Re: Mersenne: 50% CPU?
I have a Pentium 4 processor and TM indicates an average usage of close to 100% CPU for Prime 95 - am I running 'multiple instances' without being aware of it? If so, how do I prevent this if it will degrade efficiency? Not all P4's have hyper threading not all motherboards support it on top of that. So it requires a HT enabled CPU, HT enabled Motherboard, HT supported OS for HT to function. From my experience HT is a nice feature since it gives Prime95 a chance to run even when other "not nice" programs are runningthat don't release the processor as often as they should even if it's not busy. The down side is with HT enabled Prime95 is more likely to interfere with certain performance sensitive applications. If you want to learn more about Prime95 HT there has been several recent posts on the topic at http://www.mersenneforum.org/forumdisplay.php?s=forumid=9 There is some evidence that running a LL (high usage of SSE2 floating point calculations) TF (high usage of SSE2 integer calculations) may increase overall throughput. Shane
Re: Mersenne: Poaching and related issues...
Increasing the difficulty for a poacher to _find_ a tempting target would mean other participants could be less concerned about making themselves into such a target, and just concentrate on doing the work they considered most suitable within the rules. If the rules you are referring to include the possible new guidelines George proposes (which in a nut shell goes something like this -- snips taken from a couple of posts on the forum by George) Consensus seems to be building around a sliding scale. It's 2 to 3 months for the smallest double-checks and first-time tests (to avoid holding up milestones), 6 months for recycled exponents, 12 months for an exponent at the leading edge. 2+ years for a 33M exponent. Give or take. A leading edge first time test today is unlikely to hold up a milestone for maybe 2 years. I'm not advocating yanking a reservation just because you've had it one year. I think we are proposing reassignment if you take more than a year and some other criteria is met such as: a) You aren't making significant progress. b) You are holding up a milestone. c) Require the user to fill out a web form saying I'm still working on it Then in fact, those guidelines are more stringent than ANY poaching methodology I've seen to date (including Malfoy's) other than some willy-nilly poacher who has no methodology at all (which I believe in most cases turn out to be a previous owner turning in the assignment from a expired owner 1 or 2 assignments ago). So in order to keep within these guidelines suitable types of work for a given machine would just so happen to avoid much of any chance of getting poached TODAY. Which brings to mind another part of Georges proposal which I don't see a easy *snip* for. The basic jest is that the new server would assign work to clients based upon this ideology, in other words the new server would be careful not to assigned a trailing edge exponent to historically slow computer. I whole heartily believe the best way to eliminate poaching is to minimize the reasons there are poachers to begin with rather than trying to make it more difficult to do. Even masking the exponents has a big loop hole in that it would take years to become effective even if implemented today. All that has to be done is to save a copy of status.txt today and you know a very very big chunk of the exponents that will fall in the trailing edge of the assignment list of many many years. After that it's a trivial matter of elimination to deduce which is which when masked. Shane _ Unsubscribe list info -- http://www.ndatech.com/mersenne/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
RE: Mersenne: EFF and 10,000,000 digits
I hope so too (heck, I hope I just live a long life...seeing a giga-digit prime would be a bonus). I suppose it depends on whether Moore's Law can continue to hold true. I'm not so sure that we can keep doubling speeds of processors every 18 months as predicted...it's already taken them quite a while to go from 300MHz machines to 550MHz machines for Wintel processors...and that's just barely in 18 months (close enough to doubling I s'pose). It's getting harder to eke out extra MHz without really dropping the die size alot more than what they're dealing with. But I suppose it won't be long before .15/.12/.10 micron die sizes are ready for mass producing. I have heard some insider news that Intel *could* hit the 1 GigaHertz mark by years end if they had a reason too (if AMD jumped out with a unexpected surprise). Once we start hitting the sweet spot in die size I am under the impression that they will start exploring the multiple processor route... Multiple processor systems are already becoming more mainstream. So I think we will be able to continue with MASSIVE performance increases over our lifetimes. This is assuming we stick with the Von Neumann architecture, new and EXCITING technologies (such as neural computing massively parallel systems) are just over the horizon. These technologies and others offer us unimaginable new possibilities with their own unique strengths weaknesses -- maybe when these new tools are out there we will find a new Algo. that better fits their strengths. My understanding of the purpose of rewards like the EFF is posting is to foster new and innovative ways to solve problems that almost seem impossible at the time. If asked 10 years ago who here would have thought we would be testing numbers as big as we have... George Scott's vision of this very project is such an example of break through technology, which allows us to advance in the scientific frontier at break neck speeds. Whoohoo isn't this a exciting time to live!!! Shane Unsubscribe list info -- http://www.scruz.net/~luke/signup.htm
RE: Mersenne: I am curious
At 09:56 AM 5/15/99 +0200, Henrik Olsen wrote: Just out of interest, can I have someone demand I give them a share of the money / stop being in GIMPS if they really wanted to (not that I should think they would...) One thing most people seems to have forgotten when it comes to talk about the money, is that according to the common scientific discovery rules George Woltman and Scott Kurowski will be co-discoverers of all primes found using mprime/prime95, and the client/server setup, so should rightfully get a big part of the money. From a legal stand point I think George Scott may have "signed" away most of their rights to the money (not the discovery rights though) by advertising on their web page that participating in GIMPS could win you $50,000. It certainly seems to imply that from my read anyway... Of course on the strictly ethical side of things I think George Scott deserve something for their troubles. Personally I feel that I would give a portion of the money back to GIMPS but then again that is easy to say when dealing with purely theoretical money ;-) I would think that 95% of the people here are involved with GIMPS for non monetary reasons, I would go so far as to say noble reasons, (especially the founders of GIMPS who have put in so much time and effort over the years). Sadly even the most noble of pursuits are often spoiled by squabbling over the "brass ring". Shane Sanford Unsubscribe list info -- http://www.scruz.net/~luke/signup.htm
RE: Mersenne: LLL
Maybe there something wrong with the PrimeNet server? Earlier today I had some of my machines check in and it seemed a little wacky. Also, entropia.com seems to be pretty flacky especially the status pages. When I loaded my individual account report it went completely nuts and told me I had 1000's 1000's of numbers check out (then I did a reload and it back to normal). Shane At 10:29 AM 5/13/99 -0600, Aaron Blosser wrote: Perhaps Scott could contact this fellow and see whats up? I know when I had a bunch of machines checking out numbers, Scott emailed me to be sure it wasn't just a bug or something. At any rate, it looks like all the LL exponents have been chewed up. Moreover, judging by the estimated time to complete, these are not fast machines... LLL would probably have been better off leaving the auto assignment turned on because I'd guess it would have taken DoubleCheck exponents. I hope this person knows what they're doing! Some of those numbers checked out all had the same ComputerID...hmmm... Aaron Unsubscribe list info -- http://www.scruz.net/~luke/signup.htm
