Mac Seti Enhanced Optimized

Message boards : Number crunching : Mac Seti Enhanced Optimized
Message board moderation

To post messages, you must log in.

1 · 2 · 3 · Next

AuthorMessage
Profile boog
Avatar

Send message
Joined: 28 Apr 03
Posts: 57
Credit: 1,153,933
RAC: 0
United States
Message 317103 - Posted: 26 May 2006, 1:14:32 UTC

I stated in amother thread that I was trying to build a faster Mac Enhanced client.

it has even been the canonical result a couple times, and looks to be about 9% faster than the stock client on both g4's and g5's.

The G4 version is here: http://boog.is-a-geek.org/seti/seti_enhanced_g4_b7.tgz

The G5 version: http://boog.is-a-geek.org/seti/seti_enhanced_g5_b7.tgz

I also built a boinc version 5.5.0 universal binary (but it's not needed to run the seti clients). There is also a universal binary screensaver that works too http://boog.is-a-geek.org/boinc/boinc550_screensaver.tgz.

I think I have all the files with it that are supposed to be there (gpl stuff), I borrowed (swiped) them from one of crunch3r's downloads, Thanks crunch3r!!!

Hopefully later someone with more knowledge than myself will be able to build a faster one.
ID: 317103 · Report as offensive
Penguirl
Volunteer tester
Avatar

Send message
Joined: 11 Jul 03
Posts: 61
Credit: 806,978
RAC: 0
United States
Message 317376 - Posted: 26 May 2006, 7:59:28 UTC
Last modified: 26 May 2006, 8:10:22 UTC

Thanks boog, it's great that you have worked on optimizing the Mac version! I'm trying it out now, I'll let you know how it runs.

BTW, where is the other thread?
ID: 317376 · Report as offensive
Profile boog
Avatar

Send message
Joined: 28 Apr 03
Posts: 57
Credit: 1,153,933
RAC: 0
United States
Message 317416 - Posted: 26 May 2006, 10:13:29 UTC - in response to Message 317376.  

Thanks boog, it's great that you have worked on optimizing the Mac version! I'm trying it out now, I'll let you know how it runs.

BTW, where is the other thread?



You replied to it! lol http://setiathome.berkeley.edu/forum_thread.php?id=30811

I hope it runs as well on all hardware as it did on mine.

I also wish that I could get the performance increase that crunch3r got out of his!
ID: 317416 · Report as offensive
Profile Crunch3r
Volunteer tester
Avatar

Send message
Joined: 15 Apr 99
Posts: 1546
Credit: 3,438,823
RAC: 0
Germany
Message 317840 - Posted: 26 May 2006, 18:15:16 UTC - in response to Message 317416.  

...
I also wish that I could get the performance increase that crunch3r got out of his!


If you can get your hand on the intel compiler and the ipp libraries for OSX on intel macs... That'll surely boost the performance on intel macs.

Regarding the G4/G5 macs... well i know that alex kan is looking at it but i wouldn't expect much speed improvements.

P.S.

Did you compile fftw with fma enabled ? at least g5 are capable of fma and it should give a little performance increase.











Join BOINC United now!
ID: 317840 · Report as offensive
Profile boog
Avatar

Send message
Joined: 28 Apr 03
Posts: 57
Credit: 1,153,933
RAC: 0
United States
Message 317983 - Posted: 26 May 2006, 21:18:21 UTC - in response to Message 317840.  

...
I also wish that I could get the performance increase that crunch3r got out of his!


If you can get your hand on the intel compiler and the ipp libraries for OSX on intel macs... That'll surely boost the performance on intel macs.

Regarding the G4/G5 macs... well i know that alex kan is looking at it but i wouldn't expect much speed improvements.

P.S.

Did you compile fftw with fma enabled ? at least g5 are capable of fma and it should give a little performance increase.



I compiled fftw with altivec and fma enabled for both the g4 and g5, along with other options (took lots of research and trial and error).

And on the intel Macs, I wish I could afford to get one right now, might be a bit before I can get the $$ up to get one of the intel iMacs, or mini for that matter.
ID: 317983 · Report as offensive
Profile Crunch3r
Volunteer tester
Avatar

Send message
Joined: 15 Apr 99
Posts: 1546
Credit: 3,438,823
RAC: 0
Germany
Message 317987 - Posted: 26 May 2006, 21:29:07 UTC - in response to Message 317983.  

