GPU Price Performance Curve

dskagcommunity
dskagcommunity
Joined: 16 Mar 11
Posts: 89
Credit: 1,185,517,870
RAC: 237,928

Yes this page is very nice

Yes this page is very nice comparing GFLOPs and Shaderunits :)

DSKAG Austria Research Team: [LINK]http://www.research.dskag.at[/LINK]

MAGIC Quantum Mechanic
MAGIC Quantum M...
Joined: 18 Jan 05
Posts: 1,785
Credit: 1,221,917,000
RAC: 2,047,653

GTX 550 TI $114.99 if you

GTX 550 TI

$114.99 if you try the $30 rebate

edit: I just ordered it without the rebate and I got it for $124.04 with shipping included

So if you do the rebate $94 which is pretty cheap.

dunx
dunx
Joined: 13 Aug 10
Posts: 119
Credit: 53,470,527
RAC: 0

I used to run 3 x GTX 460

I used to run 3 x GTX 460 OC... and a GTX 480. But UK energy prices have hit me hard, so I stopped.

I imagine the throughput of my collection of PC's is still on this site.

dunx

dunx
dunx
Joined: 13 Aug 10
Posts: 119
Credit: 53,470,527
RAC: 0

So I'm back with one PC

So I'm back with one PC !

LOL

dunx

MAGIC Quantum Mechanic
MAGIC Quantum M...
Joined: 18 Jan 05
Posts: 1,785
Credit: 1,221,917,000
RAC: 2,047,653

RE: So I'm back with one PC

Quote:

So I'm back with one PC !

LOL

dunx

But with that one pc you still do more than the average member here with several pcs dunx!

(I need a rainy day so I can install the nVidia card I just got)

I just stopped by here to look at those charts for some friends.

.....back to work.....here at home of course.....

Tex1954
Tex1954
Joined: 15 Mar 11
Posts: 28
Credit: 741,587,567
RAC: 12,994

Ya'll are welcome to check

Ya'll are welcome to check out various tasks using GPU's and CPU's here...

http://spreadsheets0.google.com/spreadsheet/pub?hl=en_US&hl=en_US&key=0AmE73gddEiprdFBHMml3dmxqTjB4T21Mc3Mya3p1Snc&output=html

This is a LIVE spreadsheet, always being updated as tasks change, revs change, and new info is received from TEAM MEMBERS.

8-)

But, great graphs and information! Thanks tons!

:D

PS: And yes, my undisturbed Linux box with a pair of 460's in it is suddenly not getting WU's anymore due to problems described elsewhere...[url][/url]

Abhijit Borah
Abhijit Borah
Joined: 1 Jan 06
Posts: 6
Credit: 137,279,232
RAC: 152,240

I added a GTX 570 to my Core

I added a GTX 570 to my Core i7 together with the existing 9500GT. To my dismay, my GTX 570 usage as shown by the GPU Meter (Gadget) on win 7 (64bit) never crosses 60% or so. My 9500GT operates above 80%. Is all this what the GPU price performance curves (of Robert) is talking about?

Can any one help me to get the maximum credits out of my investment. Normal tweakings on BOINC manager (6.12.34(x64)) are done.

Thanking in advance.

Abhijit

Abhijit Borah
Abhijit Borah
Joined: 1 Jan 06
Posts: 6
Credit: 137,279,232
RAC: 152,240

RE: I added a GTX 570 to my

Quote:

I added a GTX 570 to my Core i7 together with the existing 9500GT. To my dismay, my GTX 570 usage as shown by the GPU Meter (Gadget) on win 7 (64bit) never crosses 60% or so. My 9500GT operates above 80%. Is all this what the GPU price performance curves (of Robert) is talking about?

Can any one help me to get the maximum credits out of my investment. Normal tweakings on BOINC manager (6.12.34(x64)) are done.
---------------------------------------------------------------------------

Quoting myself for more clarity:

My system specifications are: -

CPU - Core i7 CPU 870 @ 2.93GHz (overclocked to 3019MHz)
RAM - 4GB
Graphics Card #1 - GTX 570 (1.28GB)
Graphics Card #2 - 9500 GT (1.00GB)
Motherboard - ASUS P7P55D
OS: Windows 7 (64bit)
BOINC - 6.12.34 (64bit)

I wish to know how to get the maximum workwunits from my system. No app_info.xml at present. only cc_config.xml file which reads -

1

At present my GTX 570 usage is about 50% with more than 60% gpu ram left free.

Thanks

archae86
archae86
Joined: 6 Dec 05
Posts: 3,152
Credit: 7,131,994,931
RAC: 527,872

RE: To my dismay, my GTX

Quote:
To my dismay, my GTX 570 usage as shown by the GPU Meter (Gadget) on win 7 (64bit) never crosses 60% or so.
[snip]
I wish to know how to get the maximum workwunits from my system. No app_info.xml at present.


Two possible improvements you might consider are to use the anonymous platform mechanism (app_info.xml) to run two or three BRP4 tasks simulataneously, and to adjust the CPU configuration with a view to improving the servicing of the GPU.

There is a considerable amount of prior posting here on the app_info multiple task, matter, so I'll just mention that if you lack experience at this, you may well make a mistake and lose your queue of work at first try, but if you start from a recently posted model, and check each entry against what you can find in your own client_state.xml (making sure, for example, that file names and application names match exactly) you should be able to get there. You'll also probably find you want to use the specification for both your GPU and your CPU projects, which if done right can help avoid some of the more severe scheduler oddities but is rather a pain in the neck.

Regarding CPU--the issue is that the GPU task has to sit around and wait when it wants services from the support application (*cuda32.exe) running on the CPU. So, especially if you get up to 2-fold or 3-fold, you want somehow to assure that that (those) programs run when wanted as promptly as you can manage. Many people advocate using the preference item "On multiprocessors, use at most % of processors" specification to hold down CPU usage by their CPU BOINC applications, thus "saving room" for the GPU support. I've had some luck doing both some of that, and raising the priority of the cuda32 applications (using Process Lasso), and, on my hyperthreaded CPU, segregating the constantly running GW CPU applications and the intermittently running--but urgently needing prompt service cuda32 applications to opposite virtual halves of the physical cores.

Of course, anything which makes your CPU run faster, especially memory operations, will help also, so you could consider trying more aggressive memory timings, CPU overclocking, and the like if that suits your style.

As I've reported at length in my GTX 460 thread, I've recently been through this sort of tuning exercise for two GTX 460 hosts, and got to roughly the mid-80% GPU load as reported by GPU-Z running 3-fold with raised priority on the cuda32 processes on two hosts, one of which was only about 58% GPU load running 1-fold without tinkering.

hotze33
hotze33
Joined: 10 Nov 04
Posts: 100
Credit: 368,387,400
RAC: 0

On my i7 2600K(@4.6GHz) the

On my i7 2600K(@4.6GHz) the gpu usage for running 1 task @ GTX460/GTX470 is arround 80%. When running 2 units on a gpu the usage increases to >90%.
I see smaller gpu load levels when the gpu is starving bandwidth. @ Abhijit your motherboard has only one PCIeX16 slot. The other is only PCIeX4. For maximum performance I would only stick in the GTX570 in the x16 slot. The 9500GT just uses bandwidth and has a poor performance.
Running 2 or more workunits at the GTX570 gets more work done. You can also consider a higher overclock because the high end gpus really need a fast cpu.

Comment viewing options

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