View Single Post
Old Feb 8, 2013, 07:58 PM   #264
[Ion]
WCG Team Assistant
 
[Ion]'s Avatar
 
Join Date: Sep 2009
Location: North Carolina, US
Posts: 10,646 (7.94/day)
Thanks: 8,237
Thanked 9,298 Times in 4,254 Posts

System Specs

Quote:
Originally Posted by xvi View Post
So, um, why are we collecting hardware stats?

Crunching on a little dual P3 server at work, HP NetServer LPr.
Code:
Your Fortune:
Your reasoning powers are good, and you are a fairly good planner.

user@mango:~$ lscpu
Architecture:          i686
CPU(s):                2
Thread(s) per core:    1
Core(s) per socket:    1
CPU socket(s):         2
Vendor ID:             GenuineIntel
CPU family:            6
Model:                 8
Stepping:              3
CPU MHz:               798.635

That must be a speed-demon!
Quote:
Originally Posted by AnnCore View Post
I've enlisted my son's PC.

AMD 1090T
ATI 5850
16 GB memory.

Trying:

<max_concurrent>6</max_concurrent>
<gpu_versions>
<gpu_usage>0.5</gpu_usage>
<cpu_usage>.175</cpu_usage>

But I am open to suggestions.
I would argue that dedicating one sixth of a core to each GPU WU doesn't make very much sense. I'd say run two GPU WUs each with one CPU core and then leave the other four cores for CPU tasks.
__________________
Crunching (64 Threads + 896 CUDA Cores + 6272 Shaders): i3-2100@ 3.1 + HD7850 -- Atom D510 @ 1.66 -- C2D-M T9600 @ 2.8 -- i7-3612QM @ 2.8 -- i7-860 @ 2.9 + HD7950 -- i7-2700k @ 4.4 + 2xGTX470 -- PentDC-M T4200 @ 2.0 -- i7-920 @ 3.83 + 3xHD7770 -- DP Xeon E5420 @ 2.5 + HD7930 -- E1600 @ 2.4
[Ion] is offline  
Crunching for Team TPU More than 25k PPD
Reply With Quote
The Following 2 Users Say Thank You to [Ion] For This Useful Post: