Pace of Innovation for Custom Silicon on Arm Continues with AWS Graviton4
It’s been said that the best way to predict the future is to create it. This anecdote is clearly reflected in the data center and infrastructure market we see today being built on Arm. Ten years ago, no one had heard of a data processing unit (DPU); and it was early days for the Arm CPU server market. But some insightful and innovative people at Amazon had the vision to see where compute was heading, and that vision led to investments and partnerships and to what we now know today as AWS Nitro – one of the first true DPUs – and AWS Graviton – the first CPU custom-built by a hyperscale cloud provider.
Both represented the future of purpose-built infrastructure for the era of AI and workload-optimized computing we see clearly emerging at scale today. Having worked closely with AWS for almost 10 years, it’s fantastic to see what they have brought to market. This collaboration between AWS and Arm is at the forefront of driving the transformational changes we are seeing in the datacenter.
Today, we celebrate another major milestone as AWS announces a new Neoverse-based CPU, the AWS Graviton4. This marks the fourth Graviton CPU in five years – an incredible pace of innovation, and proof of the advantages of building custom silicon on Arm. Graviton4 supports 50 percent more cores and up to 75 percent more memory bandwidth per CPU compared to its predecessor, AWS Graviton3. These capability upgrades result in some very impressive performance improvements – up to 30 percent faster for web applications, 40 percent for databases, and 45 percent for large Java applications.
According to AWS, Graviton4 is the most powerful and energy efficient chip they have ever built. Best of all? Across their entire fleet, Graviton4 delivers the best performance and energy efficiency for a broad range of workloads running on Amazon EC2.
AWS also announced the first instance family using Graviton4, the Amazon EC2 R8g. EC2 R8g instances are ideal for memory-intensive workloads such as open-source databases and real-time big data analytics. With these instances, AWS is able to deliver the best price-performance for memory-intensive workloads. R8g instances are available in preview today, and customers can request access here.
We are very excited about this announcement and the foundational role Arm technology plays in helping AWS customers improve performance while reducing their monthly cloud computing costs and carbon footprint. Congratulations to AWS and the team at Annapurna Labs for continuing to push the pace of custom silicon innovation on Arm.
The announcement of AWS Graviton4 builds on what has been a monumental year for Arm Neoverse and our mission to drive a transformation in the world’s computing infrastructure. From Marvell unveiling their OCTEON 10 Fusion Processor family for 5G networks, to Ampere shipping their next-generation AmpereOne cloud-native CPU, to SiPearl “Rhea” being selected to power Europe’s first Exascale supercomputer, Arm helped drive choice and innovation across all infrastructure segments. The software ecosystem grew by leaps and bounds as well, with Snowflake, Databricks, SAP Hana, Oracle Database, and Stripe, to name a few, announcing Arm support. NVIDIA began shipping Grace CPU and Grace-Hopper Superchips for powering next-generation AI datacenters, and Microsoft announced their own Arm-powered custom silicon CPU, the Cobalt 100, based on Arm Neoverse CSS.
As exciting as 2023 has been, we’re even more excited about what is over the horizon for Arm and our partners. Computing infrastructure is firmly stepping into the AI era and data centers are being reimagined top-to-bottom and optimized for the ML-based workloads that will define the coming decades. The market leaders of this transition are choosing Arm Neoverse as their computing foundation for the performance, efficiency and unmatched flexibility we provide alongside an unparalleled software and silicon ecosystem – the future is being built, today, on Arm.
Any re-use permitted for informational and non-commercial or personal use only.
Editorial Contact
Latest on Twitter
Meet the SpiNNaker2, @SpiNNcloud's brain-inspired hybrid AI processor powered by Arm Cortex-M4.
It's delivering algorithms 10x more efficient than conventional AI, with our Arm Flexible Access for Startups Program helping to make this a reality: https://okt.to/jCyUc3
AI 🤝 IoT
As AI touches a growing number of connected applications, developers are turning to our software ecosystem for innovation and a consistent experience.
@pnwilliamson shares insights into AI in the embedded space at Embedded World.
We've done it again with record revenue in Q4! 🚀
As we build upon our power efficient CPU, Q4 saw us unlock new levels in royalty revenue and licensing growth. With 280+ bn Arm-based chips shipped to date, the future is built #onArm.
In April, we celebrated Neurodiversity Awareness Month with internal events including a session on parenting children with neurodiverse needs.
This is part of our ERGs efforts to create a supportive community that allows everyone to thrive and reach their full potential.
🤝 We're taking our partnership with @GoogleCloud to the next level.
Axion processors, built #onArm Neoverse V2, are the newest example of how we're working together to optimize for workload performance and efficiency.
