Back to Volume
Paper: HPC Development for the ALMA Pipeline
Volume: 521, Astronomical Data Analysis Software and Systems XXVI
Page: 581
Authors: Castro, S.; Gonzalez, J.; Taylor, J.; Bhatnagar, S.; Caillat, M.; Ford, P.; Golap, K.; Jakobs, J.; Kawasaki, W.; Kern, J.; Kuniyoshi, M.; Loveland, S.; Mehringer, D.; Miel, R.; Moellenbrock, G.; Nakazato, T.; Petry, D.; Pokorny, M.; Rao, U.; Schiebel, D.; Kugimoto, K.; Suoranta, V.; Tsutsumi, T.
Abstract: CASA, the Common Astronomy Software Applications, has the primary goal of supporting the data processing needs of ALMA and VLA. The Parallelisation framework implemented in CASA uses MPI, the Message Passing Interface, which is accessible at run time through a wrapper of the MPI executor called mpicasa. We use MPI Python bindings to control the parallelisation of high-level CASA tasks and will soon start to use MPI C bindings for specific low-level C++ parts of CASA.
The parallelisation in CASA is achieved by partitioning the input MeasurementSet (MS) into several pieces that are virtually concatenated. Once the data is partitioned into a so-called Multi-MS, the CASA parallelised tasks are able to detect it automatically and if a cluster is available, sub-tasks are sent to the cluster nodes using MPI.
Back to Volume