Over the last 18 months, we have launched AMD-powered M5a and R5a/M5ad and R5ad, and T3a instances to provide customers additional choice for running their general purpose and memory intensive workloads. Built on the AWS Nitro System, these instances are powered by custom 1st generation AMD EPYC
Today, I am excited to announce the general availability of compute-optimized C5a instances featuring 2nd Gen AMD EPYC
You can launch C5a instances today in eight sizes in the US East (N. Virginia), US East (Ohio), US West (Oregon), Europe (Ireland), Europe (Frankfurt), Asia Pacific (Sydney), and Asia Pacific (Singapore) Regions in On-Demand, Spot, and Reserved Instance or as part of a Savings Plan. Here are the specs:
Instance Name | vCPUs | RAM | EBS-Optimized Bandwidth | Network Bandwidth |
c5a.large | 2 | 4 GiB | Up to 3.170 Gbps | Up to 10 Gbps |
c5a.xlarge | 4 | 8 GiB | Up to 3.170 Gbps | Up to 10 Gbps |
c5a.2xlarge | 8 | 16 GiB | Up to 3.170 Gbps | Up to 10 Gbps |
c5a.4xlarge | 16 | 32 GiB | Up to 3.170 Gbps | Up to 10 Gbps |
c5a.8xlarge | 32 | 64 GiB | 3.170 Gbps | 10 Gbps |
c5a.12xlarge | 48 | 96 GiB | 4.750 Gbps | 12 Gbps |
c5a.16xlarge | 64 | 128 GiB | 6.3 Gbps | 20 Gbps |
c5a.24xlarge | 96 | 192 GiB | 9.5 Gbps | 20 Gbps |
But wait, there’s more! Disk variants, C5ad, that come with fast, local NVMe instance storage and bare metal variants, C5an.metal and C5adn.metal, are coming soon.
The C5a instances will be supported across a broad set of AWS services that support C5 today, including AWS Batch, Amazon EMR, Elastic Container Service (ECS), and Elastic Kubernetes Service(EKS). C5a are fully-compatible 64-bit x86 and managed by the same Nitro platform used across Amazon EC2. Again, these instances are available in similar sizes as the C5 instances, and the AMIs work on either, so go ahead and try both!
To learn more, visit our AMD Instances page and please send feedback to ec2-amd-customer-feedback@amazon.com, AWS forum for EC2 or through your usual AWS Support contacts.
— Channy;
Originally posted on AWS News Blog
Author: Channy Yun