Hey Reader
Welcome to Issue # 11 of AWS Graviton Weekly, which will be focused on sharing everything that happened in the past week related to AWS Graviton: from November 11th, 2022 to November 18th, 2022.
This week, I've had the pleasure to meet and hang out with incredible folks in the AWS Security Day 2k22 here in Lima, Peru.
It was my first in-person event since 2019, and from my point of view, it was a huge success and showed the incredible health of the AWS community here in the country and in the region as well.
Thanks to Gerardo, Dario, and the whole crew behind the organization of the event. We need more events like this. Seriously.
To check out the posts related to the event, feel free to use the #awssecurityday2k22 hashtag on LinkedIn.
If you want to see some of the talks, you can watch them here in its YouTube channel.
Now, back to Graviton news, this week I participated in an incredible livestream with Will Koplitz (Solution Architect from AWS) and JP Robinson (Staff Engineer at Datadog), where they discussed Datadog's journey to use Graviton based infrastructure.
Serious Tip: Your technical knowledge will be challenged here, so feel free to take your notes.
And don't miss the post from Lewis Monteith, co-founder of Squeaky, where he explained the entire process how the company migrated all components of its architecture to Graviton based infrastructure (AWS Fargate + Ruby on Rails + ClickHouse).
Enjoy !!!
This issue is sponsored by Deel
Deel is your one-stop shop for hiring, paying, and managing your remote team.
Thye will help your company to stay on top of local labor laws across the world to ensure compliance and mitigate risk so that you don't have to.
News
Articles and Tutorials
How switching to AWS Graviton slashed our infrastructure bill by 35%, by Lewis Monteith, co-founder of Squeaky
Aerospike 6.2 on AWS Graviton2 significantly reduces total cost of ownership: An image worths more than just words
AWS Graviton3 improves Cadence EDA tools performance for Arm, by Tim Thornton (Director of ARM Based Engineering at ARM)
Optimized Video Encoding with FFmpeg on AWS Graviton Processors, by Jonathan Swinney (Software Development Engineer at AWS)
When the AWS Graviton2 instances were introduced, they provided 40% better price performance for many workloads, compared to similar x86 Amazon EC2 instances. Graviton3 features an additional 25% improved performance over Graviton2.
Video processing and transcoding has been growing in importance, and Graviton is well suited for this workload. AWS engineers and the open source community have worked on video encoding tools, such as FFmpeg and the codec libraries, to further optimize for Graviton.
You can get these improvements on GitHub from a build in the development branch of FFmpeg, or use FFmpeg version 5.2 when it is released.
Run machine learning inference workloads on AWS Graviton-based instances with Amazon SageMaker, by Victor Jaramillo, PhD, Zmnako Awrahman, PhD, Sunita Nadampalli, Johna Liu and Alan Tan from the AWS team
Practical tricks and tips to reduce AWS EMR costs, by Wenhe Ye, Software Development Manager at Adevinta
How to reduce 40% cost in AWS Lambda without writing a line of code!, by Turan Seza Akgün (Senior Software Engineer at Insider).
Hint?
Runtime Architecture is changed from X86_64 to ARM64. This results in no visible performance increase for our case but AWS charges 25% less for ARM64 so we went with it.
AWS libcrypto (AWS-LC): a general-purpose cryptographic library maintained by the AWS Cryptography team for AWS and their customers. It іs based on code from the Google BoringSSL project and the OpenSSL project. The project is using AWS Graviton processors to test ARMv8 optimizations
How I Found a Go Issue on ARM that Crashed the Database Server, by Kangli Mao fron PingCAP
Slides, Videos and Audio
[VIDEO] Under the hood with AWS Compute - Hear from AWS partner Datadog on their Graviton Journey with Will Koplitz (Senior Specialist Solutions Architect - Graviton - ISVs at AWS), and JP Robinson (Staff Engineer at Datadog). Again: Highly recommended. BTW, they mentioned this interesting talk from KubeCon: Building Container Images In Kubernetes: It’s Been a Journey! - Laurent Bernaille & Eric Mountain from Datadog. Very interesting as well.
