We touched on this a wee bit in my FAH@GPU thread, but I think it might be interewsting to go into a little greater depth. They Stanford boys have been hinting at a revamp of the points system for quite some time on account of the outdatedness of the single core benchmark machine and the rise of high performance clients on GPUs and the PS3.

That makes me think about how they're going to structure the system to

1. Be fair to contributors, however they choose to perceive that
2. Be respectful of the existent points of current contributors, e.g. don't suddenly make the benchmark score 10k PPD, thus making past contributors think their effort was chopped liver
3. Add incentives for people to use machines and clients that give the best scientific performance, not just points

That last one is particularly relevant to me. I had a go with the GPU client which is about 10x as productive as a standard client. I usually run the Linux MSP client on the machine. We'll say that that gives 4x the performance of a standard client to be generous. The GPU WUs give me less PPD than the SMP WUs. If the GPU WUs scored better they'd be getting more than twice the productivity out of me in terms of scientific output.

How would you enterprising chaps address the problem?

Interesting points. Yes the PS3 and the GPUs rock and peta flops are usual rather than some distant goal; but the bulk of the work has been done by Windows PCs running single processes. It would be cruel and unusual to trash that by a radical points change. I'd probably go do something else with my time and computers if there were to be a seismic shift in credits (PPD).

Regarding c. (above) I think that each type of contributor (CPU) should be rewarded based on what their type of machine can do. By that I also want to plug for 24/7 Folders, let's have some bonus points for Folders with OCD.

If your machine can spit out 3 WUs per day at 24X the FLOPS of a P4 like a PS3 does, should that be worth any more points than a bottom of the barrel SMP machine that takes three days to do one WU? I say no. They should be about equal, and right now they've done a pretty good job of being fair. Hope that they keep it so that no one jumps ship.

ps. New PS3 System update 2.10 and a new F@h client are out today (downloading now). There was an improvement in PS3 PPD with the Advanced Mode of the last update and this one is supposed to bring further points increases. They are doing more complex work than at first.

pps. I also have a faint hope that Stanford will fix Alzheimer's and prostate cancer before the family's genetics deals my next hand in life.

The PS3 update also allows timed shutdown and music playing the background while you fold.

How would you calculate the best scientific performance?

:\

Just don't touches my points... i has none

seriously though, i hope they make it retro-active, so my 50k points are worth the equiv.

Moar points

It's something that the Stanford folks deal with. I don't think it's easily quantified but some architectures and methods are able to go through the same work much quicker than others.