Podcasts about nersc

Episode notes: Richard Gerber ensures the National Energy Research Scientific Computing Center remains responsive to the needs of scientific researchers.

Addison Snell, Tiffany Trader, and Oliver Peckham discuss the launch of NERSC's new Perlmutter system, plus news from an Australian research team that lends credibility to the theory that COVID-19 could have originated from a Wuhan lab leak.

NVIDIA A100を6159基搭載　米NERSCのAIスパコン「Perlmutter」がついに稼働。　米国立エネルギー研究科学計算センター（NERSC）は5月27日（米国太平洋夏時間）、NVIDIA製GPU「NVIDIA A100」を6159基搭載したスーパーコンピューター「Perlmutter（パールマッター）」のバーチャル除幕式を開催した。Perlmutterは、NVIDIA A100を利用したスーパーコンピューターとしては現時点で世界最大規模となる。

A Day in the Half Life is a podcast from Lawrence Berkeley National Laboratory (Berkeley Lab) about the incredible and often unexpected ways that science evolves over time, as told by the researchers who led it into its current state and those who are going to bring it into the future.In our very first episode, we discuss machine learning. First developed about 80 years ago, machine learning (ML) is a type of artificial intelligence centered on programs – called algorithms – that can teach themselves different ways of processing data after they are trained on sample datasets.In the early days of ML, the technology was used for simple tasks such as voice recognition or identifying a specific type of object in images, and was only found in high-end academic, government, or military devices. But now, advanced ML algorithms are everywhere, powering everything from our cars to our voice assistants to the ads appearing on our news feeds. And, in addition to making everyday life easier, ML algorithms are beginning to improve and expedite scientific and medical research in truly dramatic ways. In fact, the range of potential applications is so huge that the question has shifted from “Can we use machine learning to solve this?” to “Do we understand the way these algorithms work well enough to feel comfortable using ML for this?” Our two ML expert guests are:John Dagdelen, a materials science graduate student researcher at Berkeley Lab and UC Berkeley. John is part of several scientific teams using ML to discover new materials and material properties, as well as using ML to make discoveries in COVID-19 research.Prabhat, the former leader of the Data and Analytics Services group at NERSC, Berkeley Lab's world-renown supercomputing center. Prabhat has been using and developing ML for decades, including for use in climate research. He is now at Microsoft.

NERSC Director Sudip Dosanjh discusses the highlights of 2020 at NERSC, as well as what to look forward to in 2021 and beyond.

In this interview with NERSC HPC Consultant Steve Leak, learn about the new NERSC software support policy: what it is, how it works, and its benefits for users and NERSC staff alike.

In this interview with Berkeley Lab Infrastructure Modernization Division's David Topete, learn about the power upgrade happening this weekend, the work that has to be done, and the steps taken to ensure the safety of the workers involved in the effort.

In this interview with NERSC Building Infrastructure Group's Norm Bourassa, learn about how NERSC is saving energy with the dynamic fan setting on the Cori supercomputing cabinets, and what we are doing to make the cabinets even more energy efficient.

In this interview with NERSC Application Performance Specialist Kevin Gott, learn about the upcoming GPU Hackathon sponsored by NERSC: what it's for, the format of the event, and how to apply.

We fire up the show with introductions and a little snippiness on Dan’s part. Henry reports that the weather in Minnesota is nearly human.AI in ScienceJumping into our main topic, Shahin introduces an article from HPCwire interviewing Argonne’s Associate Laboratory Director Rick Stevens about how the DOE will be using AI in science. This is one of the biggest potential changes in our industry and well worth the investigation. But figuring out where AI fits into the traditional world of research and simulation is a difficult problem. Henry points out that nearly every grant proposal needs to include “AI” in order to get serious consideration.We discuss Dan's Great HPC Road Trip* of national labs in 2018 and how nearly every lab is looking at using AI to inform their simulations and cut down on the brute force computing they’re doing now. Dan’s national lab interviews are here: Idaho National Lab, NCAR, NREL, Los Alamos, Sandia, NERSC, Lawrence LivermoreThere’s also a slight tangent where Dan talks about driving hundreds of miles out of his way to mess with Henry’s Las Cruces lot and future home. This resulted in an epic short film “The Haunting of Henry House” which is stuck in bureaucratic  approval cycles according to Henry. RFHPC Hall of Fame?We also discuss the possibility of founding a Radio Free HPC Hall of Fame, but discarded it when we realized that no one would want to be in it.COVID-19As the conversation continues, Dan brings up an article that discusses how COVID-19 might affect processor foundry revenues and demand. We are, as a group, underwhelmed by the analysis. Henry notes that he has seen a significant increase in the price of laptops when shopping for a graduation gift for his nephew. Henry has reportedly seen an increase of around 20% in prices since February.Reasons Why No One Should Ever Be Online. Ever.Hackers have stolen and ransomed AMD’s GPU test files, a dastardly act, but not surprising to see. They’re looking for $100 million to give the files back, while AMD has downplayed their importance and value.Catch of the WeekHenry:  Another empty net week for our pal HenryShahin: How is the internet coping with all of the extra traffic caused by Covid19 isolation?Jessi:   For the first time in recorded history, Jessi’s net is empty….sad.SuperCatchDan:  has a SuperCatch! He does a promo of the inaugural episode of a new RadioFreeHPC segment. Suffice to say that RadioFreeHPC Studios has a brand new production of “Charles Babbage, His Life & Times,” a gripping radio drama that will engage your emotions from A-B.Listen in to hear the full conversation* Download the MP3 * Sign up for the insideHPC Newsletter* Follow us on Twitter * Subscribe on Spotify * Subscribe on Google Play * Subscribe on iTunes * RSS Feed * eMail us

