Climbing El Capitan? Details Detailed!

 Supercomputer Leaps to New Peaks

At the top of the show we discuss whether Indiana (where Jessi is located at Purdue) is in the heartland or not. We all agree that it is and, yes, Jessi sees Larry Bird all the time.

Getting into the heart of the episode, Dan talks about the briefing he received on the new Lawrence Livermore El Capitan system to be built by HPE/Cray. This new $600 million system will be fueled by the AMD Genoa processor coupled with AMD’s Instinct GPUs. Performance should come in at TWO 64-bit exaflops peak, which is very, very sporty. The new box (more like a room) will be 10x faster than today’s fastest supercomputer and faster than the top 200 supercomputers in the world – combined.

As the show continues, we talk about the specifics of the system and components. Henry make the unfortunate mistake of bringing up IEEE floating point and sending Dan into a mini-rant. Back to the show, the system should require somewhere close to 30MW worth of electricity, which is much lower than the nearly 60MW predicted just a year or so ago. Not surprisingly, the system will be liquid cooled, but not, as we speculate, cooled by Slushy machines. We have a tremendous tech talk around the varying aspects of the machine and AMD’s great progress in clawing their way back into the market. Well worth a listen.

Why No One Should Ever Be Online. Ever.

In this edition, Henry talks about how an ultrasonic hack can make your phone vulnerable to pownership. Just sending the exact right frequency of sound to a phone sitting on a solid object might be enough to unlock it and let a miscreant get at all of your goodies. Yikes!

Catch of the Week

Jessi:  Astronaut applications have opened up again! If you ever wanted to go to space, this might be your chance. You’ll want to have a strong science and computing background – plus hero or heroine good looks wouldn’t hurt either.

Shahin:  Discusses AMD vs. NVIDIA GPU comparative shipment figures from 4Q2019.

Henry:  Net is empty, ouch.

Dan:  Bees can count to six, which is hugely disquieting. If bees can do math, we might be doomed. Maybe this is why beehives are hexagonal?

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

One Big Debate over OneAPI

For RF-HPC aficionados, it’s a typical opening for this episode. Henry is counting down the days until he moves to sunny Los Cruces and we have a lull in the conversation right after the introductions. We recover quickly and move onto the main course of today’s show:

Intel’s OneAPI project

The OneAPI project is a highly ambitious initiative; trying to design a single API to handle CPUs, GPUs, FPGAs, and other types of processors. In the discussion, we look under the hood and see how this might work. One thing working in Intel’s favor is that they’re using data parallel C++, which is highly compatible with CUDA – and which is probably Intel’s target with this new initiative.

Henry points out that porting codes is a pain and that no one wants to port to another API if it can possibly be avoided, so he predicts that most customers will not want to use it and if they consider it, before they move any code, they need to be sure that this new API is going to stick around for many years.

Shahin is generally positive on the project. Henry and Dan to have a rare moment of agreement in disputing Shahin’s thoughts about several things! Let's start with his view that Java has provided portability in exchange for performance – and then improved its performance. Henry and Dan take issue with this, with Henry saying that Java provides little real performance and Dan saying that programs have changed to provide Java performance rather than Java changing to provide performance. Shahin believes that OneAPI is a good thing for the industry and will be successful. Dan believes it’s a good thing for Intel, but has doubts about whether it’s good for the industry. Henry doesn’t see big adoption for the foreseeable future saying, “It has a long way to go and it’s a significant risk.” Dan and Henry end up agreeing and agreeing to disagree with Shahin. Jessi is safely on the fence on this one.

It’s a very good conversation, well worth a listen.

Why Nobody Should Ever be Online. Ever.

This week, Henry shares a personal story about key fobs and a very troubling problem he found with his latest rental car. It has everything, thrills, chills and a shocking conclusion.

Catch of the Week

Jessi:  The Department of Defense has built a supercomputer in a shipping container, for sending to wherever its computation is needed. The supercomputer itself is designed to work on AI-related problems, and falls under the classification of "AI on the edge," where data is processed in the same location it is collected. While it’s not news, it’s news to Jessi and it’s cool, so it’s her catch of the week.

Shahin:  Tells the story of a reporter renting a shared car service, which is unlocked by a cell phone. The reporter ventures out into the hinterlands a little bit and finds that she can’t get the car to work anymore. Why? Because there wasn’t enough cell phone coverage to properly start the car – meaning that the reporter had to wait (and wait) for a person to be sent out to physically interact with the car and get it going again. Yikes – think out your products, people, ok?

Henry:  Hackers made a home for themselves inside Citrix for five months, siphoning off personal and financial information. Yikes again. The company had to be alerted by the FBI to the hack and, assumedly, their internal tools didn’t pick up the penetration. That’s a long time to be exploited!

Dan:  McAfee researchers show that just a few strips of tape on a road sign can prompt a Tesla car to accelerate by an astounding 50 miles per hour over the posted speed limit on that sign. According to Dan, this is a bad thing.

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

Let's Learn Deeply about Extreme Weather

This week we have Dan, Jessi, and Shahin on the call. Henry is off in Los Cruces overseeing construction of what can only be called a bunker. Why? Its main feature is 21-inch rammed earth walls, guaranteed to withstand withering heat waves, cold snaps, and probably any high caliber round. We speculate on the exact configuration of the home, wondering if Henry is running wild with the rammed earth and concrete theme, with concrete chairs and tables, plus rammed earth interior walls.

