IBM Spectrum LSF is available on the IBM Cloud starting June 30, 2021.

The vast majority of enterprises today are leveraging the agility, cost advantages and convenience offered by cloud computing. For example, IBM Cloud is trusted by 47 of the Fortune 50, 10 of the largest banks and 8 of the 10 largest airlines. Similarly, organizations that rely upon high-performance computing (HPC) to design and deliver better products are also adopting cloud computing. These organizations are looking at hybrid HPC Cloud as a way to accelerate time to market, reduce IT lead times, lower costs and accommodate spikes in demand.

According to the recent Hyperion Research May 2021 HPC Market Update, “HPC in the cloud is expected to grow more than 2.5 times faster than the on-prem HPC server market” and “HPC cloud spending is projected to reach ~$9B by 2024.”

And not to burst your bubble, but bursting to the cloud for HPC can be complex. The reality of creating a hybrid HPC cloud environment that can run workload on-premises and in the cloud involves many moving parts and smarts. For example, how does your workload scheduler decide where to send jobs? How can you easily make your applications and all-important data available in the cloud? How can I make this all seamless to my end consumers of HPC? 

IBM Spectrum LSF is an advanced workload management solution for demanding HPC environments. It supports hybrid HPC cloud with powerful capabilities like seamless, policy-driven bursting of workloads to the cloud, dynamic provisioning of cloud resources, intelligent movement of data and support for containerized workloads, including support for Docker, Shifter, Singularity, Nvidia Docker, Enroot and Podman.

And now, IBM Spectrum LSF is available on the IBM Cloud starting June 30, 2021. IBM has taken its combined cloud and HPC experience and is delivering this turnkey hybrid cloud solution that enables organizations to deploy a fully functional LSF cluster in the IBM Cloud in a few hours or less.

Overview

IBM® Spectrum LSF is now available on IBM Cloud and provides a fully automated and configurable deployment of LSF-based HPC clusters. This offering is ideal for customers who require IBM Spectrum LSF in a cloud environment for their computationally intensive workloads. The offering leverages IBM Cloud VPC featuring Intel Xeon processors.

IBM Spectrum LSF on IBM Cloud provides HPC environments deployed to a customer-owned IBM Cloud account. HPC cluster deployment starts with the definition of the desired cluster configuration; for example, count of management nodes, worker nodes, amount of storage and so on. Open-source technologies like Terraform and Ansible have been used to automate the provisioning and configuration of all associated IBM Cloud VPC resources and LSF. For cloud compute resources, customers pay only for what they need when it is needed, all compute configurations used have per-second and/or per-hourly consumption-based pricing. Customers can choose any virtual server configurations available as part of IBM Cloud VPC resource list.

This baseline architecture below provides the fundamental building blocks for the solution:

Key benefits

IBM Spectrum LSF offering makes it very easy for customers to create IBM Spectrum LSF-based HPC environments. Customers can easily scale up and down their environments as their requirements change.

  • Automated deployment for compute, network and storage resources on IBM Cloud
  • Support for all three interfaces — UI, API and CLI — for API and CLI customers using the IBM Cloud Schematics solution
  • Default setup for auto-scaling using IBM Spectrum LSF Resource Connector
  • IBM Spectrum LSF multi-cluster configuration allows seamless bursting to IBM Cloud — jobs can be routed to run in cloud or on-premises with simple queue configuration
  • IBM Spectrum LSF data manager enables intelligent caching of data between on-premises and cloud cluster to assist hybrid deployments

By defining simple configuration properties and using automation, customers can quickly create HPC environments on IBM Cloud with their choice of compute node types. The cluster instance can be easily scaled up or down by adding more compute nodes or deleting some depending on what the workload needs might be.

The IBM Spectrum LSF offering on IBM Cloud delivers the following benefits:

  • Accelerating delivery of an HPC environment for developers and lines of business by reducing the procurement, architecture, implementation and deployment time from weeks (or even months) to minutes.
  • Easy scale up and down, enabling customers to add or remove capacity as desired.
  • Hybrid cloud enabling seamless connection between on-premises and on-cloud HPC environments to support true cloud bursting use cases.
  • Consumption based pricing using per-second and/or per-hour billing for cloud compute resources allows customers to pay only for when they used them.

Get started

In summary, the IBM Spectrum LSF offering is a tile in the IBM Cloud catalog for automated deployment of Virtual Private Cloud (VPC) HPC clusters and workload management. Clients must have entitlement to Bring Your Own License (BYOL) for IBM Spectrum LFS Standard, Data Manager and License Scheduler.

To learn more about the offering, please see the documentation.

Further reading: “IBM and Synopsys Demonstrate EUV OPC Workload Runs >11,000 Cores on the Hybrid Cloud

Categories

More from Analytics

Data science vs data analytics: Unpacking the differences

5 min read - Though you may encounter the terms “data science” and “data analytics” being used interchangeably in conversations or online, they refer to two distinctly different concepts. Data science is an area of expertise that combines many disciplines such as mathematics, computer science, software engineering and statistics. It focuses on data collection and management of large-scale structured and unstructured data for various academic and business applications. Meanwhile, data analytics is the act of examining datasets to extract value and find answers to…

Financial planning & budgeting: Navigating the Budgeting Paradox

5 min read - Budgeting, an essential pillar of financial planning for organizations, often presents a unique dilemma known as the “Budgeting Paradox.” Ideally, a budget should give the most accurate and timely idea of anticipated revenues and expenses. However, the traditional budgeting process, in its pursuit of precision and consensus, can take several months. By the time the budget is finalized and approved, it might already be outdated.In today's rapid pace of change and unpredictability, the conventional budgeting process is coming under scrutiny.It's…

How Macmillan Publishers authored success using IBM Cognos Analytics

5 min read - Macmillan Publishers is a global publishing company and one of the “Big Five” English language publishers. If you're a reader, chances are good you've read a book from Macmillan. They published many perennial favorites including Kristin Hannah’s The Nightingale, Bill Martin’s Brown Bear, Brown Bear, what do you see? and some of the more recent bestsellers such as The Silent Patient by Alex Michaelides, Identity by Nora Roberts and Razorblade Tears by S. A. Cosby. It’s no wonder then that Macmillan…

MLOps and the evolution of data science

7 min read - The advancement of computing power over recent decades has led to an explosion of digital data, from traffic cameras monitoring commuter habits to smart refrigerators revealing how and when the average family eats. Both computer scientists and business leaders have taken note of the potential of the data. The information can deepen our understanding of how our world works—and help create better and “smarter” products. Machine learning (ML), a subset of artificial intelligence (AI), is an important piece of data-driven…