In this interview with NERSC HPC Data Analytics Engineer Jialin Liu, learn about a case study on I/O optimization, in which the team took the Etalumis learning application from spending 75% of its time on I/O down to spending only 5% of its time on I/O.
In this interview with NERSC Application Performance Specialist Charlene Yang, learn about the roofline model for application performance: what it is and how it works, how to use it to improve your application's performance, and future directions in roofline model research.
In this interview with Appentra Solutions CEO and co-founder Manuel Arenaz, learn about the Appentra Parallelware Trainer tool: how it can help you learn to code with OpenMP and OpenACC, the features of the tool, and how to use it on Cori.
In this interview with NERSC Building Infrastructure Group lead Ben Maxwell, learn about the mechanical substation work that will take NERSC offline the last weekend of July: what it's for, what work will be performed, and how NERSC plans these events.
Learn about Jupyter at NERSC: what it is, how it works, and what people are using it for, as well as plans for the future of Jupyter at NERSC, in this interview with the NERSC Data and Analytics Services Group's Rollin Thomas.
In this interview with Cray senior principal engineer and senior manager in programming environments Heidi Poxon, learn about why you would want to profile your code, what kind of differences you might see in performance on different architectures, and hear an overview of how to use the performance tools provided by Cray that are available on Cori.
In this interview with NERSC Application Performance Group Lead Jack Deslippe, learn about NERSC's KNL Office Hours (held every Friday in May from 9 am to 3 pm Pacific): why we're holding them, what users can join in to get help with, and the advantages of porting your codes to work on the Cori KNL nodes!
In this interview with NERSC Application Performance Specialist Kevin Gott, learn about the upcoming community GPU hackathon NERSC will be hosting in July: what it's about, what happens at a hackathon, and how to apply (due date May 15)!
In this interview with NERSC HPC Consultant Zhengji Zhao, learn the detailed schedule for Edison's retirement, a little Edison history, and how NERSC is helping you get prepared for running your codes on Cori KNL with KNL Office Hours (starting this Friday and continuing through May).
In this interview with Lawrence Livermore National Laboratory HPC I/O Specialist Elsa Gonsiorowski, learn about the Productivity and Sustainability Improvement Planning (PSIP) process originating from the IDEAS productivity project, how it can work for you, and some web resources for PSIP.
In this interview with David Bernholdt, a distinguished R&D staff member and leader of the Computer Science Research group at Oak Ridge National Laboratory, learn about the IDEAS Productivity project: its goal of increasing productivity for HPC software developers, the many ways in which the project addresses this goal, and how you can get involved!
In this interview with NERSC HPC Application Specialist Brandon Cook, learn about the High-Impact Science at Scale on Cori program: what it's for, how to apply, and what to do if you aspire to run at large scale but you're not quite ready yet.
In this episode, NERSC Data and Analytics Services Group's Machine Learning Engineer Mustafa Mustafa discusses the upcoming Deep Learning for Science (DL4Sci) Summer School (https://dl4sci-school.lbl.gov/) hosted by Berkeley Lab's Computing Sciences Area (which includes NERSC). Learn what deep learning is and how it can be applied to science, as well as more information about the summer school and how to apply!
In this episode, meet NERSC Assistant Building Manager Ernie Jew, who helps make sure that the facilities at NERSC run smoothly. Find out about what his job entails, what special skills he brings to NERSC, and how he spent eight summers at Yellowstone National Park on his career path!
In this interview with NERSC HPC Systems Engineer Aditi Gaur, learn about the pros and cons of using open-source software, how to get started contributing to an open-source project, and how to make your own project open source!
In this interview with NERSC Operations Technology Group's Tom Davis, learn about why NERSC started collecting data on its machines, what sort of data NERSC collects, and how NERSC uses that data to diagnose issues on its machines and in the machine room.
In this interview with NERSC HPC Architecture and Performance Engineer Taylor Groves, find out what's happening in the HPC networks research area, how Perlmutter's network will be better than what we have today, and what you can do to get better network performance in your applications.
In this interview with Berkeley Lab's Building Technologies and Urban Systems Division principal engineering associate and building energy efficiency expert Norm Bourassa, learn about how NERSC assures that our machines are operating at peak efficiency with minimal energy overhead, including how we take advantage of the mild Berkeley climate, how we look for inefficiencies via extensive instrumentation, and what is happening on the global scale as a result of NERSC's energy efficiency efforts.
In this interview with Berkeley Lab construction project director Ben Maxwell, learn about all the facilities work to prepare for the arrival of Perlmutter. Find out how much power and cooling is being added to the machine room, how the earthquake isolation floor works, and what computer cooling and viticulture have in common!
In this interview with NERSC Site Reliability Engineer Owen James, learn about what it's like in the Operations Control Room, what the Operations Technology Group is responsible for, and the tools they use to keep the systems up and running for you!
