Franz Franchetti, Yevgen Voronenko and G. Almasi (Proc. High Performance Computing for Computational Science (VECPAR), 2012)
Automatic Generation of the HPC Challenges Global FFT Benchmark for BlueGene/P
Preprint (151 KB)
Published paper (link to publisher)

We present the automatic synthesis of the HPC Challenge’s Global FFT, a large 1D FFT across a whole supercomputer system.We extend the Spiral system to synthesize specialized single-node FFT libraries that combine a data layout transformation with the actual on-node FFT computation to improve the network performance through enabling all-to-all collectives. We run our optimized Global FFT benchmark on up to 128k cores (32 racks) of ANL’s BlueGene/P “Intrepid” and achieved 6.4 Tflop/s, outperforming ANL’s 2008 HPC Challenge Class I Global FFT run (5 Tflop/s). Our code was part of IBM’s winning 2010 HPC Challenge Class II submission. Further, we show first single-thread results on BlueGene/Q.

Fast Fourier Transform, BlueGene, Automatic generation