I'd be worried about heat on something that compact. Running the processor at 100% in such a confined case could cause issues.
What kind of FPU is on those chips? Is the math precision even going to be good enough to crunch the data with accuracy? Music and videos are different to process than high end math functions.
I wasn't able to find any specs on that particular model (probably need an NDA to get them), but decoding video needs the equivilant of a several hundred mhz pentium class FPU so it can't be too limited. I don't think overheat would be a problem either. I can't see apple paying for a chip with significantly more power than they need, so I'd assume it's running at a large fraction of max while playing video.
I have attempted to figure WU completion time on a 80MHZ iPod with general variables of OS, and Application lag.
Average Small (12.5 Credit Work Units) would take about 36.1 hours to complete, given the iPod is running non-stop at full CPU power.
I used a mathematical conversion, taking into account, lag from low RAM, OS Lag, and Application Lag. At about 87 Percent of raw CPU ability, then subtracting a RAM Lag variable.
If anyone wants the conversion calculations I used, let me know. Hope this helps. :D
wow, i completely forgot about this thread. I posted the same idea on seti and it just got ridiculed. What I understand from this thread, is that its possible but wouldn't be worth the effort other than as a proof of concept type of thing.
wow, i completely forgot about this thread. I posted the same idea on seti and it just got ridiculed. What I understand from this thread, is that its possible but wouldn't be worth the effort other than as a proof of concept type of thing.
Well, all in all. It may SEEM not worth it. But in the same idea of BOINC in the first place. You get MANY iPod's, or alike, to participate, and you have a much larger computational ability.... I know I am interesting in loading E@H on my Dell Axim X5 PDA.... Hmmm... The possibilities intrigue me... :)
I'd be interested in where you found the flops data for the ipod CPU that was something I couldn't find anywhere, and there was enough variation between different models (Even excluding the ones with a DSP) that I didn't feel confident in making a SWAG.
And I felt kinda crazy planning to attach my parents' old P3. But okay, quite a few people do that. Just out of interest, and as you could also count it as "low tech computing"... how long would a 667 MHz Coppermine need for a short WU? It would only get shorts, right? I can't see it meet the requirements for not being considered a "slow host", really... It has 256 MB of memory (old SD memory, cheap stuff like the mainboard and controllers) and is running Windows XP (I'm convinced it would do better under Linux but no one else in my family really shares that POV ;-) I could only guess how much time it would need, but I seem to remember installing BOINC on it for benchmarking and getting something around 900 integer, 550 floating point, or so. Could be mistaken there.
As for the iPod idea- sounds interesting, though I'm not quite sure how practical this is and (as I only have a rather old flash-memory MP3 player without video capability) I have no way to figure it out myself. But while we're at it... what about cell phones? They can do Java and stuff (the modern ones with video and organizer), though it tends to be laggy. Which kind of CPU do they use, and could they theoretically do BOINC?
If you look at my computer, and my results, you can see that I have less than 600MHX and I complete workunits well in time for deadline. My minimum time for small WU's is about 17,500 seconds about 4.861 Hours. If my computer was only crunching all day everyday 24 hours, with no user use, my computer's RAC (Recent Average Credit) would be about 60 per day. So, it won't be a waste to attach that computer. Mine is a Intel PIII 448MHZ 320MB Ram, Windows XP Service Pack 2.
I'd be worried about heat on
)
I'd be worried about heat on something that compact. Running the processor at 100% in such a confined case could cause issues.
What kind of FPU is on those chips? Is the math precision even going to be good enough to crunch the data with accuracy? Music and videos are different to process than high end math functions.
I wasn't able to find any
)
I wasn't able to find any specs on that particular model (probably need an NDA to get them), but decoding video needs the equivilant of a several hundred mhz pentium class FPU so it can't be too limited. I don't think overheat would be a problem either. I can't see apple paying for a chip with significantly more power than they need, so I'd assume it's running at a large fraction of max while playing video.
I have attempted to figure WU
)
I have attempted to figure WU completion time on a 80MHZ iPod with general variables of OS, and Application lag.
Average Small (12.5 Credit Work Units) would take about 36.1 hours to complete, given the iPod is running non-stop at full CPU power.
I used a mathematical conversion, taking into account, lag from low RAM, OS Lag, and Application Lag. At about 87 Percent of raw CPU ability, then subtracting a RAM Lag variable.
If anyone wants the conversion calculations I used, let me know. Hope this helps. :D
d3xt3r.net
wow, i completely forgot
)
wow, i completely forgot about this thread. I posted the same idea on seti and it just got ridiculed. What I understand from this thread, is that its possible but wouldn't be worth the effort other than as a proof of concept type of thing.
RE: wow, i completely
)
Well, all in all. It may SEEM not worth it. But in the same idea of BOINC in the first place. You get MANY iPod's, or alike, to participate, and you have a much larger computational ability.... I know I am interesting in loading E@H on my Dell Axim X5 PDA.... Hmmm... The possibilities intrigue me... :)
d3xt3r.net
I'd be interested in where
)
I'd be interested in where you found the flops data for the ipod CPU that was something I couldn't find anywhere, and there was enough variation between different models (Even excluding the ones with a DSP) that I didn't feel confident in making a SWAG.
And I felt kinda crazy
)
And I felt kinda crazy planning to attach my parents' old P3. But okay, quite a few people do that. Just out of interest, and as you could also count it as "low tech computing"... how long would a 667 MHz Coppermine need for a short WU? It would only get shorts, right? I can't see it meet the requirements for not being considered a "slow host", really... It has 256 MB of memory (old SD memory, cheap stuff like the mainboard and controllers) and is running Windows XP (I'm convinced it would do better under Linux but no one else in my family really shares that POV ;-) I could only guess how much time it would need, but I seem to remember installing BOINC on it for benchmarking and getting something around 900 integer, 550 floating point, or so. Could be mistaken there.
As for the iPod idea- sounds interesting, though I'm not quite sure how practical this is and (as I only have a rather old flash-memory MP3 player without video capability) I have no way to figure it out myself. But while we're at it... what about cell phones? They can do Java and stuff (the modern ones with video and organizer), though it tends to be laggy. Which kind of CPU do they use, and could they theoretically do BOINC?
If you look at my computer,
)
If you look at my computer, and my results, you can see that I have less than 600MHX and I complete workunits well in time for deadline. My minimum time for small WU's is about 17,500 seconds about 4.861 Hours. If my computer was only crunching all day everyday 24 hours, with no user use, my computer's RAC (Recent Average Credit) would be about 60 per day. So, it won't be a waste to attach that computer. Mine is a Intel PIII 448MHZ 320MB Ram, Windows XP Service Pack 2.
d3xt3r.net
IIRC when I was briefly
)
IIRC when I was briefly using, it my parents athlon-900 took about a day to do a long WU. Since your p3 is SSE capable it should run about as fast.
Nope, earlier PIII's aren't
)
Nope, earlier PIII's aren't fast enough to draw long results. I know 550 and 600 MHz Katmai aren't. A 700 MHz Coppermine might just squeak in barely.
Generally I've found you need to be in the 1 GHz ballpark for the longs.
Alinator