Changes between Version 16 and Version 17 of 2016WP/CMCC_2016
- Timestamp:
- 2016-01-05T13:05:14+01:00 (8 years ago)
Legend:
- Unmodified
- Added
- Removed
- Modified
-
2016WP/CMCC_2016
v16 v17 34 34 ---- 35 35 === '''CMCC-1 - Scalability with MPI-OPENMP ''' === 36 ''' Motivation:''' Improving NEMO scalability. ''' Status: ''' continuation of 2015 dev CMCC-1 [[BR]] '''Main Tasks:'''36 ''' Motivation:''' Improving NEMO scalability. ''' Status: ''' continuation of 2015 dev CMCC-1 [[BR]] ''' Main Tasks:''' 37 37 38 38 * the activity started at the end of 2013 with the analysis of three OpenMP approaches (implemented using “mini-apps”) on several multicore architectures; the second step was the implementation of the hybrid version of the GYRE configuration using the best OpenMP approach. Some improvements to the implementation have been performed by Intel to match Intel architectures. During 2016, the extension of the hybrid implementation to the entire code is planned 39 39 * analysis of scalability improvement using MPI3 new communications (e.g. collective neighbours communications), instead of point to point communications 40 40 41 ''' Science Reviewer:''' Prof. G. Aloisio (University of Salento & CMCC)[[BR]] ''' System Reviewer:''' [[BR]] ''' Deadline:''' December 2016[[BR]] ''' Priority:''' HIGH [[BR]] ''' Depends on:''' results of the same action in 2015[[BR]] ''' Principal Investigator : '''Silvia Mocavero (silvia.mocavero@cmcc.it)41 ''' Science Reviewer:''' Prof. G. Aloisio (University of Salento & CMCC)[[BR]] ''' System Reviewer:''' Tim Graham[[BR]] ''' Deadline:''' December 2016[[BR]] ''' Priority:''' HIGH [[BR]] ''' Depends on:''' results of the same action in 2015[[BR]] ''' Principal Investigator : ''' Silvia Mocavero (silvia.mocavero@cmcc.it) 42 42 43 43 === '''CMCC-2 - Suppress global communications ''' === 44 '''Motivation:''' Removing global communications could help improve the speed of NEMO [[BR]]'''Status: '''Not started [[BR]]'''Main Tasks:''' 44 ''' Motivation:''' Removing global communications could help improve the speed of NEMO [[BR]] ''' Status: ''' Not started [[BR]] ''' Main Tasks:''' 45 45 46 * code analysis to list all mpp_sum, mpp_max, mpp_min in the code, except those used in the initialisation phase and those used in the solver routines (that will disappear). Silvia Mocavero to investigate which communications could be safely removed. Tim Graham to look at a more efficient implementation of functionality in stp_ctl 46 * [https://forge.ipsl.jussieu.fr/nemo/wiki/discussion discussion] 47 * [https://forge.ipsl.jussieu.fr/nemo/wiki/discussion discussion] with NEMO_st to see what can be done to suppress the identified global communications 47 48 * implementation of the solution. 48 49 49 ''' Science Reviewer:''' [[BR]]'''System Reviewer:''' [[BR]]'''Deadline:''' June 2016[[BR]]'''Priority:''' HIGH[[BR]]'''Depends on:''' [[BR]]'''Principal Investigator : '''Silvia Mocavero (silvia.mocavero@cmcc.it)/Tim Graham50 ''' Science Reviewer:''' [[BR]] ''' System Reviewer:''' [[BR]] ''' Deadline:''' June 2016[[BR]] ''' Priority:''' HIGH[[BR]] ''' Depends on:''' [[BR]] ''' Principal Investigator : ''' Silvia Mocavero (silvia.mocavero@cmcc.it)/Tim Graham 50 51 51 52 === '''CMCC-3 - BDY for nested limited area models''' === 52 ''' Motivation:''' Improving nesting techniques for regional and sub-regional circulation models nested into coarser models [[BR]] ''' Status :''' [[BR]] ''' Main tasks :''' 1. Implementation of the generalised Flather’s condition for the barotropic component (Oddo & Pinardi, 2008); 2. Interpolation Constraint applied to total velocity field for preserving the transport conservation across open boundaries [[BR]] ''' Science Reviewer:''' Prof. N. Pinardi (University of Bologna) [[BR]] ''' System Reviewer:''' [[BR]] ''' Deadline:''' [[BR]] ''' Priority:''' [[BR]] ''' Depends on:''' [[BR]] ''' Principal