Thought for the month
“The great tragedy of science - the slaying of a beautiful hypothesis by an ugly fact.”
Thomas Huxley, Scientist (1825-95).
Wednesday, 6 April 2011
Game Over or Next Level?
The above question is the subtitle and in effect the conclusion of a report into the future of computing power published by the National Research Council. The electronics industry is greatly concerned that microprocessor computing is coming to a “power wall”. As Moore’s Law runs out of steam and computing goes mobile, everyone is looking for ways to make the leap to new parallel programming solutions that use low-power multicore architectures. As single processors and CMOS technology approach the end of the technology line, the report concludes that chip designers and software developers must shift their focus to parallelism. To that end, the report specifically recommends that research should focus on:New algorithms that can exploit parallel processing; Developing new programming methods with an eye toward broader industry use; overhauling the traditional computing “stack” to account for parallelism and resource-management challenges; investing in new parallel architectures that are driven by emerging applications like mobile computing; investing in R&D that focuses on power efficiency at all system levels.