Supercomputing for the Exascale Era

Supercomputing for the Exascale Era

Cray, an HPE company, held a panel discussion webinar on October 18 to discuss Exascale (10^18, get it?) supercomputing. This is definitely not in my area of expertise, but it is certainly interesting.

Following is information I gleaned from links they sent to me. Basically, it is Why Supercomputing. And not only computers, but also networking to support them.

Today’s science, technology, and big data questions are bigger, more complex, and more urgent than ever. Answering them demands an entirely new approach to computing. Meet the next era of supercomputing. Code-named Shasta, this system is our most significant technology advancement in decades. With it, we’re introducing revolutionary capabilities for revolutionary questions. Shasta is the next era of supercomputing for your next era of science, discovery, and achievement.

WHY SUPERCOMPUTING IS CHANGING

The kinds of questions being asked today have created a sea-change in supercomputing. Increasingly, high-performance computing systems need to be able to handle massive converged modeling, simulation, AI, and analytics workloads.

With these needs driving science and technology, the next generation of supercomputing will be characterized by exascale performance, data-centric workloads and diversification of processor architectures.

SUPERCOMPUTING REDESIGNED

Shasta is that entirely new design. We’ve created it from the ground up to address today’s diversifying needs.

Built to be data-centric, it runs diverse workloads all at the same time. Hardware and software innovations tackle system bottlenecks, manageability, and job completion issues that emerge or grow when core counts increase, compute node architectures proliferate, and workflows expand to incorporate AI at scale.

It eliminates the distinction between clusters and supercomputers with a single new system architecture, enabling a choice of computational infrastructure without tradeoffs. And it allows for mixing and matching multiple processor and accelerator architectures with support for our
new Cray-designed and developed interconnect we call Slingshot.

EXASCALE-ERA NETWORKING

Slingshot is our new high-speed, purpose-built supercomputing interconnect. It’s our eighth generation of scalable HPC network. In earlier Cray designs, we pioneered the use of adaptive routing, pioneered the design of high-radix switch architectures, and invented a new low-diameter system topology, the dragonfly.

Slingshot breaks new ground again. It features Ethernet capability, advanced adaptive routing, first-of-a-kind congestion control, and sophisticated quality-of-service capabilities. Support for both IP-routed and remote memory operations broadens the range of applications beyond traditional modeling and simulation.

Quality-of-service and novel congestion management features limit the impact to critical workloads from other applications, system services, I/O traffic, or co-tenant workloads. Reduction in the network diameter from five hops (in the current Cray XCTM generation) to three reduces cost, latency, and power while improving sustained bandwidth and reliability.

FLEXIBILITY AND TCO

As your workloads rapidly evolve, the ability to choose your architecture becomes critical. With Shasta, you can incorporate any silicon processing choice — or a heterogenous mix — with a single management and application development infrastructure. Flex from single to multi-socket nodes, GPUs, FPGAs, and other processing options that may emerge, such as AI-specialized accelerators.

Designed for a decade or more of work, Shasta also eliminates the need for frequent, expensive upgrades, giving you exceptionally low total
cost of ownership. With its software architecture you can deploy a workflow and management environment in a single system, regardless of packaging.

Shasta packaging comes in two options: a 19” air- or liquid-cooled, standard datacenter rack and a high-density, liquid-cooled rack designed to take 64 compute blades with multiple processors per blade.

Additionally, Shasta supports processors well over 500 watts, eliminating the need to do forklift upgrades of system infrastructure to accommodate higher-power processors.

Siemens Spotlight on Innovation

Siemens Spotlight on Innovation

I flew to Orlando May 22 as a guest of Siemens along with a select few other “influencers” to be introduced to a number of innovation projects fueled by Siemens technology. We met at the Dr. Phillips Center for Performing Arts in downtown Orlando (did you even know there was a downtown?), which itself is filled with Siemens equipment. There are few companies in the industrial area which I cover that have the vision and execution that Siemens is exhibiting right now.

