Seonglae Choexperimental
trueGPU Acceleration in Windows Containers
For many containerized workloads, CPU compute resources provide sufficient performance. However, for a certain class of workload, the massively parallel compute power offered by GPUs (graphics processing units) can speed up operations by orders of magnitude, bringing down cost and improving throughput immensely.
https://docs.microsoft.com/en-us/virtualization/windowscontainers/deploy-containers/gpu-acceleration
MicrosoftDocs/Virtualization-Documentation
This sample demonstrates containerizing and running a DirectX workload with GPU acceleration. Specifically, we use the WinMLRunner machine learning inference app. WinMLRunner is a command-line tool that evaluates trained models on tensor or image inputs. For the purposes of demonstrating GPU acceleration, this sample uses the app's performance benchmarking mode rather than providing real input.
https://github.com/MicrosoftDocs/Virtualization-Documentation/tree/live/windows-container-samples/directx