Applying Deep Learning to Extreme Weather

Dan deftly moves us on to the main topic of this show, how researchers are using supercomputers to apply deep learning to extreme weather. A research team from Rice University utilized three supercomputers (TACC’s Stampede 2, Wrangler, and Pittsburg Supercomputing Center’s Bridges system) to see if data on heat waves and cold spells could be predicted by analysis of atmospheric circulation and prior surface temperature. The results of these tests indicated that this deep learning approach is more accurate at predicting extreme weather.

In the call, we discuss the computational difficulty of weather forecasting and the use case that the Rice researchers are testing. This promising research can pay great dividends in terms of  giving early warning to hazardous weather, saving crops and perhaps saving lives in the process.  As promised in the podcast, here’s a link to the paper. We also have a short discussion of what motivates Dan to read a particular paper and what turns him off. Jessi’s main standard in papers is that it has to be able to be printed in black and white and remain legible and understandable. So if you want to attract Jessi’s attention for your paper, make sure your charts don’t use color.

Things You Think You Know, But Maybe Don't.

The question this week is why Cray computers were horseshoe shaped.  One of the reasons was wire length and this shape puts the components closely together to reduce the length of the wires needed to connect them. It also gave them enough room for a person to get their hands inside to weave the wires. So the key was minimal, uniform, and accessible wire length. There are also a couple of other explanations, one is that it gave room for the liquid cooling pipes necessary to cool the box, another is that the system forms a capital “C” shape, which stands for, of course, Cray.

Catch of the Week

Henry: is away this week. (We know some of you don't read this all and come straight here!)

Jessi:  Tells us that the US might want to take a close look at Estonia as a model to overcome cybersecurity. The country has put together a civilian cybersecurity force and instituted mandatory cyber classes in schools. This is a response to massive cyberattacks launched against Estonia in 2007 that took down much of their digital infrastructure for weeks.

Shahin:  Discusses how Justine Haupt came up with a way to keep her cell phone from distracting her – she built a rotary dial interface for it. Along with helping save her from using the most time-wasting features on her phone, it will also confound an entire generation of folks who have never seen a rotary phone dialer. Justine also is working in robotics and has a page of her inventions and thoughts.

Dan:  Brings up a story about a man convicted of murder mainly on the basis of DNA evidence, although that evidence was shaky, mainly saying that they couldn’t exclude him. His case was reopened by the Innocence Project who reached out to a company called Cybergenetics for further analysis. Cybergenetics ran samples through their 170,000 line AI algorithm and found that there was zero chance that the convicted man’s DNA was present in the sample. So the man will be released, which is great. The problem is that the Cbyergenetics code is a black box and the company, citing competitive advantage, will not release the code.  How should we deal with situations like this in the future?

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

Slingshotting to Exascale, It's Hot!

At the top of this episode, Henry notes that the temperature in his city will be touching -15F, which is plenty cold. However, it’s very good overclocking weather as Dan and Shahin point out. Not quite quantum weather, unfortunately.

Cray Slingshot Interconnect

We quickly get to the main topic of the day, an examination of HPE/Cray’s Slingshot interconnect. It’s Ethernet on HPC steroids and will be the interconnect of choice for their upcoming slate of Exascale systems. Slingshot includes a bunch of HPC enhancements while maintaining compatibility with existing Ethernet devices and protocols. Cray has designed a new Ethernet superset of features that includes smaller headers, support for smaller message sizes, plus other features aimed at cutting Ethernet latency and improving performance on HPC-oriented interconnect tasks. At the heart of this new interconnect is their innovative 64 port switch that provides a maximum of 200 Gb/s per port and can support Cray’s enhanced Ethernet along with standard Ethernet message passing. It also has advanced congestion control and quality of service modes that ensure that each job gets their right amount of bandwidth.
The architecture can scale to an astounding 279,040 endpoints, which is, as we note, “a lot of endpoints.” We also kick around the possibility that HPE/Cray might sell the interconnect as a standalone for use with competitive gear.



As mentioned on the call, the chips on this switch run so hot that they need liquid cooling – a first for interconnect processors. We also discuss the rising heat load coming from new CPUs and particularly ASICs and how network design can greatly impact costs. Listen to the show to learn about more, it’s a good and meaty discussion.

Why Nobody Should Ever be Online. Ever.

Henry’s latest reason why we need to abandon the internet cracks us all up. What’s so funny? It’s that the Phillips smart lightbulbs need a firmware upgrade in order to prevent miscreants from pwoning your entire network. No kidding, it’s true. And hilarious. Here’s the link. This has Henry thinking about how to protect his new home from war flying drones. He’s looking into drone killing home-based air defense systems or perhaps a whole-home Faraday cage.

Catch of the Week

Henry:  Another security related story, this time about low level exploits in the Cisco Discovery Protocol (CDP) that can expose tens of millions of devices to internet troublemakers. This is highly disturbing since there is so much Cisco gear out there and the fix relies on users updating their firmware to plug the holes. Ouch.

Jessi:  Brings athletics into the podcast, which is the cause of some banter about how totally un-athletic the rest of us are (with the exception of Jessi, of course). Nike is using big time computation to 3D print their new uppers to give athletes the ultimate advantage in shoe performance.

Shahin:  Alerts us to a comprehensive review of AMD’s Ryzen Threadripper 3990X, the first CPU in the world to sport 64 cores. This CPU is currently the top of AMD’s line and is just another signpost signaling AMD’s resurgence. Welcome back, AMD.

Dan:  As we covered in a prior episode, Microsoft had the fantastic idea of forcing their corporate Office 365 users to have Microsoft’s Bing installed as their default search engine, using an update to accomplish this task. Well, the users have spoken and their voice was heard loud and clear in Redmond. The company is retreating from their forced ‘upgrade’ to Bing and back pedaling with all due speed. Hee. Hee.

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