...
I also wish that I could get the performance increase that crunch3r got out of his!


If you can get your hand on the intel compiler and the ipp libraries for OSX on intel macs... That'll surely boost the performance on intel macs.

Regarding the G4/G5 macs... well i know that alex kan is looking at it but i wouldn't expect much speed improvements.

P.S.

Did you compile fftw with fma enabled ? at least g5 are capable of fma and it should give a little performance increase.



I compiled fftw with altivec and fma enabled for both the g4 and g5, along with other options (took lots of research and trial and error).

And on the intel Macs, I wish I could afford to get one right now, might be a bit before I can get the $$ up to get one of the intel iMacs, or mini for that matter.


IMHO

selling the G4 and G5 mac as fast as you can is the best you can do atm to get the most money out of them.

PPC apps are dead and won't be able to compete in any further applications.
(remember the change from 68k to ppc ? But this time the transition will go even faster while apple allready developed darin x86 along to the ppc version)

Just think of what will happen if adobe decides to compile photoshop with the intel compiler...

Maybee only a g5 quad is capable of compete with a dual core intel.



Join BOINC United now!
ID: 317987 · Report as offensive
Profile boog
Avatar

Send message
Joined: 28 Apr 03
Posts: 57
Credit: 1,153,933
RAC: 0
United States
Message 318010 - Posted: 26 May 2006, 22:13:31 UTC - in response to Message 317987.  

IMHO

selling the G4 and G5 mac as fast as you can is the best you can do atm to get the most money out of them.

PPC apps are dead and won't be able to compete in any further applications.
(remember the change from 68k to ppc ? But this time the transition will go even faster while apple allready developed darin x86 along to the ppc version)

Just think of what will happen if adobe decides to compile photoshop with the intel compiler...

Maybee only a g5 quad is capable of compete with a dual core intel.




Maybe I could name my computer "Charity" and take donations to get an intel mini and the intel compiler? lol
ID: 318010 · Report as offensive
Profile Crunch3r
Volunteer tester
Avatar

Send message
Joined: 15 Apr 99
Posts: 1546
Credit: 3,438,823
RAC: 0
Germany
Message 318024 - Posted: 26 May 2006, 22:36:37 UTC - in response to Message 318010.  
Last modified: 26 May 2006, 22:51:26 UTC

IMHO

selling the G4 and G5 mac as fast as you can is the best you can do atm to get the most money out of them.

PPC apps are dead and won't be able to compete in any further applications.
(remember the change from 68k to ppc ? But this time the transition will go even faster while apple allready developed darin x86 along to the ppc version)

Just think of what will happen if adobe decides to compile photoshop with the intel compiler...

Maybee only a g5 quad is capable of compete with a dual core intel.




Maybe I could name my computer "Charity" and take donations to get an intel mini and the intel compiler? lol


Well at least you can try to get yourself into intels beta test programm for the compiler and the ipp library on osx... ;)

I'm pretty sure if you mention what you'll like to do with the compiler they'll grant you access.

P.S.

I would have distributed optimized mac biniaries myself but i realy dont have the time to look into it any further.

ATM I'll have to maintain more windows & linux apps on different platforms than i could handle.

Taking one more is not possible atm. Maybe later if the whole thing settled a bit.


EDIT

If you'd like me to add you app to my webpage, just contact me ;)
You can find my mail adress on my page.

/EDIT





Join BOINC United now!
ID: 318024 · Report as offensive
Profile boog
Avatar

Send message
Joined: 28 Apr 03
Posts: 57
Credit: 1,153,933
RAC: 0
United States
Message 319087 - Posted: 28 May 2006, 3:49:29 UTC - in response to Message 317840.  



Regarding the G4/G5 macs... well i know that alex kan is looking at it but i wouldn't expect much speed improvements.



Alex is working on it now! :)

And his 1st release that is very unfinished is about fast as mine without heavy compiler flags!

I'm actually excited to see what his final result will bring!
ID: 319087 · Report as offensive
Profile boog
Avatar

Send message
Joined: 28 Apr 03
Posts: 57
Credit: 1,153,933
RAC: 0
United States
Message 329190 - Posted: 6 Jun 2006, 23:08:58 UTC

After some trials, alex over at Team MacNN has outdone himself!

