Amazon Elastic Compute Cloud (Amazon EC2) C7g instances, powered by the latest generation AWS Graviton3 processors, provide the best price performance in Amazon EC2 for compute-intensive workloads. C7g instances are ideal for high performance computing (HPC), batch processing, electronic design automation (EDA), gaming, video encoding, scientific modeling, distributed analytics, CPU-based machine learning (ML) inference, and ad serving. They offer up to 25% better performance over the sixth-generation AWS Graviton2-based C6g instances. C7g instances are the first in the cloud to feature Double Data Rate 5 (DDR5) memory, which provides 50% higher memory bandwidth compared to DDR4 memory to enable high-speed access to data in memory.
C7gn instances are powered by AWS Graviton3E processors and the latest generation Nitro Cards. C7gn instances offer up to 200 Gbps of network bandwidth and up to 50% higher packet-processing performance than existing Graviton-based EC2 instances. These new instances are ideal for running the most demanding network-intensive workloads, such as network virtual appliances, data analytics, and CPU-based artificial intelligence and machine learning (AI/ML) inference.
Best price performance for compute-intensive workloads in Amazon EC2
C7g and C7gn instances deliver up to 25% better performance over Graviton2-based C6g and C6gn instances respectively. They are ideal for a large number of compute-intensive applications, such as HPC, video encoding, gaming, and CPU-based ML inference, that are built on Linux.
Enhanced security and maximized resource efficiency
C7g and C7gn instances are built on the AWS Nitro System. AWS Nitro System is a combination of dedicated hardware and a lightweight hypervisor that delivers isolated multi-tenancy, private networking, and fast local storage. AWS Graviton3 and AWS Graviton3E processors offer enhanced security with always-on memory encryption, dedicated caches for every vCPU, and support for pointer authentication. These instances also support encrypted Amazon Elastic Block Store (EBS) volumes by default.
Extensive software support
AWS Graviton-based instances are supported by many Linux operating systems, including Amazon Linux 2, Red Hat Enterprise Linux, SUSE, and Ubuntu. Many popular applications and services for security, monitoring and management, containers, and continuous integration and delivery (CI/CD) from AWS and software partners also support AWS Graviton-based instances. The AWS Graviton Ready program offers certified solutions from partner software vendors that can be used on AWS Graviton-based instances.
Powered by AWS Graviton3 processors
AWS Graviton3 is the latest generation of AWS-designed Arm-based processors that provide the best price performance for workloads in Amazon EC2. AWS Graviton3 processors deliver up to 25% better compute performance, up to 2x higher floating-point performance, and up to 2x faster cryptographic workload performance compared to AWS Graviton2 processors. Additionally, Graviton3 processors deliver up to 3x better performance compared to Graviton2 processors for ML workloads, including support for bfloat16. C7gn instances are powered by AWS Graviton3E processors, which provide up to 35% higher vector-instruction performance compared to AWS Graviton3 processors. This improvement provides higher performance benefits for HPC applications.
C7g and C7gn instances use leading edge DDR5 memory to provide 50% higher bandwidth compared to C6g and C6gn instances. C7gn instances deliver 2x higher enhanced networking bandwidth compared to C6gn instances for network-intensive applications, such as network appliances and data analytics. C7g and C7gn have support for Elastic Fabric Adapter (EFA).
Built on the AWS Nitro System
The AWS Nitro System is a rich collection of building blocks that offloads many of the traditional virtualization functions to dedicated hardware and software. It delivers high performance, high availability, and high security, reducing virtualization overhead.
Amazon EC2 C7g instances are powered by Arm-based AWS Graviton3 processors. They deliver the best price performance in Amazon EC2 for compute-intensive applications.
Instance Size vCPU Memory (GiB) Instance Storage (GB) Network Bandwidth (Gbps) EBS Bandwidth (Gbps)
Up to 12.5
Up to 10
Up to 12.5
Up to 10
Up to 12.5
Up to 10
Up to 15
Up to 10
Up to 15
Up to 10
Founded in 1991, Epic Games is the creator of Fortnite, Unreal, Gears of War, Shadow Complex, and the Infinity Blade series of games. Epic’s Unreal Engine technology brings high-fidelity, interactive experiences to PC, console, mobile, AR, VR, and the web.
“As we look to the future and building increasingly immersive and compelling experiences for players, we are excited to use AWS Graviton3-based EC2 C7g instances. Our testing has shown they are suitable for even the most demanding latency-sensitive workloads while providing significant price performance benefits and expanding what is possible within Fortnite and any Unreal Engine-created experience.”
Mark Imbriaco, Senior Director of Engineering at Epic Games
Formula 1 (F1) racing began in 1950 and is the world’s most prestigious motor racing competition, as well as the world’s most popular annual sporting series.
