▷ the Bright blog

Bright’s Jupyter integration provides a rich set of features that provide a point-and-click interface to the underlying compute cluster. The Jupyter Kernel Creator is one of them. It allows users to create kernels that run on the cluster, either through an HPC workload scheduler or through Kubernetes. But some organizations want to prepopulate the launcher with kernel definitions that can be used by any user – without customizing a template. This article shows how to do it.

Join us on November 17th virtually or in person, as Bright Computing, GigaIO, and San Diego Supercomputing Center present a BOF (Birds of a Feather) at Supercomputing Conference 2021. They will foster a technical discussion with the audience around the challenge and promise of composable infrastructures for HPC/AI, and then discuss different approaches for realizing easy-to-use composable systems. This highly relevant HPC industry topic will increase resource utilization, enable resource sharing, boost system performance, and drive down OpEx and CapEx expenditures.

The Jupyter Notebook is a popular open-source development tool used by data scientists, programmers, analysts, and engineers to create and share “notebooks” that integrate live code, equations, computational output, visualizations, and other multimedia resources, along with explanatory text. Redesigned in Bright Cluster Manager 9.1, Bright’s Jupyter integration takes this tool a step further and accomplishes several important things that make Jupyter a more effective and powerful tool for users. Namely, data scientists and ML practitioners can leverage this integration to conveniently run applications by writing notebooks in their browsers. Bright makes it possible and easy for Jupyter notebooks to run on a cluster, increasing the scope of work that can be performed through Jupyter and providing a point-and-click interface for users that are not familiar with the complexity of submitting jobs to a cluster. This workflow makes it easy to run different experiments, enables rapid prototyping, and allows fine-tuning ML models.

This week, Bright featured an article in InsideHPC which highlights how Bright users can achieve real competitive advantage in the cloud using Bright Cluster Manager. As traditional mindsets towards high-performance computing (HPC) increasingly give way to cloud-based approaches, organizations are seizing the advantages of time and reduced capital outlays compared to traditional on-premise approaches. ”Cloud continues to be a top priority for companies that are seeking ways to accelerate HPC projects or quickly extend the capacity and capabilities of their on-premise systems” says Bill Wagner, CEO of Bright Computing. According to Intersect360 Research, in 2020, cloud computing experienced 78.8% growth, on top of an underlying double-digit growth rate, as organizations turned to cloud computing to cope with accelerated projects and deferred acquisitions. Leveraging HPC in the cloud has important business applications for companies trying to get into HPC and haven’t yet decided, or can’t afford, to deploy an HPC cluster. Cloud technology means that companies can now adapt and scale more easily to accelerate innovation, drive business agility, streamline operations, and potentially reduce costs.

We are excited to announce that Bright Computing has been invited to participate in the next Dell Technologies HPC Community Event:

The HPC industry is marching towards the delivery of the first exascale systems, composed of tens-of-thousands or hundreds-of-thousands of server nodes and exotic software stacks to manage it all. While the first systems will have a limited audience, exascale systems will increasingly move down-market to reach large numbers of enterprises. As exascale systems make their way into commercial enterprises, the need for more standardized, out-of-the-box management tools will follow.   

HPC is undergoing massive changes that present both challenges and opportunities for organizations across industries. Historically, HPC has been defined by a consistent and well-known set of applications for modeling and simulation running on bare metal servers in an organization’s data center—but that is changing. We now have machine learning and data analytics applications vying for access to trusted HPC systems, ultimately throttling important work in one place or another.

ICYMI, Bright recently announced that Bright Cluster Manager was selected to support the new artificial intelligence supercomputer to be installed at National Supercomputer Centre (NSC) at Linköping University.

Earlier this week, Bright CEO Bill Wagner wrote an article featured by InsideHPC where he discusses how changes in HPC are demanding that businesses unify their HPC infrastructure from edge to core to cloud. He goes on to explain that, at the edge, while sensors and new apps that require low-latency compute certainly necessitate systems that live in close proximity (outside of public clouds and traditional data centers), the reality is, new compute-intensive/data-intensive apps in machine learning and analytics are driving the need for organizations to have a growing number of high-performance clusters in an expanding number of physical locations, as well as in the public cloud. With compute and systems destined to become increasingly decentralized in this way, the notion of the edge being an outlier to some dominant central computing infrastructure overlord will quickly become dated.

Did you see that Bright Cluster Manager 9.1 introduces support for Redfish BIOS management? This feature enables administrators to view and update BIOS parameters on any/all nodes of the cluster that support the Redfish specification from the command line or Bright View. This reduces complexity and the effort that admins face when updating BIOS settings across their cluster.