A new, patent-pending idea called “Warp processing” has been developed by Frank Vahid, a Prof of Computer Science and Engineering at the University of California, Riverside.
The technique give computers the ability to improve their own performance over time.
Here’s how Warp processing works: when a program first runs on a microprocessor (such as a Pentium), the chip monitors the program to detect its most frequently-executed parts.
The microprocessor then automatically moves those parts to 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,’ explained Vahid.
‘If the microprocessor then finds that the FPGA is faster for that particular part of the program, it automatically moves it to the FPGA, causing the program execution to ‘warp.’”
By performing optimisations at runtime, Warp processors eliminate the extra designer effort associated with traditional compile-time optimisations.
FPGAs can benefit a wide range of applications, including video and audio processing, encryption and decryption, encoding, and compression and decompression – anything that is compute-intensive and operates on large streams of data.
The benefits of Warp processing are just being discovered by the computing industry. A range of companies including IBM, Intel and Motorola’s Freescale have already pursued licenses for the technology through UCR’s funding source, the Semiconductor Research Corporation.