Posts by [AF>Le_Pommier] McRoger
log in
1) Message boards : Number crunching : ZDnet overclocking tool for Macs (Message 15379)
Posted 14 Mar 2009 by [AF>Le_Pommier] McRoger
Just one comment: ony use it for cunching with Mac Pros 2008 and 2009.

With the 2006-2007 model, the FSB clock is directly linked to the Real Time Clock and the time is then wrong, which can cause problems if you use automated jobs (crons) like Time Machine.
2) Message boards : Number crunching : post milkyway_x86_84-apple-darwin problems here (Message 6461)
Posted 22 Nov 2008 by [AF>Le_Pommier] McRoger
Well, I simply do not get the new app on Mac OS 10.5, on a Mini (C2D T7200) and on a Mac Pro Rev1 (Xeon 5150).

I've:

- removed the appinfo.xml
- reset the project
- still app 1.22 (of Crunch3r) running

If I remove the 1.22 app, the WU go in error, even after a reset.
3) Message boards : Number crunching : Improved App will be released on Halloween (Message 5688)
Posted 31 Oct 2008 by [AF>Le_Pommier] McRoger
Good news ! :-)

Is a Mac OS client version also foreseen and if yes, for x86 only or also PPC ?

Thx !

In the moment I have only versions for Win and Linux on x86er CPUs. But I told already the project staff that they could again ask Crunch3r, as he has some experience in compiling things for OSX.
I can't make a promise, but maybe I could get access to a PPC and create a version for it over the weekend.

Btw., I planned to post a link to this topic in the fora/forums of some of the big teams. But frankly, my French isn't sufficient for this. It would be great if you could bring this to the attention of your team members.


No problem, it was actually already done on the Alliance Francophone newsgroup a couple of minutes after my post. :-)
4) Message boards : Number crunching : Improved App will be released on Halloween (Message 5665)
Posted 31 Oct 2008 by [AF>Le_Pommier] McRoger
Good news ! :-)

Is a Mac OS client version also foreseen and if yes, for x86 only or also PPC ?

Thx !
5) Message boards : Number crunching : Compute errors (Message 5231)
Posted 16 Sep 2008 by [AF>Le_Pommier] McRoger
No problem here on my Mac Pro rev1.
http://milkyway.cs.rpi.edu/milkyway/show_host_detail.php?hostid=11397

Using Boinc 5.10.45 and v1.22 apps (optimized by Crunch3r early this year and advertized in the forum).

I had problems with several projects with Boinc 6.x.y (asking for 64 bits apps while the project could not deliver these), so I reverted to 5.10.45.

McRoger


Edit: what happened to the sticky with these apps ?
6) Message boards : Number crunching : I've had enough !!! (Message 4796)
Posted 18 Aug 2008 by [AF>Le_Pommier] McRoger
@Poorboy

Optimizing an open source code is not cheating.

And certainly not more than trying to get the most of your hardware by fine-tuning or overclocking it.

These are simply normal ways to progress: optimize the use of existing resources and if possible find a new way to achieve the same result with less resources (or better results with same resources)..

Crunch3r optimized the Mac Intel apps several months ago, after some weeks/months of testing, these were publicly released. That is a fact.

All the rest is philosophy (and I may be misleading but this might not be the place therefore) or trial of intentions.

Keep cool and keep on crunching. ;-)

Regards

McRoger
7) Message boards : Number crunching : No new WU (Message 3831)
Posted 18 Jun 2008 by [AF>Le_Pommier] McRoger
Receiving sporadic work as well, guess we're just crunching too fast! :O



If I recall, the AF Spring assault led to a higher total RAC than presently.

The bottleneck was hard disk space.

We did not encounter the current issues. :(

Rank Team / Production /Daily average
1 L'Alliance Francophone/ 10 732 691 / 671 667
2 BOINC@AUSTRALIA / 3 174 823 / 198 684
3 SETI.USA / 1 475 878 / 92 362


Edit: add stats
8) Message boards : Number crunching : No new WU (Message 3791)
Posted 15 Jun 2008 by [AF>Le_Pommier] McRoger
Results ready to send: 509

Shan't we run short again soon ? :(


the assimilator generates WUs to send dynamically, so they're as up to date as possible. when the number of WUs in the queue drops below 200 (i think) it will generate more.


