Hey Reader
Welcome to Issue # 15 of AWS Graviton Weekly, which will be focused on sharing everything that happened in the past week related to AWS Silicon: from December 9th, 2022, to December 16th, 2022.
After the re:Invent crazy week, this week is less challenging, but still with a great pack of news and resources related to the AWS Silicon universe.
Actually: if you pay attention, you will see that Graviton has more presence everywhere:
So, the Graviton wave is coming stronger than ever my friend.
BTW: if you are using Graviton in your organization, or you are planning to use it, let me know. I would love to hear more.
Reply to this email if you want to chat about it.
Now, enjoy the content.
News
Amazon Elastic Container (Amazon ECS) Service Connect now supports AWS Fargate workloads running on AWS Graviton Processors. Service Connect simplifies service discovery, connectivity and traffic observability for Amazon ECS and helps you build applications faster by letting you focus on the application code instead of your networking infrastructure.
Read the documentation here
Marco Botros, (a Technical Product Manager at Rapid7) announced that the Insight Agent now supports the AWS Graviton processor.
Among the indicators of Ampere Computing growth indirectly, and ARM directly, is the continued expansion of AWS Graviton. Like Ampere Computing, Graviton uses the ARM architecture. Adoption of Graviton within AWS is a good signal for interest and willingness of companies to shift from x86 to ARM-based chips like what Ampere Computing offers.
Liftr Insights has tracked the growth of AWS Graviton from the first generation to the latest generation released this year. Graviton has grown 20% over the past 6 months according to Liftr Insights data.
Announcing General Availability (GA) of Linux and K8s Agents v22.3 for Cloud Workload Security, by Rich Bosworth (Director of Product Marketing at SentinelOne)
The SentinelOne Kubernetes agent now supports the AWS Graviton-based EC2 instances. Our Linux agent achieved the AWS Graviton Ready Service Designation back in July 2022.
Extending that support to Kubernetes clusters was a logical next step. The arm64 architecture of Graviton brings with it some compelling efficiency gains which make it very attractive to compute-intensive workloads. Singularity Cloud Workload Security for Kubernetes stands ready to deliver runtime workload protection to your Graviton-based clusters.
Vice president of ML and AI Services says more than 100,000 customers are doing machine learning on AWS.
Articles and Tutorials
Accelerating SDV development with KPIT Cloud-Native Engineering Workbench on AWS, by Sushant Dhamnekar ( a Senior Solutions Architect at AWS), Stefano Marzani (Senior Solutions Architect at AWS) and Vijay Balani (Principal Architect - SDV Middleware at KPIT)
This blog post will elaborate how use of AWS Graviton-based hardware bit parity environment and continuous integration/continuous deployment (CI/CD) pipelines in KPIT’s Cloud-Native Engineering Workbench solution is accelerating SDV development globally. We will walk you through a diagnostic use case.
The Stack counted over 119 new AWS services and features landing during the cloud hyperscaler’s re:Invent 2022 conference. Many were jargon-dense. We mainlined some coffee and reviewed every single one.
Our goal was to distil each release into clear synopses of ~30 words for time-poor readers – and also to get a sense, whilst doing so, of thematic/strategic direction amidst the barrage of new AWS products.
Graviton3E: Here’s what you need to know about the new AWS chip unveiled at reInvent, by Dashveenjit Kaur (Senior Tech Reporter at Tech Wire Asia & TechHQ)
The latest Graviton3E, according to AWS utility computing senior VP Peter DeSantis, is made with noticeable performance improvements over the standard Graviton3, sustaining over 35% better performance for vector-based workloads.
Exafunction supports AWS Inferentia to unlock best price performance for machine learning inference, by Nicholas Jiang (Software Engineer at Exafunction), Jonathan Ma (Software Engineer at Exafunction), Prem Nair (Software Engineer at Exafunction), Anshul Ramachandran (Software Engineer at Exafunction), Shruti Koparkar (Sr. Product Marketing Manager at AWS), Max Liu (Principal Specialist, AWS), Jianying Lang (Principal Solution Architect, AWS) and Kamran Khan (Sr Technical Product Manager, AWS)
Across all industries, machine learning (ML) models are getting deeper, workflows are getting more complex, and workloads are operating at larger scales. Significant effort and resources are put into making these models more accurate since this investment directly results in better products and experiences.
