What you missed from the Open Source Summit North America 2022

Over 1,200 people gathered in a baking hot Austin to talk about open source. We were there too, showing Intel code optimizations and enabling, plus Intel’s support of the open source ecosystem. 

If you missed the conference, the session videos are now available online.    

Announcements

The Open Programmable Infrastructure (OPI) project was unveiled at this event by conference organizers Linux Foundation, with support from many hardware and software vendors, including Intel.  The OPI seeks to help define the architecture and frameworks for the Data Processing and Infrastructure Processing Unit (DPU and IPU) software stacks that can be applied to any vendor’s hardware offerings. The OPI Project also aims to foster a rich open source application ecosystem, leveraging existing open source projects, such as Data Plane Development Kit (DPDK), Storage Performance Development Kit (SPDK), Open vSwitch (OvS), P4 programming language, etc., as appropriate.

Sessions

We had seven sessions at OSS and co-hosted events, and a keynote.  All these videos can be quickly accessed from a playlist.  

• Discovering Toolchains Victor Rodriguez, Software Engineer 
• Computer Vision to Secure Your Surroundings with AI/ML Solution Built Using Open Source Tools  
  Samantha Coyle, Software Engineer ¦ Neethu Elizabeth Simon, Senior Software Engineer 
• Application AutoScaling Through Elastic Kubernetes POD  
  Cathy Zhang, Senior Principal Engineer ¦ Theresa Shan, Senior Software Engineer 
• Lessons Learned Creating A Robust, Hardened, Kernel Driver for A Hardware Device   
  Fiona Trahe, Senior Software Engineer ¦ Adam Guerin, Device Driver Engineer  
• Hardening the Linux Guest for the Confidential Cloud Computing: Deep Dive and Results Elena Reshetova, Intel 
• Securing Open Source Software - End-to-End, at Massive Scale, Together   
  Christopher R Robinson,  Ambassador of Intel Product Assurance and Security ¦ Anne Bertucio, Senior Program Manager, Google 
• Converting an Old-school Textile Inspection Machine into a Smart System Using AI/ML   
  Neethu Elizabeth Simon, Senior Software Engineer ¦ Scott Thomas, Solutions Architect 
• Keynote: The Future of Open Source is Trust  
  Arun Gupta, Vice President & General Manager, Open Ecosystem Initiatives 

Demos

We cycled through three different demos in the booth over three days, showcasing Intel code optimizations and enabling and Intel’s support of the open source ecosystem. 

• Intel optimized code for your workflows - With code you can use, Intel Optimizations for popular open source projects like WordPress, NGINX, TensorFlow, PyTorch and HAProxy are conveniently packaged by Bitnami for use in your workflows, and GPU and XPU path tracing rendering, featuring Intel^® Open Image Denoise from the Intel® oneAPI Rendering Toolkit (Render Kit), is providing real time feedback as you create. 
• Intel is investing in key open source technologies - Intel reaffirms its commitment to open source, with recent hiring of open source software teams, such as Linutronix, Codeplay, and the Open Networking Foundation engineers.  The ONF team will be showing how Project Pronto, based on Aether, can provide a network for autonomous drones, showing resiliency in the face of denial-of-service attacks. 

Many thanks to all our demo owners, who were prepared, present on time, ready to demo, and very engaged with attendees.  

1. If You Want To Be A Winner, Adopt the Intel Optimization Philosophy Now! (Olu Ajayi, Anil Pakkala) Explore the ready-to-run optimized NGINX for Intel packaged on Bitnami with the enhanced Intel software stack to deliver breakthrough performance on the 3rd Gen Intel® Xeon® Scalable Processor platform.  Attendees were encouraged try out the Intel optimized NGINX image from Bitnami in their production environment.  
2. Intel(R) oneAPI Rendering Toolkit – Embree and Open Image Denoise (Adam Duran, Alok Hota) The demo showed a path tracer written in SYCL*, performing real time rendering using CPU and GPU.  With Embree and SYCL, this renderer has a single code path that runs everywhere, CPU or GPU, on your workstation or in a render farm. Full film quality ray trace can be rendered in real time, without having to wait hours for results, increasing engagement and productivity.  We raised awareness of the Intel(R) oneAPI Rendering Toolkit  and potential for inclusion of the renderer into other projects.
3. Project Pronto  (Woojoong Kim, Hungwei Chiu) demonstrates an open source end-to-end 5G connected edge cloud as a programmable, verifiable network with closed loop control;  based on Aether, the first open source 5G Connected edge platform to enable enterprise digital transformation.  This Project Pronto demo showed the result of a proof of concept engagement with DARPA for a network for autonomous drones, showing resiliency in the face of denial-of-service attacks, and also emphasized Intel’s commitment to the open source ecosystem with the hiring of the Open Network Foundation engineers.  

This was the first Linux Foundation event I attended in person after a several year gap and it was a wonderful opportunity to get back out meeting people, old friends and new acquaintances alike. Kudos to the open.intel team, speakers and demo staffers for making the event very successful. 
I'm looking forward to seeing what gets presented at the Open Source Summit in Dublin, Ireland in September - raise a beer for me!  

About the author

Chris Norman is an Open Source Advocate who has promoted the use of open source ecosystems for over a decade.  You can find him as pixelgeek on Twitter, IRC and GitHub.