AWS Announces General Availability of Amazon EC2 X2gd Instances Powered by AWS-designed Graviton2 Processors

AWS Announces General Availability of Amazon EC2 X2gd Instances Powered by AWS-designed Graviton2 Processors

March 17, 2021 Off By David

Amazon Web Services, Inc. (AWS) announced general availability of Amazon Elastic Compute Cloud (EC2) X2gd instances, the next generation of memory-optimized instances powered by AWS-designed, Arm-based Graviton2 processors. New X2gd instances utilize AWS Graviton2 processors to deliver up to 55% better price/performance compared to current generation x86-based X1 instances, while also offering increased memory per vCPU compared to other Graviton2-based instances. Together, the higher performance and additional memory of X2gd instances make it possible for customers to more efficiently run memory intensive workloads like in-memory databases, relational databases, electronic design automation (EDA) workloads, real-time analytics, and real-time caching servers. There are no minimum commitments or up-front fees to use X2gd instances, and customers pay only for the amount of compute used. To get started with X2gd instances visit https://aws.amazon.com/ec2/instance-types/x2.

Since becoming available in May 2020, Amazon EC2 instances powered by AWS-designed, Arm-based AWS Graviton2 processors have provided customers with up to 40% better price/performance for a broad range of workloads compared to current generation x86-based instances. Customers including Domo, Formula One, Honeycomb.io, Intuit, LexisNexis Risk Solutions, Nielsen, NextRoll, Redbox, SmugMug, Snap, and Twitter have seen significant performance gains and reduced costs from running AWS Graviton2-based instances in production. Additionally, many popular AWS services including Amazon Elastic Container Service, Amazon Elastic Container Registry, Amazon Elastic Kubernetes Service, AWS CodeBuild, AWS CodeCommit, AWS CodePipeline, AWS CodeDeploy, Amazon CloudWatch, Amazon ElastiCache, and Amazon Elastic Map Reduce now support AWS Graviton2-based instances to deliver to customers of those services up to 40% better price/performance on their use of the underlying EC2 instances. With increasing support from a broad ecosystem of operating system and independent software vendors, Arm processors have become mainstream, and now customers want to take advantage of the performance and cost saving benefits for more workloads, including their most demanding workloads that require even higher memory per vCPU. Additionally, there are other customers that simply want to use the higher memory to scale up the number of containers they can run on EC2 instances to reduce their overall spend on compute.

Today, customers use memory-optimized AWS Graviton2 powered R6g instances (which deliver up to 40% better price/performance than current generation x86-based R5 instances) to optimize performance and cost for workloads like relational databases and big data analytics. For workloads like in-memory databases that need an even larger memory footprint, customers typically use x86-based X1 instances, which offer 2x memory per vCPU compared to R6g instances. New X2gd instances utilize AWS Graviton2 processors and deliver the same amount of memory per vCPU as X1 instances, but with up to 55% better price/performance compared to current generation x86-based X1 instances. X2gd instances deliver the lowest cost per GiB of memory of any Amazon EC2 instance to support workloads like in-memory databases (e.g. Redis, Memcached, etc.), relational databases (e.g. MySQL, PostGreSQL, etc.), data warehousing applications (e.g. Amazon Redshift), and electronic design automation (EDA). Additionally, as more customers run containers on AWS for application portability and infrastructure efficiency, X2gd instances also make it possible for them to bundle more memory-intensive containerized applications on a single instance to lower their total cost of ownership.

“Graviton2 processors have proven incredibly popular with customers because they deliver a major improvement in performance while also significantly lowering costs for a wide variety of workloads,” said David Brown, Vice President, Amazon EC2, at AWS. “With up to 55% better price/performance than current generation X1 and double the memory per vCPU compared to the latest Graviton2 R6g instances, new X2gd instances provide the lowest cost per gigabyte of memory we have ever offered in EC2. X2gd instances give customers the ability to consolidate their memory-intensive workloads on instances with fewer vCPUs and realize game-changing performance benefits and cost savings.”

X2gd instances join the growing portfolio of Amazon EC2 instances powered by AWS Graviton2 instances, including M6g/M6gd, C6g/C6gd/C6gn, R6g/R6gd, and T4g instances. X2gd instances also benefit from use of the AWS Nitro System, a collection of AWS-designed hardware and software innovations that streamline the delivery of isolated multi-tenancy, private networking, and fast local storage. X2gd instances are available for purchase as On-Demand, with Savings Plans, as Reserved Instances, or as Spot Instances. X2gd instances are initially available in US East (N. Virginia), US East (Ohio), US West (Oregon), and Europe (Ireland), with availability in additional regions coming later this year.

SmugMug is a paid image sharing service, image hosting service, and online video platform on which users can upload photos and videos. The company facilitates the sale of digital and print media for amateur and professional photographers. “SmugMug operates two very large online photo platforms, SmugMug and Flickr, enabling more than 100 million members to safely store, search, share, and sell tens of billions of photos,” said Andrew Shieh, Director of Operations, at SmugMug. “Last year we were able to transition our caching servers to r6gd.8xlarge instances with a simple recompile and are enjoying a 33% price benefit and improved latency. The large memory footprint of the new X2gd instances allows us to consolidate our caching on instances that closely match our workload, lowering our cost per instance and cost per GB of RAM by an additional 28%.”

As an S&P 500 company, Synopsys has a long history of being a global leader in electronic design automation (EDA) and semiconductor IP and offers the industry’s broadest portfolio of application security testing tools and services. “Synopsys’ customers are increasingly leveraging cloud for scaling and accelerating applications across our portfolio for system-on-chip (SoC) design processes, including verification, library characterization, analog and digital design implementation flows,” said Deirdre Hanford, Chief Security Officer, Synopsys. “Our anchor products, such as Synopsys’ VCS functional verification solution, are optimized to use advances in hardware performance and memory introduced in AWS’s Graviton2-based X2gd instances, enabling our customers to accelerate SoC verification and design.”

Cadence is a pivotal leader in electronic design, building upon more than 30 years of computational software expertise. “Cadence’s computational software heritage enables customers to turn electronic design concepts into reality across a variety of end markets, including hyperscale computing, mobile and 5G communications,” said Nimish Modi, Senior Vice President, Marketing & Business Development at Cadence. “We have successfully run our verification and library characterization products on the AWS Graviton2-based R6g memory optimized instances, delivering compelling price-performance benefits. The new Graviton2-based X2g instances have a much larger memory footprint, which will allow for more efficient runs and enable even more memory-intensive EDA workloads.”

Arm is a global leader in semiconductor design and silicon intellectual property development and licensing. “Technology has become ubiquitous in all industries, driving the need for more compute products in less time while simultaneously using fewer resources to keep costs low,” said Mark Galbraith, head of productivity engineering, Arm. “The design, verification, and implementation of silicon IP are the most critical phases between idea and a finished product produced in volume, and we have measured a performance uplift of 45% on EDA workloads when running on Arm-based Graviton2-powered X2gd cloud instances compared to previous generation X1 instances.”

Annapurna Labs, an Amazon company, is the chip development arm of AWS responsible for designing the AWS Nitro System, AWS Graviton processors, AWS Inferentia chips, and AWS Trainium chips. “At Annapurna Labs, we have been running almost all of our chip simulations and verification up till now on Graviton2-based R6g instances,” said Nafea Bshara, Vice President, and Distinguished Engineer, at Annapurna Labs. “With the new X2gd instances, we are able to double the number of full chip and cluster level simulations for same instance size, allowing us to do twice the output while reduce costs at the same time.”