Professor Camille Li works on storm tracks, the warm, moist conveyor belt that deliver storm after storm to us here in Western Norway and the British isles. Learn how these storm tracks works, how they will change and the research Camille Li and her colleagues are conducting at the Bjerknes centre for climate research. Our host, the NERSC researcher Stephen Outten and editor and associate professor Ingjald Pilskog, talk with Camille Li about why we are getting wet here in northwestern Europe.

NERSC Director Sudip Dosanjh discusses the highlights of 2019 at NERSC, as well as what to look forward to in 2020 and beyond.

Einar Örn Ólason is working on sea ice forecasting and improving how sea ice is modelled in the future generations of earth system models. Learn how we will improve our predictions of what is going on in the high north and how this gives us a better understanding of our future. Learn about neXtSIM the future of sea ice prediction. Our host, the NERSC researcher Stephen Outten and editor and associate professor Ingjald Pilskog, talk with Einar Ólason about a model that means more for you then you know.

Weather models are made primarily for making good weather forecasts in the mid-latitudes, i.e. Europe and north America. They are also made to be able to calculate forecasts fast enough to be helpful on computers that are not as fast as the current computers. Therefore we have used a lot of short cuts that are not physical. PhDs as Marvin Kähnert are working on improving the models in the Arctic and introduce more physical correct assumptions. Our host the NERSC researcher Stephen Outten and editor and associate professor Ingjald Pilskog talk with Kähnert about the problem and what is done to fix it. Music by Lee Rosevere - Arcade montage, B.Y. 3.0.

Geologists need to use the right methods when estimating the tonnage and grade they can expect from an ore body. For recoverable resources, when uniform conditioning doesn't work, you need to turn to alterative techniques. In part two of this two-part series, Senior Geostatistician at Geovariances, David Barry, and Director of Geology at Optiro, Ian Glacken, discuss MIK and conditional simulation. In this episode: 2:05 There are alternatives to uniform conditioning for when it isn't suitable 4:15 What are the alternatives to uniform conditioning? 7:45 There are several theoretical objections to Multiple Indicator Kriging in the French school 9:38 What is conditional simulation and how does it apply to recoverable resource estimation? 11:49 So how would we get a single optimal result from multiple conditional simulations? 12:50 How would you use Isatis to help you with your estimation techniques? 14:44 Where can people go to get more information on this subject? For more information: Contact Ian Glacken - Optiro Director of Geology: iglacken@optiro.com Contact David Barry - Senior Geostatistician: barry@geovariances.com Optiro website 2-day Recoverable Resources course Links: Wackernagel, H (2013) Basics in Geostatistics 3. Geostatistical Monte-Carlo methods: Conditional Simulation. NERSC, Accessed 17/10/2019. Glacken, I & Blackney, P (1998) A practitioners implementation of indicator kriging, The Geostatistical Association of Australasia “Beyond Ordinary Kriging” Seminar October 30th, 1998  Perth, Western Australia    

In this episode we introduce the new IRIS allocation banking and identity and access management system that NERSC has developed to replace NIM. Learn from NERSC Infrastructure Services Group's Gabor Torok and Mark Day about how the system was built, the improvements over NIM, and its upcoming rollout in December!

In this interview with NERSC Computational Systems Group's Eric Roman, learn about how NERSC is monitoring the performance of our systems, what we're doing with that data, and how we plan to use it in the future.

In this interview with NERSC Data Science Engagement Group Lead Debbie Bard, learn about the superfacility concept: what it means, how facilities interact, and what NERSC and partner experimental facilities are doing to prepare for the future of data-intensive science.

