File input and output can become bottlenecks for parallel programs running on large numbers of processors. EuroCC-UK staff at EPCC investigated how to increase the MPI-IO performance on ARCHER2, the UK National HPC service, using the Cray Lustre lockahead options, which had not been previously investigated on this system. This was followed by an investigation of the performance of ADIOS2, a more modern parallel IO library. Finally, the team looked at the performance of IO from a real HPC application rather than a synthetic benchmark.
New EuroCC-UK Technical Report: Increasing the MPI-IO performance on ARCHER2
File input and output can become bottlenecks for parallel programs running on large numbers of processors. EuroCC-UK staff at EPCC investigated how to increase the MPI-IO performance on ARCHER2, the […]
YOU MAY ALSO LIKE
-
Workshop: CFD on HPC – OpenFOAM case (May 27 – 29, 2024 via Zoom)
The three-day workshop organised by NCC Slovenia and its partner, Faculty of Mechanical Engineering, University of Ljubljana, is aimed at researchers, engineers, students and others interested in CFD on HPC […]
-
Registration to the 4th Baltic HPC and Cloud Conference is now open
We invite research communities that use HPC, including students, HPC experts, industry representatives, as well as governmental representatives to attend the 4th Baltic HPC and Cloud Conference that will take […]