but mostly not the people complaining, and they probably never would have either
but mostly not the people complaining, and they probably never would have either
Many research companies, universities, and other organizations use clustered PS3s running Linux (or some other OS) as an alternative to some supercomputers due to their good price/performance and scalability. Hell, I think the Air Force has clusters that use hundreds of PS3s.
http://gravity.phy.umassd.edu/ps3.html
http://www.ps3cluster.umassd.edu/index.html
Hopefully Sony will still provide PS3s for them if they want to expand or replace failed units.
I still don't know what normal gamers do with it though.
PS3 under linux wasn't that powerful thanks to the hypervisor limiting it to two cores (used to be six long ago) and the dinky amount of RAM it has access to, requiring you to be anal about what's current loaded, even from terminal.
Could they not get something built miles better at the $500 price range (what they ran at that time) that the uni would have otherwise had to pay for them if they were not partially donated?
http://www.wired.com/techbiz/it/news..._supercomputer
3.2k to build a cluster of 8 that's capable of computations that cost 5k to run a single set on a "proper" supercomputer
it's freaking amazing what that processor can do
also, seeing how those were donated to him by Sony, I'm pretty sure they're keeping this in mind
No, for that type of computing the PS3 cluster was they best they could do. I think I read that to build a conventional system it would have cost over 10 times as much.
As Plow said, most of these types of calculations are outsourced for thousands of dollars per run. In addition, the time on those supercomputers is limited and you have to wait for your program to be run. Putting together a 'cheap' PS3 cluster would allow you to run your programs whenever needed and however many times you'd like to do it.
By the way, that Air Force project is actually using over 2000 PS3s in a cluster, not just hundreds. It supposedly will be in the top ten supercomputers when finished when measure by FLOPS.
http://gravity.phy.umassd.edu/ps3.html
The Sony PlayStation 3 has a number of unique features that make it particularly suited for scientific computation. First, the PS3 is an open platform, which essentially means that one can run a different system software on it, for example PowerPC Linux. Next, it has a revolutionary processor called the Cell processor which was developed by Sony, IBM and Toshiba. This processor has a main CPU (called the PPE) and several (six (6) for the PS3) special compute engines (called SPEs) available for raw computation. Moreover, each SPE performs vector operations, which implies that they can compute on multiple data, in a single step (SIMD). Finally, its incredibly low cost make it very attractive as a scientific computing node i.e. part of a compute cluster. In fact, its highly plausible that the raw computing power-per-dollar that the PS3 offers, is significantly higher than anything else on the market today.
Thanks to a very generous, partial donation by Sony, we have a sixteen (16) PS3 cluster in our department, which we call PS3 Gravity Grid.
Overall, the performance of our PS3 Gravity Grid compares to nearly 100 cores of high-end Intel Xeon processors or as many as 500 nodes of an IBM Blue Gene supercomputer. Here is a list of research articles published using results generated using this cluster: Phys. Rev. D78 064042 (2008); Class. Quant. Grav. 26 015014 (2009); PPAM (2009); PDCS (2009); IJMSSC (2009)
•HPL - Standard supercomputer cluster benchmark (GK)
This project is about performing a standard LINPACK cluster benchmark on our sixteen (16) PS3 cluster. This is the benchmark that is used by the top500.org site that lists the most powerful supercomputers in the world. We worked with IBM to port their QS22 Cell blade benchmark code to our PS3 cluster. The results? The PS3 Gravity Grid generates a total performance of 40 GFLOP/s (40 billion calculations per second). It should be noted that this benchmark was run in double-precision and because of the limited RAM on each PS3 we were only able to fit a matrix of size 10K on the entire cluster. The larger the problem size, the better the Cell's efficiency, therefore these testing conditions were far from optimal (unfortunately). We expect to be able to get much much better performance from the cluster if we had significantly more RAM available. Even with the 40 GFLOP/s, our PS3 cluster is very competitive (in terms of performance-per-dollar) with the low-cost compute clusters out there. And if one could take advantage of doing some of the computation in single-precision, the performance would jump several fold -- likely achieve nearly one-half a TFLOP/s (half a trillion calculations a second). The benchmark code with Cell specific patches is available here: HPL.
And if you bothered reading my first post in this topic you would realize that I'm repeating myself in asking wtf people did with it. This has yet to be answered outside of these supercomputer clusters that probably haven't, nor will ever, run a Sony update making the removal of OtherOS moot for them. And I'm sure that everyone that's QQing over this is really shedding tears for the Air Force and not the diminished prospect of cracking the system to play games for free...
It allowed people to use PS3 as a computer, and gives access to things like:
bots, microsoft word/excal etc, better version of the dvd player, and many other things,
Similar to the astrophysicist: http://www.computerworld.com/s/artic...3_for_Research
I guess this deal is off. Either that or we have one seriously pissed off Air Force.
Okay even though I have a PS3 and could mention a few good titles, I chuckled at this.
Also, yeah, throw me in behind removing otherOS is bs, and I only own a slim. My reasoning behind this has already been mentioned by others, but removing features you bought (as a selling point, mind you) is bs.
Do we have any idea if debug units still have OtherOS access in the latest test firmware? I'm assuming the Air Force would be (if they haven't already given the date of the article) purchasing directly from Sony given the size of the order, and I'm sure they'd make exceptions to accommodate them.
Agreed anyone who's useing PS3s as a cluster, atleast at large scales, would most likely have a contract with Sony, and therefor Sony would most likely by pass, or realise a better version of the system, tbh i dnt see Airforce useing a system that anyone can buy anyway, wouldnt be surpised if sony designed there system.
To the people saying OtherOS was an advertised feature, please show me the ad that showcases this feature along with a group of people who bought them JUST for that feature alone and I'll concede. No, Air Force / others using them for research don't count because they probably have a contract with Sony and would never lose the OtherOS support anyway.
Who cares how many people actually used Other OS? Removing features because it could potentially contain a security loophole is a giant step in the absolute wrong direction, toward RIAA/MPAA-tier obnoxious DRM.
Interesting if true.
http://www.ironstarmovement.com/prof...are-update-321
Update 3.21 which Sony described as a security update and removes installing another OS is a lie. Apparently Sony had claimed that the 8th SPE was not used to increase production yields, when in fact it was reserved for running the "Other OS". Update 3.21 by Sony is in fact an advanced strike by Sony to hide the fact that the 8th SPE is needed to process the "Move Controller/s" without sacrificing existing graphics and game play.
Yeah, I should have read a little bit further lol. Disregard that post entirely.