HPCwire Virtual Panel: Addressing Network Congestion in Multi-Workload Environments

Rockport has teamed up with HPCwire, Hyperion Research, Dell, OSU and TACC for a virtual panel on the topic of network congestion. Join us on Wednesday, November 10, from 1:00-2:30pm EDT / 11:00-12:30pm PDT for an interactive discussion.

Watch the Replay Here

 

Quieting Noisy Neighbors: Addressing Network Congestion in Multi-Workload Environments

Monitoring and controlling network congestion is now a critical element of operating large scale HPC clusters. Amdahl’s law predicts an effective maximum scale for HPC workloads related to the time taken for the parts of the workload that must be executed serially. However, Amdahl’s law ignores the cost associated with inter-process communication by assuming that the serial part of a workload is fixed. In fact, network congestion caused by parallelization increases the serial part of a workload, further limiting workload scale.

This roundtable will offer real-world insights on the challenges of congestion in multi-workload environments. We will discuss the root causes of congestion and the resulting ripple effect it can have on performance and scale. We will share benchmarking approaches to help measure and even predict the impact in production. And finally, we will explore the strategies and techniques available to mitigate or eliminate these impacts altogether.

 

Our panelists:

Erik Smith

Distinguished Member of Technical Staff,  Integrated Products and Solutions CTIO team
Dell Technologies 

Hari Subramoni

Research Scientist, Department of Computer Science and Engineering,
Ohio State University (OSU)

John D. McCalpin

Research Scientist, HPC Performance and Architectures Group
Texas Advanced Computing Center, TACC

Matthew Williams

Chief Technology Officer
Rockport Networks

Bob Sorensen

Senior Vice President of Research and Chief Analyst for Quantum Computing,
Hyperion Research
(moderator)

Don’t miss this event.

Watch the replay here.

Here’s something similar we think you’ll like.