OnDeloc-MPI: automatic MPI process mapping for adapting to tasks' communication behaviors and coordinating locality and memory congestion

Please see the following papers for more details:

Agung, M., Amrizal, M. A., Egawa, R., & Takizawa, H. (2019). An Automatic MPI Process Mapping Method Considering Locality and Memory Congestion on NUMA Systems. IEEE 13th International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSoC), 17-24. https://doi.org/10.1109/MCSoC.2019.00010.

Agung, M., Amrizal, M. A., Egawa, R., & Takizawa, H. (2020). Online MPI Process Mapping for Coordinating Locality and Memory Congestion on NUMA Systems. Supercomputing Frontiers and Innovations, 7(1), 71–90. https://doi.org/10.14529/jsfi200104

Usage

Prerequisite:

• OpenMPI 3.x dependencies

Compile:

$ ./configure
$ make & make install

How to cite

If you find this work useful in your research, please cite the paper using this bibtex reference:

    @ARTICLE{Agung_Amrizal_Egawa_Takizawa_2020, 
    title={Online MPI Process Mapping for Coordinating Locality and Memory Congestion on NUMA Systems}, 
    volume={7}, 
    url={https://superfri.org/index.php/superfri/article/view/299}, 
    DOI={10.14529/jsfi200104}, number={1}, journal={Supercomputing Frontiers and Innovations}, 
    author={Agung, Mulya and Amrizal, Muhammad Alfian and Egawa, Ryusuke and Takizawa, Hiroyuki}, 
    year={2020}, 
    month={Apr.}, 
    pages={71–90} }