User achievements thread.........

Message boards : Number crunching : User achievements thread.........
Message board moderation

To post messages, you must log in.

Previous · 1 . . . 18 · 19 · 20 · 21 · 22 · 23 · 24 · Next

AuthorMessage
Profile petri33
Volunteer tester

Send message
Joined: 6 Jun 02
Posts: 1668
Credit: 623,086,772
RAC: 156
Finland
Message 1988053 - Posted: 30 Mar 2019, 22:14:58 UTC - in response to Message 1988047.  

Thanks!

I'm sure it (new code) could help ATI/AMD and NV on Windoze too.

Preliminary reports from TBar say that tasks validate even better than V0.97 when compared to the 'official' CPU version. My inconclusive count was dropping from near 300 to nearer 250 when I looked at it last time.

The CPU does minimal work and during the various stages CPU runs parallel to GPU. The CPU does mainly wait for the GPU to finish a kernel and fetch flags to see if any results should be fetched. The default is to run with CPU friendly options. To make more use of a spare CPU core one can specify -nobs option. (nobs = no blocking sync. I.e. active waiting in a busy loop.)

... but what if the CPU version of Seti MB could benefit from the new algorithm? No "read"-"write"-"read again" to the RAM.

Petri

Ffs!! You rock!

Now if anyone could port it to Wintendo too, but for my part it doesn't matter nowadays.
Hats off to the achievement!

As we all know, make sure that it validates thoroughly towards old 0.97 version, and the main cpu executable (s@h original).
Valid work is crucial at this rate it completes work.

Btw, is it possible to "look" at the cpu portion of the code to see if other optimisations can be done there. In my case i use old cpus to feed new gpus. So less "cpu" is wanted if possible :) Lol.

To overcome Heisenbergs:
"You can't always get what you want / but if you try sometimes you just might find / you get what you need." -- Rolling Stones
ID: 1988053 · Report as offensive
Profile bloodrain
Volunteer tester
Avatar

Send message
Joined: 8 Dec 08
Posts: 231
Credit: 28,112,547
RAC: 1
Antarctica
Message 1988058 - Posted: 30 Mar 2019, 22:28:07 UTC

well i finale going to have a small gpu farm. just got 4 rx 580s
for 230.
ID: 1988058 · Report as offensive
Profile Keith Myers Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 29 Apr 01
Posts: 13161
Credit: 1,160,866,277
RAC: 1,873
United States
Message 1988095 - Posted: 31 Mar 2019, 4:06:55 UTC - in response to Message 1988053.  
Last modified: 31 Mar 2019, 4:26:56 UTC

Great news! Petri. Thanks for continuing to squeeze every last ounce of performance out of our Nvidia cards. If you want, you can release it to a few GPUUG members. I am ready and willing to employ Rick's great benchMT tool https://github.com/Ricks-Lab/benchMT/releases/tag/v1.4.0 to verify similarity against the stock cpu app on AMD hosts.
Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)
ID: 1988095 · Report as offensive
Profile Keith Myers Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 29 Apr 01
Posts: 13161
Credit: 1,160,866,277
RAC: 1,873
United States
Message 1988101 - Posted: 31 Mar 2019, 6:45:44 UTC - in response to Message 1988099.  

Raistmer has been very quiet with his Linux special app experiment. Hope he is gleaning some insights into bringing the special app over to the Windows x86 platform.
Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)
ID: 1988101 · Report as offensive
Stephen "Heretic" Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 20 Sep 12
Posts: 5557
Credit: 192,787,363
RAC: 628
Australia
Message 1988107 - Posted: 31 Mar 2019, 7:06:41 UTC - in response to Message 1828718.  

We appreciate your dedication kittyman. Just passed a personal milestone myself.

100 million SETI credits and 200 million overall BOINC credits.


