The US Air Force is less than pleased with Sony for removing the PS3’s Linux support, although unlike most Sony critics it does actually use the OtherOS feature, in a supercomputing cluster of PS3s which it complains is now doomed by a lack of replacement units.
The US Air Force Research Laboratory built a 53 teraflop cluster of 336 PS3s in 2009 by way of a test, and then added a further 1,700 PS3s in early 2010 after being satisfied with the results. It claims the PS3 cluster solution is much cheaper than the conventional alternatives.
The Air Force Research Laboratory now publicly laments the decision by Sony to remove Linux support, as although it does not connect to the PlayStation Network or use games, it does make it impossible to replace broken units:
“This will make it difficult to replace systems that break or fail. The refurbished PS3s also have the problem that when they come back from Sony, they have the firmware (gameOS) and it will not allow Other OS, which seems wrong.
We are aware of class-action lawsuits against Sony for taking away this option on systems that used to have it.”
Sony’s supposed advertising of such alternative usages of the PS3 has been mentioned in the lawsuit, so the Air Force may yet find itself drawn into the fray.
Sony for its part is probably happy to be rid of its research customers – console hardware is usually sold at a loss, with profits coming from software sales, so from Sony’s perspective cluster users are little better than parasites taking advantage of its subsidised Cell processors.
The PR benefits of such usage may well be vastly outweighed by the cost of such subsidies.
Equally, cheapskate research institutes cobbling together supercomputers from subsidised home consoles are hardly in a position to complain – on the contrary, the Air Force appears happy to suck up the loss and has no intention of stopping with the PS3:
“The gaming and graphics market continues to push the state of the art and lowers the cost of High Performance Computing, FLOPS/WATTS per dollar. This is important for embedded HPC, our area of expertise.
The HPC environment is rapidly changing; leveraging technology that is subsidized by large consumer markets will always have large cost advantages.
This gives us the experience (lesson learned) to develop HPC with low-cost hardware, benefitting the tax payer, Air Force, Air Force Research Lab while utilizing limited DoD budgets.”