Welcome to MilkyWay@home

Posts by Dunx

1) Message boards : Number crunching : New Benchmark Thread - times wanted for any hardware, CPU or GPU, old or new! (Message 71038)
Posted 29 Jul 2021 by Dunx
Post:
Radeon VII 8x WU average 11 seconds each, sadly sits idle waiting for Wu's for too long....
R9 280x - HD 7970 average 42 seconds.

D.C.
2) Message boards : News : New Poll Regarding GPU Application of N-Body (Message 71037)
Posted 29 Jul 2021 by Dunx
Post:
Please run this code on a Radeon VII....

But mine sits idle waiting for WU's anyway, so why bother ?

Seriously, if it will keep my PC running 100% of the time then YES do it !

D.C.
3) Message boards : Number crunching : No credit! (Message 70792)
Posted 17 May 2021 by Dunx
Post:
Is credit the be-all and end-all ?

The situation would be far worse if the "science" were "lost".

IMHO

dunx

P.S. I can't remember how many tasks I had completed....
4) Message boards : News : Where MilkyWay@home Was The Last Few Days (Message 70791)
Posted 17 May 2021 by Dunx
Post:
Welcome Back !

My poor PC isn't keeping me warm without it's GPU wattage !

Glad you are on top of the situation, it's always worse when the academic side of operations is down.

Back in the 90's we had it easy ! Nobody was really "hacking" the mini-computers the college here had.

Looking forward to some more Work Units soon !

Regards,

D.C. ( Wakefield, U.K. )
5) Message boards : Number crunching : Ideal number of concurrent tasks. (Message 70781)
Posted 7 May 2021 by Dunx
Post:
Thanks, for the info guys....

I was of the opinion that multiple clients wouldn't be allowed.

The project sends 900 tasks which process in about 10 seconds each, then it sits for 15 minutes to pass, before sending more.

At my desk I can poke it into action quite easily, but all day whilst at work it's on autopilot.

Must investigate further !

Regards,

Dunx
6) Message boards : Number crunching : Ideal number of concurrent tasks. (Message 70698)
Posted 26 Mar 2021 by Dunx
Post:
I'm running 8x on my Radeon VII but the real problem....

is the "Project" is not willing to keep it fed with work 24/7 !

I should sell it to some Bitcoin nut-job and scalp the hell out of them....

Grumpy old man,

dunx
7) Message boards : Number crunching : Run Multiple WU's on Your GPU (Message 70341)
Posted 12 Jan 2021 by Dunx
Post:
You need to build a tired old PC and add a few HD 7970 or R9 280X cards to it....

Just because Nvidia sell you a high priced item doesn't make it suitable for efficient use on this project.

I bought a used Gen 1 GTX Titan Black for the high DP and extra RAM, but it is still 3x slower than a cheap R9 280X.

I currently run a Radeon VII and spews out a result every 11 seconds, running multiple tasks on a quad core CPU.

I would say Nvidia cards would be better used for GPUGrid, but they have no work available....

dunx
8) Message boards : Number crunching : Multiple GPU Problem (Message 69988)
Posted 12 Jul 2020 by Dunx
Post:
I run six WU at once for an average time to completion of 10 seconds per WU.... eight is as fast, but my PC can't keep up with the multiple GPUs.

The machine is limited to only four cores/eight threads, and the GTX 970 needs some CPU time too !

I now have an X79 system with a six core/12 thread CPU to play with, but it doesn't like my memory, so having to manually step through all the DRAM variables.

dunx
9) Message boards : News : Testing Some New Plan Classes (Message 67236)
Posted 10 Mar 2018 by Dunx
Post:
https://milkyway.cs.rpi.edu/milkyway/results.php?hostid=767829

Like this ?

dunx
10) Message boards : Number crunching : Thousands of validation errors, no good work? (Message 66241)
Posted 23 Mar 2017 by Dunx
Post:
If it has failed on four attempts,

On four different systems,

then it's.... garbage in = garbage out !

