We’re absolutely delighted to share that our own Sylabs CEO and founder Gregory Kurtzer has been identified as a person to watch in 2019 by HPCwire. Compiled annually by the publication, this is a
… list of People to Watch to foster a dialogue about our industry and give our readers a personal look at the hard work, dedication, and contributions from some of the best and brightest minds in HPC. These research efforts, accomplishments and technologies are shaping our future, and these are the people who are making it happen.
Greg is placed in fine company on this list, owing to his recent efforts aimed at developing products, services, and solutions based upon and around open source Singularity containers.
You might expect that the founder of CentOS Linux and the Warewulf cluster management toolkit, along with Singularity, would place a lot of emphasis on his past accomplishments. However, Greg embraces HPCwire’s 2019 (and beyond) emphasis, in relating how Sylabs is addressing emerging to existing requirements for those with compute-intensive workloads that characterize HPC and Enterprise Performance Computing (EPC); for example:
Moving forward, one of the biggest needs we are hearing about is a better solution for building containers. HPC sites want to give their users the ability to build containers on their systems without the need for root access, bleeding edge unsupported kernels, as well as support building containers for multiple architectures, like ARM and Power. For this reason we created the Remote Builder: a cloud and on-prem based service that allows users to build containers in a trusted way.
Remarkably, it will soon be possible for users of the Sylabs Cloud Remote Builder to create containers remotely via a desktop version of Singularity that runs natively on their macOS based platforms. Arriving later for Microsoft Windows as well, desktop support
… means that you can build, design, test, and sign containers from your personal laptop, and then use them anywhere, from an HPC resource to the cloud, making the transition and onramp anywhere seamless.
Greg also alludes to a developing convergence between compute-driven workloads (i.e., HPC and EPC) with those typical of a microservices based architectures. The resulting hybrid use cases demand that Singularity be integrated with “… Kubernetes, Kubeflow, and Hashicorp Nomad (with Apache Mesos coming soon).” On all of these fronts, integration efforts are well underway to supporting
… a new kind of real-time streaming workflow … Users in many different contexts want to run a series of containers as services and want to stream massive amounts of data to these services in real time. Then, rather than saving this data, users want to orchestrate compute focused containers to analyze and then discard this data in near real time.
For additional details on this emerging workflow, as well Singularity integrations, the interested reader is referred to our Year-End White Paper.
From past successes, to the present and future emphasis on Singularity, we wholeheartedly agree with HPCwire that Greg indeed merits attention in 2019 – and beyond. In fact, we can’t think of a better way for you to validate this for yourself than through the upcoming and inaugural meeting of the Singularity User Group (SUG), March 12-13, 2019 in San Diego. Not only will SUG provide a unique opportunity to hear about Singularity from its founder, through contributed talks from the software’s user, developer, and provider community, an even more impactful impression is certain to develop.
Finally, if you’d like to take watching literally, we suggest Greg’s recent presentation at the 2019 Stanford HPC Conference. Recorded just last week, Singularity: Container Workflows for Compute provides a compelling and comprehensive technical overview that could only be delivered by someone with Greg’s unique perspective and experience.