AWS Unveils Amazon EC2 R9g and R9gd Instances Powered by Graviton5: A New Era for Memory-Optimized Cloud Computing

aws-unveils-amazon-ec2-r9g-and-r9gd-instances-powered-by-graviton5-a-new-era-for-memory-optimized-cloud-computing

SEATTLE — Amazon Web Services (AWS), an Amazon.com company, has officially announced the general availability of the Amazon EC2 R9g and R9gd instance families. Driven by the next-generation AWS Graviton5 processors—touted as the most energy-efficient silicon ever developed by the cloud giant—these memory-optimized virtual servers deliver up to a 25% boost in compute performance compared to their Graviton4-based predecessors, the R8g series.

Designed to tackle the world’s most demanding memory-intensive workloads, the launch marks a major milestone in AWS’s continuous push to redefine price-performance benchmarks in enterprise cloud computing, while simultaneously advancing industry standards in cloud security through advanced formal verification.


Main Facts

The newly released EC2 R9g and R9gd instances are engineered from the ground up to support high-throughput, latency-sensitive applications. At their core are the AWS Graviton5 processors, which introduce significant architectural enhancements over previous generations, translating to higher instructions-per-cycle, larger L3 caches, and vastly improved energy efficiency.

  • Performance Uplift: R9g instances deliver up to 25% better compute performance than R8g instances, yielding superior performance per vCPU, quicker memory access, expanded network bandwidth, and higher Amazon Elastic Block Store (EBS) throughput.
  • Target Workloads: The instances are exceptionally well-suited for distributed relational and open-source databases, in-memory caching solutions (such as Redis, Valkey, and Memcached), real-time big data analytics, and containerized microservices running on Kubernetes, Docker, Amazon EKS, and Amazon ECS. They also natively support modern programming languages including C/C++, Rust, Go, Java, Python, .NET Core, Node.js, Ruby, and PHP.
  • Storage Variants: While the standard R9g instances rely on network-attached EBS storage, the R9gd variants are equipped with high-speed, local NVMe-based SSD block-level storage. These are tailor-made for open-source databases, large-scale caching engines, and distributed analytics needing rapid, low-latency scratch space.
  • Instance Bandwidth Configuration (IBC): Both instance families support IBC, giving administrators the flexibility to dynamically adjust bandwidth allocation between Amazon EBS and Amazon VPC networking by up to 25% to fit specific application bottlenecks.
  • Formally Verified Security: Operating on the AWS Nitro System, R9g and R9gd instances incorporate the Nitro Isolation Engine (NIE). The NIE leverages formal verification—a mathematical technique used to prove system correctness—to establish an unprecedented level of hardware-enforced isolation between virtual machines.

Chronology: The Evolution of AWS Graviton and Nitro

To understand the magnitude of the R9g launch, it is helpful to examine the deliberate, multi-year trajectory of AWS’s custom silicon strategy.

  • November 2018 (re:Invent): AWS introduces its first-ever custom ARM-based processor, the AWS Graviton, setting off a wave of disruption in a cloud market historically dominated by x86 architectures.
  • December 2020: The release of Graviton2 marks a turning point, offering a massive 40% price-performance improvement over first-generation instances and convincing major enterprises to transition mainstream workloads to Arm.
  • November 2023: AWS rolls out Graviton4, bringing substantial leaps in core counts, memory bandwidth, and security encryption features. This paves the way for the R8g memory-optimized family.
  • Early 2025: AWS introduces the C9g (compute-optimized) and M9g (general-purpose) instances, alongside the initial rollout of the Nitro Isolation Engine, pioneering mathematically proven cloud hypervisor security.
  • September 2025: AWS achieves general availability for the R9g and R9gd memory-optimized families powered by Graviton5, fully integrating the latest silicon innovations with the Nitro Isolation Engine across its high-end enterprise portfolio.

Supporting Data: Instance Specifications and Configurations

To accommodate diverse enterprise architectures, AWS has made R9g and R9gd instances available in 11 distinct sizing tiers, ranging from nimble single-vCPU entry points to massive bare-metal configurations.

Amazon EC2 R9g Specifications (EBS-Only)

Instance Size vCPUs Memory (GiB) Instance Storage Network Bandwidth (Gbps) EBS Bandwidth (Gbps)
r9g.medium 1 8 EBS-Only Up to 15 Up to 12
r9g.large 2 16 EBS-Only Up to 15 Up to 12
r9g.xlarge 4 32 EBS-Only Up to 15 Up to 12
r9g.2xlarge 8 64 EBS-Only Up to 17 Up to 12
r9g.4xlarge 16 128 EBS-Only Up to 17 Up to 12
r9g.8xlarge 32 256 EBS-Only 17 12
r9g.12xlarge 48 384 EBS-Only 25 18
r9g.16xlarge 64 512 EBS-Only 34 24
r9g.24xlarge 96 768 EBS-Only 50 36
r9g.48xlarge 192 1536 EBS-Only 100 72
r9g.metal-48xl 192 1536 EBS-Only 100 72