“We had already seen that Graviton2-based C6gn instances provided us the best price performance for some of our CFD workloads. We have now found Graviton3 C7g instances to be 40% faster than the Graviton2 C6gn instances for those same simulations. We’re excited that EFA will be standard on this instance type, and given this much-improved price performance, we expect Graviton3-based instances to become the optimal choice to run all of our CFD workloads.”
Pat Symonds, CTO at Formula 1 Management
NextRoll Inc. is a marketing and data technology company with a mission to accelerate growth for companies, big and small. Powered by machine learning, NextRoll’s technology gathers data, delivers reliable insights, and provides business with approachable tools to target buyers in strategic ways – all on one platform.
"We have found that Graviton3-based C7g instances are ideal for bidders, ad servers, and ElastiCache clusters. We are seeing about 15% more requests handled by C7g instances compared to Graviton2-based C6g instances. With C7g instances, we also observed up to 40% better latency. Based on these findings, we are looking forward to adopting AWS Graviton3-based C7g instances in production."
Valentino Volonghi, CTO - Nextroll
Snap Inc, known for its popular social media services such as Snapchat and Bitmoji, adopted AWS Graviton2-based instances to optimize their price performance on Amazon EC2.
"We trialed the new AWS Graviton3-based Amazon EC2 C7g instances and found that they provide significant performance improvements on real workloads compared to previous generation C6g instances. We are excited to migrate our Graviton2-based workloads to Graviton3, including the messaging, storage and the friend graph workloads."
Aaron Sheldon, Software Engineer - Snap
As the only unified customer experience management platform (Unified-CXM), Sprinklr helps the world's largest and most valuable companies make their customers happier across 30+ digital channels — using industry-leading AI to create insight-driven strategies and better customer experiences.
“We run a wide variety of workloads on AWS Graviton-based instances for their significant price performance benefits. After the announcement of AWS Graviton3, we benchmarked our workloads on the new Amazon EC2 C7g instances and observed 27% better performance compared to the previous generation instances. Based on these results, we are looking forward to adopting AWS Graviton3-based instances in production.”
Jamal Mazhar, VP Infrastructure and DevOps - Sprinklr
Twitter is what’s happening and what people are talking about right now.
“Twitter is working on a multi-year project to leverage AWS Graviton-based EC2 instances to deliver Twitter timelines. As part of our ongoing effort to drive further efficiencies, we tested the new Graviton3-based C7g instances. Across a number of benchmarks that we've found to be representative of the performance of Twitter workloads, we found Graviton3-based C7g instances deliver 20-80% higher performance vs. Graviton2 based C6g instances, while also reducing tail latencies by as much as 35%. We are excited to utilize Graviton3-based instances in the future to realize significant price performance benefits."
Nick Tornow, Head of Platform - Twitter
As a dedicated simulation solutions provider, Ansys leads the industry in physics-based and multiphysics simulation, supporting transformational product development for customers across industries.
“As engineers and designers face increasingly complex problems, cloud computing helps lower the barrier of access to high-performance computing, allowing users to solve problems faster. Ansys has also been focusing on green computing initiatives with the goal of improving energy efficiency and reducing costs to customers. We benchmarked 35% better performance on AWS Graviton3-based C7g instances compared to the previous generation instances. With the support of LS-DYNA on the AWS Graviton3 processor, Ansys customers will get the best of both worlds – access to a world-class multiphysics solver without comprising on speed, and lower energy and costs.”
Prith Banerjee, Chief Technology Officer - Ansys
Beamr is a leading provider of image and video optimization solutions that enable professional photographers to improve their workflows, photo sharing services to improve UX and reduce churn, and video service providers to reduce storage and delivery costs.
"Beamr's JPEGmini software, written in C/C++, optimizes JPEG image files by reducing their file size without compromising quality. The application is a compute-intensive and includes functions for image decoding, image encoding, and a quality measure algorithm that analyzes various image attributes. Since the mobile version of this software runs on Arm processors, we decided to test its performance on AWS Graviton3-based Amazon EC2 C7g instances. Rebuilding our software to run on C7g instances took us one working day, and the results were promising. When running on C7g instances, we saw 30% improved performance over comparable x86-based instances. Based on these results, we plan to recommend to our customers to run the Beamr JPEGmini software on Graviton3-based instances once those become GA, and we plan to benchmark Beamr’s H.264 and HEVC video encoders on Graviton instances as well."
Dan Julius, VP R&D - Beamr
CloudFix is the easiest way to fix your cloud cost issues. It just takes 5 clicks to save 10-20% on your AWS bill.
