Print

Please login or register.
1 Hour 1 Day 1 Week 1 Month Forever
Login with username, password and session length

[bob_bowen5]

Use your GPU for scientific computing 

     

--------------------------------------------------------------------------------
 Most computers are equipped with a Graphics Processing Unit (GPU) that handles their graphical output, including the 3-D animated graphics used in computer games. The computing power of GPUs has increased rapidly, and they are now often much faster than the computer's main processor, or CPU.
Some BOINC-based projects have applications that run on GPUs. These applications run from 2X to 10X faster than the CPU-only version. We urge BOINC participants to use them if possible. Just follow these instructions:


1) Check whether your computer has a capable GPU
 
Identify the model name of your GPU. On Windows, right-click on your desktop, and select Properties / Settings / Advanced / Adapter. Note the Adapter Type and Memory Size.
To find out if your NVIDIA GPU is compatible: check NVIDIA's list of CUDA-enabled products. If your GPU is listed here and has at least 256MB of RAM, it's compatible.
ATI GPUs: you need a platform based on the AMD R600 GPU or later. R600 and newer GPUs are found with ATI Radeon HD2400, HD2600, HD2900 and HD3800 graphics board. A full list is here.

2) Get the latest BOINC software
Download and install version 6.6.36 or later of the BOINC software.
ATI GPUs: you'll need 6.10.3 or later.

3) Get the latest driver
Run BOINC, and look at the Messages. If BOINC reports a GPU, your current driver is OK. Otherwise
NVIDIA: download and install the latest driver (a reboot will be required).
ATI GPUs: get the latest driver here.
You're done! Now start up BOINC, and soon you'll be racking up big credit numbers.

Projects with NVIDIA applications:

GPUgrid.net
SETI@home
Projects with ATI applications (coming soon):
Milkyway@home
Collatz Conjecture
Of course, you can attach to other projects too; BOINC will keep both your CPU and GPU busy.
--------------------------------------------------------------------------------

Return to BOINC main page
Last modified 9:15 PM UTC, September 08 2009.
Copyright © 2009 University of California. Permission is granted to copy, distribute and/or modify this document under the terms of the GNU Free Documentation License, Version 1.2 or any later version published by the Free Software Foundation.

[Phoenix]

Is there a full list of GPUs supported?  Any chance that NVIDIA GeForce 6150 LE shows up...?

[bob_bowen5]

Big Bird,

http://www.nvidia.com/object/cuda_learn_products.html


Though I don't see the 6150 on the list.

Bob

[Phoenix]

Me neither,  but thanks... heck maybe it's not "CUDA" (whatever that is?)  No idea.

[Txakura]

Me neither,  but thanks... heck maybe it's not "CUDA" (whatever that is?)  No idea.

nope not CUDA, neither is my 6600GT

but, I'll be getting an ATI soon and we'll see how that goes

[bob_bowen5]

"NVIDIA® CUDA™ is a general purpose parallel computing architecture that leverages the parallel compute engine in NVIDIA graphics processing units (GPUs) to solve many complex computational problems in a fraction of the time required on a CPU. It includes the CUDA Instruction Set Architecture (ISA) and the parallel compute engine in the GPU. To program to the CUDA architecture, developers can, today, use C, one of the most widely used high-level programming languages, which can then be run at great performance on a CUDA enabled processor."

[Txakura]

I've been waiting for the new ATI cards, until I saw the price tag for the top of the line 5870... dude, thats more than I spent on my last car 

Like I'm going to put a $1,000 card in a $300 computer, sure. 

[DBall]

I've been waiting for the new ATI cards, until I saw the price tag for the top of the line 5870... dude, thats more than I spent on my last car 

Like I'm going to put a $1,000 card in a $300 computer, sure. 

Where did you see that price? The going price for HD 5870 is about $380 although finding them in stock is a little iffy right now.

[Txakura]

on the ATi website, but someone told me later that I was looking at the dual core 5870 super deluxe hahn-yocker zoom dweebi special

so just never mind me, I'm on crack

[mattio79]

Me neither,  but thanks... heck maybe it's not "CUDA" (whatever that is?)  No idea.

CUDA stands for Compute-Unified Driver Architecture