CUDA Samples

This is a collection of containers to run CUDA workloads on the GPUs. The collection includes containerized CUDA samples for example, vectorAdd (to demonstrate vector addition), nbody (or gravitational n-body simulation) and other examples. These containers can be used for validating the software configuration of GPUs in the system or simply to run some example workloads.

The vectorAdd example is used by the NVIDIA GPU Operator as part of its self-validation.

Usage

The containers can be run on the Docker command-line or in Kubernetes pod specs. For example, in Kubernetes use the following podspec:

cat << EOF | kubectl create -f -
 apiVersion: v1
 kind: Pod
 metadata:
   name: vectorAdd
 spec:
   restartPolicy: OnFailure
   containers:
   - name: vectorAdd
     image: nvcr.io/nvidia/k8s/cuda-sample:vectoradd-cuda10.2
     resources:
       limits:
          nvidia.com/gpu: 1
EOF

or run on the Docker CLI:

docker run --rm --gpus all nvcr.io/nvidia/k8s/cuda-sample:vectoradd-cuda10.2

License Agreements

The containers are licensed under Apache 2.0.

Suggested Reading

• Code Repository for the samples is available here

NVIDIA AI Enterprise Support

This product is supported when deployed by the NVIDIA GPU Operator.