Dim 15 jui 16:55:14 2008|Milkyway@home|Sending scheduler request: To fetch work. Requesting 689985 seconds of work, reporting 16 completed tasks
Dim 15 jui 16:55:29 2008|Milkyway@home|Scheduler request succeeded: got 0 new tasks

Switching to my spare project, nothing to crunch...

Edit: add comment
9) Message boards : Number crunching : No new WU (Message 3777)
Posted 14 Jun 2008 by [AF>Le_Pommier] McRoger
Results ready to send: 509

Shan't we run short again soon ? :(
10) Message boards : Number crunching : No new WU (Message 3708)
Posted 9 Jun 2008 by [AF>Le_Pommier] McRoger
Could simply be that it is the exams period....
11) Message boards : Number crunching : No new WU (Message 3685)
Posted 8 Jun 2008 by [AF>Le_Pommier] McRoger
Well, it's the weekend..

[Half-remembered lyrics]
"Monday's black,
and Tuesday's blue;
Wednesday's grey,
and Thursday, too;
it's Friday- I'm in love...
[/half-remembered lyrics]
(The Cure?)


This song is "Friday I'm in love", from The Cure, indeed. ;-)
12) Message boards : Number crunching : Os-X Time comparisons PPC vs. Intel (Message 3436)
Posted 1 May 2008 by [AF>Le_Pommier] McRoger


The optimized app are not endorsed by the University. However, this project is open source so we will not restrict people from doing this. Also, the administration says we can't "notify" people, but if Cruncher wants to make a thread to list optimized apps, I will be happy to make it a sticky.[quote]

I see. I brought up the question of certain optimizations being more advantageous to some platforms more than others because it's known that there can be differences in the efficiency of optimizations across platforms. Though, I'm thinking more of the type of compiler used rather than a 32-bit vs 64-bit system difference. And I was wondering how the Core 2/Core Duo Intel-based Mac optimizations compare to any Core 2/Core Duo Windows-based ones.

On the issue of notifications. If people can't be notified that there are optimized apps via email, than I suppose a sticky "optimizations" thread would be the next best thing.


On the other side, here we should rather speak of "catching up" than of an optimization that gives an edge over other platforms, since the Mac OS X platform was clearly behind and far behind (as mentionned in the beginning of the present thread and in other threads on this very same forum).

I presume it will not be very long before such optimizations are evaluated and incorporated in the next offcial version; which will be then broadcasted automatically via Boinc.

Beta tester who will use these optimized apps in the meantime and know/dare to type some command lines (what a thrill :-) ) , are not the majority of MW volunteers, far from that.

Thus I'm affraid this discussion, although being conceptually right, is practically speaking of a "non-problem". My 2 cents...
13) Message boards : Number crunching : Os-X Time comparisons PPC vs. Intel (Message 3404)
Posted 28 Apr 2008 by [AF>Le_Pommier] McRoger
OK... so here we go...

OSX optimized applcations

Have fun :)






Wowow, x Mas time !

Mac Pro Quad 2.66 (thus Rev 1): 350 vs 688

That is simply great, and only in a couple of days, thanks a lot Crunch3r !!!

:-)))
14) Message boards : Number crunching : Os-X Time comparisons PPC vs. Intel (Message 3391)
Posted 27 Apr 2008 by [AF>Le_Pommier] McRoger


Can you give more information about how to achieve these results ?

Yes, we can develop the compiling technology so that the project can make better executables to be delivered to the participants.

The person (zombie67) who's computer that was referred to as proof that there was something somehow wrong with OS-X and / or my computer is running an optimized compile. Thusly, they are obtaining faster run times.



Obvious there was something with an optimized app/compilation there for OS X. :-)

My question to Crunch3r was aimed at getting more than clues about this beta app.

Since we cannot get to know more, let's just wait for it to be released.
15) Message boards : Number crunching : Os-X Time comparisons PPC vs. Intel (Message 3379)
Posted 26 Apr 2008 by [AF>Le_Pommier] McRoger
[quote]Unfortunately, I'm only able to notice the fact, not to propose any practical solution.

