Speaker
Robin bozennec
(INRIA)
Description
One of the information that HPC batch schedulers use to schedule jobs on the
available resources is user runtime estimates: an estimation provide by the user
of how long their job will run on the machine. These estimates are known to be
inaccurate, hence many work have focused on improving runtime prediction.
In this work, we start by discussing bias and limitations of the most used
optimization metrics and provide elements on how to evaluate performance when
studying HPC batch scheduling,
Then we study qualitatively the impact of improving runtime estimates on
these various optimization criteria.
| JLESC topic | scheduling in HPC |
|---|
Primary authors
Robin bozennec
(INRIA)
Guillaume Pallez
(Inria)