You can find optimized PPC seti workers over at http://forums.macnn.com/showthread.php?t=295708&page=5

They are at v5 you can find it on that page, and it looks like what he has done will rival the binaries that were compiled with the intel compiler!

I forsee the G5 quads back at the top of the participating computers list soon :)
ID: 329190 · Report as offensive
Chris Bosshard

Send message
Joined: 5 Jun 99
Posts: 86
Credit: 3,474,583
RAC: 0
Switzerland
Message 331152 - Posted: 8 Jun 2006, 16:10:11 UTC
Last modified: 8 Jun 2006, 16:10:57 UTC

Bump!

This Seti Client is great, Alex's 5.13 Seti client is up to 80% faster than the original Berkeley client. And therefore far more productive.

Thanks Alex for making our PPC Mac's competitive again.

Chris Bosshard
Visit my homepage
astroinfo SETI page
ID: 331152 · Report as offensive
Profile KWSN - Chicken of Angnor
Volunteer developer
Volunteer tester
Avatar

Send message
Joined: 9 Jul 99
Posts: 1199
Credit: 6,615,780
RAC: 0
Austria
Message 332351 - Posted: 9 Jun 2006, 17:56:59 UTC

Thanks Alex!

Incredible stuff. For me, gains run somewhere between 50 and 60 percent (this is on a G4 MacMini) - all I can say is "Wow".

Great work on the optimization, I'm not getting any client errors or crashes so far. However, the fan's on way more than with the default client ;D That can only mean it's doing more real computation as opposed to wasting clocks.
Donate to SETI@Home via PayPal!

Optimized SETI@Home apps + Information
ID: 332351 · Report as offensive
Profile KWSN - Chicken of Angnor
Volunteer developer
Volunteer tester
Avatar

Send message
Joined: 9 Jul 99
Posts: 1199
Credit: 6,615,780
RAC: 0
Austria
Message 332514 - Posted: 9 Jun 2006, 21:04:19 UTC
Last modified: 9 Jun 2006, 21:05:52 UTC

Nice performance from my puny 1.42 GHz G4...one of the last results included a 3.73 GHz P4 EE..

3.73 GHz P4 EE Crunch time:
19,928.30 seconds

1.42 GHz MacMini Crunch time:
20.796.55 seconds

I can only imagine what a nice dual G5 can do. Of course, that P4EE can do up to 4 units at once...

PPC is dead - long live PPC! ;D
Donate to SETI@Home via PayPal!

Optimized SETI@Home apps + Information
ID: 332514 · Report as offensive
Profile Gecko
Volunteer tester
Avatar

Send message
Joined: 17 Nov 99
Posts: 454
Credit: 6,946,910
RAC: 47
United States
Message 332760 - Posted: 10 Jun 2006, 2:48:17 UTC
Last modified: 10 Jun 2006, 2:48:47 UTC

FYI.

Alex posted a new G4-specifc compile of his v5 worker at:

http://forums.macnn.com/showthread.php?t=295708

It will make a G4 sizzle!
On a 1.33 G4, v5-G4 tests @ 96%!!! faster than the standard worker against a reference WU.

http://tbp.berkeley.edu/~alexkan/seti/seti_enhanced-ppc-v5-g4.zip

1) Suspend Seti-Enhanced project
2) Close Boinc
3) Navigate to system Library\\Application Support\\BOINC Data\\projects\\setiathome.berkeley.edu
4) Trash (or save in folder elsewhere) stock seti worker & app_info.xml
5) unzip file & drag the seti_enhanced-ppc-v5 worker and new app_info.xml into folder
6) restart BOINC, resume project

You do not have to reduce cache or wait until the WU completes before install. You can install w/ a WU already in process and the new worker will pick-up from the point the old worker stopped.
You can also verify that it recognized and is crunching w/ the new worker by looking at the messages tab of BOINC Mgr. and looking for this: "Found app_info.xml; using anonymous platform"
In the WU result, the stderr out will show the worker version as well as the other customary info.

http://setiathome.berkeley.edu/result.php?resultid=338837248

If you like it, please be sure to drop a line and let Alex know. He's workin' hard to keep our PPCs competitive.
Regards.


