U.S. IBM supercomputer is world's fastest: It does matter

My ZDnet colleague Zack Whittaker, just published a commentary called U.S.
Written by Dan Kusnetzky, Contributor on

My ZDnet colleague Zack Whittaker, just published a commentary called U.S. IBM supercomputer is world's fastest: Does it matter?. In this piece, Zack looked at the announcement that IBM’s “Sequoia” has taken the crown as the world’s fastest supercomputer and dismissed it as just another announcement of another tool for research.

What the good Mr. Whittaker had to say

It’s not the computing power that matters: it’s the human capital. In a global environment where a U.S. scientist can rent access to an Asian supercomputer, it doesn’t particularly matter which country boasts the top supercomputer.

Ultimately it’s about where the people who know how to use these machines are. The scientists, the researchers, the meteorologists, astrologists: the list goes on.

The U.S. may claim home to some the world’s top scientists, just as China has for two non-consecutive years claimed the world’s fastest computer.

At the end of the day: supercomputers are just tools.

Quick rejoinder

After reading Zack's commentary, I felt that I had to reply. On the one hand, he is right. A supercomputer is a very useful tool for many types of research and analysis. Like any other tool, the research and analyis is where the focus should be.

On the other hand, IBM or any other supplier's ability to create such a complex, powerful computing research is of extreme importance. The thought, the tools and the procedures needed to build and operate such a huge system are directly applicable to other types of computing.

For example, by deploying such a huge system IBM and other supercomputer competitors are demonstrating the following:

  • They are investing in developing faster and faster computing resources. In IBM's case, this means pushing the abilities of its Power Architecture processors, the supporting internal bus structure, the supporting memory infrastructure, the supporting network and storage I/O infrastructure to new heights.
  • They have developed ways to tie a very large number of systems together and make it work like a single computing resource -- this ability to scale monitoring, operations and automation software is highly useful today and will be increasingly useful as organizations deploy cloud computing solutions
  • They have developed ways to reduce the overall power consumption and heat production that will help the industry make best use of our limited environmental resources.
So, Zack, while the research and analysis supported by this supercomputer are very important, it really is a demonstration of how IBM has pushed the underlying technology to new levels of power and scalability. This push demonstrates the company's ability to address even the most extreme computing requirements. Doesn't this benefit the whole market rather than just the few researchers who will be able to use this individual supercomputer?
Editorial standards