By the way, there is a fantastic little taco place in downtown Orlando. Email or DM on Twitter, and I’ll share the name. Greg Hale of ISSSource.com and I had dinner there Wednesday. We agreed—among the best tacos we’ve had.

Barbara Humpton, CEO Siemens USA, led with an overview. Siemens has made a greater than $1B investment in R&D in the US with 7,000 engineers churning out 700 inventions per year.

She introduced former stunt man and motorcycle racer turned CEO Mike “Mouse” McCoy, CEO & Founder of HackRod. McCoy built on a foundation of Siemens PLM and SolidEdge CAD. He added a gaming engine. He was able to use VR for design reviews, interference checking, and simulation during the design process. We followed along with design and review of a new motorcycle. A few parts required somewhat exotic materials. Oak Ridge National Labs printed the parts from the design files downloaded from HackRod. The design teams were in Ventura, CA and Princeton, NJ with input from Munich, Germany. Collaboration was not a problem.

Beginning of design until component parts shipped to Orlando—2 weeks. The parts arrived Tuesday. McCoy and a partner assembled the motorcycle on Tuesday evening and wheeled (not drove) it onto the stage Wednesday about 1:30. Not bad? Heck, in my early career, we couldn’t have done a foam-core mock up in that time frame.

One thought McCoy left us with. “We need to talk STEAM, not just STEM—science, technology, engineering, arts, math.” It is now possible for artists and designers to be an intimate part of the team going from art to finished product quickly. 3D printing from PLM files. Way cool.

How about a high school mechanical design student given a project to provide a lighter prosthetic foot for an Army vet? Humpton introduced 18-year-old high school student Ashley Kimbel who had undertaken just such a project. She worked with the veteran to analyze his current “foot” looking for areas where weight could be eliminated. Then she had to learn how to fabricate and manufacture the device. We saw films of the veteran running with Ashley proving out the new prosthetic.

This is a long way from projects I had as a 17-year-old senior. Education and technology have come a long way in a lifetime. Oh, and her future? She wants to work in bioengineering designing and 3D printing organs. She will be working on that during her tenure at UAB. She is going to make a difference for many people.

I have many more ideas and conversations to capture. This will serve for now.
Check out #SiemensInnovates

Three Dangerous Ideas From Ray Kurzweil

Three Dangerous Ideas From Ray Kurzweil

Peter Diamandis, entrepreneur and founder of Singularity University and XPRIZE among many other things, interviewed his friend Ray Kurzweil at the Googleplex for a 90-minute (live) webinar on disruptive and dangerous ideas.

Diamandis promotes what he calls Abundance Thinking. He says, “By consuming and considering a steady diet of ‘crazy ideas,’ you train yourself to think bigger and bolder… a critical requirement for making impact. As humans, we are linear and scarcity-minded. As entrepreneurs, we must think exponentially and abundantly. At the end of the day, the formula for a true breakthrough is equal to ‘having a crazy idea’ you believe in, plus the passion to pursue that idea against all naysayers and obstacles.”

Kurzweil is Co-founder and Chancellor of Singularity University. He is also an XPRIZE Trustee, the Director of Engineering at Google, and “one of the best predictors of our exponential future.”

Diamandis and Kurzweil recorded a 90-minute conversation recorded on the YouTube video linked above. Here are 3 compelling ideas that came from the conversation as reported by Diamandis and sent in his newsletter. If you haven’t run across him, I recommend subscribing and having your mind blown.

The Nation-State Will Soon Be Irrelevant

Historically, we humans don’t like change. We like waking up in the morning and knowing that that the world is the same as the night before.

That’s one reason why government institutions exist: to stabilize society.

But how will this change in 20 or 30 years? What role will stabilizing institutions play in a world of continuous, accelerating change?

