Warp Speed Computing
by
Charlie Bess
There’s been talk for a while about the slowing down of Moore’s law, for a variety of reasons like: gates are only 5 atoms thick, can’t get the heat out of the chip, etc. Various techniques are being used to get around this limitations, like multi-core. Frank Vahid at U of Cal Riverside is working on research that leads to processors that can optimize on the fly. In some situations, it claims to be able to process work 1000 times faster than conventional microprocessors, by using field-programmable gate arrays.
When a program first runs on a microprocessor chip, the chip monitors the program to detect its most frequently-executed parts. The microprocessor then automatically tries to move those parts of the program to a special kind of chip called a field-programmable gate array, or FPGA. “An FPGA can execute some (but not all) programs much faster than a microprocessor – 10 times, 100 times, even 1,000 times faster,” explains Vahid.
