From d67ce1a98aba0ac1809cab980096bab36ef53c20 Mon Sep 17 00:00:00 2001 From: Haley Yandt <46908710+yandthj@users.noreply.github.com> Date: Thu, 16 Jan 2025 11:29:49 -0700 Subject: [PATCH] Update virtualgl_fastx.md --- docs/Documentation/Viz_Analytics/virtualgl_fastx.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/Documentation/Viz_Analytics/virtualgl_fastx.md b/docs/Documentation/Viz_Analytics/virtualgl_fastx.md index 8c3d8b1a9..2c90e6461 100644 --- a/docs/Documentation/Viz_Analytics/virtualgl_fastx.md +++ b/docs/Documentation/Viz_Analytics/virtualgl_fastx.md @@ -139,7 +139,7 @@ $ vglrun matlab ## Choosing a GPU on Kestrel Kestrel DAV nodes have two NVIDIA A40 GPUs. Using vglrun will default to the first GPU available, which may leave one GPU overutilized while the second is underutilized. -To run your OpenGL software with a GPU of your choosing, you may add the `-d ` flag to vglrun to pick a GPU. The first GPU is referred to as 0:0, the second as 0:1. For example, to run Matlab on the second GPU: +To run your OpenGL software with a GPU of your choosing, you may add the `-d ` flag to vglrun to pick a GPU. The first GPU is referred to as :0.0, the second as :0.1. For example, to run Matlab on the second GPU: `vglrun -d :0.1 matlab`