Message boards :
Number crunching :
Astropulse units too big?
Message board moderation
Previous · 1 · 2
Author | Message |
---|---|
pete1939 Send message Joined: 30 Aug 99 Posts: 4 Credit: 251,809 RAC: 0 |
Sorry about that last post, I replied without entering anything. My system is running 24/7. This system does little else, except for running an AVGFree process every night. I normally have a Seti process running on each CPU. Because of heat issues, I've got "Use at most" set to 50%. When two Seti processes are running, Task Manager shows a little over 50% CPU usage. The Progress column for the AP WU shows 19%, so, I assume this WU will use about 350 hours of CPU before completing. Is that about right? I suspended the Seti Enhanced 6.03 WU a couple of hours ago. We'll see if that helps. Thanks. Hi, one of my systems has been crunching an AP WU for several weeks now. |
Richard Haselgrove Send message Joined: 4 Jul 99 Posts: 14653 Credit: 200,643,578 RAC: 874 |
That sounds more reasonable, but still seems on the long side. For comparison, I've recently reported (details are on this message board somewhere) that one of my P4 single cores, running at 2.0 GHz, completed an AP task in 146 hours. Yours should be faster. You haven't mentioned your operating system, but 2 GB should be enough for anything - even Windows Vista ;-) ! So unless you need to run applications which need all that RAM, I would suggest you find the preference for "Leave applications in memory when suspended?", and ensure that it's ticked. (You should find it in much the same area as the CPU usage that you're already using). The only other thing would be to minimise your use of the SETI graphics or screensaver - they can eat into your CPU usage as well. |
Cosmic_Ocean Send message Joined: 23 Dec 00 Posts: 3027 Credit: 13,516,867 RAC: 13 |
Alright then, I stand corrected. I was going off of the information I had and at the time, didn't feel like doing research to get new information. Didn't think there was anything new. I figured Intel would just keep continuing on with their technique from the P4s.Intel being faster than AMD in these kinds of scenarios are due to Intel's large L2, and that the L2 is shared amongst the cores. About 90% of the crunch time can be decided with the built-in benchmark of BOINC. Integer math doesn't do anything for crunching, it's the floating point benchmark that matters. Linux laptop: record uptime: 1511d 20h 19m (ended due to the power brick giving-up) |
Eric Korpela Send message Joined: 3 Apr 99 Posts: 1382 Credit: 54,506,847 RAC: 60 |
You should complain to Rom and David on the BOINC forums (http://boinc.berkeley.edu). The BOINC windows client doesn't actually try to figure out the total cache. It just puts in the value 1,000,000 bytes, and then divides that by the number of cores. If you look at our host stats you'll see that this "feature" of boinc makes it look like cache sizes are decreasing as the number of cores increases. Eric Have a QX9650 @ 3500MHz, FSB 1400, running UBUNTU 8.04 (x86), for a change. @SETIEric@qoto.org (Mastodon) |
arkayn Send message Joined: 14 May 99 Posts: 4438 Credit: 55,006,323 RAC: 0 |
You should complain to Rom and David on the BOINC forums (http://boinc.berkeley.edu). The BOINC windows client doesn't actually try to figure out the total cache. It just puts in the value 1,000,000 bytes, and then divides that by the number of cores. Same thing with OSX, the Manager says I have 972k of cache when I really have 4MB. I only have a C2D. |
pete1939 Send message Joined: 30 Aug 99 Posts: 4 Credit: 251,809 RAC: 0 |
That sounds more reasonable, but still seems on the long side. For comparison, I've recently reported (details are on this message board somewhere) that one of my P4 single cores, running at 2.0 GHz, completed an AP task in 146 hours. Yours should be faster. OK, I made the changes suggested, and increased the "Use at most" percentage back up to 100% despite CPU heating concerns. These changes were made on 8/22 and BOINC started showing better progress almost immediately. My AP WU finally completed sometime this morning. It took almost 227 hours of CPU time to complete the WU, or about 9.5 days of CPU time. The WU took just over 20 days wall clock time to complete with the Task Manager CPU showing just over 50% usage during the entire period. All is well. |
ML1 Send message Joined: 25 Nov 01 Posts: 20314 Credit: 7,508,002 RAC: 20 |
Intel being faster than AMD in these kinds of scenarios are due to Intel's large L2, and that the L2 is shared amongst the cores. ... And that's only part of the 'story'. The main aspect for a particular class of CPU is how well the application is 'sympathetic' to the CPU and the system hardware. This is where the Chicken Coop optimisers have made such fantastic improvements in the s@h code for various CPUs. [edit] This is also where some "Who?"-esq specialised CPU instructions can help with streamlining any time consuming or 'expensive' code sequences used by certain applications. This could improve on the existing assembler speed-up tricks used. [/edit] Another (and to my mind a very devious and wasteful) aspect is whether a certain series of Intel compilers or code has been used that unnecessarily and unfairly 'sabotages' AMD CPUs with the well known "Naughty Intel" trick... Has the Astropulse client been compiled with the 'Naughty Intel' silliness included, or is it just a question of how the client uses the different sizes of CPU cache? Happy crunchin', Martin (All just my opinions and observations as ever.) See new freedom: Mageia Linux Take a look for yourself: Linux Format The Future is what We all make IT (GPLv3) |
Raistmer Send message Joined: 16 Jun 01 Posts: 6325 Credit: 106,370,077 RAC: 121 |
MS VC++ build has comparable to stock times. No IPP or Intel-specific code used on stock AP. Not only cache sizes different. Quality of reordering, branch prediction and so on and so forth. Unfortunately (because I like AMD ;) ) Intel clearly wins this round for SETI-like apps... |
SATAN Send message Joined: 27 Aug 06 Posts: 835 Credit: 2,129,006 RAC: 0 |
Same thing with OSX, the Manager says I have 972k of cache when I really have 4MB. I only have a C2D. Arkayn, you have the same cache as the Mac Pro's according to the manager so look on the bright side. |
lynxtra Send message Joined: 3 Sep 04 Posts: 137 Credit: 273,636 RAC: 0 |
You can choose not to run astropulse in the future, by unselecting it in your account, in your SETI@home preferences section the truth is out there |
The Fiend Send message Joined: 23 Sep 01 Posts: 6 Credit: 3,051,288 RAC: 0 |
I have 5 computers running SETI 24/7, 4 are AMD and 1 is an Intel. I have come to the conclusion that I will only run Astrokitty on my Laptop which is an Intel C2D. And I have set my preferences to do that. |
Byron S Goodgame Send message Joined: 16 Jan 06 Posts: 1145 Credit: 3,936,993 RAC: 0 |
I have 5 computers running SETI 24/7, 4 are AMD and 1 is an Intel. I have come to the conclusion that I will only run Astrokitty on my Laptop which is an Intel C2D. I'm going to be doing the same with my AMD Athlon 64 Processor 3800+ 2.4 GHz. An average AP unit on my Intel Pentium Dual CPU E2180 @ 2.00GHz takes under 60 hours to complete. On the AMD I'm at 85 hours at almost 89% complete. I just feel I accomplish more on this sys doing the MB's. Also with some of the problems I've seen with the AP's I just don't want to also risk having the sys tied up for 100 hours or so and have problems with it in the end. If/When they come out with an app that allows AMD to compete with my Intel I'll be putting the sys back on track with AP. |
Byron S Goodgame Send message Joined: 16 Jan 06 Posts: 1145 Credit: 3,936,993 RAC: 0 |
|
©2024 University of California
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.