Delving into Highly Efficient Fast Fourier Transform for Exascale Computing

A feature article contributed to the high-performance computing (HPC) industry publication HPCwire by Jack Dongarra and Stanimire Tomov of the University of Tennessee examines what is called Fast Fourier Transform (FFT) relative to exascale computing. FFT is considered one of the top 10 algorithms of the 20th century.

At the heart of the piece is an examination of a Highly Efficient FFT for exascale (heFFTe) library for the coming class of exascale supercomputers. The design and implementation of the library is the aim of an effort within the Software Technology research focus area of the US Department of Energy’s Exascale Computing Project. Read more.