We don't know what to do with all the multi-core chips we already have, never mind the eight and sixteen core processors looming on the horizon. The software is not keeping pace with the hardware. That realization is dawning over all the big players in computer chip design and tech educators. Think tanks dedicated to parallel computing are being founded and funded at numerous prestigious universities, including Stanford University, with support from all the big chip players, hoping to close the gap between the silicon and the ones and zeros.
The Stanford lab, which will cost $6 million over three years, will be led by Kunle Olukotun, a professor of electrical engineering and computer science. Olukotun helped pioneer the idea of multicore microprocessors, which have since gained rapid popularity in both corporate and consumer computer hardware.
The most advanced corporate server microprocessor, as well as processors for video game machines, have up to eight cores. While operating systems -- the basic layer of software that runs a computer -- can work with this type of hardware, software engineers widely acknowledge that most applications, ranging from corporate productivity software to multimedia programs, are not designed for efficient use of the dozens or hundreds of processors expected in future computers.
Chip manufacturers understand that there's no reason for you to upgrade your machines if the increases in computing hardware are wasted by a lack of multi-thread software to run them, so they're stepping up to the plate to fund the research. See? Greed is good sometimes.