ID: 332760 · Report as offensive
Profile KWSN - Chicken of Angnor
Volunteer developer
Volunteer tester
Avatar

Send message
Joined: 9 Jul 99
Posts: 1199
Credit: 6,615,780
RAC: 0
Austria
Message 332766 - Posted: 10 Jun 2006, 3:05:37 UTC
Last modified: 10 Jun 2006, 3:07:09 UTC

Well,

the G5 version already worked wonders, even on my G4. Now if this version can do even more remains to be seen :)
Will post more stats as results finish.

In any case, really good work, thanks again Alex!
Donate to SETI@Home via PayPal!

Optimized SETI@Home apps + Information
ID: 332766 · Report as offensive
Profile Gecko
Volunteer tester
Avatar

Send message
Joined: 17 Nov 99
Posts: 454
Credit: 6,946,910
RAC: 47
United States
Message 332768 - Posted: 10 Jun 2006, 3:13:59 UTC
Last modified: 10 Jun 2006, 3:19:02 UTC

Should be @ 5%-7% faster than the G5 compile on G4.
I've benched each revision against a Ref WU on my G4 going back to the stock worker.
Take a look:

AlexKan v5-G5 compile (Test4 6.6.06)
real 276m12.600s ( =16572.600s)
user 275m38.475s
sys 0m32.771s
wu_cpu_time = ????

AlexKan v5-G4 compile (Test5 6.9.06)
real 258m57.563s (= 15537.563s)
user 258m24.204s
sys 0m31.797s
wu_cpu_time = 15298.139857

& stock worker to compare:

Stock 5.13 Worker (Test1 5.24.06)
real 499m12.054s ( = 29952.054s)
user 498m11.342s
sys 0m57.878s
wu_cpu_time = 29915.352618

ID: 332768 · Report as offensive
Joaquin Montes-Leston
Volunteer tester

Send message
Joined: 1 Feb 02
Posts: 66
Credit: 1,256,229
RAC: 0
United States
Message 332783 - Posted: 10 Jun 2006, 3:55:41 UTC - in response to Message 332760.  
Last modified: 10 Jun 2006, 4:01:19 UTC

FYI.

Alex posted a new G4-specifc compile of his v5 worker at:

http://forums.macnn.com/showthread.php?t=295708

It will make a G4 sizzle!
On a 1.33 G4, v5-G4 tests @ 96%!!! faster than the standard worker against a reference WU.

http://tbp.berkeley.edu/~alexkan/seti/seti_enhanced-ppc-v5-g4.zip

1) Suspend Seti-Enhanced project
2) Close Boinc
3) Navigate to system Library\\Application Support\\BOINC Data\\projects\\setiathome.berkeley.edu
4) Trash (or save in folder elsewhere) stock seti worker & app_info.xml
5) unzip file & drag the seti_enhanced-ppc-v5 worker and new app_info.xml into folder
6) restart BOINC, resume project

You do not have to reduce cache or wait until the WU completes before install. You can install w/ a WU already in process and the new worker will pick-up from the point the old worker stopped.
You can also verify that it recognized and is crunching w/ the new worker by looking at the messages tab of BOINC Mgr. and looking for this: "Found app_info.xml; using anonymous platform"
In the WU result, the stderr out will show the worker version as well as the other customary info.

http://setiathome.berkeley.edu/result.php?resultid=338837248

If you like it, please be sure to drop a line and let Alex know. He's workin' hard to keep our PPCs competitive.
Regards.



I just installed it on my [edit] imac [/edit] PPC G3 350 and it seems to be working fine so far. I'll keep you guys posted as to successful completion and times. Current estimated time for the work unit is 41 hours.

messages when installed follow:


