@inproceedings{ author={ K. Kandalla, H. Subramoni, K. Tomko, D. Pekurovsky, S. Sur, D. Panda }, title={ High-Performance and Scalable Non-Blocking All-to-All with Collective Offload on InfiniBand Clusters: A Study with Parallel 3D FFT }, conference={ International Supercomputing Conference '11 (ISC'11) }, year={ 2011 }, month={ June }, location={ }, source={ http://nowlab.cse.ohio-state.edu/publications/ }, }