@inproceedings{ author={ K. Kandalla, U. Yang, J. Keasler, T. Kolev, A. Moody, H. Subramoni, K. Tomko, J. Vienne, D. Panda }, title={ Designing Non-blocking Allreduce with Collective Offload on InfiniBand Clusters: A Case Study with Conjugate Gradient Solvers }, conference={ International Parallel and Distributed Processing Symposium 2012 }, year={ 2012 }, month={ May }, location={ }, source={ http://nowlab.cse.ohio-state.edu/publications/ }, }