Well, I did some research and am also trying to see if I can get some advice from other sources ...


the practical solution is already there... and seems to be working well


On the other side, while this users Mac Pro is performing well under Leopard, his iMac is not doing that well under Tiger:

http://milkyway.cs.rpi.edu/milkyway/show_host_detail.php?hostid=1160

My Mini was going more than twice as fast (2.00 Ghz, T7200) under Ubuntu than his iMac 2.33Ghz (T7600) under Tiger.

Thus, strange, is he using a beta/own decompiled/recompiled version on the Mac Pro (this is how optimized clients appeared first on SETI) ?

Edit: add my Mini info + question
16) Message boards : Number crunching : Os-X Time comparisons PPC vs. Intel (Message 3378)
Posted 26 Apr 2008 by [AF>Le_Pommier] McRoger
Unfortunately, I'm only able to notice the fact, not to propose any practical solution.

Well, I did some research and am also trying to see if I can get some advice from other sources ...


the practical solution is already there... and seems to be working well



I see nice computing time indeed, that is a result.

My Mac Pro Quad 2.66Ghz takes 11:29 / WU under Leopard. It should take around 4-5 minutes (as under Ubuntu). It has 4 Gigs of ram, thus memory should not be an issue.

Can you give more information about how to achieve these results ?

Thanks!
17) Message boards : Number crunching : Os-X Time comparisons PPC vs. Intel (Message 3346)
Posted 24 Apr 2008 by [AF>Le_Pommier] McRoger
Fully agree with you Paul.

Besides, we have been several members of the Alliance Francophone who noticed this during our race.

The "geekiest" of us have crunched under Ubuntu 64, more than doubling the crunching speed vs OS 10.5 (provided you do not forget to adapt the cpu throttling if you have a mobile CPU, like iMacs do).

Thus, there "must be something' with the compilation or libraries used, since such problems have not been mentionned with other Boinc project clients.

Unfortunately, I'm only able to notice the fact, not to propose any practical solution.
18) Message boards : Number crunching : Os-X Time comparisons PPC vs. Intel (Message 3254)
Posted 20 Apr 2008 by [AF>Le_Pommier] McRoger

Astro,

unfortunately you are completely right: My 8-core MacPro 3.0 GHz takes more than twice as much time (535 sec/WU) for a work-unit than the 2.4 GHz Linux machines (190-210 sec./WU) and almost exactly the same time as my 3-year-old G5 Dual 2.7 GHz machine. Any chance we will see optimized Mac-apps soon?


More info in this thread.

http://milkyway.cs.rpi.edu/milkyway/forum_thread.php?id=279

FYI, my Mac Pro 2.66 Quad takes 4:33 / WU under Ubuntu 64 vs 11:29 in OS 10.5.

Clear that when the AF race is over (today 20:00 CEST), MW will get a low priority in my settings when I return to Leopard (as long as the optimization has not occurred).
I'm currently crunching with Ubuntu Livecd's.
19) Message boards : Number crunching : New OSX App (Message 3052)
Posted 6 Apr 2008 by [AF>Le_Pommier] McRoger
Hi fellow crunchers of Macgé,

You will probably see that under Windows or Linux your Mac crunches 30% faster.

That's what I'm noticing when I compare my Dell Latitude with my Mac Mini (very same CPU).

http://forum.macbidouille.com/index.php?s=8987193da7a5a89a366e61a99d549206&showtopic=248789&st=270

Read you on MacG one of these times....

;-)
20) Message boards : Number crunching : Macintel and OS X performance issue (Message 3011)
Posted 4 Apr 2008 by [AF>Le_Pommier] McRoger

well, it's also sort of personal. both my machines are macs :D dave uses one as well. we just need to dig a bit farther into xcode and get it to use the same optimization flags we used on the other versions.


Okido, in the meantime, I put all my machines (PC and Macs) 99% on MW for the Alliance Francophone Raid.

Thanks !



Next 20

Main page · Your account · Message boards


Copyright © 2017 AstroInformatics Group