November 16, 2012
There are two types of people in supercomputing – people that have a top 10 supercomputer and people that don’t. Or people who understand the exascale problem and people who understand the missing middle problem. Or people who have scalable applications and people that don’t.
Or people who claim just two types of person and then list several non-exclusive options.
In my usual part serious, part provocative style, here is my light-hearted look at the different personality stereotypes involved in high performance computing. This is by no means an exclusive list, but it does illustrate the range of people who contribute to the flavor of the world of supercomputing.
1. The Great Wall of China type. “Our supercomputer is so big you can see it from outer space!” To these people, the size of the supercomputer is the primary factor determining standing in the supercomputing world. They’ll talk to you if your supercomputer can be seen from low orbit, will feel sorry for you if your machine is only visible from low flying aircraft, and refuse to acknowledge your relevance if your system is only visible from the ground.
Now, in no way am I suggesting that the size of a supercomputer is not important. Almost self-evidently it is. A more powerful supercomputer can enable more realistic simulations, new kinds of science enquiry, or more comprehensive data analytics.
And sometimes real breakthroughs do occur as a direct result of the scale of the supercomputer used. But smaller supercomputers, even ones not visible from altitude, also deliver cutting edge science, engineering and data analytics.
2. The Apocalypse type. These people are convinced the end of supercomputing is at hand. Most of them focus on the technology challenges that seemingly erect impassable barriers to our progress. Exascale can’t happen because of power. And even if we could afford the power, we wouldn’t be able to program it. And even then, the system/application would collapse in a statistically inevitable heap of errors after a few minutes. Not to mention the skills shortage. We may as well give up now and just keep deploying the systems we have now.
Then there are the ones who proclaim that doom is not technological; it is political and financial. They argue that we cannot sustain the increasing budgets at the national lab scale, nor will senior managers in research-led businesses fund the increasing demand for supercomputer technology to enable higher fidelity simulation and deeper analytics. Quite rightly, they preach that simply quoting wonderful science is not enough justification (to the world outside of HPC) for these investments. This is where the Fort Knox types come in.
3. The Fort Knox type. It’s about the money to these people. They are driven by the big dollar deals, ideally, the high profit margin ones. They are reluctant to invest time in meetings, travel, projects, or acquisitions that don’t provide a substantial financial return this year. They often inhabit the parts of the ecosystem with better margins or with commercial applicability outside HPC (e.g. storage, networking, and so on) or sometimes can be found in those HPC vendors that keeping trying to discover a profitable business in selling solutions to buyers of technology with aggressive cost ambitions.
They are among the sharpest dressers, the most ardent advocates of their piece of the ecosystem, and get the least passionate interest from the buyers and users of supercomputers. Money and supercomputing always have been strange partners. Clearly, money, and lots of it, is required to fund the development, deployment, and operation of supercomputers and their enabling technologies (e.g. software).
But with such a technically dominated population of inhabitants, the HPC space often struggles to focus on this harsh reality. If companies can’t make money, or we can’t persuade politicians (and, by extension, the general public) to invest, then the R&D that is the lifeblood feeding the future of our world will weaken.
Likewise, the need to prove the economic return on investments in HPC services (both hardware and software) in commercial and academic/national lab spaces cannot be forgotten. The Fort Knox types have a crucial role to play in ensuring HPC continues to sustainably deliver its great potential. But the focus on money must balance with the pursuit of the technical race without which supercomputing would be meaningless.
4. The Art Gallery type. Keen to assure you as early as possible in the conversation that they are not technical – they leave technical detail to other people. Presenting a front of pride in their non-technical status, these people are usually, but not always, sales or business management people. However, a chink in their psyche appears, when they almost immediately follow up and make sure you know they once wrote some code.
Thus, they probably do recognize the integral value of technical understanding in the HPC world. But, either they are nervous about their lack of understanding (don’t be – not everyone is an expert – just be willing!) or they are hoping their stance will come across as above the detail (not good – this is often a detail game). And, in reality, the world of HPC is marked by significant technical expertise in so many of the people in sales positions, senior management or other traditionally business focused roles.
But there are also many who are not experts (or maybe aren’t anymore) but who have enough technology or science understanding to play their part in the ecosystem. Be proud of the technical knowledge you do have, honestly admit its limits, and be keen to learn more as needed. But then, you could say that about any skill, not just HPC.
5. The Horse-drawn Cart type. “I remember when …” This person is able to turn any conversation about next year’s technology or this week’s implementation issue into a prolonged reminiscence of their distant childhood making supercomputers out of wooden sticks and spittle. Filled with “we tried that years ago,” “we had it much harder,” or “we should go back to the way we used to do it,” these monologues eventually stall as the polite but glazed expressions cemented on the faces around the room slowly reveal the audience has departed to mind-wandering land.
Occasionally, these reminiscences take a life of their own as dialogue springs forth – yes, those dreaded occasions when there is more than one Horse-drawn Cart type in the room. Sometimes, there are gems of insight relevant to the present or future to be found in these experiences though. The key to finding the gems is distinguishing the Horse-drawn Cart types from the Concorde types.
6. The Concorde type. Now that it is no longer flying the world with brutal performance and elegant class, this marvel of engineering brilliance and commercial application is distressingly easily seeping away from our memory. I’m writing this article sat in one of the other flagships of aviation, the Boeing 747, as I cross the Atlantic on my way to Salt Lake City for SC12 (there are about a dozen other HPC people just within a few rows of me).
But, much as I appreciate the 747 as probably the elder statesman of the skies, I wish the Concorde was still flying. Not that I’d expect to ride in it; it’s out of my league. But it is a shame that we have thrown away such a monumental capability: the 3 hour transatlantic crossing. That is a different class of interchange between London and New York than the current journey of a whole day’s flying.
More amazing still was that it was essentially 1960s technology. And this is my link to supercomputing. Some great technological achievements have peppered the history of supercomputing – processors, systems, algorithms, software implementations, etc. Many of them have been overtaken by subsequent products or technology shifts, but many we still rely on directly or via their evolutionary successors. And, supercomputing too, is judged on the capability it enables, not merely the engineering brilliance of the technology implementation.
And the people part? Well, people made those great supercomputing technology advances. Some are sadly gone, many are still with us. In the fullness of the modern HPC ecosystem it is easy to let the impact of those technological leaps and their creators seep from our memory. Don’t.
So there you go – a selective stereotyping of the people that make supercomputing the marvel that we know - so powerful in its impact, often frustrating in its reality, usually addictive to those who encounter it, but always special. And, hopefully a few serious points about our community have been highlighted along the way. How many of these types did you see at SC12 this week? What types have I missed? Which, if any, are you?
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?