Learn about ERCAP, the allocation request process for NERSC, which opens today (August 12), in this interview with NERSC allocations and account support specialist Clayton Bagwell.

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 the NERSC User Group (NUG), the upcoming NUG annual meeting (July 19, 2019 in Rockville, MD), and what NUG can do for you in this interview with NERSC HPC Department Head Richard Gerber.

Learn all about containers, how people are using them at NERSC, and how to get started with them yourself, in this interview with NERSC Data Analytics and Services Group's Shane Canon!

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 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 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 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.

NERSC Director Sudip Dosanjh discusses the highlights of 2018 at NERSC, as well as what NERSC is looking forward to in the next year and beyond.

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-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!

Learn about the various filesystems available at NERSC, which filesystem to use when, and how HPSS accounting works in this interview with NERSC HPC Data Consultant Lisa Gerhardt.

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 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 HPC Consultant Zhengji Zhao of the User Engagement Group, learn about what variable-time jobs are, what they can be used for, and how to run them on NERSC resources!

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!

In this episode, learn about what it takes for NERSC to bring you a new supercomputer!

In this interview with NERSC's Glenn Lockwood, learn why the outlook for storage systems is rosy for the next several years, how flash storage works, and what NERSC has in common with Netflix!

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 NERSC's Archive HPSS system: what it is, how it works, and how NERSC plans to relocate the data on it from Oakland to the main Berkeley Lab campus!

Find out all about multi-factor authentication (MFA) at NERSC, as well as the name of the podcast theme song, in this interview with NERSC security analyst Abe Singer.

A summary of the May quarterly maintenance, plus an interview with NERSC system administrator James Botts on why it takes so long to upgrade the operating system on a supercomputer.

The Celeste Project: Celeste is a collaboration between MIT, UC Berkeley, Harvard, Julia Computing, Intel, and NERSC (the DoE's supercomputing center). They recently managed to calculate the first comprehensive statistical catalog of astronomical objects in the visible universe. That's over 188 million stars and galaxies! Using some nifty new methods they developed, the collaboration managed to complete the entire calculation in only 15 minutes. We believe this system will massively accelerate astronomy research, especially once scientists start receiving higher-resolution images from new telescopes like the LSST and the James Webb Space Telescope.   Purchase the brand new Ad Astra merch here!!!   Further Reading: Info about Julia   Here are some Celeste pointers Honored for HPC Innovation Excellence Celeste Enhancements Create New Opportunities In Sky Surveys A New Model For Cataloging the Universe   and some other projects at NERSC Big Science Problems, Big Data Solutions A Look At Deep Learning for Science     Follow Ad Astra on Twitter at @AdAstra_Podcast, on Facebook, and subscribe to the mailing list for future updates and events!

In this Rich Report podcast, Pradeep Dubey discusses AI & The Virtuous Cycle of Compute.Traditionally, there has been a division of labor between computers and humans where all forms of number crunching and bit manipulation are left to computers, whereas intelligent decision-making is left to us humans. We are now at the cusp of a major transformation that can disrupt this balance. This disruption is triggered by an unprecedented convergence of massive compute with massive data, and some recent algorithmic advances. This confluence has the potential to spur a virtuous cycle of compute.Deep Learning was recently scaled to obtain 15PF performance on the Cori supercomputer at NERSC. Cori Phase II features over 9600 KNL processors. It can significantly impact how we do computing and what computing can do for us. In this talk, I will discuss some of the application-level opportunities and system-level challenges that lie at the heart of this intersection of traditional high performance computing with emerging data-intensive computing. Dr. Pradeep Dubey is an Intel Fellow and Director of Parallel Computing Lab (PCL), part of Intel Labs. His research focus is computer architectures to efficiently handle new compute- and data-intensive application paradigms for the future computing environment. He previously worked at IBM’s T.J. Watson Research Center, and Broadcom Corporation. He has made contributions to the design, architecture, and application-performance of various microprocessors, including IBM Power PC, Intel i386, i486, Pentium Xeon, and the Xeon Phi line of processors. He holds over 36 patents, has published more than 100 technical papers, won the Intel Achievement Award in 2012 for Breakthrough Parallel Computing Research, and was honored with Purdue University’s 2014 Outstanding Electrical and Computer Engineer Award. Dr. Dubey received a PhD in electrical engineering from Purdue University. He is a Fellow of IEEE.  Download the MP3 * Subscribe on iTunes * Subscribe to RSS  Check out our insideHPC Events Calendar

Shifter is a prototype implementation that NERSC is developing and experimenting with as a scalable way of deploying containers in an HPC environment. It works by converting user or staff generated images in Docker, Virtual Machines, or CHOS (another method for delivering flexible environments) to a common format. This common format then provides a tunable point to allow images to be scalably distributed on the Cray supercomputers at NERSC. The user interface to shifter enables a user to select an image from their dockerhub account and then submit jobs which run entirely within the container.

