The New HPC Era Needs New HPC Storage

  • Business White Paper
  • PDF 686 KB
  • 8 pages

Overview

The confluence of traditional simulations with AI changes everything!


The impact of the workload convergence is most disruptive on the HPC storage layer, as the input/output (I/O) profiles of both workloads could not be more different. The storage architectures that served us well when simulation and AI were deployed on separate infrastructure stacks are breaking ...

The confluence of traditional simulations with AI changes everything!


The impact of the workload convergence is most disruptive on the HPC storage layer, as the input/output (I/O) profiles of both workloads could not be more different. The storage architectures that served us well when simulation and AI were deployed on separate infrastructure stacks are breaking architecturally and economically in the new era.

The costs of staying with legacy storage architectures in the new era range from idling, unproductive compute nodes due to I/O bottlenecks to exploding HPC storage costs and high coordination efforts between different vendors.

Read this white paper to learn how to address these challenges.

Learn how HPE can help you in the new era to feed your CPU and GPU-accelerated compute nodes without I/O bottlenecks, how to put the HPC storage beast on an effective diet and how to have unified accountability of HPE Pointnext Services.