Posted On: Jan 11, 2023

Starting today, the Amazon Elastic Compute Cloud (Amazon EC2) G5g instances powered by AWS Graviton2 processors and featuring NVIDIA T4G Tensor Core GPUs are now available in Europe (Frankfurt). G5g instances can be used for a wide range of graphics intensive and machine learning use cases. They provide the best price performance in Amazon EC2 for Android game streaming use-cases. With G5g instances, developers can run Android games natively, encode the rendered graphics, and stream the game over network to end user devices. This helps simplify development effort and can lower the hourly cost per stream by up to 30% compared to G4dn instances. G5g instances are also ideal for machine learning developers who are looking for cost-effective inference, have ML models that are sensitive to CPU performance, and leverage NVIDIA’s AI libraries. Embedded developers using Arm-based compute with GPU acceleration can also leverage G5g instances to scale their CI/CD and simulation workloads in the cloud.

G5g instances, are supported by popular Linux operating systems including Red Hat Enterprise Linux, SUSE, and Ubuntu. Many popular applications and services for security, monitoring and management, containers, and CI/CD from AWS and Independent Software Vendors also support AWS Graviton2-based instances.

The G5g instances are now available in 6 regions globally, including the AWS Europe (Frankfurt), US East (N. Virginia), US West (Oregon), and Asia Pacific (Tokyo, Seoul, Singapore) Regions, and are purchasable On-Demand, as Reserved instances, as Spot instances, or as part of Savings Plans. They are available in 6 sizes providing up to 64 vCPUs, 2 NVIDIA T4G Tensor Core GPUs, 32 GB memory, 25 Gbps of networking bandwidth, and 19 Gbps of Amazon Elastic Block Store (Amazon EBS) bandwidth.

Machine learning developers can quickly get started with G5g instances by using AWS Deep Learning Linux AMI with NVIDIA drivers and popular machine learning frameworks such as Tensorflow and PyTorch pre-installed. Graphics customers can download the NVIDIA drivers from NVIDIA’s public driver download page or visit the Install NVIDIA drivers documentation page. To learn more, visit the Amazon EC2 G5g page.