Bright Cluster Manager for Data Science Now Available at No Charge with Easy8

Print Friendly, PDF & Email

Today Bright Computing announced that Bright Cluster Manager for Data Science is now available at no charge as part of the Easy8 program. Launched in November of 2019, Easy8 is designed to put Bright’s award-winning cluster management software in the hands of every organization working with high-performance Linux clusters. Easy8 offers the full-featured Bright Cluster Manager software free for up to 8 nodes, and now includes Bright Cluster Manager for Data Science. Bright Cluster Manager automates the process of building and managing heterogeneous Linux clusters that span from your on-premise datacenter to the cloud, and to the edge.

With Easy8, our goal is to give every organization the ability to use our software, free of charge for clusters up to 8 nodes, to demonstrate how powerful and easy Bright Cluster Manager software is.”, said Bill Wagner, CEO of Bright Computing. “With the inclusion of Bright Cluster Manager for Data Science in the Easy8 program, we are giving organizations the ability to quickly deploy cluster-based machine learning environments for data scientists and researchers that can be easily maintained and scaled out.”

Bright Cluster Manager for Data Science is an add-on to Bright Cluster Manager―providing the computing infrastructure and pre-packaged tools needed to accelerate data science projects and make them production-ready. This add-on introduces a wealth of data science features including:

  • Modern Deep Learning Environment – Provides everything needed to quickly spin up a complete machine learning environment for data scientists that is cluster-ready and easy to manage
  • Choice of Machine Learning Libraries and Frameworks – Includes the most popular machine learning libraries and frameworks such as NVIDIA cuDNN, CUB, CUDA, TensorRT, Dynet, Fastai, JupyterHub, NCCL2, MXNet, pyTorch, and more.
  • Scale-out JupyterHUB – JupyterHub makes data science easy to use and Bright provides custom JupyterHub spawners that allow notebooks to be scheduled through the HPC scheduler or Kubernetes.
  • Support for NVIDIA GPU Cloud (NGC) – Makes it easy to use NVIDIA NGC deep learning containers in so many ways―run them in containers, through a batch scheduler, on physical nodes, or in a cloud.

The stage is set for high-performance Linux clusters to become the cornerstone of corporate data centers, well beyond their origins for modeling & simulation applications in the high-performance computing market. With a rapidly growing number of applications and industries requiring high-performance clusters, the free and easy availability of Bright’s market leading cluster management software is perfectly timed to give organizations a way to deploy and manage the infrastructure they need without the complexity or burden typically associated with high-performance clusters.

Sign up for our insideHPC Newsletter