativity sometimes... I suggest you deprive yourself of sleep, overdose on caffeine, read something by Neal Stephenson (Snow Crash or Diamond Age), and meditate on your question with a 2-3 geeky buddies of yours around 2am.
1) Find a picture/piece of code/ISO image/etc. you'd like to compress. Treat it as a very big number. Now find a prime number that comes very close to it. Compress it by treating it as the Nth prime + the remainder. Repeat for the remainder See if the compression is any better than bzip. (I think i saw something like this done for the DeCSS code once...)
2) Find something to optimize via brute-force. (My favorite is neural nets predicting time-series). Run a distributed simulated annealing algorithm. (Run an instance of the algorithm on every core, check every N cycles to see which core is more "optimal", share the parameters with the rest of the instances).
3) Create an interactive multi-user raytraced environment. Get someone to bring in an ImmersaDesk or a CAVE. Stun all visitors.
4) Model a giant neural network. Teach it to do something cool in real-time with your favorite training algorithm...
5) Get dictionaries from 50-60 languages. Write something to correlate similarity of words meaning the same thing. Make pretty graph clustering them by similarity. Post pretty graph on Slashdot.
6) ???
7) Profit!
Given the costs of producing IMAX moves (millions of dollars each) this could be a very inexpensive IMAX movie, even if you had to purchase the cluster.
Hell, forget IMAX, just render a big-ass movie and seed it on thepiratebay.
Used to be the only reason to purchase a Silicon Graphics Onyx... Then again they had the 4 large monitors on them...
I think that would be an ideal setup to run Vista on.
Vista is licensed for a limited number of processors. Vista would still be a slug on it as it couldn't use it to it's potential. )-:
The truth shall set you free!
Totally, think about the botnet that system would host. Start the matrix man!
Because the Java codes I have to optimise to run on our cluster (or SMP machine) still run like lame, wet dogs. I'm sorry, but Java's performance is really, really shitty and I'm considering removing Java and Javac from the systems altogether. When you compare another object oriented language, like C++, at least with that you can write your codes to make use of multiple instructions per cycle ... and then with a good compiler and appropriate hardware, you can vectorize the instructions themselves. When you have codes that for a single processor, would run for about 50.9 years (an example I pulled from just today) those 'simple' little things go a long way. Now where can you tweak that sort of thing in Java? ... Oh, that's right, YOU CAN'T.
But that's object oriented languages (which is getting better since I'm learning how to make myArray[i] run twice as fast), I prefer to use C and fortran. Those babies are low memory and totally rock. You don't spend all your time making method calls, which chew cycles for each call (let alone being in large nested loops).
I don't mind punching out Java code; it's extremely good for some tasks, but it is not a language I'd use on a high performance system. Just in my experience. I could be wrong and would love to be proven wrong.
.
aye. It's not the writing of the words that's the problem. Great books are created daily on chatroom logs!
It's the *ordering* of the words that's the rub...
What's the difference?
This sounds like a job for Core Wars! http://en.wikipedia.org/wiki/Core_War
Here's some speculative science that might be worthy of modeling: Ionic Kinetic Energy Conversion Effect
Are there limits to the fact that when a charged particle is accelerated, it emits a photon? I was once told that below a certain point, the charge does not emit a photon. Really? Why? A possibly useful phenomenon needs relevant data! Thanks!
i'd put a girl right on the Raid-5 and let those 15,000 RPM drives go to town. Then, I'd make her sit on a cluster and do REALLY weird stuff to her. Or, just imagine it.
Start cranking out Ackermann values.
--<Mike>--
Wulll Lesee,
My fun with home clustering was mostly done on Dyne:Bolic 1.4.1 the last of the OpenMosix releases.
For me the ability to farm out some audio effects rendering on large tracks to my home network was a gas.Ripping cds to mp3 made the datarate from the cdrom the slow part.I'm not really a video guy but it must be cool to render video stuff without the wait.3d rendering I'm sure.
Others would have you run some socially conscious @home program.Others still would have you crack encryption for good or evil.Some would even have you crunch numbers for everything from gambling to politics.
I suppose fun could be as creative as running
a simulation of a world based on John Lennons "Imagine" You could create a virtual projection of a world where Environmentalists do cleanup in the meatworld where it will do some good instead of on a cluster "spinning" a world for political power.What a kick.
"Imagine all the Hippies picking up the goop.
Yoouuuouuuuu may say I'm not a greenie,
But it's only just for fun,
I hope someday to cluster and the woooorrrrld will be more fun.
*Repent!Quit Your Job!Slack Off!The World Ends Tomorrow and You May Die!
A number of other posters have suggested this answer, but I wanted to emphasize it.
You are lucky enough to have a massive, desirable resource that is underutilized while we are in the midst of an academic funding environment which has been called the worst ever for supporting basic and applied research. You, as an academician, have an unwritten duty to help other academicians, and so rather than think of geeky ways to mess around with your new toy, why not share your wealth?