IMHO

dunx

P.S. It is NOT just your system.
11) Message boards : Number crunching : New Benchmark Thread - times wanted for any hardware, CPU or GPU, old or new! (Message 66182)
Posted 12 Feb 2017 by Dunx
Post:
Windows 7 Ultimate 64 bit - BOINC 7.6.33 - GPU Driver 14.1
Xeon E3 1270 V3 @ 3.7 GHz HT on
MW 1 task only - GPU @ 1065MHz - Memory @ 1555MHz 40 seconds - NO CPU tasks !
Same with CPU tasks limited to 88% - 43 seconds

dunx

P.S. Tried two tasks per GPU, and it messed up all four GPUs.... liking the sensible VRM temps though !
12) Message boards : Number crunching : New Benchmark Thread - times wanted for any hardware, CPU or GPU, old or new! (Message 63814)
Posted 18 Jul 2015 by Dunx
Post:
Theoretical yes. But windows throws around the Threads at random. I don't know any option or program that can reserve one Module.

The 323 second times apply when i only run Milkyway@home, no CPU tasks from Boinc. But i should keep the times, when i could reserve one Module exclusively.


I use process lasso on my Intel i7 - W7 system, don't know if it can help you here ?

dunx
13) Message boards : Number crunching : What is the cause of these 'validate errors' (Message 63235)
Posted 15 Mar 2015 by Dunx
Post:
Well, TBH having nearly reached 10^8 I'm ready to move to another project for credits....

dunx
14) Message boards : Number crunching : What is the cause of these 'validate errors' (Message 63232)
Posted 15 Mar 2015 by Dunx
Post:
I have two R9 280X cards and my error rate is similar to yours Tex....

I'm running two WU's per card and Cosmology on the free CPU cores.

dunx

P.S. Much as I dislike the waste of resources, it's a %age I'm able to tolerate....

P.P.S. NOT using X-Fire as ( like you I'm not a gamer ! ) - wonder if actually using X-Fire with two cards might work better overall ? ? ?
15) Message boards : News : New Modfit Runs (Message 63115)
Posted 7 Feb 2015 by Dunx
Post:
Hmmmmm. Magically I now have tens of minutes of WU to crunch (vs 1-2 minutes). Perhaps the Weiss IS listening in?


Try :-

<max_file_xfers>N</max_file_xfers> Maximum number of simultaneous file transfers (default 8).
<max_file_xfers_per_project>N</max_file_xfers_per_project> Maximum number of simultaneous file transfers per project (default 2).

dunx

P.S. Not sure I've found the right options TBH....
16) Message boards : Number crunching : Lowering required cpus (Message 62949)
Posted 4 Jan 2015 by Dunx
Post:
I get better results using 0.5 cpus per 0.5 gpus.... 32 per WU two at a time HD 5870

dunx

P.S. @ 88% CPU utillisation - too leave a spare "core" for the GPUs....
17) Message boards : News : New Modfit Runs (Message 62947)
Posted 4 Jan 2015 by Dunx
Post:
I found I needed 0.5 cpus per 0.5 GPUs to maintain a decent workload.
Dropped CPU to 88% in BOINC manager. At 100% each WU took 50% longer to process.

HTH

dunx
18) Message boards : Number crunching : Tesla K40 & System Upgrade Thoughts? (Message 61447)
Posted 29 Mar 2014 by Dunx
Post:
I would suggest that managing a system with two or more cards is made easier by mixing ATI/AMD with Nvidia GPU's, you can mix and run many projects, but a pair of cards can be set up as an SLI/X-fire pair. Each brand have their strengths on different projects, but I find managing them is easier. IMHO

( P6T7 WS + HD7900 + HD5800 + GTX 480 currently adding water cooling bit-by-bit...)

dunx

P.S. If that is an i7 4770 it has an i-GPU which can be used with the Intel OpenCL SDK - I'm running E@H on mine...
19) Message boards : Number crunching : Benchmark results - times wanted for any hardware, CPU or GPU, old or new! (Message 61313)
Posted 3 Mar 2014 by Dunx
Post:
So you found my secret stash of 1000 R9 280X's cards, running in a cupboard....

( HTH - Hope this helps... )

dunx

P.S. Anyone else had problems with x-fire and drivers on system with two R9 280x / HD79xx cards ?
20) Message boards : Number crunching : Benchmark results - times wanted for any hardware, CPU or GPU, old or new! (Message 61287)
Posted 1 Mar 2014 by Dunx
Post:
76.6 seconds..... 1030 GHz R9 280X - HD 7970.

HTH

dunx


Next 20

©2024 Astroinformatics Group