Posted On: Jun 23, 2022
Amazon WorkSpaces is introducing two new graphics bundles based on the EC2 G4dn family: Graphics.g4dn and GraphicsPro.g4dn. These bundles allow you to run graphics- and compute-intensive workloads on desktops in the cloud as cost-effective solutions for graphics applications that are optimized for NVIDIA GPUs using NVIDIA libraries such as CUDA, CuDNN, and Video Codec SDK. They come with the NVIDIA T4 Tensor Core GPU that features multi-precision Turing Tensor Cores and RT Cores, Amazon Web Services custom second generation Intel® Xeon® Scalable (Cascade Lake) processors, and the local NVMe storage designed for applications that require fast access to locally stored data.
Graphics.g4dn bundle provides 4vCPUs, 16 GB of RAM, 16 GB of video memory, 125 GB of temporary NVMe SSD local instance store, and a minimum 100 GB of persistent storage for the user volume and root volumes. It is ideal for customers seeking low-cost GPU-enabled virtual desktops to operate mainstream graphics-intensive applications, such as engineering, design, and architectural applications.
GraphicsPro.g4dn bundle offers 16vCPUs, 64 GB of RAM, 16 GB of video memory, 225 GB of temporary NVMe SSD local instance store, and a minimum 100 GB of persistent storage for the user volume and root volumes. The offering enables high-end workstation workflows on WorkSpaces and is ideal for media production, seismic visualization, GIS data processing, data intelligence, small-scale ML model training, and ML inference.
You can deploy Graphics.g4dn or GraphicsPro.g4dn bundles with Windows 10 Desktop experience powered by Windows Server 2019, or you can bring your own Window licenses. You can launch the new graphics bundles by selecting their names in the Amazon WorkSpaces management console, or through the Amazon WorkSpaces APIs. You can use the new graphics bundles with Amazon WorkSpaces client applications with PCoIP streaming protocols. The new graphics bundles will be available in Amazon Web Services China (Ningxia) Region, operated by NWCD.
For more information, please visit the Amazon WorkSpaces website. To get started, sign in to the Amazon WorkSpaces Management Console.