The O’Reilly Bots Podcast: Solutions from big data sets.In this episode of the O’Reilly Bots Podcast, I talk about deep learning at the extremes of scale and computing power with Prabhat, who leads the data and analytics group at Lawrence Berkeley National Laboratory’s supercomputing center. If you’re working on commercial AI, it’s worth glancing across the divide at scientific AI.Prabhat talks about his work at the the National Energy Research Scientific Computing Center (NERSC), including a project that aims to locate and quantify extreme weather events. He explains how this moves climate data analysis from a focus on core statistics—especially the change in the average mean temperature of the Earth in any given year—to analyzing the impact of extreme events.  He’s also working on the Celeste project, which uses telescope data to create a unified catalog of all objects in the visible universe. Looking ahead, Prabhat sees broad applications for deep learning in scientific research beyond climate science—especially in astronomy, cosmology, neuroscience, material science, and physics. Links: Prabhat’s new O’Reilly article, "A look at deep learning for science" Prabhat’s 2015 O’Reilly article "Big science problems, big data solutions" Prabhat’s presentation at Strata + Hadoop World 2016

The O’Reilly Bots Podcast: Solutions from big data sets.In this episode of the O’Reilly Bots Podcast, I talk about deep learning at the extremes of scale and computing power with Prabhat, who leads the data and analytics group at Lawrence Berkeley National Laboratory’s supercomputing center. If you’re working on commercial AI, it’s worth glancing across the divide at scientific AI.Prabhat talks about his work at the the National Energy Research Scientific Computing Center (NERSC), including a project that aims to locate and quantify extreme weather events. He explains how this moves climate data analysis from a focus on core statistics—especially the change in the average mean temperature of the Earth in any given year—to analyzing the impact of extreme events.  He’s also working on the Celeste project, which uses telescope data to create a unified catalog of all objects in the visible universe. Looking ahead, Prabhat sees broad applications for deep learning in scientific research beyond climate science—especially in astronomy, cosmology, neuroscience, material science, and physics. Links: Prabhat’s new O’Reilly article, "A look at deep learning for science" Prabhat’s 2015 O’Reilly article "Big science problems, big data solutions" Prabhat’s presentation at Strata + Hadoop World 2016

Addison Snell discusses how burst buffers are accelerating scientific solutions at NERSC with special guests Debbie Bard, Big Data Architect, National Energy Research Scientific Computing Center (NERSC) at Lawrence Berkeley National Lab and Mark Wiertalla, Product marketing director of the storage solutions team at Cray.

https://fasterdata.es.net/ http://www.es.net/about/esnet-staff/office-of-the-cto/Eli-Dart/ Eli Dart is a network engineer in the ESnet Science Engagement Group, which seeks to use advanced networking to improve scientific productivity and science outcomes for the DOE science facilities, their users, and their collaborators. Eli is a primary advocate for the Science DMZ design pattern, and works with facilities, laboratories, universities, science collaborations, and science programs to deploy data-intensive science infrastructure based on the Science DMZ model. Eli also runs the ESnet network requirements program, which collects, synthesizes, and aggregates the networking needs of the science programs ESnet serves. Eli has over 15 years of experience in network architecture, design, engineering, performance, and security in scientific and research environments. His primary professional interests are high-performance architectures and effective operational models for networks that support scientific missions, and building collaborations to bring about the effective use of high-performance networks by science projects. As a member of ESnet's Network Engineering Group, Eli was a primary contributor to the design and deployment of two iterations of the ESnet backbone network - ESnet4 and ESnet5. Prior to ESnet Eli was a lead network engineer at NERSC, DOE's primary supercomputing facility, where he co-led a complete redesign and several years of successful operation of the high-performance network infrastructure there. In addition, Eli spent 14 years as a member of SCinet, the group of volunteers that builds and operates the network for the annual IEEE/ACM Supercomputing conference series, from 1997 through 2010. He served as Network Security Chair for SCinet for the 2000 and 2001 conferences and was a member of the SCinet routing group from 2001 through 2010. Eli holds a Bachelor of Science degree in Computer Science from the Oregon State University College of Engineering.

This Week In HPC Episode 67 featuring Addison Snell and Michael Feldman. Bio-IT World Wrap-Up; NERSC Buys Another Cray Super.