Here are the advantages:
1. You can wrangle additional publications out of it by being an author on published papers by providing sufficient support. Publications are the lifeblood of academics.
2. You can use it to leverage improved relations (or establish relations) with other departments within your university, or across universities. This might not seem like it would be worth much to you, but it will be impressive to your supervisors and department heads (they can take credit for it), and will make you look good in their eyes.
3. You can leverage it to good-news PR. University administrations love good PR. Talk to your PR department. Involve your department.
4. You can do good in the world.
I, personally, run an analysis of neural recordings every so often using Matlab that takes about a week on a reasonably modern dual-core system. It sure would be nice to have that finish in 1/500 as much time! There are about 20 or so researchers who are doing work like mine, and none of them, to my knowledge, are using a high-performance computing environment to analyze their data. It just isn't within their means. I'm not talking about some esoteric, arcane basic science research (although I'm a huge, huge proponent of that), but helping the paralyzed to walk again.
Put my fist through my alarm clock with its ding-dong death inside my ear. - The Blackjacks.
Or maybe even more than one ...
run Vista with Aero enabled
I have been a user for about 10 years. This ends Feb 2014. The site's been ruined. I'm off. Dice, FU
Neural nets, optimization sorting, whatever it is... what I would really be inclined to do with a vastly huge amount of spare computing power.. would be to try to run the most interesting evolutionary systems that might exhibit some emergent behavior that I had never initially expected/hoped for.
---
the pen is mightier then the sword. the sword is mightier then the court. the court is mightier then the pen.
Imagine a beowulf clus.... No forget that.
How about a Quake server?
#include <sig.h>
Build a debian repository with performance optimized scientific software for a large number of different architectures.
Telling the truth, not so much.
And the truth is?....http://ebgp.net/ccc/
And save the environment a little bit?
:P
Try to find the least power consuming configuration that works under full load.
Then, starting from that point try to find the best way to automatically adjust between idle and full load (think disabling/enabling cores).
After you're done compare the power consumption with that after your modifications, translate that into management speak ($/year saved) and go get your fat bonus.
Oh, once you get it you owe me a beer
How about doing this to this?
Help them, to help us.
Mod points are a dangerous tool. Abuse them wisely.
[Joshua]Shall we play a game? [/Joshua] How about Global Thermonuclear War. [Joshua]Wouldn't you prefer a nice game of chess?[/Joshua] Later. Right now lets play Global Thermonuclear War. [Joshua]Fine.[/Joshua]
i hope that you're joking since a freezer/fridge outputs more heat on the warm side, than it draws on the cold side, i.e. to open a freezer to get the room colder is a really bad idea, since it would actually make the room warmer.
i find your lack of faith in science disturbing!
Telling the truth, not so much.
And the truth is?.... OUt There man, it's out there i tell ya!!When my Karma level reaches 0 I feel in piece with the Universe
Run your own MMORPG private server?
So at times when there's no stuff to crunch
So just that I understand this correctly. A university gets acces to such a badass piece of hardware which seems to me as a pretty expensive toy and basicly you're wondering what the fuck to do with it?
This seems like a pretty big waste of money to me. I'm sure there are lot's of other uni's and research groups who'd die for such a machine and would make sure that thing would be working it's ass of 24/7 for the couple of years at least.
Life starts at the end of your comfort zone.
Interesting definition of "high performance cluster" you have there.
Gigabit interconnect? Running your simulations in java?
I have no idea what kind of simulations you're running there but I seriously question the price/performance ratio of Opteron hardware for such an application. Sounds like you could save a ton of money by building your cluster from off-the-shelf hardware.
Recently, we managed to get a bunch of money for a High Performance Cluster to run our stuff on. The code is mostly written in Java.
Wait...let me get this straight. You just bought a high performance cluster but your high performance apps are written in Java? HAHAHAHAHAHAHAHAHAHAHAHA!!! That's funny. Let me guess, you couldn't find anyone who knew Visual Basic? You know, if you had written them in something a little faster like C or C++ you could probably run it on a single 4-way box instead of needing an entire cluster.
play Crysis on a super Hi-Vision reso :p
And then post your benchmark results. Don't think anybody is gonna beat them for at least a few years.
Using Mesa Software Rendering and Equalizer!
I would help my Folding@Home score.
And at the same time, have it drive my desktop screensaver.
This is actually exactly what I did with a cluster I had for a few weeks with nothing better to do on it during the interval.
XML is like violence. If it doesn't solve the problem, use more.
I'd imagine you could put together a rather impressive 10000x10000x10000 cell 3D variation on Conway's game of life.
I put together one of these on my laptop a few years ago and saw some really interesting things (500x500x500 at ~1Hz).
