AWS Graviton is a family of

64-bit In computer architecture, 64-bit integers, memory addresses, or other data units are those that are 64 bits wide. Also, 64-bit central processing units (CPU) and arithmetic logic units (ALU) are those that are based on processor registers, a ...

ARM-based

CPU A central processing unit (CPU), also called a central processor, main processor, or just processor, is the primary processor in a given computer. Its electronic circuitry executes instructions of a computer program, such as arithmetic, log ...

s designed by the

Amazon Web Services Amazon Web Services, Inc. (AWS) is a subsidiary of Amazon.com, Amazon that provides Software as a service, on-demand cloud computing computing platform, platforms and Application programming interface, APIs to individuals, companies, and gover ...

(AWS) subsidiary Annapurna Labs. The processor family is distinguished by its lower energy use relative to

x86-64 x86-64 (also known as x64, x86_64, AMD64, and Intel 64) is a 64-bit extension of the x86 instruction set architecture, instruction set. It was announced in 1999 and first available in the AMD Opteron family in 2003. It introduces two new ope ...

, static

clock rate Clock rate or clock speed in computing typically refers to the frequency at which the clock generator of a processor can generate pulses used to synchronize the operations of its components. It is used as an indicator of the processor's s ...

s, and lack of

simultaneous multithreading Simultaneous multithreading (SMT) is a technique for improving the overall efficiency of superscalar CPUs with hardware multithreading. SMT permits multiple independent threads of execution to better use the resources provided by modern proces ...

. 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 High availability (HA) is a characteristic of a system that aims to ensure an agreed level of operational performance, usually uptime, for a higher than normal period. There is now more dependence on these systems as a result of modernization ...

and security, while reducing

virtualization In computing, virtualization (abbreviated v12n) is a series of technologies that allows dividing of physical computing resources into a series of virtual machines, operating systems, processes or containers. Virtualization began in the 1960s wit ...

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 Redis (; Remote Dictionary Server) is an in-memory key–value database, used as a distributed cache and message broker, with optional durability. Because it holds all data in memory and because of its design, Redis offers low- latency reads ...

, 30% faster running

Apache Cassandra Apache Cassandra is a free and open-source software, free and open-source database management system designed to handle large volumes of data across multiple Commodity computing, commodity servers. The system prioritizes availability and scalab ...

, and up to 117% higher throughput for

MongoDB MongoDB is a source-available, cross-platform, document-oriented database program. Classified as a NoSQL database product, MongoDB uses JSON-like documents with optional database schema, schemas. Released in February 2009 by 10gen (now 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 ARM (stylised in lowercase as arm, formerly an acronym for Advanced RISC Machines and originally Acorn RISC Machine) is a family of RISC instruction set architectures (ISAs) for computer processors. Arm Holdings develops the ISAs and lice ...

ISA including

Neon Neon is a chemical element; it has symbol Ne and atomic number 10. It is the second noble gas in the periodic table. Neon is a colorless, odorless, inert monatomic gas under standard conditions, with approximately two-thirds the density of ...

, crc,

crypto Crypto commonly refers to: * Cryptography, the practice and study of hiding information * Cryptocurrency, a type of digital currency based on cryptography Crypto or krypto may also refer to: Cryptography * Cryptanalysis, the study of methods f ...

. The vCPUs are physical cores in a single

NUMA Numa or NUMA may refer to: * Non-uniform memory access (NUMA), in computing Places * Numa Falls, a waterfall in Kootenay National Park, Canada * 15854 Numa, a main-belt asteroid United States * Numa, Indiana * Numa, Iowa * Numa, Oklahoma * ...

domain, running at 2.3 GHz. It also includes hardware acceleration for

floating-point math In computing, floating-point arithmetic (FP) is arithmetic on subsets of real numbers formed by a ''significand'' (a signed sequence of a fixed number of digits in some base) multiplied by an integer power of that base. Numbers of this form ...

SIMD Single instruction, multiple data (SIMD) is a type of parallel computer, parallel processing in Flynn's taxonomy. SIMD describes computers with multiple processing elements that perform the same operation on multiple data points simultaneousl ...

, plus AES,

SHA-1 In cryptography, SHA-1 (Secure Hash Algorithm 1) is a hash function which takes an input and produces a 160-bit (20-byte) hash value known as a message digest – typically rendered as 40 hexadecimal digits. It was designed by the United States ...

SHA-256 SHA-2 (Secure Hash Algorithm 2) is a set of cryptographic hash functions designed by the United States National Security Agency (NSA) and first published in 2001. They are built using the Merkle–Damgård construction, from a one-way compressi ...

, GCM, and

CRC-32 Computation of a cyclic redundancy check is derived from the mathematics of polynomial division, modulo two. In practice, it resembles long division of the binary message string, with a fixed number of zeroes appended, by the "generator polynom ...

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

, LSE,

fp16 In computing, half precision (sometimes called FP16 or float16) is a binary floating-point computer number format that occupies 16 bits (two bytes in modern computers) in computer memory. It is intended for storage of floating-point values in a ...

, rcpc, dotprod, crypto. The vCPUs are physical cores in a single

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 4×128 bit

, 2×256 bit SVE, , rng,

bf16 The bfloat16 (brain floating point) floating-point format is a computer number format occupying 16 bits in computer memory; it represents a wide dynamic range of numeric values by using a floating radix point. This format is a shortened (16-bi ...

, , crypto. Organized in a single

domain, all vCPUs are physical cores running at 2.6 GHz. Graviton3 has 8 DDR5-4800 memory channels. Compared to Graviton2, Graviton3 provides up to 25% better compute performance, up to 2× higher floating-point performance, up to 2× faster cryptographic workload performance, up to 3× better performance for

machine learning Machine learning (ML) is a field of study in artificial intelligence concerned with the development and study of Computational statistics, statistical algorithms that can learn from data and generalise to unseen data, and thus perform Task ( ...

workloads including support for bfloat16, and 50% more memory bandwidth. 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 plus the SVE2-crypto extension. 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, X8g, C8g, M8g, I8g.

References

External links

* * AWS
AWS Graviton Technical Guide
* List of Independent Software Vendor (ISV) products publicly listing arm64/Graviton support

* 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
{{Application ARM-based chips, state=expanded ARM-based systems on chips Amazon (company) hardware Amazon Web Services