“Institutions stick around, but they change their role in our lives,” Ray explained. “They already have. The nation-state is not as profound as it was. Religion used to direct every aspect of your life, minute to minute. It’s still important in some ways, but it’s much less important, much less pervasive. [It] plays a much smaller role in most people’s lives than it did, and the same is true for governments.”

Ray continues: “We are fantastically interconnected already. Nation-states are not islands anymore. So we’re already much more of a global community. The generation growing up today really feels like world citizens much more than ever before, because they’re talking to people all over the world and it’s not a novelty.”

(Diamandis) previously shared (his) belief that national borders have become extremely porous, with ideas, people, capital and technology rapidly flowing between nations. In decades past, your cultural identity was tied to your birthplace. In the decades ahead, your identify is more a function of many other external factors. If you love space, you’ll be connected with fellow space-cadets around the globe more than you’ll be tied to someone born next door.

We’ll hit longevity escape velocity before we realize we’ve hit it

Ray and I share a passion for extending the healthy human lifespan.

I frequently discuss Ray’s concept of “longevity escape velocity” — the point at which, for every year that you’re alive, science is able to extend your life for more than a year.

Scientists are continually extending the human lifespan, helping us cure heart disease, cancer, and eventually neurodegenerative disease. This will keep accelerating as technology improves.

During my discussion with Ray, I asked him when he expects we’ll reach “escape velocity…”

His answer? “I predict it’s likely just another 10 to 12 years before the general public will hit longevity escape velocity.”

“At that point, biotechnology is going to have taken over medicine,” Ray added. “The next decade is going to be a profound revolution.”

From there, Ray predicts that nanorobots will “basically finish the job of the immune system,” with the ability to seek and destroy cancerous cells and repair damaged organs.

As we head into this sci-fi-like future, your most important job for the next 15 years is to stay alive. “Wear your seatbelt until we get the self-driving cars going,” Ray jokes.

The implications to society will be profound. While the scarcity-minded in government will react saying, “Social Security will be destroyed,” the more abundance-minded will realize that extending a person’s productive earning lifespace from 65 to 75 or 85 years old would be a massive boom to the GDP.

Technology will help us define and actualize human freedoms

The third dangerous idea from my conversation with Ray is about how technology will enhance our humanity, not detract from it.

You may have heard critics complain that technology is making us less human, and increasingly disconnected.

Ray and I share a slightly different viewpoint: that technology enables us to tap into the very essence of what it means to be human.

“I don’t think humans even have to be biological,” explained Ray. “I think humans are the species that changes who we are.”

Ray argues that this began when humans developed the earliest technologies — fire and stone tools. These tools gave people new capabilities, and became extensions of our physical bodies.

At its base level, technology is the means by which we change our environment, and change ourselves. This will continue, even as the technologies themselves evolve.

“People say, ‘Well, do I really want to become part machine?’ You’re not even going to notice it,” says Ray, “because it’s going to be a sensible thing to do at each point.”

Today, we take medicine to fight disease and maintain good health, and would likely consider it irresponsible if someone refused to take a proven, life-saving medicine.

In the future, this will still happen — except the medicine might have nanobots that can target disease, or will also improve your memory so you can recall things more easily.

And because this new medicine works so well for so many, public perception will change. Eventually, it will become the norm… as ubiquitous as penicillin and ibuprofen are today.

In this way, ingesting nanorobots, uploading your brain to the cloud, and using devices like smart contact lenses can help humans become, well, better at being human.

Ray sums it up: “We are the species that changes who we are to become smarter and more profound, more beautiful, more creative, more musical, funnier, sexier.”

My Take

I began studying international relations 50 years ago under an interesting professor. He was well up the chain at the CIA, Colonel in US Army Intelligence, PhD from Georgetown. Also, he was sort of a rebel. He took a liking to a somewhat rebellious kid from the farmlands.

It’s evident that the nation-state is in its death-throes. Trump and Xi and Putin are all trying to find ways to reassert power over a society and businesses that are increasingly global. Yes, there are emotional loyalties. But take a big step back and look at the sweep of history of the past 150 years. Think about what you see.

