|
Show Posts
|
Pages: [1] 2 3
|
2
|
Optimized Seti@Home apps / Windows / Re: V8 Optimized App
|
on: 20 Oct 2007, 03:07:20 am
|
Thanks Jason. Makes good sense. I'm going to give it a whirl and see how it works. Regards, Ian
It'll be interesting to see if the theories apply in practice on non-server hardware too. If low latency's the ticket whatever speed you buy I'll have to improve the ram in my old clunkers I'm actually going to tighten-up a pair of Team Xtreem DDR2-1200 and try to run 1:1 at 400Mhz & CL3-3-3-8 1T w/ FSB 400x8 on P5k Dlx.
Key word is "try". |
|
|
3
|
Optimized Seti@Home apps / Windows / Re: V8 Optimized App
|
on: 20 Oct 2007, 02:36:25 am
|
Noticed your comment regarding latency.
So, on a Q6600 Quad for example, Seti would respond better w/ DDR2-800 @ CL-3 than cranking to higher bandwidth, say DDR2-1200 but having to run CL5?
Is this right?
[PS: As a guesstimate , if 3 cycle latency and 400Mhz (DDR2-800) is 7.5ns , and 5 cycle latency at 600MHz (ddr2-1200) is 8.33ns then a small access will start about 10 % faster with the low latency ddr2 800.
So if I was just doing seti and checking my emails I'd go the ddr2-800 low latency,
Thanks Jason. Makes good sense. I'm going to give it a whirl and see how it works. Regards, Ian |
|
|
4
|
Optimized Seti@Home apps / Windows / Re: V8 Optimized App
|
on: 19 Oct 2007, 10:24:48 pm
|
Fast Latency is more important for small random memory accesses (Like seti) , and high bandwidth is more important for database servers and stuff. (depending what they store )
I think adding more sticks would increase bandwidth but raise latency too, making that more suitable for a high capacity database server that accesses big blocks of continuous data. (less suitable for seti / workstation]
Jason
Noticed your comment regarding latency.
So, on a Q6600 Quad for example, Seti would respond better w/ DDR2-800 @ CL-3 than cranking to higher bandwidth, say DDR2-1200 but having to run CL5?
Is this right? |
|
|
6
|
Optimized Seti@Home apps / Discussion Forum / Re: CPU temperature
|
on: 15 Sep 2007, 04:59:56 pm
|
There are always on and off threads regarding CPU temperature and computer overheating due to BOINC.
Here is a curious fact.═ Seti@Home is the hottest.═ My notebook CPUs run up to 75C during Seti runs.═ The lowest I've seen at 100% CPU utilization on both CPUs was another project which peaked at 60C. I've often wondered if it would be possible to code a sequence which has no pipeline stalls, keeps all execution units fully occupied, uses cache fully, and uses main memory transfers at peak. In a sense that's the ultimate goal of optimization; nothing wasted. I don't think we're anywhere near that yet, but I take higher CPU temperatures as a good sign in general. OTOH, a bad algorithm can use a lot of CPU without being optimal, so I don't think temperature is a sufficient indicator of effective optimization. Joe Along your comment Joe, I remember Francois commenting once (& Alex long before him ), about the importance of minimizing L1 thrashing. Francois rather threw that in everyone's face a year ago that the then-current code thrashed heavily and that would be a primary area he'd focus/clean-up. To your point, this would contribute to higher CPU temps, right?.... but would certainly not be optimized performance.
How much validity do you think there is to his L1 thrashing comment today? Is it really that much of an issue/area of opportunity? |
|
|
7
|
Optimized Seti@Home apps / Discussion Forum / MB ARs: Apples to Apples
|
on: 26 Aug 2007, 02:34:38 pm
|
Question for Joe or Crunch3r:
Been seeing many WUs granting 63.98 credits these past several weeks.
Just compared times on my T7200 -doze box w/ Crunch3r's 2.4 MB ssse3 vs. OSX box T7200 w/ Alex's revised 7.2 for C2D.
The iMac crunched several WUs w/ AR=.010024 in 7751.81 for 63.98 credits The Dell, WUs w/ AR=.006913 in 8319.08 for the same 63.98
Both rigs have crunched dozens of 63.98 credit WUs, yet the AR of the same credit WUs is distinctly different for each platform. Different AR = same WU credit?
I know there is a simple explanation for this. A refresher lesson from the resident professors? |
|
|
8
|
Optimized Seti@Home apps / Windows / Re: 2.4 Unrecoverable Errors ??
|
on: 24 Aug 2007, 11:37:29 pm
|
I'll back Crunch3r's comments on 5.10.13 as it would not work w/ x32 -doze 2.4 SSSE3 on my T7200.
WUs would randomly slow by 75% and take 2-2.5 times as long to complete as they should. I was getting longer times than a P-M 1.7 running stock 5.27. NO WAY that is correct. in other cases, threads would start and freeze leaving only 1 thread running.
FWIW, this "stable" BOINC version also froze-up running 2.3 development aps and 2.2B. I've tried resets, uninstalls/reinstalls, defrag/restart etc. Once I went back to 5.4.11, everything ran perfect. I also had issues w/ 5.10.13 on T7200 iMactel and "reverted" to 5.4.9. Problems went away. IMO, 5.10.13 has problems and isn't a stable release. Actually, I've run Betas w/ less issues in the past than this "stable" one.