Amazon EC2 R9gd Specifications (Local NVMe SSD Storage)

Instance Size vCPUs Memory (GiB) Instance Storage (NVMe SSD) Network Bandwidth (Gbps) EBS Bandwidth (Gbps)
r9gd.medium 1 8 1 x 59 GB Up to 15 Up to 12
r9gd.large 2 16 1 x 118 GB Up to 15 Up to 12
r9gd.2xlarge 8 64 1 x 474 GB Up to 17 Up to 12
r9gd.4xlarge 16 128 1 x 950 GB Up to 17 Up to 12
r9gd.8xlarge 32 256 1 x 1900 GB 17 12
r9gd.12xlarge 48 384 3 x 950 GB 25 18
r9gd.16xlarge 64 512 1 x 3800 GB 34 24
r9gd.24xlarge 96 768 3 x 1900 GB 50 36
r9gd.48xlarge 192 1536 3 x 3800 GB 100 72
r9gd.metal-48xl 192 1536 3 x 3800 GB 100 72

Official Responses and Engineering Insights

In the official product announcement authored by AWS compute specialist Daniel Abib, the emphasis was heavily placed on seamless developer migration pathways and breakthrough security engineering.

"If you’re running workloads on R8g instances today, R9g gives you more performance per vCPU with faster memory, higher network and Amazon EBS bandwidth, and a larger L3 cache, all while using less energy," Abib noted.

AWS has engineered the migration path from R8g to R9g to be frictionless. For the vast majority of enterprise applications, no code refactoring is required. Multi-architecture container images compiled for Arm64 can be deployed directly onto Amazon EKS, ECS, or standard Kubernetes environments without modification.

Furthermore, AWS highlighted the deeper cryptographic and mathematical security assurances woven into the Nitro System. Through the integration of the Nitro Isolation Engine (NIE), AWS has implemented a purpose-built architecture that explicitly mediates all access to virtual machine memory, CPU register states, and I/O devices via a strictly minimized set of application programming interfaces (APIs).

Amazon EC2 R9g and R9gd instances powered by AWS Graviton5 processors are now generally available | Amazon Web Services

By employing formal verification—a rigorous methodology that mathematically proves system code behaves strictly as intended across all possible states, rather than merely passing empirical test cases—AWS has positioned the Nitro System as the cloud industry’s first formally verified hypervisor. This development establishes a rigorous new benchmark for multi-tenant cloud security and strict isolation compliance.


Implications for Enterprise Architecture and Sustainability

The introduction of R9g and R9gd instances carries profound strategic, financial, and environmental implications for global enterprises.

1. Accelerated Cloud Cost Optimization

As economic headwinds prompt IT leaders to scrutinize cloud budgets, the search for maximum compute efficiency has intensified. Because Graviton processors are engineered entirely by AWS to sidestep traditional licensing and architectural bottlenecks, AWS routinely passes cost savings on to consumers. Organizations migrating memory-intensive database tiers and caching clusters from x86 architecture or older Graviton generations can expect immediate reductions in their total cost of ownership (TCO), further tracked via tools like the AWS Graviton Savings Dashboard.

2. Meeting Corporate Net-Zero Targets

With data center energy consumption under increasing regulatory and social scrutiny, sustainability has become a core board-level priority. Graviton5 represents the most energy-efficient processor lineage AWS has ever built. Enterprises shifting compute-heavy, memory-bound workloads to R9g instances will directly reduce their scope 3 carbon footprint associated with cloud infrastructure usage, aligning corporate IT growth with enterprise sustainability commitments.

3. Raising the Bar for Cloud Security Assurance

The integration of formal verification via the Nitro Isolation Engine shifts the paradigm of cloud trust. In regulated industries such as finance, healthcare, and government—where data isolation and protection against hypervisor-level vulnerabilities are paramount—mathematical proof of isolation offers an unassailable audit trail. This effectively removes traditional ambiguities surrounding virtualized multi-tenant boundaries.


Getting Started, Pricing, and Availability

Amazon EC2 R9g and R9gd instances are immediately available in select AWS Regions, including:

  • US East (N. Virginia, Ohio)
  • US West (Oregon)
  • Europe (Frankfurt)

Developers and enterprise architects can deploy these instances via the Amazon EC2 console utilizing supported Arm-based Amazon Machine Images (AMIs), which include Amazon Linux 2023, Amazon Linux 2, Ubuntu 22.04 and newer, Red Hat Enterprise Linux (RHEL) 8.4+, SUSE Linux Enterprise Server 15 SP3+, and Debian 12+.

Purchasing models span On-Demand, Savings Plans, Spot Instances, Dedicated Instances, and Dedicated Hosts. To assist with cross-architecture migrations, AWS provides robust documentation, the AWS Graviton Getting Started Guide, and AWS Transform—an automated code-transformation utility designed to seamlessly transition Java workloads from x86 to Graviton.

As artificial intelligence integration advances, engineers can also interact with technical documentation, regional availability trackers, and API reference materials using the AWS MCP Server and associated plugins within their preferred AI-assisted development environments.