High performance FFT on GPUs

A reader writes: "The UNC GAMMA group has recently released a high performance FFT library which can handle large 1-D FFTs. According to their webpage, the FFT library is able to achieve 4x higher computational performance on a $500 NVIDIA 7900 GPU than optimized Intel Math Kernel FFT routines running on high-end Intel and AMD CPUs costing $1500-$2000. The library is supported for both Linux and Windows platforms and is tested to work on many programmable GPUs. There is also a link to download the library freely for non-commerical use."

Comments

Cray-1 comparison

[Mostly a lurker]

The Cray-1A supercomputer, weighing in at 5.5 tons, had an absolute maximum peak performance of 250 megaflops. It, of course, cost millions and the power requirements (including for cooling) were in excess of 200 kW. I remember marveling at the advanced nature of this technological achievement.

Thirty years later, a $500 GPU, weighing less than 1 pound, can produce 6 gigaflops. People complain about its power and cooling needs, but they are rather below 200 kW! We sometimes forget just how amazing the developments in computing have been over the last three decades.