Not ranting on BOINC, but this one version is just particularly bad. |
|
|
12
|
Optimized Seti@Home apps / Discussion Forum / Re: I hate Deers ....
|
on: 07 Jul 2007, 11:50:44 pm
|
Holy S**t!
Glad to hear you're still w/ us. BTW, it's 50/50 hitting a deer vs. ditching the car. You may still get toasted by hitting it since they have a tendency do go THOUGH the windshield and their hoofs can end-up inside the car w/ you.
I rolled a compact during a storm in 93' 7 times through a telephone pole into a field and ended up-side down w/ the roof buried in the mud. Every window was blown-out, glass everywhere including in me. The car was destroyed. Got a few nice scars on my back and a stiff neck for remembrance. Darn lucky to be alive.
You probably didn't feel much during the accident, but you will now and later as the adrenaline in your system wears off. Trust me and see a doctor. You may have injuries you don't recognize yet (as my neck showed on the x-rays. No pain, but dislocation of 2 vertebrate that REALLY concerned the doctors at the time).
Take care of yourself. Ian
|
|
|
13
|
Optimized Seti@Home apps / Discussion Forum / Re: Simplified stats gathering
|
on: 07 Jul 2007, 04:19:12 pm
|
Hello Is there any table with results aquired with benchmarks (KWSN Knabench 1.43 Benchmark for example) on different platforms to compare ?
There really isn't anything like this consolidated w/ the recent aps. Early-on, a few charts were created w/ some of the first opt aps on different platforms for S-Enhanced @ 1 year ago. Since then, speed of later aps has improved dramatically and the hardware mix has advanced w/ more C2D and xeon rigs. So....the earlier charts are rather worthless to your question.
However, there have been a couple of recent discussions re: how to measure FPU and INT performance accross platforms for comparison. As Crunch3r points-out, as long as bitness (x32 or x64) is consistant between aps and hardware, then S@H and ABC could provide a decent set of benches using a uniform WU for each project that different platforms could be measured and logged. This would not only give a better relative comparison of CPUs for S@H, but would also give better insight into relative processor performance for those that run projects that have both FPU and INT processing bias.
In some cases, many older p4 and AMD processors that are rather melba-toast today on S@H (compared to C2D), may perform comparatively much better in 64-bit mode w/ projects like ABC that focus on INT processing. For those that run multiple projects, this could be helpful info.
Could be a fun side-project and not too hard other than the maintance and updating of the central database. |
|
|
15
|
Optimized Seti@Home apps / Discussion Forum / Re: Anybody running on Bearlake yet?
|
on: 17 Jun 2007, 10:59:08 am
|
Hi folks, while it may not be an Asus board, this one looks pretty promising as far as Bear Lake boards go: http://www.theinquirer.net/default.aspx?article=40381 DFI LanParty P35-T2R I mean, 2.5 GHz FSB? Whoa...digital PWM power converter circuits really seem to be the way to go in the future. No way you're gonna get close to that with analog ones. When you look at the picture, note the area above (as the board lies) the CPU socket. Notice the lack of tons of large condensators, and the general flat and heatsink-less area? Ever put a thermometer on your analog PWM? Not sure what price that DFI board is going to be, but it may be worth it coupled with a 6420 or a new Q6600 vs. another board with a higher-specced chip. Regards, Simon. Drooollllll........ By the time Penryn arrives, there should be a few bios updates and wider/lower latency DDR3 available. This board should be huge grins and giggles! |
|
|
|
|
Quote!
Two wrongs are only the beginning.- Murphy's Law
|
| | |
|
Site Statistics |
Total Members: | 678 |
Total Posts: | 4,969 |
Total Topics: | 337 | Downloads |
Apps |
Windows R-1.x | 24,079 |
Windows R-2.0 | 19,299 |
Windows R-2.2 | 33,941 |
Linux 32bit 1.x | 6,261 |
Linux 32bit 2.2 | 3,786 |
Linux 64bit 2.2 | 1,268 |
Alpha/IA64 | 84 |
FreeBSD | 246 |
HPUX | 166 |
Subtotal: | 88,634 |
Source packs: | 3,400 |
Tool/WU packs: | 5,483 |
Total: | 114,017 | GBs dl'd: | 173.85 | Pages served |
Today: | 1,674 |
Total: | 2,099,949 |
(since 6/26/2006) |
171 Donations to S@H |
U.S. Dollars: | 3,190.59 |
Euros: | 830.90 |
Last 24h: | $ 0.00 |
Avg./24h: | $ 15.74 |
Estim. total: | $ 4,270.76 |
Latest Member: cjdigresia |
| |
| | |
| | |
|
Online users/last 15m
12 Guests, 1 User
Astro 28 Members/last 24hErektile Dysfunktion, Astro, WHRoeder, j_groothu, TheGasGiant, seti_britta, msattler, WinterKnight, Raistmer, DerToT, The Grinch, Alex Kan, firefox, Gecko_R7, korpela, Fivestar Crashtest, Geek@Play, sunu, wes_shaw, ajs, an_heol_a_zo_glaz, ppppgabor, s52d, Devaster, Arnulf, hiamps, Bluesilvergreen, sweede, autocrosser
| |
| | |
|