Changes between Version 5 and Version 6 of Public/User_Guide/TAMPI_NAM
- Timestamp:
- Mar 3, 2021, 12:53:37 PM (4 years ago)
Legend:
- Unmodified
- Added
- Removed
- Modified
-
Public/User_Guide/TAMPI_NAM
v5 v6 28 28 * The '''GNU''' or '''Intel®''' Compiler Collection. 29 29 30 * The '''ParaStationMPI''' installation supporting '''multi-threading''' and featuring the '''libNAM''' extension that allows access to NAM memory regions through MPI RMA windows.30 * The '''ParaStationMPI''' installation supporting '''multi-threading''' and featuring the '''libNAM''' integration that allows access to NAM memory regions through MPI RMA windows. 31 31 32 32 * The '''Task-Aware MPI (TAMPI)''' library which defines a clean '''interoperability''' mechanism for MPI and OpenMP/!OmpSs-2 tasks. It supports both blocking and non-blocking MPI operations by providing two different interoperability mechanisms. Downloads and more information at [https://github.com/bsc-pm/tampi]. … … 35 35 36 36 * The NAM software allowing access to NAM memory. 37 38 In this benchmark, we use the NAM memory to perform checkpointing of the matrix that we are computing. During the execution of the application and every a few timesteps, the benchmark instantiate multiple tasks that save the whole matrix into a NAM region. There is a task for saving the data of each block into that region and may run in parallel. 37 39 38 40 === Building & Executing on DEEP ===