Glen Knight

New – Amazon EC2 R6a Instances Powered by 3rd Gen AMD EPYC Processors for Memory-Intensive Workloads

July 19, 2022 by knightglen_sruobz

We launched the general-purpose Amazon EC2 M6a instances at AWS re:Invent 2021 and compute-intensive C6a instances in February of this year. These instances are powered by the 3rd Gen AMD EPYC processors running at frequencies up to 3.6 GHz to offer up to 35 percent better price performance versus the previous generation instances.

Today, we are expanding our portfolio to include memory-optimized Amazon EC2 R6a instances featuring AMD EPYC (Milan) processors 10 percent less expensive than comparable x86 instances.

R6a instances, powered by 3rd Gen AMD EPYC processors are well suited for memory-intensive applications such as high-performance databases (relational databases, noSQL databases), distributed web scale in-memory caches (such as memcached, Redis), in-memory databases such as real-time big data analytics (such as Hadoop, Spark clusters), and other enterprise applications.

R6a instances are built on the AWS Nitro System and support Elastic Fabric Adapter (EFA) for workloads that benefit from lower network latency and highly scalable inter-node communication, such as high-performance computing and video processing.

Here’s a quick recap of the advantages of the new R6a instances compared to R5a instances:

• Up to 35 percent higher price performance per vCPU versus comparable R5a instances
• Up to 10 percent less expensive than comparable x86 instances
• Up to 1536 GiB of memory, 2 times more than the previous generation, giving you the benefit of scaling up databases and running larger in-memory workloads.
• Up to 192 vCPUs, 50 Gbps enhanced networking, and 40 Gbps EBS bandwidth, enabling you to process data faster, consolidate workloads, and lower the cost of ownership.
• SAP-certified instances require memory-intensive applications such as high-performance enterprise databases like SAP Business Suite.
• Support always-on memory encryption with AMD transparent sngle key memory encryption (TSME), and support new AVX2 instructions for accelerating encryption and decryption algorithms.

Here are the specs of R6a instances in detail:

Name	vCPUs	Memory (GiB)	Network Bandwidth (Gbps)	EBS Throughput (Gbps)
r6a.large	2	16	Up to 12.5	Up to 6.6
r6a.xlarge	4	32	Up to 12.5	Up to 6.6
r6a.2xlarge	8	64	Up to 12.5	Up to 6.6
r6a.4xlarge	16	128	Up to 12.5	Up to 6.6
r6a.8xlarge	32	256	12.5	6.6
r6a.12xlarge	48	384	18.75	10
r6a.16xlarge	64	512	25	13.3
r6a.24xlarge	96	768	37.5	20
r6a.32xlarge	128	1024	50	26.6
r6a.48xlarge	192	1536	50	40
r6a.metal	192	1536	50	40

Now Available
You can launch R6a instances today in the AWS US East (N. Virginia, Ohio), US West (Oregon), Asia Pacific (Mumbai) and Europe (Frankfurt, Ireland) as On-Demand, Spot, and Reserved Instances or as part of a Savings Plan.

To learn more, visit the R6a instances page. Please send feedback to ec2-amd-customer-feedback@amazon.com, AWS re:Post for EC2, or through your usual AWS Support contacts.

— Channy

Source: AWS News