yade-users team mailing list archive

Thread
Date

Re: [Question #685647]: Problem in CHOLMOD test with GPU acceleration

To: yade-users@xxxxxxxxxxxxxxxxxxx
From: Robert Caulk <question685647@xxxxxxxxxxxxxxxxxxxxx>
Date: Wed, 06 Nov 2019 12:57:14 -0000
Reply-to: question685647@xxxxxxxxxxxxxxxxxxxxx
Sender: bounces@xxxxxxxxxxxxx

Question #685647 on Yade changed:
https://answers.launchpad.net/yade/+question/685647

    Status: Open => Answered

Robert Caulk proposed the following answer:
Ok, I will point out to you that the Quadro P1000 is useless for
scientific calculations since the double precision processing power is
weaker than your CPU. You need to look for cards with high dp processing
power such as Tesla, new quadros, Titan V, etc. if you wish to gain
performance from this acceleration technique.

And for the problem at hand:
It appears CUDA recognizes the card and CHOLMOD is compiled with GPU options as well as linked to CUDA libraries.

The next step is to make sure you are executing cholmod_l_demo properly.
Execute it manually with

export CHOLMOD_USE_GPU=1
./cholmod_l_demo < nd6k.mtx

Where nd6k.mtx is the matrix.

Cheers,

Robert

-- 
You received this question notification because your team yade-users is
an answer contact for Yade.