Posted On: Nov 29, 2021

Today, we are announcing the new Amazon EC2 G5g instances powered by AWS Graviton2 processors and featuring NVIDIA T4G Tensor Core GPUs. G5g are the first Arm-based instances in a major cloud to feature GPU acceleration and provide the best price performance in Amazon EC2 for Android game streaming. With G5g instances, Android game developers can run natively on Arm-based GPU instances, encode the rendered graphics, and stream the game over network to a mobile device. This helps simplify development effort and lowers the cost per stream per hour by up to 30%. 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.

AWS Graviton2 processors are custom-designed by AWS using 64-bit Arm Neoverse N1 cores to enable the best price performance for workloads in Amazon EC2. They deliver a major leap in performance and capabilities over first-generation AWS Graviton processors, with 7x performance, 4x the number of compute cores, 2x larger caches, and 5x faster memory. AWS Graviton2 processors feature always-on 256-bit DRAM encryption and 50% faster per core encryption performance compared to the first-generation AWS Graviton processors. G5g instances are built on the AWS Nitro System, a collection of AWS-designed hardware and software innovations that enable the delivery of efficient, flexible, and secure cloud services with isolated multi-tenancy, private networking, and fast local storage.

Amazon EC2 instances powered by the AWS Graviton2, including 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 5 regions globally, including the AWS US East (N. Virginia), US West (Oregon), and Asia Pacific (Tokyo, Asia Pacific (Seoul), Asia Pacific (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. To get started, visit the AWS Management Console, AWS Command Line Interface (CLI), and AWS SDKs. To learn more, visit the Amazon EC2 G5g page.