% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@INPROCEEDINGS{Li:1033553,
      author       = {Li, Jie and Michelogiannakis, George and Maloney, Samuel
                      and Cook, Brandon and Suarez, Estela and Shalf, John and
                      Chen, Yong},
      title        = {{J}ob {S}cheduling in {H}igh {P}erformance {C}omputing
                      {S}ystems with {D}isaggregated {M}emory {R}esources},
      publisher    = {IEEE},
      reportid     = {FZJ-2024-06434},
      pages        = {297-309},
      year         = {2024},
      abstract     = {Disaggregated memory promises to meet growing memory
                      requirements of applications while improving system resource
                      utilization in high-performance computing (HPC) systems.
                      Compared to traditional systems—where expensive resources
                      such as CPUs, GPUs, and memory, are assigned to jobs in
                      units of nodes—systems with disaggregated memory introduce
                      memory pools that can be shared among jobs; this introduces
                      new optimization metrics to the job scheduler. In this
                      paper, we propose a data-driven approach to evaluate job
                      scheduling and resource configuration in HPC systems with
                      disaggregated memory. To incorporate the memory requirements
                      of jobs for both local and disaggregated memory resources
                      and improve system efficiency in open-science HPC systems,
                      we introduce a novel job scheduling algorithm called FM
                      (Fair Memory). Our simulation results show that FM
                      outperforms commonly-used job schedulers in terms of jobs’
                      bounded slowdown when the shared memory pool capacity is
                      limited, and in terms of fairness under all conditions.},
      month         = {Sep},
      date          = {2024-09-24},
      organization  = {2024 IEEE International Conference on
                       Cluster Computing, Kobe (Japan), 24 Sep
                       2024 - 27 Sep 2024},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {5122 - Future Computing $\&$ Big Data Systems (POF4-512) /
                      DEEP-SEA - DEEP – SOFTWARE FOR EXASCALE ARCHITECTURES
                      (955606)},
      pid          = {G:(DE-HGF)POF4-5122 / G:(EU-Grant)955606},
      typ          = {PUB:(DE-HGF)8},
      doi          = {10.1109/CLUSTER59578.2024.00033},
      url          = {https://juser.fz-juelich.de/record/1033553},
}