Programmer Jack Dongarra receives Turing Award for bringing linear algebra to supercomputers

Jack Dongarra, the programmer who wrote a key piece of code for modern supercomputers, recently received one of computer science’s highest accolades: the Turing Prize, named after the tenth grade mathematician, computer scientist and code breaker. World War, Alan Turing.

Scientific research often relies on modeling things with numbers, because computer simulations are usually the best way to simulate something that you can’t – or at least really shouldn’t – make happen in the world. real world. You can watch what happens and hopefully learn something useful, but nothing (usually) actually explodes and no one is labeled a supervillain. And it turns out that a surprising number of things scientists like to simulate — from weather to economies — can be described in numerical form by a type of math called linear algebra.

In its most basic form, linear algebra uses equations of the form “y=mx+b” to describe the shape of a line on a graph. At the risk of inducing high school flashbacks, remember that “m” represents the slope of a line, and “b” represents the point where the line intersects the y-axis of the graph, while “x” and ” y” can represent any set of coordinates along the line.

These equations are a handy way to model how changing one variable will change another (if you already know how variables are related). On the other hand, they’re also great for understanding how two variables are related (if you just have a bunch of data but don’t yet know the equations that tie them all together). And the less basic linear equations are the tools scientists in multiple fields use to construct their mathematical simulations of the world around us — or of us and our behavior, for that matter.

In the late 1970s, Dongarra wrote a computer program called Linear Algebra Package, or Linpack for short, which made it easy to program and run complex linear equations on supercomputers.

About 20 years later, in the early 1990s, he used Linpack – the software he wrote – to measure how many calculations per second a supercomputer could perform. Called “floating point operations per second” or FLOPS, they measure the speed and power of a supercomputer. And of course, once engineers can consistently compare the speed and power of a technology, they’re going to, and they’re going to make lists about it.

The inevitable “Top500” list of the world’s most powerful supercomputers has tracked a major shift in the way the world’s most powerful computers are put together. For a long time, a supercomputer was a supercomputer because it had a much more powerful central processor (the main circuit of a computer) than a regular computer. However, from the early 2000s, parallel computing began to take over; the most powerful supercomputers in the world were actually huge arrays of ordinary desktop-sized processors, all networked together so that tens or hundreds of processors could be working on a problem at the same time . The Top500 list reflected this change; the newer parallel computers began to show themselves capable of more FLOPS than the old school type.

Recently, however, a new type of supercomputer is starting to dominate the list: cloud computers, which are just very, very large parallel computers, whose processors may not even all be in one place. Their development is mainly driven by private companies: mainly the big names in technology like Amazon and Google. But without Dongarra’s work providing a way to actually measure their potency, this trend might be harder to spot.

“We rely even more on cloud computing and will eventually abandon the ‘big iron machines’ inside national labs today,” Dongarra predicted in a recent interview with the New York Times.

Today, Dongarra is a professor at the University of Tennessee and a researcher at the Oak Ridge National Laboratory. The Association for Computing Machinery presented him with its prestigious Turing Award, which comes with a million dollar prize and well-deserved bragging rights, on March 30.

Leave a Reply

Your email address will not be published.