The code in question is called "FUN3D" and was first developed in the 1980s. It's still an important part of the agency's computational fluid dynamics (CFD) capability, and had its most recent release in September 2016.
The agency is now sponsoring a competition with the aim of getting it to go at least 10 times faster. If you can crank it up to ten thousand times faster – without any loss of accuracy – all the better.
Michael Hetle, program executive at NASA's Transformative Aeronautics Concepts Program (TACP) explains that "some concepts are just so complex, it's difficult for even the fastest supercomputers to analyse these models in real time. Achieving a speed-up in this software by orders of magnitude hones the edge we need to advance our technology to the next level".
[Update: Original story title was taken directly from the referenced article; updated to remove condescension. --martyb]
(Score: 1, Funny) by Anonymous Coward on Friday May 05 2017, @05:30AM
I'm sure there are plenty of overeager students who would invest a free summer for a chance at the $55K in prize money.
True, but their schedule would look something along the lines of
Week1: Try to learn FORTRAN, bitch loudly about FORTRAN and its limitations, try to grok existing codebase in said language..
Week2: Bitch about what little of the code they've grokked in Week1, make sarky remarks on forums/IRC about the code and its original programmers
Week3: Re-implement their vision of what the code should really be like, and what the code should really do, in JavaScript/Rust/Go/whatever .. and, as they're all wunderkinder nowadays they'll have the code done and dusted by day2, week3, then they'll crow about how superior their new code is vs the old stuff on forums/IRC, then slack off the rest of the week...
Week4: Testing? what do you mean?, what is this testing thing that you speak of? (I once had to deal [read: bug fix/rewrite] with the output of a wunderkind who couldn't get his little head round the idea that his task was to re-implement an existing FORTRAN codebase in a.n.other language, not fucking with the algorithms, not decide that the algorithms were somehow 'wrong' and fixing them... his improvements showed up when we ran the test data-sets through his code and compared the results to those produced by the old code, he was so cock-sure of himself he'd never tested that his code gave the right answers with real data, just tested that it worked with his idea of test data..)