Hi Ildiko, I'm a Cyborg core. I think it's cool to promote the integration of Cyborg and Zun. I'm happy to push the whole thing if I could. Zun's PTL Shengqin Feng is my colleague. I suggest you send her and me a reminder email before the meeting. Her Email: feng.shengqin@zte.com.cn Thanks, Ke Chen At 2021-08-31 22:39:01, "Ildiko Vancsa" <ildiko.vancsa@gmail.com> wrote:
Hi,
It is a friendly reminder that the OpenInfra Edge Computing Group is having a joint session with the Chameleon project.
During this session you can learn about the Chameleon project and how they are using OpenStack to build an edge platform for scientific research and academic purposes. They have also found some gaps during their journey. To mention an example the integration between Cyborg and Zun is missing to be able to use acceleration devices with containers orchestrated by OpenStack and they have been working to fill in this gap.
The session will start with a presentation about the project and then we will use the remaining time to talk about solutions and next steps. I would like to invite everyone who is interested in learning about how OpenStack can be turned into an edge platform and what are the missing pieces of the puzzle that still need to be enhanced or implemented.
The session will take place on the OpenInfra Edge Computing Group weekly call on __September 13, at 1300 UTC / 6am Pacific__. The meeting will be held on Zoom, for the latest dial-in information please refer to this page: https://wiki.openstack.org/wiki/Edge_Computing_Group#Meetings
Please let me know if you need a calendar invite and I can send you one to get reminded about the meeting.
Thanks and Best Regards, Ildikó
On Aug 25, 2021, at 17:00, Ildiko Vancsa <ildiko.vancsa@gmail.com> wrote:
Hi,
I’m very excited to invite you to a session with the Chameleon project to discuss how edge computing is powering education, scientific research and more! As always in the area of edge there are challenges and gaps that we need to solve together. In that sense the session will start with a presentation that we will then turn into a discussion to turn towards discussing solutions.
Please also note that the Chameleon project is using OpenStack to build edge solutions. As they identified some gaps they would like to work with the community to address the challenges that they’ve been hitting. Please join us to get their feedback and find the best way to improve OpenStack to deliver a platform that can be used on the edge!
The session will take place on the OpenInfra Edge Computing Group weekly call on __September 13, at 1300 UTC / 6am Pacific__. For the latest dial-in information please refer to this page: https://wiki.openstack.org/wiki/Edge_Computing_Group#Meetings
Please find the details of the session below.
Thanks and Best Regards, Ildikó
Title: Chameleon: a cloud to edge infrastructure for science
Abstract: The NSF-funded Chameleon project (www.chameleoncloud.org) provides an OpenStack-based bare metal reconfigurable cloud that supports systems research, education, and emergent application projects in science. The facility has been in existence for 6+ years, and has served ~6,000 users working on a variety of projects ranging from networking, operating systems design, and security, to innovative applications in astronomy, physics, and life sciences. Recent research trends in IoT and edge computing, as evidenced by increased numbers of project applications in those areas, made it clear that Chameleon needed to expand into the edge space. Remaining within the OpenStack framework allowed us to leverage end-user features that we developed for Chameleon, such as access via federated identity and Jupyter integration. Accordingly, we developed infrastructure called CHI@Edge that adapts Zun to provision containers on edge devices and significantly expands its capabilities to work in the edge space. The talk will describe our use case and the emergent product definition, the OpenStack adaptations we made to the current preview implementation, the directions we plan to take in our further work, as well as the ecosystem of projects and NSF infrastructure deployments leveraging this work and collaborating with us.