Browsing by Author "Jokanovic, Ana"

Now showing items 1-5 of 5

    • DJSB: Dynamic Job Scheduling Benchmark 

      López Herrero, Víctor; Jokanovic, Ana; D'Amico, Marco; Garcia Gasulla, Marta; Sirvent Pardell, Raül; Corbalán González, Julita (Springer, 2018-02-28)
      Conference lecture
      Open Access
      High-performance computing (HPC) systems are very big and powerful systems, with the main goal of achieving maximum performance of parallel jobs. Many dynamic factors influence the performance which makes this goal a ...

    • DROM: Enabling Efficient and Effortless Malleability for Resource Managers 

      D'Amico, Marco; Garcia Gasulla, Marta; López, Victor; Jokanovic, Ana; Sirvent, Raül; Corbalán González, Julita (Association for Computing Machinery (ACM), 2018-08-13)
      Conference lecture
      Open Access
      In the design of future HPC systems, research in resource management is showing an increasing interest in a more dynamic control of the available resources. It has been proven that enabling the jobs to change the number ...

    • Evaluating SLURM simulator with real-machine SLURM and vice versa 

      Jokanovic, Ana; D'Amico, Marco; Corbalán González, Julita (Institute of Electrical and Electronics Engineers (IEEE), 2018)
      Conference report
      Open Access
      Having a precise and a fast job scheduler model that resembles the real-machine job scheduling software behavior is extremely important in the field of job scheduling. The idea behind SLURM simulator is preserving the ...

    • Holistic slowdown driven scheduling and resource management for malleable jobs 

      D'Amico, Marco; Jokanovic, Ana; Corbalán González, Julita (Association for Computing Machinery (ACM), 2019)
      Conference report
      Open Access
      In job scheduling, the concept of malleability has been explored since many years ago. Research shows that malleability improves system performance, but its utilization in HPC never became widespread. The causes are the ...

    • Randomizing task placement does not randomize traffic (enough) 

      Jokanovic, Ana; Prisacari, Bogdan; Rodriguez, German; Minkenberg, Cyriel (2013)
      Conference report
      Restricted access - publisher's policy
      Dragonflies are one of the most promising topologies for the Exascale effort for their scalability and cost. Dragonflies achieve very high throughput under uniform traffic, but have a pathological behavior under other ...