“We are really excited about the new Graviton3 processors given the amazing 25-35% higher performance that we are seeing in almost all cases. We recommend that everyone should move to Graviton3 for its amazing price/performance ratio and are really excited about the upcoming release of fixers that will help customers migrate their workloads over with a few simple clicks.”
Rahul Subramaniam, CEO - CloudFix
Honeycomb.io develops an observability platform that allows engineering teams to visualize, analyze, and improve cloud application quality and performance.
“We're excited to have tested our high-throughput telemetry ingestion workload against early preview instances of Graviton3 and have seen a +35% performance increase for our workload over Graviton2. We were able to run 30% fewer instances of C7g than C6g serving the same workload, and with 30% reduced latency. Once this instance type reaches production, we believe we'll see over 50% price-performance improvement over Intel instances overall.”
Liz Fong-Jones, Principal Developer Advocate - honeycomb.io
Modern Electron is a technology company focused on the decarbonization of heat and power. Our power products generate electricity from heat in furnaces and boilers; and our gas decarbonization products generate clean hydrogen for fuel blending in commercial and industrial heating.
"We use the simulation software WarpX, part of the Exascale Computing Project, to simulate our novel heat-to-electricity devices. In 2020, we began using Graviton2-based C6g instances to realize a 50% cost improvement over C5 instances. Recently we tested C7g instances with simulations we are currently running on C6g, and have seen computation speed improvements of another 50%. This gives us a significantly lower time-to-solution that greatly improves our rate of learning."
Peter Scherpelz, Senior Computational Physicist - Modern Electron
The National Supercomputing Centre (NSCC) Singapore was established in 2015 and manages the nation’s petascale facilities. NSCC’s high performance (HPC) resources support the research needs of Singapore’s public and private sectors, including research institutes, institutes of higher learning, government agencies and companies.
“As part of a trial we ran Gromacs benchmarks on AWS Graviton3-based Amazon EC2 C7g instances for molecular dynamics simulations and found that it outperforms comparable x86-based instances by 15-20% and the previous generation of C6g powered by AWS Graviton2 instances by 40%-50%. The benchmarking took just two days and was achieved without any specific performance tuning efforts using solely GCC 11.2.0 and ARM performance libraries. We are impressed with the performance AWS Graviton3 offers for HPC workloads.”
Jernej Zidar, Senior HPC Application Analyst - NSCC
ProSiebenSat.1 Media SE is a German digital and media company focused on entertainment, dating, commerce, and other ventures. Its wholly owned subsidiary, Seven.One Entertainment Group, offers viewers entertainment content across a variety of media technologies.
"The Seven.One Entertainment Group runs video transcoding, based on the open source tool ffmpeg, for on-demand content in Amazon EC2. In 2021, we switched to AWS Graviton2-based C6g instances and realized significant cost benefits over comparable x86-based instances. With C6g instances, we could also run more parallel transcoding tasks per EC2 instance, resulting in fewer instances and more cost savings. We have run transcoding tests with ffmpeg version 4.4.1 on the new AWS Graviton3-based C7g instances and benchmarked up to 40% faster performance compared to C6g instances. With a new build of ffmpeg version 5 using Arm64 optimizations, there are even greater performance gains, especially in near-live use cases. This enables to provide video on-demand content faster to our users."
Wolfgang Dworzak, Head of Video Engineering - Seven.One Entertainment Group GmbH
Tuya Smart offers a cloud platform that connects a range of devices via the IoT to make lives smarter.
“Our application is network intensive with a large number of persistent connections. We were amazed to see a 40% performance improvement for this application on AWS Graviton2-based Amazon EC2 C6g instances compared to x86-based instances. We have been running most of our production workloads on Graviton-based instances for over 1.5 years now. After the launch of AWS Graviton3-based Amazon EC2 instances, we benchmarked 15% performance improvement on general tasks and 50% on encrypt/decrypt intensive tasks compared to the C6g instances. We are looking forward to adopting the new C7g instances in production soon.”
Simon Shu, Senior Platform Technical Director - Tuya Smart
Viant is a leading advertising software company enabling ad buyers to plan, create, execute and measure their digital advertising investments through a cloud-based platform.
“We are extremely excited about AWS Graviton3 performance. As our application heavily relies on CPU vectorization, AWS Graviton3 SVE comes with substantial performance improvement over the AWS Graviton2 Neon extension. On production testing, we’ve seen ~45% performance improvement for heavy CPU workloads on AWS Graviton3-based Amazon EC2 C7g instances compared to AWS Graviton2-based C6g instances. AWS Graviton3 is going to be pivotal component for growing our platform and reducing operational cost.”
Adrian Witas, SVP Chief Architect - Viant