EuroMPI/USA 2021 will have a renewed focus on new developments and applications of the Message Passing Interface (MPI). This includes new proposed concepts and extensions to the MPI standard, libraries and languages built on top of MPI, interfaces to other standards in parallel programming, applications and optimizations to new architectures and networks, novel algorithms, and tools, with particular focus on quality, portability, performance, and scalability.

We invite high-quality, full and short paper submissions on all topics related to MPI. Papers will be reviewed for quality, originality, clarity, correctness, technical strength, and relevance to the topics of the meeting. Reviews are blind (but not double-blind), the names of the authors will be seen by the program committee.

To be considered, papers must be formatted according to the "sigconf" style in the ACM 2017 Template and up to 10 pages in length (full paper) or up to 5 pages in length (short and position papers) in PDF format, however shorter papers are welcome.

The page limit includes figures, tables, and appendices, but does not include references, for which there is no page limit. Margins and font sizes should not be modified. Submissions will be handled via EasyChair.

TOPICS

We focus on all topics related to MPI. Topics of interest include, but are not limited to:

    Efficient and scalable implementations of MPI libraries.
    Scalability of MPI for Exascale and beyond
    Interactions of MPI with accelerators (including GPUs, FPGAs and Quantum Systems)
    Support in MPI for modern network hardware and in-network compute
    Extensions to MPI, alternative interfaces and solutions.
    New, parallel MPI-I/O mechanisms optimizations, incl. near storage compute.
    Hybrid and heterogeneous programming with MPI and other interfaces.
    Interactions between MPI and other parallel programming standards
    MPI-based concepts for new workloads, including AI and data-intensive applications.
    Fault tolerance in and with MPI
    MPI parallel programming in clouds and non-dedicated systems.
    Performance evaluation for MPI libraries and MPI-based applications.
    Automatic performance tuning of MPI applications and implementations.
    Verification of message-passing applications, implementations and protocols.