There's only one thing worthy of all that sheer, godly processing power, my friend: Run Zork, of course!
Last night I played a blank tape at full volume. The mime next door went nuts.
A while back someone made a nifty little executable that when executed would create a duplicate of itself and then after a time execute the duplicate (I think it was 60 seconds or something).
The twist is that the program would have random chance of mixing up bits of itself when duplicating itself (mutating if you will). Some mutations would break the resulting executable rendering it 'sterile', some mutations cause the filename of the executable to be different than expected etc etc. The point is the mutation was pretty much random in what code it changed. This process would continue untill the computer froze after being overrun by thousands of little executables running and duplicating themselves every 60 seconds. All that was needed was a simple reboot and the system would be working fine again (albeit there would be a directory full of executables).
I believe the original creator found some interesting results after leaving his machine on for a while... some of the progranisms were in different directories, others had weird names, and a bunch of other stuff I'm probably forgetting.
I'd imagine a super computer would yield some pretty cool results...
Or of course, you could always do what I'd be tempted to do... Install WoW (using wine if needed) and then brag in trade channel about massive your computer is...
There are a lot of things a cluster could do. Even this;
10 PRINT "DAVE"
20 GOTO 15
I know that I would just write a Mandelbrot set displayer that used arbitrary precision and make high rez videos of ultra deep zooms.
The new MSV alpha
Bah. Too slow. Inifiniband FTW!
You should look into utilizing the hub0 concept on your cluster. www.hubzero.org. Its an excellent way to allow users to utilize the system at all hours, and for a myriad possibilities.
f or when the aliens want to be found, it will probably be in Hollywood ID4 style and not some little green guy screetching "Can you hear me now?" on all frequencies and modulations.
I do not think you understand the concept of space-time.
Methinks you would change your opinion if you understood that concept.
Short version: The universe is 20 bil yrs old. What if that smart race of aliens lived and died out between 1 and 2 billion? We'd never see them.
You see, "intelligent" man has only been around maybe a few million years. That is insignificant compared to 20 billion. In order for us to "see" aliens, we both have to be sufficiently evolved at the same time so we can chat. Now throw in the speed of light and how far/fast signals can travel and you have an interesting problem.
Run any simple parallel alpha-beta searcher on games like chess, go or arimaa.
Or paralelize several algorithms for these lkind of games and see how well they scale.
"I do this for a living at a genetics research lab"
That they key here. We have nobody like that. So we accept a little performance loss...
Complexity is a measure of our ignorance...
Indeed. Properly optimised C++ would be way more than ten times faster than the equivalent Java. Until you screwed up your pointer arithmetic and brought the whole thing crashing down.
Gory, how quickly do you manage to boot all 500 cores to a 'weird' system image of your choice?
How about renting out the spare time to smaller university professors that would like to do chemical modeling or something that they've been working on but don't have the raw computing power to speed up their work? I know there are some cool things being tried but the results take a long time because the models take a while to run on second rate (albeit pretty good) modeling setups.
IMHO
Use the Beowulf cluster to hunt down and kill the grendel that's attacking the /. mead hall.
Prevent Windows piracy. Use Linux instead.
http://www.globus.org/
Have it calculate rainbow tables out to as many characters as it can
Calculate some serious lego math:
Solve this math problem
I hear that there are still some digits of pi that need finding...
The random number generator on FULLTILT has some major patterns to it. Figure out why I keep playing and losing money for no reason with your super duper computer.
Setting up a game server would be nice on it.
Make it spam this site like mad till you get a proper answer.
Run a program that creates every possible permutation of Lego bricks up to a certain size. Sort through the cool ones and sell them to Lego, say for a lifetime supply of Legos.
I live in a small urban area near Rome, Italy. I have a 2 rooms apartment and i work and study in Rome. I commute to Rome by train and i don't have a car. My house is well insulated and i hardly need any heating in the winter. I don't have air conditioning at home and i do the totality of my geekyness from a 2002 50watt laptop. I don't have incandescent lighting at home and when the CFLs wear out, i deliver them to a proper disposal center (mandatory here for the heavy metals present in the CFLs). I do every week differential collecting/recycling (plastics,glass,paper,meds,batteries,cans all go in different containers) and all my organic wastes go to a neighbor of mine with a little orticultural garden, he does compost with mine and others' garbage.
I try not to buy packaged foods, preferring to them the ones sold by weight (still not that common here but increasing), i don't use plastic bags when i shop (i usually go with my empty backpack and i buy just as much as it can hold, which is still a lot) and i buy most of the vegetables and fruits by the said neighbor. I proposed to the landlord to install a rain-collecting tank (quite cheap) and to use it for water needs that don't involve drinking (W.C., maybe laundry if the rain doesn't prove very polluted). I wash my laundry with a greasy vegetable soap (i think it's from coconut oil, no addictives) and it has proven quite effective (results differ from person to person, i've heard of people not very happy with it) for me, most of the cloths doesn't need softeners or other addictives either. My washer is rated AA+, it's a low volume one and it uses a hot-water tap instead of an internal heater (the hot-water tap is attached to my heating system, a condensation heater,methane-based. Much more efficient than the electrical internal heater of most washers).