[VIDEO] Graviton Workloads | The Keys to AWS Optimization | S5 E8 with Will Koplitz (Senior Specialist Solutions Architect - Graviton - ISVs at AWS), John Masci (AWS Strategic Accounts at AWS) and Rem Baumann (Commercial Architect at AWS).
[VIDEO] AWS re:Invent 2020: Snap Inc.: Leveraging the benefits of AWS Graviton on Amazon EKS, by Aaron Sheldon (Software Engineer at Snap, Inc) and David Murray (former Principal Software Engineer at AWS, and CTO at To the Moon PR)
[PODCAST] Episode #103 Developer Tools Designed to Make AWS Easy, with Stephen Barr (Chief Technical Evangelist at DevGraph) and Jon Myer from the Jon Myer Podcast. Listen on Spotify, Apple Podcasts or watch it on YouTube
Jobs
Events
Building real-time applications to utilize AWS Graviton: this interesting article from Matt Bushell (Sr. Director of Product Marketing at Aerospike) explained how Fidelity and Wix.com use Aerospike on top of AWS Graviton to build real-time apps. They will give a session at the upcoming reInvent 2022 called Building real-time applications to utilize AWS Graviton (Session ID # PRT246). Speakers: Tal Gabay ( Engineering Manager, Wix.com), Raj Pai (Vice President, AWS), Subbu Iyer (President and CEO, Aerospike), and Kyle Bush( VP, Data Analytics Architecture, Fidelity Investments)
Sustainability in the cloud with Rust and AWS Graviton (Tuesday, November, 29th ), with Emil Lerch (Principal DevOps Specialist at AWS) and Esteban Kuber (Principal Software Engineer at AWS)
AWS Graviton adoption by Honeycomb.io using Amazon EC2 and AWS Lambda, by Sunil Ramachandra (Sr.Solutions Architect at AWS) and Pierre Tessier (Director of Solution Architects at Honeycomb.io) (Monday, November 28th , 4:45 PM - 5:45 PM PST & Tuesday, November 29th , 5:00 PM - 6:00 PM PST )
Accelerating machine learning inference on AWS Graviton CPUs, by Ashok Bhat (Senior Product Manager at ARM) and Milos Puzovic (Principal Software Engineer, Arm) in the SC 22:
Over the last few years, machine learning (ML), more specifically deep learning (DL), has become important for the HPC community. DL uses frameworks like TensorFlow and PyTorch, which use underlying hardware features for better performance. In this session, learn about how DL frameworks use ML-specific Arm architecture features like BFloat16 for faster inference on AWS Graviton3 compared to other platforms.
Quote of the week
We’re strong believers in continuously improving tools and process, and that’s really paid off this time.
By having all our apps running the latest versions of languages, frameworks and dependencies, we’ve been able to switch over to brand new infrastructure with almost zero code changes.
Switching our entire operation over to Graviton only took one day and we’ve saved approximately 35% on our infrastructure costs.
When comparing our CPU and memory usage, along with latency metrics, we’ve seen no performance degradation. In fact, our overall memory footprint has dropped slightly, and we expect to see further improvements as the month rolls on.
It’s fair to say we're all-in on ARM, and any future pieces of infrastructure will now be powered by Graviton.
Lewis Monteith, Co-founder and CEO of Squeaky
Deel is global payroll and compliant hiring for remote teams. That means anyone, anywhere can get hired and paid with Deel.
Using a tech-enabled self-serve process, companies can instantly hire full-time employees or independent contractors across the world legally, in minutes.
With Deel, companies can take care of payroll and create localized legal contracts in over 150 countries. Teams even get the freedom to choose how they withdraw their funds. Deel does it all.