In this interview with NERSC HPC architecture and performance engineer Doug Doerfler, learn about what NERSC is doing to plan for the next NERSC machine, why performance portability is vital for code development teams who want their application to run on future Post-Moore's Law systems, and tips on making your code as performance-portable as possible.
In this episode, Application Performance Specialist Brian Friesen discusses the postdoctoral fellowships at NERSC. Find out how you can join NERSC as a postdoc, either working in the NESAP program to prepare codes for Perlmutter, or as the Grace Hopper Postdoctoral Fellow, preparing your own code for Perlmutter!
In this interview with NERSC security specialist Abe Singer, learn about NERSC's plans for Multi-Factor Authentication (MFA), discover what will happen when MFA becomes mandatory in the new allocation year, and hear answers to some frequently asked user questions about MFA.
In this interview with NERSC Application Performance Specialist Brandon Cook, learn about the NERSC Exascale Scientific Applications Program (NESAP), the benefits of participation, and how you can participate (as a code team or a recent graduate looking for a job).
In this interview with NERSC-9 project manager Jay Srinivasan and chief architect Nick Wright, learn about the new machine arriving at the end of 2020, why it was named Perlmutter, and the new features of the machine that users will especially like.
In this interview with Berkeley Lab Computational Research Division staff scientist and prolific NERSC user David Trebotich, learn what all those big jobs of his are for, what makes running at full-machine scale challenging, and pick up some tips from David on how to run at scale at NERSC!
In this interview with NERSC Security Engineer Craig Lant, learn about how NERSC keeps our machines safe, the unique security challenges in high-performance computing, and an exciting opportunity to join our team!
In this interview with Division Deputy and Data Department Head Katie Antypas, learn about what a superfacility is, how NERSC is helping users from experimental facilities to analyze their data, and what challenges lie ahead!
In this interview, NERSC Allocations and Account Support specialist Clayton Bagwell discusses the ERCAP process. Learn what ERCAP stands for, find out the latest developments in the ERCAP system, and how to get help if you're struggling with your ERCAP submissions.
This week NERSC Security Analyst Abe Singer returns to the show to discuss the latest developments with Multi-Factor Authentication (MFA) at NERSC. Tune in to hear about sshproxy (a NERSC-developed utility for generating ssh keys with MFA that can be used all day) and hear Abe's answers to common user questions. Be sure to listen until the end for a question even Abe can't answer!
In this interview with NERSC Application Performance Specialist Thorsten Kurth, learn about some interesting applications of machine learning to science, why some of the most interesting applications require computing at scale, and hear Thorsten's recommendations for how someone with a science background can get started in the field.
In this interview with NERSC Infrastructure Services Group's Gabor Torok, learn about best practices for software development, what kinds of skills are important for an effective software engineer, and how Gabor went from scientific illustrator to software engineer at NERSC!
In this interview with NERSC HPC Consultant Mario Melara, learn about NERSC's management of the software we install for users with Spack, opportunities for getting involved with the growing Spack community, and how Mario went from driving a bus to being a NERSC consultant!
In this interview with NERSC's Richard Gerber, learn about the types of scientific research going on at NERSC, why computers are used for scientific research, and how a sports writer ended up becoming the senior science advisor at NERSC!
Listen in to find out why NERSC switched to Slurm as its batch system and job scheduler, how Slurm schedules jobs, and how you can get jobs through the queue faster in this interview with NERSC Computational Systems Group lead Doug Jacobsen.
Spin is NERSC's new service platform to be used as a complement to computational tasks. In this interview with NERSC Infrastructure Services Group Lead Cory Snavely and Berkeley Lab computer systems engineer Val Hendrix, find out more about what Spin is, how it's being used for climate data, and how you can start using it too!
In this episode, learn about the scratch filesystems available to NERSC users, why we purge them, and how the purge is performed in this interview with NERSC HPC Storage Systems Analyst Kirill Lozinskiy.
Learn what Identity and Access Management (IAM) is, how NERSC uses it to manage our many users, and our plans for the future, including the potential to enable you to use your institutional identity instead of having to memorize yet another username and password.
Find out more about the maintenance that will bring NERSC offline the weekend of August 18 and 19! Learn what a switchgear is, why it's important, and how NERSC tries to minimize disruptive outages for users in this interview with NERSC Deputy for Operations Jeff Broughton.
Learn what performance portability is, what makes it so difficult to achieve, and tools and programming environments that can help in this interview with NERSC's application performance group leader, Jack Deslippe.
Learn about how some users are using Python in their daily workflows, what a Jupyter notebook is, and how to get the best Python performance at NERSC in this interview with NERSC data architect Rollin Thomas.
Learn about what deep learning is, how it can benefit your science, and what Debbie Bard (who leads NERSC's Data Science Engagement Group) has in common with some of the biggest-name bands in the world!