The High Performance Computing PodcastTopics including (but not limited to)....
Radio Free HPC (RFHPC) started in 2012 and, after a short break of 193 months, has returned to the airwaves (cyber waves?) with co-hosts Dan Olds, Henry Newman, and Shahin Khan.
The podcast covers a wide range of topics but is particularly focused on data center technology and challenges. These include high performance computing, power and cooling, new technology, and, really, whatever the hell they want to talk about.
Quick FAQ
"Why are you just covering HPC? There's this new thing called AI, have you heard of it?"
Yeah, we've heard of it and we do cover it. To us, HPC is a broad term used to refer to a very broad group of apps/workloads that have common characteristics.
- They are computationally intense
- Time to solution and quality of solution are critical
- The output is important enough to justify investment in high-end clusters and associated hardware/software
AI meets all of the criteria above just like bioscience, aerospace, weather prediction, and several other domains. In fact, AI is or will soon be folded into the workflows of nearly every 'traditional' HPC and enterprise application over time. This is going to put a lot of pressure on data centers and we'll be talking about how to deal with it.
"Was the old version of Radio Free HPC popular? I've never heard of it..."
Yes, it rose from obscurity to being mildly popular and, at times, entertaining. At our peak, we had as many as 16 sustained listeners and as many as 19 theoretical max listeners.
"I listened to the old show a couple of times and liked the arguing. Will there be more of that in this reboot?"
Yes, in fact we expect as much as 29% more arguing and a significant increase in the number of personal insults per episode.
"How often will this thing come out and how do I find out about it?"
We used to try to do weekly shows but failed due to other commitments, travel, etc. And there were just weeks when nothing important happened. But to answer your question, could be every couple of weeks, could be once a month, or we could record a marathon 8-10 hour single episode. Depends on what's happening and our mood.
We're getting together our RSS feeds and such but in the short term we'll be publicizing the episodes through the RFHPC X account and our individual social media accounts.
Ok, enough questions. If you want to learn more about the show and hosts, check out the "About" page.
Here are our most recent episodes along with the 345 or so previous editions, enjoy!
Latest Episode
-
In this podcast, the Radio Free HPC team reviews the latest TOP500 list of the world’s fastest supercomputers.The TOP500 celebrates its 25th anniversary with a major shakeup at the top of the list. For the first time since November 2012, the US claims the most powerful supercomputer in the world, leading a significant turnover in which four of the five top systems were either new or substantially upgraded.
Highlights:
#1 is Summit, an IBM-built supercomputer now running at the Department of Energy’s (DOE) Oak Ridge National Laboratory (ORNL), captured the number one spot with a performance of 122.3 petaflops on High Performance Linpack (HPL), the benchmark used to rank the TOP500 list. Summit has 4,356 nodes, each one equipped with two 22-core Power9 CPUs, and six NVIDIA Tesla V100 GPUs. The nodes are linked together with a Mellanox dual-rail EDR InfiniBand network.
#2 is Sunway TaihuLight, a system developed by China’s National Research Center of Parallel Computer Engineering & Technology (NRCPC) and installed at the National Supercomputing Center in Wuxi, drops to number two after leading the list for the past two years. Its HPL mark of 93 petaflops has remained unchanged since it came online in June 2016.
#3 is Sierra, a new system at the DOE’s Lawrence Livermore National Laboratory took the number three spot, delivering 71.6 petaflops on HPL. Built by IBM, Sierra’s architecture is quite similar to that of Summit, with each of its 4,320 nodes powered by two Power9 CPUs plus four NVIDIA Tesla V100 GPUs and using the same Mellanox EDR InfiniBand as the system interconnect.
#4 is Tianhe-2A, also known as Milky Way-2A, moved down two notches into the number four spot, despite receiving a major upgrade that replaced its five-year-old Xeon Phi accelerators with custom-built Matrix-2000 coprocessors. The new hardware increased the system’s HPL performance from 33.9 petaflops to 61.4 petaflops, while bumping up its power consumption by less than four percent. Tianhe-2A was developed by China’s National University of Defense Technology (NUDT) and is installed at the National Supercomputer Center in Guangzhou, China.
#5 The AI Bridging Cloud Infrastructure (ABCI) is the fifth-ranked system on the list, with an HPL mark of 19.9 petaflops. The Fujitsu-built supercomputer is powered by 20-core Xeon Gold processors along with NVIDIA Tesla V100 GPUs. It’s installed in Japan at the National Institute of Advanced Industrial Science and Technology (AIST).
#6 is Piz Daint in Switzerland with 19.6 petaflops.
#7-10 Titan (17.6 petaflops), Sequoia (17.2 petaflops), Trinity (14.1 petaflops), and Cori (14.0 petaflops) move down to the number six through 10 spots, respectively.
Download the MP3 * Subscribe on iTunes * RSS Feed
Sign up for our insideHPC Newsletter.
Recent Episodes
-
Episode 346: SC22 Preview
We’ve got the whole crew here as we look at the upcoming SC22 event. How many will be there? What will be happening? We answer only some of these questions.…
-
Episode 345: Dow Gets Cloudy
Dan rides alone on this one as he interviews the HPC folks from Dow who are behind their move to cloud bursting. Interesting and informative. *Download the MP3 * Follow…
-
Episode 344: Finally back! And with a new co-host!
We introduce new co-host Ben Carr and talk some NIST and Intel trevails. RadioFreeHPC is distributed in partnership with HPCwire. *Download the MP3 * Follow us on Twitter * Subscribe on Spotify * Subscribe…
-
Episode 343: It’s GTC, Baby
In this episode of RadioFreeHPC, Dan and Jessi talk GTC along with special guest Todd Weiss. RadioFreeHPC is distributed in partnership with HPCwire. *Download the MP3
-
Episode 342: Jazz, Melting Diamonds, and Schrödinger’s Cat
In this episode of RadioFreeHPC, the crew round up the most intriguing batch of recent HPC topics including Graphcore, HPC efforts to better understand melting diamonds and Jazz, as well…
-
Episode 341: Ponte Vecchio
In this episode of RadioFreeHPC, the crew talk Intel’s Ponte Vecchio. RadioFreeHPC is distributed in partnership with HPCwire. *Download the MP3 * Follow us on Twitter * Subscribe on Spotify * Subscribe on…
-
Episode 340: HPC with Trish Damkroger and Brent Gorda
In this episode of RadioFreeHPC, Dan and Jessi are joined by Trish Damkroger and Brent Gorda to talk HPC topics, thoughts, and intriguing trends. RadioFreeHPC is distributed in partnership with HPCwire.…
-
Episode 339: 12 Cores Per Soul
In this episode of RadioFreeHPC, the crew discusses Intel’s investment into RISC-V, the 2022 Winter Classic student cluster competition, and quantum computing in Canada. RadioFreeHPC is distributed in partnership with HPCwire.…
-
Episode 338: NVIDIA Slinks Away, Meta Bulks Up, And We Zap Bugs
In this episode of RadioFreeHPC, the crew talks Meta’s new AI supercomputer, NVIDIA abandoning ARM, and our latest competition winners. RadioFreeHPC is brought to you by the Surfs Up Hippie and…