Technology throughout the entire history of humans has been both good and bad. But overall, it has benefitted humans. We eat better (well within our power of choice—don’t choose Doritos), live longer, have better housing and clothing, travel faster. We also have machines to help with backbreaking and dangerous labor.

As Diamandis says, think abundance rather than scarcity.

The Future of Farming with Internet of Things

The Future of Farming with Internet of Things

We need to feed an ever increasing global population. One major problem concerns loss of good farmland to urban development.

AeroFarms is an agriculture start up leveraging the latest of ag science along with technologies such as Internet of Things with Dell Technologies IoT platform to help solve a big problem.

The company president presented at the IQT Day event. It’s a powerful example of using technology to do good for the world. Here is a link to a video interview.  You’ll have to scroll down when you get to the page. Worth three minutes of your time–followed by an hour of thinking about using your engineering talents to solve big problems.

 

Rockwell Automation Invests $12M to Bring Science and Technology to Next Generation Workforce

Rockwell Automation Invests $12M to Bring Science and Technology to Next Generation Workforce

11-14-16-first-students-and-rockwell-automation-ceoRockwell Automation has long supported FIRST — For Inspiration and Recognition of Science and Technology —  among other things supplying floor space during Automation Fair so that students can show off robotic projects. Now Rockwell Automation has announced a $12M, four-year commitment to inspire young people’s interest and participation in science and technology.

Over the past 10 years, Rockwell Automation has provided more than $15M of broad-based support to address the critical need to fill science, technology, education and math (STEM) jobs that drive innovation. Many of these jobs go unfilled because of both the lack of awareness of the kinds of high-tech jobs available, and the lack of skills to qualify for today’s needs.

“Through our technology and people, we are helping to inspire the next generation of innovators to fill the talent pipeline for our customers and for our company,” said Blake Moret, President and CEO, Rockwell Automation. “Our strategic partnership with FIRST helps us increase our reach and visibility to STEM students around the world.”

11-14-16-first-girls-working-on-robot

In addition to being a global sponsor of the FIRST LEGO League program and sole sponsor of the FIRST Robotics Competition (FRC) Rockwell Automation Innovation in Control Award, nearly 200 Rockwell Automation employees around the world donate their time for the FIRST programs, and more than 300 employees volunteer for the organization in other capacities. The company also donates products integral to FIRST program games and scoring. These product donations are specifically used for the FIRST Robotics Competition playing fields and scoring systems, and they are included within the parts kits teams use to build their robots.

“This generous, multiyear commitment from Rockwell Automation will allow us to focus on the strategic aspects of our partnership while continuing to help scale our programs and expose students to a broader range of industry-leading products and applications,” said Donald E. Bossi, President, FIRST. “The company has a long, rich history of supporting FIRST.”

11-14-16-first-and-rockwell-automation-with-check

Rockwell Automation is recognized as a FIRST Strategic Partner, which signifies the highest levels of sponsorship available at FIRST. It is also a FIRST Robotics Competition Crown Supplier.

Accomplished inventor Dean Kamen founded FIRST (For Inspiration and Recognition of Science and Technology) in 1989 to inspire an appreciation of science and technology in young people. Based in Manchester, N.H., FIRST designs accessible, innovative programs to build self-confidence, knowledge, and life skills while motivating young people to pursue opportunities in science, technology, and engineering. With support from over 200 of the Fortune 500 companies and more than $30 million in college scholarships, the not-for-profit organization hosts the FIRST Robotics Competition for students in Grades 9-12; FIRST Tech Challenge for Grades 7-12; FIRST LEGO League for Grades 4-8; and FIRST LEGO League Jr. for Grades K-4. Gracious Professionalism is a way of doing things that encourages high-quality work, emphasizes the value of others, and respects individuals and the community.

Follow this blog

Get a weekly email of all new posts.