Enterprise customers consistently demand improved performance from every component in their HPC infrastructure, including their workload manager. Ian Lumb, Solutions Architect at Univa Corp., speaks on the importance of an innovative workload manager to overall success.
In this podcast, the Radio Free HPC team looks at a recent update on the Exascale Computing Project by Paul Messina. “The Exascale Computing Project (ECP) was established with the goals of maximizing the benefits of HPC for the United States and accelerating the development of a capable exascale computing ecosystem.”
“This talk will present the motivating factors for considering OpenStack for the management of research computing infrastructure. Stig Telfer will give an overview of the differences in design criteria between cloud, HPC and data analytics, and how these differences can be mitigated through architectural and configuration choices of an OpenStack private cloud. Some real-world examples will be given that demonstrate the potential for using OpenStack for managing HPC infrastructure. This talk will present ways that the HPC community can gain the benefits of using software-defined infrastructure without paying the performance overhead.”
Ingolf Wittmann from IBM presented this talk for the Switzerland HPC Conference. “This presentation will point out based on real examples how HPC environments can benefit from such solutions and technologies to drive cognitive solutions, machine/deep learning where we can ask ourselves, ‘What will be possible in the near future – can the future computers be smarter than humans?”
Simon Fraser University (SFU), Compute Canada and WestGrid were all part of the major new update to Canada’s HPC resources with the recent announcement of the launch of the most powerful academic supercomputer in Canada, Cedar. Housed in the new data centre at SFU’s Burnaby Campus, Cedar will serve Canadian researchers across the country in all scientific disciplines by providing expanded compute, storage and cloud resources.
“In this talk we will discuss a workflow for building and testing Docker containers and their deployment on an HPC system using Shifter. Docker is widely used by developers as a powerful tool for standardizing the packaging of applications across multiple environments, which greatly eases the porting efforts. On the other hand, Shifter provides a container runtime that has been specifically built to fit the needs of HPC. We will briefly introduce these tools while discussing the advantages of using these technologies to fulfill the needs of specific workflows for HPC, e.g., security, high-performance, portability and parallel scalability.”
“Just as developers need tools to understand the performance of a CPU intensive application in order to modify the code for higher performance, so do those that develop interactive 3D computer graphics applications. An excellent tool for t this purpose is the Intel Graphics Performance Analyzer set. This tool, which is free to download, can help the developer understand at a very low level how the application is performing, from a number of aspects.”
This Rock Stars of HPC series is about the men and women who are changing the way the HPC community develops, deploys, and operates the supercomputers and social and economic impact of their discoveries. “As the lead developer of the VMD molecular visualization and analysis tool, John Stone’s code is used by more than 100,000 researchers around the world. He’s also a CUDA Fellow, helping to bring HPC to the masses with accelerated computing. In this way and many others, John Stone is certainly one of the Rock Stars of HPC.”
In this video from the Switzerland HPC Conference, Jeffrey Stuecheli from IBM presents: Open CAPI, A New Standard for High Performance Attachment of Memory, Acceleration, and Networks. “OpenCAPI sets a new standard for the industry, providing a high bandwidth, low latency open interface design specification. This session will introduce the new standard and it’s goals. This includes details on how the interface protocol provides unprecedented latency and bandwidth to attached devices.”
“HPC software is becoming increasingly complex. The space of possible build configurations is combinatorial, and existing package management tools do not handle these complexities well. Because of this, most HPC software is built by hand. This talk introduces “Spack”, an open-source tool for scientific package management which helps developers and cluster administrators avoid having to waste countless hours porting and rebuilding software.” A tutorial video on using Spack is also included.