Speaker
Adam Kisiel
(Warsaw University of Technology)
Description
MPD experiment requires running a massively parallel computing tasks (hundreds of thousands of jobs) for the simulation of physics processes and MPD detector response. The advanced management, monitoring and reporting for such large-scale tasks is required. The task involves development and/or application of proper management, monitoring and reporting tools for routine operation of the Monte-Carlo simulations for MPD. Tasks will be run on large-scale computing clusters - LIT and NICA Cluster (>5k CPU cores each).
Work requires good knowledge of Linux, cluster management software (job schedulers) and web technologies for on-line reporting of computing resources status.
Primary author
Adam Kisiel
(Warsaw University of Technology)
