Your Browser is Out of Date

Nytro.ai uses technology that works best in other browsers.
For a full experience use one of the browsers below
VDI Design Guide—Dual VDI and AI on Dell 15G vSAN Ready Nodes in a Healthcare Environment
Introduction
Solution introduction
Overview Document purpose Audience
What's new?
Design guide introduction
Solution Architecture Validation Sizing the Solution Summary References

Solution introduction

Home > Workload Solutions > Virtual Desktop Infrastructure > Design and Implementation Guides > VDI Design Guide—Dual VDI and AI on Dell 15G vSAN Ready Nodes in a Healthcare Environment > Solution introduction

Solution introduction

  • Overview

    This design guide describes the architecture required to provide a GPU-enabled vSAN environment that supports vGPU-accelerated VDI desktops, and AI training and inferencing, allowing both workloads to run simultaneously on the same host server.

    The solution defined in this design guide focuses on the healthcare vertical that demonstrates a workflow and its subsequent workload. Additionally, this guide provides recommended solution components. Both AI activities and graphics are performed on X-ray images concurrently to demonstrate the capability of the system.

    Virtual Desktop Infrastructure (VDI) users increasingly require graphics-rich environments that demand GPU resources. GPU environments are also widely deployed for AI activities such as machine learning and deep learning, driving a significant increase in AI activities across multiple settings. Due to being intensely data-driven, healthcare represents a primary field for GPU resources.

    This design guide presents the results of work performed by the VDI Solutions team to demonstrate the performance of GPU resources in a healthcare setting between graphics-accelerated VDI, including Digital Imaging and Communications in Medicine (DICOM) X-ray viewing and healthcare-related AI. The AI tests include disease prediction from public domain chest X-ray datasets released by the US National Institutes of Health (NIH).

    The architecture and performance testing described in this document for a shared VDI and AI infrastructure include scenarios where the VDI and AI workloads run as dual workloads simultaneously. The testing also includes scenarios where the VDI runs as a single workload on the same hardware.

    By implementing a common platform for VDI and AI workloads to increase GPU utilization, healthcare organizations can improve IT efficiency and reduce TCO. The Dell VDI Solutions team offers a tested and validated VMware Horizon solution based on 15G vSAN Ready Nodes, built on Power Edge servers, with NVIDIA L40 GPUs that run dual VDI and AI workloads. Sharing the GPU cards between the workloads to meet various business requirements can achieve maximum return on investment (ROI).

    Dell Validated Designs for VDI on vSAN-based infrastructure simplify and extend your VMware environment. By combining compute, storage, networking, virtualization, and management, Dell Validated Designs for VDI are the ideal solutions for your VDI applications.