Aller au contenu principal

AWS Graviton


AWS Graviton


AWS Graviton is a family of 64-bit ARM-based CPUs designed by the Amazon Web Services (AWS) subsidiary Annapurna Labs. The processor family is distinguished by its lower energy use relative to x86-64, static clock rates, and omission of simultaneous multithreading. It was designed to be tightly integrated with AWS servers and datacenters, and is not sold outside Amazon.

In 2018, AWS released the first version of Graviton suitable for open-source and non-performance-critical scripting workloads as part of its A1 instance family. The second generation, AWS Graviton2, was announced in December 2019 as the first of its sixth generation instances, with AWS promising 40% improved price/performance over fifth generation Intel and AMD instances and an average of 72% reduction in power consumption. In May 2022, AWS made available Graviton3 processors as part of its seventh generation EC2 instances, offering a further 25% better compute performance over Graviton2.

Origin

The first Annapurna Labs silicon product launched under the AWS umbrella was the AWS Nitro hardware and supporting hypervisor in November 2017. Following on from Nitro, Annapurna began to develop general-purpose CPUs using its expertise.

The benefits AWS anticipated included:

  • Offering more choice in terms of selection of EC2 instances for customers
  • Targeting Arm-based applications
  • Providing high availability and security, while reducing virtualization costs
  • Offering decent server performance with lower prices for customers

The first Graviton processor reached these goals. Graviton2 now offers better performance compared to X86-64: 35% faster running Redis, 30% faster running Apache Cassandra, and up to 117% higher throughput for MongoDB. In addition to higher performance, Graviton offers 70% lower power consumption and 20% lower price.

Graviton

The first Graviton CPU has 16 Cortex A72 cores, with ARMv8-A ISA including Neon, crc, crypto. The vCPUs are physical cores in a single NUMA domain, running at 2.3 GHz. It also includes hardware acceleration for floating-point math, SIMD, plus AES, SHA-1, SHA-256, GCM, and CRC-32 algorithms.

Only the A1 EC2 instance contains the first version of Graviton.

Graviton2

The Graviton2 CPU has 64 Neoverse N1 cores, with ARMv8.2-A ISA including 2×128 bit Neon, LSE, fp16, rcpc, dotprod, crypto. The vCPUs are physical cores in a single NUMA domain, running at 2.5 GHz.

EC2 instances with Graviton2 CPU: M6g, M6gd, C6g, C6gd, C6gn, R6g, R6gd, T4g, X2gd, G5g, Im4gn, Is4gen, I4g. One or more of these instances are available in 28 AWS regions.

Graviton3

The Graviton3 CPU has 64 Neoverse V1 cores, with ARMv8.4-A ISA including 4x128 bit Neon, 2×256 bit SVE, LSE, rng, bf16, int8, crypto. Organized in a single NUMA domain, all vCPUs are physical cores running at 2.6 GHz. Graviton3 has 8 DDR5-4800 memory channels.

Graviton3 provides up to 25% better compute performance, up to 2x higher floating-point performance, up to 2× faster cryptographic workload performance, up to 3× better performance for machine learning workloads including support for bfloat16, and 50% more memory bandwidth compared to AWS Graviton2 processors. Graviton3-based instances use up to 60% less energy for the same performance than comparable EC2 instances.

Graviton3E is a higher power version of Graviton3.

EC2 instances with Graviton3 CPU: C7g, M7g, R7g; with local disk: C7gd, M7gd, R7gd.

EC2 instances with Graviton3E CPU: C7gn, HPC7g.

Graviton4

The Graviton4 CPU has 96 Neoverse V2 cores, with ARMv9.0-A ISA. It has 2 MB of L2 cache per core (192 MB total), and 12 DDR5-5600 memory channels. Graviton4 supports Arm's Branch Target Identification (BTI).

Amazon claims that Graviton4 is up to 40% faster for databases, 30% faster for web applications, and 45% faster for large Java applications than the Graviton3.

EC2 instances with Graviton4 CPU: R8g.

Collection James Bond 007

See also

  • Annapurna Labs, the chip-design subsidiary of the AWS organization.
  • Timeline of Amazon Web Services for launch dates.
  • Fujitsu Fugaku, a supercomputer using the A64FX CPU implementing ARMv8.2-A.
  • Ampere Altra, a 64-bit ARM datacenter processor family implementing ARMv8.2-A deployed on Google Cloud Platform, Microsoft Azure, and Oracle Cloud.
  • NVidia Grace CPU with 144 cores in 2 NUMA domains.

External links

  • Official website
  • AWS: AWS Graviton Technical Guide
  • Dev.to: Large System Extensions for AWS Graviton Processors
  • Arm: Gain up to 35% performance benefits for deploying Redis on AWS Graviton2
  • Arm: Gain up to 30% Cost-Performance benefits for Apache Kafka on AWS Graviton2 Processors
  • AWS: AWS Lambda Functions Powered by AWS Graviton2 Processor – Run Your Functions on Arm and Get Up to 34% Better Price Performance
  • AWS: Announcing AWS Graviton2 Support for AWS Fargate – Get up to 40% Better Price-Performance for Your Serverless Containers

References



Text submitted to CC-BY-SA license. Source: AWS Graviton by Wikipedia (Historical)



INVESTIGATION