This week National Public Radio (NPR) in the United States is airing a special series that looks at the state of global supercomputing.
From China’s top position on the rankings to energy efficiency for the next generation of supers, the radio event is providing a glimpse into the world of HPC for listeners who would otherwise probably not encounter high performance computing news.
The host of the series interviewed a number of luminaries in HPC, most of whom are academics or HPC researchers. For instance, Jack Dongarra from the University of Tennessee and TOP500 suggested during yesterday’s installment that the Chinese system could be considered an “expensive white elephant” as it is not clear how it will be used. As Dongarra told host Louisa Lim:
“So they have a race car. And now you have to build something around the race car in order to effectively use it. You can’t just invest in the hardware. You need to make an investment across the board. Sometimes these ecosystems are out of balance, and as a result of that, the computer would be very hard to use.”
This particular installment focused on supercomputing as a national point of pride and the perceived “usefulness” of China’s Tianhe-1A. It also touched on the challenges that China will face in developing applications that are well-suited to run it, addressing the idea that this is a “gaming” system versus anything of practical value.
Outside of its emphasis on competition versus solid technology, this installment is worth a listen, as are others that can be found at npr.org.