. . Hey there keith,

. . Here it is 2.5 years later and I have cracked the 100 million too :)

Cheers

:)
ID: 1988107 · Report as offensive
Stephen "Heretic" Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 20 Sep 12
Posts: 5557
Credit: 192,787,363
RAC: 628
Australia
Message 1988108 - Posted: 31 Mar 2019, 7:08:57 UTC - in response to Message 1988101.  

Raistmer has been very quiet with his Linux special app experiment. Hope he is gleaning some insights into bringing the special app over to the Windows x86 platform.


. . My thoughts as well, but I had not dared voice them.

Stephen

:)
ID: 1988108 · Report as offensive
Stephen "Heretic" Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 20 Sep 12
Posts: 5557
Credit: 192,787,363
RAC: 628
Australia
Message 1988109 - Posted: 31 Mar 2019, 7:19:00 UTC - in response to Message 1988046.  

Hi,
I'd like to report a small achievement.
I managed to make a complete rewrite of the pulse find scan part of the code. It does not need to save and re-read any intermediate values during the pulse search stage. (Saves millions of read and write cycles.)
All (Gbt and Arecibo) Vlar work is completed now in 75% of the time it took on V0.97. Shorties are not affected since they do not do almost any pulse finding. Mid ar (0.4*) benefits from the new search. An average of 13% more performance is a realistic guesstimate.
TBar is testing the code and an executable will be released when the tests say it is ready for the main stream.
Petri


. . OK. I have to agree with Vyper, you Rock Dude! Way to go, just when we think there is nothing more to gain :) Now, if you can manage a version that uses Tensor cores the servers will go on strike :)

Stephen

:)
ID: 1988109 · Report as offensive
kittyman Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 9 Jul 00
Posts: 51468
Credit: 1,018,363,574
RAC: 1,004
United States
Message 1988132 - Posted: 31 Mar 2019, 13:42:12 UTC

Another vote for a Windows version from the kitties.
That would be a real big meow!

Meow.
"Freedom is just Chaos, with better lighting." Alan Dean Foster

ID: 1988132 · Report as offensive
Profile Jimbocous Project Donor
Volunteer tester
Avatar

Send message
Joined: 1 Apr 13
Posts: 1849
Credit: 268,616,081
RAC: 1,349
United States
Message 1988149 - Posted: 31 Mar 2019, 15:32:22 UTC

+1 !!
ID: 1988149 · Report as offensive
Profile Keith Myers Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 29 Apr 01
Posts: 13161
Credit: 1,160,866,277
RAC: 1,873
United States
Message 1988519 - Posted: 3 Apr 2019, 2:01:07 UTC

Today I broke through 600 million credits crunching for Seti@home.
Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)
ID: 1988519 · Report as offensive
Profile betreger Project Donor
Avatar

Send message
Joined: 29 Jun 99
Posts: 11360
Credit: 29,581,041
RAC: 66
United States
Message 1988520 - Posted: 3 Apr 2019, 2:09:34 UTC - in response to Message 1988519.  

Keith you are the man!
Congratz
ID: 1988520 · Report as offensive
Profile Mike Special Project $75 donor
Volunteer tester
Avatar

Send message
Joined: 17 Feb 01
Posts: 34253
Credit: 79,922,639
RAC: 80
Germany
Message 1988563 - Posted: 3 Apr 2019, 7:27:22 UTC

Congratz Keith.


With each crime and every kindness we birth our future.
ID: 1988563 · Report as offensive
Ian&Steve C.
Avatar

Send message
Joined: 28 Sep 99
Posts: 4267
Credit: 1,282,604,591
RAC: 6,640
United States
Message 1988573 - Posted: 3 Apr 2019, 11:28:40 UTC - in response to Message 1988519.  

