Graphics chipmaker Nvidia intends to move forward in the supercomputing segment by building neural computing networks on GPUs that replicate the electrical behavior of a brain's nerve cells. The result is cheaper computing power. "Programs that previously ran on supercomputers, we're now realizing we can rewrite to run on GPUs at a fraction of the price," said David Anderson, a computer scientist at the University of California, Berkeley. Intel is also banking on its next version of Xeon Phi to provide even greater programming efficiency.

Related Summaries