Anders Jensen (@.) on 2/14/08 wrote:
---------------------------
>Anders Jensen (@.) on 2/14/08 wrote:
>---------------------------
>>Quoted from the white paper "The Landscape of Parallel Computing Research: A View from Berkeley".
>>
>>This paper just gave Berkeley $10M over 5 years from MS and Intel to research the
>>future of parallel computing. Happy reading.
>http://www.eecs.berkeley.edu/Pubs/TechRpts/2006/EECS-2006-183.html
>
>http://www.eetimes.com/news/design/showArticle.jhtml?articleID=206503988

"The industry is in a little bit of a panic about how to program multi-core processors, especially heterogeneous ones," said Chuck Moore, a senior fellow at Advanced Micro Devices trying to rally support for work in the area. "To make effective use of multi-core hardware today you need a PhD in computer science. That can't continue if we want to enable heterogeneous CPUs," he said.

How very laughable. The computer science PhDs I've met couldn't even make effective use of *single-core* hardware. In my experience, anyone with a PhD in computer science needs to be kept very far away from actual computers. Like the newly minted CS PhD we hired at JPL, who decided it was a good idea to actually implement an FFT using recursion. I had no idea you could make an FT so slow (screw the "F")... These PhDs are probably the last guys you want telling you how to chart a course for the future.

And hello, nobody remembers Thinking Machines? We've already done the massively parallel exercise, many times before. The game hasn't changed, the rules of the game haven't changed.