Congrats!
Seti@Home classic workunits: 29,492 CPU time: 134,419 hours

ID: 1988573 · Report as offensive
Profile Kissagogo27 Special Project $75 donor
Avatar

Send message
Joined: 6 Nov 99
Posts: 715
Credit: 8,032,827
RAC: 62
France
Message 1988581 - Posted: 3 Apr 2019, 12:59:59 UTC

some explanations about tensor core in French indeed :D ( search for 4.3.7 chapter ) http://www.info.univ-angers.fr/pub/richer/cuda_crs4.php
ID: 1988581 · Report as offensive
Profile bloodrain
Volunteer tester
Avatar

Send message
Joined: 8 Dec 08
Posts: 231
Credit: 28,112,547
RAC: 1
Antarctica
Message 1988609 - Posted: 3 Apr 2019, 18:02:21 UTC

anyhow i beat my old 35 rac that i set a week ago i think. then beat a old remember of a team race number finale after years of tracing be hide him.
about to hit 37 k . then when i get the 4 cards in. am looking to get a average 50k


also congrats to.
ID: 1988609 · Report as offensive
Stephen "Heretic" Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 20 Sep 12
Posts: 5557
Credit: 192,787,363
RAC: 628
Australia
Message 1988632 - Posted: 3 Apr 2019, 21:53:02 UTC - in response to Message 1988581.  

some explanations about tensor core in French indeed :D ( search for 4.3.7 chapter ) http://www.info.univ-angers.fr/pub/richer/cuda_crs4.php


. . tant pis, je ne parle pas bien Francais. :(

Etienne

:(
ID: 1988632 · Report as offensive
Profile Tom M
Volunteer tester

Send message
Joined: 28 Nov 02
Posts: 5124
Credit: 276,046,078
RAC: 462
Message 1988671 - Posted: 4 Apr 2019, 4:36:15 UTC

Sigh, I have "only" 77,070,191 for my Seti total. But things are looking up. Maybe I will hit 78 million soon :)

I think the real achievement is how long so many of us have been crunching for Seti.

Tom
A proud member of the OFA (Old Farts Association).
ID: 1988671 · Report as offensive
Profile Jimbocous Project Donor
Volunteer tester
Avatar

Send message
Joined: 1 Apr 13
Posts: 1849
Credit: 268,616,081
RAC: 1,349
United States
Message 1988676 - Posted: 4 Apr 2019, 5:28:25 UTC - in response to Message 1988671.  

Sigh, I have "only" 77,070,191 for my Seti total. But things are looking up. Maybe I will hit 78 million soon :)
Like tomorrow? :)
ID: 1988676 · Report as offensive
Profile Kissagogo27 Special Project $75 donor
Avatar

Send message
Joined: 6 Nov 99
Posts: 715
Credit: 8,032,827
RAC: 62
France
Message 1988696 - Posted: 4 Apr 2019, 10:54:46 UTC - in response to Message 1988632.  

some explanations about tensor core in French indeed :D ( search for 4.3.7 chapter ) http://www.info.univ-angers.fr/pub/richer/cuda_crs4.php


. . tant pis, je ne parle pas bien Francais. :(

Etienne

:(


maybe this https://translate.google.fr/ could help ? ;o)
ID: 1988696 · Report as offensive
Stephen "Heretic" Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 20 Sep 12
Posts: 5557
Credit: 192,787,363
RAC: 628
Australia
Message 1988699 - Posted: 4 Apr 2019, 12:00:28 UTC - in response to Message 1988696.  

some explanations about tensor core in French indeed :D ( search for 4.3.7 chapter ) http://www.info.univ-angers.fr/pub/richer/cuda_crs4.php


. . tant pis, je ne parle pas bien Francais. :(

Etienne

:(


maybe this https://translate.google.fr/ could help ? ;o)


. . Merci bien! I have tried some online translators before (including, I thought, Google) but generally they produce unintelligible rubbish. That worked really well and produced clear coherent English. The article certainly makes that much more sense now :) I could understand the gist of it before (especially the parts with numbers :} ) but now it all makes excellent sense :)

Stephen

:)
ID: 1988699 · Report as offensive
Previous · 1 . . . 18 · 19 · 20 · 21 · 22 · 23 · 24 · Next

Message boards : Number crunching : User achievements thread.........


 
©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.