I drink tap-water, i bought a cheap water filter (a little like the Britas i heard of, but maybe more complex than that) 4 years ago and i never spent a single buck after that for bottled water. I don't have a micro-wave and i cook most of my meals on a simple methane kitchen (4 fires), i admit using my small methane oven sometimes (on occasions with friends) but it's nothing like the big ovens for turkey that i've seen somewhere, it's 35 cm wide and not very deep.
I don't have a dish washer (i live alone, washing dishes 3 times a week doesn't really ask for a dishwasher). I've a very old nokia cellphone (i think it's a 3210), it has miracolous autonomy and it works. I have a 40watt(on load) fileserver for archiving (for work) and p2p. My average energy footprint during the year is no more than 300 watt at any given time (considering the peak usage when i do laundry and not considering methane consumption, which i cannot estimate in equivalent wattage but which is quite low by any standard). To achieve this i just applied what i slowly learned (out of curiosity) on energy savings.
I take it as a social duty (to do my part to preserve the area i live in) and it's a way to re-establish social relations and to save money. There's no need to go this far but this is a little example of what someone can do with minimum effort.
I'm 24, i live by my own since i was 19 and i tried to support this kind of thinking at my parents' home too since at least 7-8 years ago. It was already a very popular subject (the envinronment) but more than a cool thing i see it as a community service. It's a way of preserving a common property.
Yes, i could do more and i will as soon as i will have the economical means of doing that. Most likely i'll buy a solar thermal panel and maybe a photovoltaic one if legislation here improve. I don't think not being gandhi is hypocrisy. Supporting the pr
Violence is the last refuge of the incompetent.
Add this cluster to one of the available Condor pools. The system is designed to do exactly what you want: Take unused resources and utilize them. The difference with you is that you'll be adding a *LOT of unused resources to whatever pool is lucky enough to have you.
http://www.cs.wisc.edu/condor/
you could run a new form of differential cryptanalysis on it, which i'm developing. contact me for details if you're interested in cracking block ciphers.
note: this is not a hoax, a spoof or a joke.
you can do a brute-force gcc flags combination searching ofr the very best options.
Looking for the very best set of options for each package, starting on the toolchain to make gcc, then the linux kernel, then starting on stuff like X11 , core desktop environment libraries, and finally the apps.
HUmm, maybe you could use a customized GCC which applies all possible combinations of all optimization flags to each individual function...
I've actually always dreamed of someone solving Chess.
There can't really be that many options, right?
Point me to a non-trivial benchmark showing C++ to be anywhere near 10x as fast as Java. Seriously, I'm waiting.
On real algorithms, properly-written Java is anywhere from roughly equal to properly-written C++ down to maybe 1/2 the speed. "Way more than ten times faster?" You're either trolling or an idiot.
I do happen to know of one case where Java really is far slower than C, and that's in its trigonometric functions on Intel processors. Of course, there's a very good reason for this: Intel processors' built-in trigonometric opcodes will give you the completely wrong answer outside of a very narrow range of inputs. C / C++ doesn't give a crap and uses the instructions anyway, whereas Java recognizes this and uses an algorithm which actually gives correct answers, but is slower.
Of course, if you're not concerned with accuracy, I can provide a really fast implementation of the functions:
float sin(float radians) {
return 0;
}
Of course, just as with the C / C++ case, we're sacrificing some accuracy -- but at least it's fast! See how much performance you can get when you don't care whether the answer is right or not?
ZFS: because love is never having to say fsck
Step 1: Develop an advance Pong playing AI.
Step 2: Duplicate AI a million times.
Step 3: Epic Pong tournament ensues.
"Napalm is nature's toothpaste" - Chef Brian
Unrelated (to JAVA), but pls email me, Gori, at brianfh1-at-gmail.com .
I've coded low level audio processing algorithms in C, C++ and assembly, and also experimented with coding them in Java and C#. The latter languages did surprisingly well, but they're nowhere near as fast. They're just not designed for that type of thing. It would be just as mad to use those languages for low level stuff as it would be trying to write a large GUI app in something like C++ these days. Every language has its uses, for most purposes you'd never need to go near C or assembly, but sometimes you just have to get as close to the metal as possible.
Having said all that, my experiences are anecdotal, I don't have any hard figures to back them up. Besides, I only mentioned it to get in the joke about pointer arithmetic.
But just for fun, here is a site showing C++ twice as fast as Java, and here's a seriously out of date one showing that Java used to be 10 times slower.