@AwadMo shares the details. 👇
👇 Get started with ExecuTorch Alpha for optimal performance of LLMs on the CPU, alongside delegation to GPU and NPU.
With LLMs already running on our efficient CPUs, our close partnership with @PyTorch is making this easier on @Meta’s Llama 2, 3 and other broad models.
We recently released the first episode of our new 'In Conversation With...' series.
Hear from renowned computer scientist and engineer Sophie Wilson as she discusses co-designing the first Arm processor and the importance of 'making things'.
Watch now 👉 https://okt.to/5ozcsy
'@Simprints fingerprint scanning solution, SimprintsID makes it easier to verify individual vaccinations using digital records rather than physical ID.
With 850M people without formal ID, this solution, built #onArm, is game-changing for healthcare equity.
#HealthierTogether
📅 Join us on Wednesday May 8 for our financial results conference call.
After market close, we'll report our results for the fourth quarter of fiscal year 2024, followed by an audio webcast discussing our business outlook.
Details ➡️ : https://okt.to/58GW2q
"Hello World, I am ARM"
39 years ago today, the first Arm microprocessor introduced itself. We've since enabled advanced, efficient computing in 280+ billion chips, with the patents to prove it.
These foundations make us the AI platform the world relies on, today & in the…
By building #onArm Neoverse, @GoogleCloud's Axion processors are well-suited for the age of AI, benefitting from:
⚡ Higher performance
🔋 Lower power consumption
⬆️ Greater scalability
@AwadMo shares why. 👇
Full interview: https://okt.to/0LPnpo
As the number of connected devices grows, so does the need for more edge compute solutions. 🚀
This is where @LinaroOrg's ONELab comes in.
Designed as a collaborative initiative, it's making it easier to build cloud-native edge deployments #onArm:
Our graduate scheme produces many exceptional engineers. Omar Ali is a great example. His impact goes far beyond his technical skills.
So, it was no surprise he was a finalist for the Rising Star Award at the @targetjobsUK National Graduate Recruitment Awards. Congrats, Omar!
Congratulations to Tamika Curry Smith, our Chief DEI Officer who has been chosen as one of @SavoyNetwork's Most Influential Executives in Corporate America for 2024. 👏
The honor recognizes Tamika's commitment to community, leadership, and success: https://okt.to/2NvDOZ
This #EarthDay, we're celebrating our collaboration with @UNICEF, to unlock the life-changing potential of technology in Malawi.💧
Our investment has helped UNICEF install two water supply systems, helping provide 11,000 people with access to safe water and sanitation services.
ISA parity is accelerating silicon and software deployment in automotive! 🚗💨
👇 At #ew24 we showcased what this looks like in practice via virtual platforms with our Neoverse-based cloud instances and new Arm AE IP, which brings almost 100% ISA parity. https://okt.to/cjVaFN
The future of automotive is here. 🚀
Hear from Dipti Vachani on @IBDinvestors as she shares details on the game-changing performance and functional safety features of our new Armv9-based AE processors and server-class Neoverse technology: https://okt.to/WVtw58
AI is expected to increase data center power consumption 3️⃣x by 2030.
To offset this, hyperscalers like Amazon and Google turn to Arm Neoverse to reduce power without compromising performance.
That's why the future of AI is built #onArm. https://okt.to/LPVFWd
We're working with our partners @Simprints, @Gavi and @_GHSofficial to enable healthcare equity in Ghana.
Built #onArm, Simprints technology is enabling vaccine equity by making it easier to verify vaccine delivery by individual: https://okt.to/MIcgxu
If Arm technology is in there, then the future will be too.
Our energy-efficient compute platforms are foundational to the world's technology and AI computing, shaping how we work, play and connect.
That's why the future is built #onArm. https://okt.to/M9wqc8
Here's to a fantastic week at Embedded World! 🎉
From lightning talks and speaker sessions to demos of our latest automotive and IoT technologies, we brought our vast ecosystem together to showcase what's possible when you build #onArm.
Thank you to everyone that joined us. 👏
🚗 Software-defined vehicles (SDVs) are the future of automotive and they're being built #onArm.
Robert Day joins @Sonatus and @MotorTrend on the latest podcast to talk all things SDVs and where the industry is headed.
🔊👇 Listen below.
🏆 And the winner of the Embedded Awards 2024 goes to… @Ambiq_AI's Apollo510 MCU!
This winning tech opens the door to new local AI opportunities on billions of devices.
Listen in as the team talk us through their exceptionally efficient Arm-based SoCs at #EmbeddedWorld.
David Maidment recently shared his thoughts on the future of edge computing at #EmbeddedWorld!
Missed the talk? Catch up on his insights into the evolution of edge computing across billions of diverse connected devices to build a secure AI-enabled future: https://okt.to/EtfSRN