Fri Jun 9 23:51:16 2006||Starting BOINC client version 5.4.9 for powerpc-apple-darwin
Fri Jun 9 23:51:16 2006||libcurl/7.15.3 OpenSSL/0.9.7i zlib/1.2.3
Fri Jun 9 23:51:16 2006||Data directory: /Library/Application Support/BOINC Data
Fri Jun 9 23:51:17 2006|SETI@home|Found app_info.xml; using anonymous platform
Fri Jun 9 23:51:17 2006||Processor: 1 Power Macintosh PowerMac2,1
Fri Jun 9 23:51:17 2006||Memory: 192.00 MB physical, 0 bytes virtual
Fri Jun 9 23:51:17 2006||Disk: 6.38 GB total, 3.43 GB free
Fri Jun 9 23:51:17 2006|SETI@home|URL: http://setiathome.berkeley.edu/; Computer ID: 2440182; location: home; project prefs: home
Fri Jun 9 23:51:17 2006|SETI@home Beta Test|URL: http://setiweb.ssl.berkeley.edu/beta/; Computer ID: 7249; location: home; project prefs: default
Fri Jun 9 23:51:17 2006||General prefs: from SETI@home (last modified 2005-10-16 18:17:04)
Fri Jun 9 23:51:17 2006||General prefs: no separate prefs for home; using your defaults
Fri Jun 9 23:51:17 2006||Listening on port 31416
Fri Jun 9 23:51:17 2006|SETI@home Beta Test|Resuming task 01jn01aa.1212.13761.254826.3.235_1 using setiathome_enhanced version 513
Fri Jun 9 23:51:17 2006|SETI@home|Deferring task 21fe99ab.27562.17218.336072.3.71_1
Fri Jun 9 23:51:23 2006||Rescheduling CPU: result suspended, resumed or aborted by user
Fri Jun 9 23:51:24 2006|SETI@home Beta Test|Pausing task 01jn01aa.1212.13761.254826.3.235_1 (removed from memory)
Fri Jun 9 23:51:24 2006|SETI@home|Restarting task 21fe99ab.27562.17218.336072.3.71_1 using setiathome_enhanced version 513

Please advise if you need any additional info, and thanks for all your work with this!

ID: 332783 · Report as offensive
Alex Kan
Volunteer developer

Send message
Joined: 4 Dec 03
Posts: 127
Credit: 29,269
RAC: 0
United States
Message 332904 - Posted: 10 Jun 2006, 7:56:33 UTC - in response to Message 332783.  

I just installed it on my [edit] imac [/edit] PPC G3 350 and it seems to be working fine so far. I'll keep you guys posted as to successful completion and times. Current estimated time for the work unit is 41 hours.

I haven't released any compiles for G3, so you should revert to the stock client. In fact, I can guarantee that you'll run into problems as soon as you hit the parts of the code that use Altivec, which are all over the place.

Thank you all for your messages of support, although I recognize a bunch of you from the MacNN forums... :)
ID: 332904 · Report as offensive
Joaquin Montes-Leston
Volunteer tester

Send message
Joined: 1 Feb 02
Posts: 66
Credit: 1,256,229
RAC: 0
United States
Message 333123 - Posted: 10 Jun 2006, 16:23:06 UTC - in response to Message 332904.  

I just installed it on my [edit] imac [/edit] PPC G3 350 and it seems to be working fine so far. I'll keep you guys posted as to successful completion and times. Current estimated time for the work unit is 41 hours.

I haven't released any compiles for G3, so you should revert to the stock client. In fact, I can guarantee that you'll run into problems as soon as you hit the parts of the code that use Altivec, which are all over the place.

Thank you all for your messages of support, although I recognize a bunch of you from the MacNN forums... :)


I didn't have any errors, yet, but I followed your advise and removed the optimized client. Upon resuming the work, however, I immediately got an unrecoverable error. Oh, well.

Can you recommend (does one exist?) an optimized client for G3s?

Jack
ID: 333123 · Report as offensive
Profile KWSN - Chicken of Angnor
Volunteer developer
Volunteer tester
Avatar

Send message
Joined: 9 Jul 99
Posts: 1199
Credit: 6,615,780
RAC: 0
Austria
Message 333420 - Posted: 11 Jun 2006, 1:57:58 UTC

So far, it seems that for results with the same credit claim, the G4 compile is really around 8-10% faster than the G5 one (on my G4 MacMini). Great work Alex!

Using your optimized client results in claimed/granted credit being perfectly the same. No computation or client errors with either G5 or G4 client, either (plus, they all validate). Very happy with it so far.
Donate to SETI@Home via PayPal!

Optimized SETI@Home apps + Information
ID: 333420 · Report as offensive
1 · 2 · 3 · Next

Message boards : Number crunching : Mac Seti Enhanced Optimized


 
©2022 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.