On the other hand, making these models run efficiently in production is a non-trivial undertaking that’s often overlooked, despite being key to achieving performance and budget goals. In this post we cover how Exafunction and AWS Inferentia work together to unlock easy and cost-efficient deployment for ML models in production.
Slides, Videos and Audio
[VIDEO] What’s New About AWS Graviton, by Arthur Petitpierre (EC2 Graviton Principal Specialist Solutions Architect at AWS)
At Unblock ‘21, Graviton Principal Specialist Solutions Architect Arthur Petitpierre presented the second generation of AWS processors, the AWS Graviton2.
Since then, AWS has released a third gen AWS processor, the AWS Graviton3. During his talk, Arthur will share what’s new and how improvements have been made to the power efficiency and performance. You can benefit from Graviton3 for your CI workloads with Buildkite. Unblock Unblock is Buildkite’s annual CI/CD conference. The two-day virtual conference brings together engineering and infrastructure leaders solving some of the most interesting challenges in software.
Learn more:
[VIDEO] Building and operating at scale with feature management, by John Kodumal (CTO at LaunchDarkly)
LaunchDarkly explains here how they migrated to Graviton based infrastructure, saving $91k USD for just one service.
[VIDEO] Optimizing price performance with feature management and observability, by Charity Majors (CTO at Honeycomb.io ) and Brian Rinaldi (Developer Experience Engineer at LaunchDarkly)
When AWS launched AWS Graviton2–based instances on Amazon EC2 and AWS Lambda functions in 2021, Honeycomb used progressive delivery techniques and observability to confidently migrate its workloads away from x86-64 architectures to Arm64-based instances on Amazon EC2.
The result? For a lower cost and with 30 percent fewer instances (meaning less environmental impact), Honeycomb was able to expand workload usage by 10 times and reduce latency by 30 percent: a win-win for Honeycomb and their customers. This session covers migration techniques that combine observability with Honeycomb and feature management with LaunchDarkly to progressively deliver a faster and less costly application architecture on a live production workload. This presentation is brought to you by LaunchDarkly, an AWS Partner.
Watch how Novus is using Graviton thanks to Caylent's helping to make the move.
[VIDEO] Keynote: AGL State of the Alliance: Looking Toward 2023 and Beyond by Dan Cauchy (Executive Director, Automotive Grade Linux & General Manager of Automotive, The Linux Foundation)
In this session, The Linux Foundation's Automotive Grade Linux (AGL) project announced they are working to add support for Graviton processors.
[LIVESTREAM] Under The Hood w/AWS Compute: Year In Review & re:Invent 2022 Recap, with Lorenzo Winfrey (Senior Specialist, Business Development Manager & GTM (Compute) at Amazon Web Services) and Martin Yip (Head of Product Marketing, EC2 Compute and Networking at AWS)
This is a full recap of everything announced at re:Invent 2022 related to everything related to Compute, including the new Graviton based instances as well. Highly recommended !!!
Jobs
Events
No events in the time of the year
Quote of the day
With Graviton, we saw that the industry is moving in a direction of utilizing ARM chipsets and we understood that for a long-term investment in terms of savings, we need to be able to support that.
We didn't necessarily move our entire platform, in fact we use a mix of both ARM and AMD Spot Instances, we just understood that we didn't we wanted the option to use ARM when available.
We first moved our MySQL databases on RDS to Graviton without any kind of impact that we could perceive and so the next step was to move our applications to Graviton.
There was really no change needed in our application it was just a matter of getting the Docker containers to be able to run on either type of node .
Uh, it's slightly less expensive in the Spot Instances type, of course spot instances price fluctuate so you keep an eye on that but it gave us about a couple of percentage points like 5 to 10 percent of savings on the Spot instances.
Noah Zucker, Head of Platform at SEI Novus. Source: Caylent