I have access to a computer with a GPU, and I wanted to play around a bit with petsc on this gpu.<br>So I have compiled petsc-dev with cusp, thrust, and cuda to give GPU support, and I am ready<br>to run some examples.<br>
<br>However, something is not clear to me: how does petsc know which gpu to run something on?<br>For example, this machine has two gpus: one for the display, and then one compute gpu.<br>So I see /dev/nvidia0 and /dev/nvidia1. If I just issue the command from the petsc web page,<br>
will it run it on the right gpu?<br><br><br>Also, what if a computer has two compute gpus? Does petsc use both of them or only one?<br><br><br>Thanks in advance,<br><br>Randy<br>