@inproceedings{
  author={ B. Ramesh, N. Contini, N. Alnaasan, K. Suresh, M. Abduljabbar, A. Shafi, H. Subramoni, D. Panda },
  title={ HINT: Designing Cache-Efficient MPI_Alltoall using Hybrid Memory Copy Ordering and Non-Temporal Instructions },
  conference={ 38th IEEE International Parallel & Distributed Processing Symposium },
  year={ 2024 },
  month={ May },
  location={ San Francisco, California },
  source={ http://nowlab.cse.ohio-state.edu/publications/ },
}