@conference {1481, title = {heFFTe: Highly Efficient FFT for Exascale}, booktitle = {International Conference on Computational Science (ICCS 2020)}, year = {2020}, month = {2020-06}, address = {Amsterdam, Netherlands}, abstract = {Exascale computing aspires to meet the increasing demands from large scientific applications. Software targeting exascale is typically designed for heterogeneous architectures; henceforth, it is not only important to develop well-designed software, but also make it aware of the hardware architecture and efficiently exploit its power. Currently, several and diverse applications, such as those part of the Exascale Computing Project (ECP) in the United States, rely on efficient computation of the Fast Fourier Transform (FFT). In this context, we present the design and implementation of heFFTe (Highly Efficient FFT for Exascale) library, which targets the upcoming exascale supercomputers. We provide highly (linearly) scalable GPU kernels that achieve more than 40{\texttimes} speedup with respect to local kernels from CPU state-of-the-art libraries, and over 2{\texttimes} speedup for the whole FFT computation. A communication model for parallel FFTs is also provided to analyze the bottleneck for large-scale problems. We show experiments obtained on Summit supercomputer at Oak Ridge National Laboratory, using up to 24,576 IBM Power9 cores and 6,144 NVIDIA V-100 GPUs.}, keywords = {exascale, FFT, gpu, scalable algorithm}, doi = {https://doi.org/10.1007/978-3-030-50371-0_19}, author = {Alan Ayala and Stanimire Tomov and Azzam Haidar and Jack Dongarra} }