file.pdf (152.4 kB)
Download file

Automatic Generation of the HPC Challenge’s Global FFT Benchmark for BlueGene/P

Download (152.4 kB)
journal contribution
posted on 01.07.2012, 00:00 by Franz Franchetti, Yevgen Voroneko, Gheorghe Almasi

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.


Publisher Statement

The final publication is available at Springer via



Usage metrics