New Improved Gravational Wave App - Discussion

Tom M
Tom M
Joined: 2 Feb 06
Posts: 6432
Credit: 9561019238
RAC: 10204944

Ian& SteveC, Right now I

Ian& SteveC,

Right now I am running at 20 percent or less CPU load which give 3.1+ MHz on the active tasks. I hope to get up to a higher CPU load later.

Running WCG since Rosetta has been down.

A Proud member of the O.F.A.  (Old Farts Association).  Be well, do good work, and keep in touch.® (Garrison Keillor)  I want some more patience. RIGHT NOW!

Tom M
Tom M
Joined: 2 Feb 06
Posts: 6432
Credit: 9561019238
RAC: 10204944

It is clear that running on

It is clear that running on "real" cores when you are running the 1.07/1.08/1.15 versions the tasks run more quickly.

I am running a 4 Titan V box with no other tasks.  It has an Epyc 7282 (16c/32t) cpu right now.

When I run it on Nvidia MPS server with 4x per GPU the time each task takes approximates the top performing Titan V boxes of the Top 50.

They are running 5x not 4x.  When I run 5x my tasks split between under 2000s and over 2000s both of which are slower than the top performer task times.

So it looks like I need more "real" cpu cores.  The choices in ascending sequence of cost are 7402 (24c/48t), 7f72 (24c/48t, 3.6MHz) and a 7742-class cpu (64c/128t).

Anyone of these choices will raise production.  In theory and probably practice the 7f72 will raise production the most.  But provide the least increase available to run any cpu-only tasks.

Comments?

 

A Proud member of the O.F.A.  (Old Farts Association).  Be well, do good work, and keep in touch.® (Garrison Keillor)  I want some more patience. RIGHT NOW!

pututu
pututu
Joined: 6 Apr 17
Posts: 63
Credit: 653417392
RAC: 10

Tom M wrote: It is clear

Tom M wrote:

It is clear that running on "real" cores when you are running the 1.07/1.08/1.15 versions the tasks run more quickly.

I am running a 4 Titan V box with no other tasks.  It has an Epyc 7282 (16c/32t) cpu right now.

When I run it on Nvidia MPS server with 4x per GPU the time each task takes approximates the top performing Titan V boxes of the Top 50.

They are running 5x not 4x.  When I run 5x my tasks split between under 2000s and over 2000s both of which are slower than the top performer task times.

So it looks like I need more "real" cpu cores.  The choices in ascending sequence of cost are 7402 (24c/48t), 7f72 (24c/48t, 3.6MHz) and a 7742-class cpu (64c/128t).

Anyone of these choices will raise production.  In theory and probably practice the 7f72 will raise production the most.  But provide the least increase available to run any cpu-only tasks.

Comments?

 

When I ran my VII, I disabled HT on my 7950x. Could have set 50% cpu utilization but that's just me. I suspect the cpu portion of the statistical recalculation in O3AS uses heavy floating point arithmetic, so each real core is fully occupied that enabling hyperthreading or running cpu at 100% (HT on) doesn't really help. Project like CPDN (climateprediction.net) and PrimeGrid PG LLR cpu subprojects use heavy floating point arithmetic. There are a few feedback posted in einstein forum earlier on about cpu portion of the O3AS taking so long than expected, even if the hosts have fast cpu. I suspect they could run other boinc projects which need heavy floating point arithmetic.

Comment viewing options

Select your preferred way to display the comments and click "Save settings" to activate your changes.