Investigator : '''Stefania Ciliberti (stefania.ciliberti@cmcc.it)53 ''' Motivation:''' Improving nesting techniques for regional and sub-regional circulation models nested into coarser models [[BR]] ''' Status :''' [[BR]] ''' Main tasks :''' 1. Implementation of the generalised Flather’s condition for the barotropic component (Oddo & Pinardi, 2008); 2. Interpolation Constraint applied to total velocity field for preserving the transport conservation across open boundaries [[BR]] ''' Science Reviewer:''' Prof. N. Pinardi (University of Bologna) [[BR]] ''' System Reviewer:''' [[BR]] ''' Deadline:''' [[BR]] ''' Priority:''' [[BR]] ''' Depends on:''' [[BR]] ''' Principal Investigator : ''' Stefania Ciliberti (stefania.ciliberti@cmcc.it) 53 54 54 55 === '''CMCC-4 - BDY tool development and tests ''' === 55 ''' Motivation: ''' Testing and assessing the pre-processing tool for the computation of boundary datasets compatible with BDY module for open boundary conditions [[BR]] ''' Status :''' [[BR]] ''' Main tasks :''' NERC will finish last improvement of the BDY tool and add some documentation, and CMCC will test the BDY tool on regional configurations [[BR]] ''' Science Reviewer:''' [[BR]] ''' System Reviewer:''' [[BR]] ''' Deadline:''' [[BR]] ''' Priority:''' [[BR]] ''' Depends on:''' [[BR]] ''' Principal Investigator : '''Stefania Ciliberti (stefania.ciliberti@cmcc.it) and James Harle (jdha@noc.ac.uk)56 ''' Motivation: ''' Testing and assessing the pre-processing tool for the computation of boundary datasets compatible with BDY module for open boundary conditions [[BR]] ''' Status :''' [[BR]] ''' Main tasks :''' NERC will finish last improvement of the BDY tool and add some documentation, and CMCC will test the BDY tool on regional configurations [[BR]] ''' Science Reviewer:''' [[BR]] ''' System Reviewer:''' [[BR]] ''' Deadline:''' [[BR]] ''' Priority:''' [[BR]] ''' Depends on:''' [[BR]] ''' Principal Investigator : ''' Stefania Ciliberti (stefania.ciliberti@cmcc.it) and James Harle (jdha@noc.ac.uk) 56 57 57 58 === '''CMCC-5 - Remove key_mpp_rep (SIMPLIF-3)''' === 58 ''' Motivation:''' Set the use of MPI safe computation as a default [[BR]] ''' Status :''' [[BR]] ''' Main tasks :''' remove the use of the macro key_mpp_rep and use as a default condition the MPI safe communications [[BR]] ''' Science Reviewer:''' Gurvan Madec [[BR]] ''' System Reviewer:''' Gurvan Madec [[BR]] ''' Deadline:''' [[BR]] ''' Priority:''' [[BR]] ''' Depends on:''' [[BR]] ''' Principal Investigator : '''Dorotea Iovino (diovino@cmcc.it)59 ''' Motivation:''' Set the use of MPI safe computation as a default [[BR]] ''' Status :''' [[BR]] ''' Main tasks :''' remove the use of the macro key_mpp_rep and use as a default condition the MPI safe communications [[BR]] ''' Science Reviewer:''' Gurvan Madec [[BR]] ''' System Reviewer:''' Gurvan Madec [[BR]] ''' Deadline:''' [[BR]] ''' Priority:''' [[BR]] ''' Depends on:''' [[BR]] ''' Principal Investigator : ''' Dorotea Iovino (diovino@cmcc.it) 59 60 60 61 === '''CMCC-6 - Remove key_bdy macro (SIMPLIF-4)''' === 61 ''' Motivation:''' reduce the use of macros in NEMO [[BR]] ''' Status :''' [[BR]] ''' Main tasks :''' Remove the macro activating the code for the open boundary treatment in favour of static code always present in compilation and activated only when bdy are required by the user configuration [[BR]] ''' Science Reviewer:''' Gurvan Madec [[BR]] ''' System Reviewer:''' Gurvan Madec [[BR]] ''' Deadline:''' [[BR]] ''' Priority:''' [[BR]] ''' Depends on:''' [[BR]] ''' Principal Investigator : '''Tomas Lovato (tomas.lovato@cmcc.it)62 ''' Motivation:''' reduce the use of macros in NEMO [[BR]] ''' Status :''' [[BR]] ''' Main tasks :''' Remove the macro activating the code for the open boundary treatment in favour of static code always present in compilation and activated only when bdy are required by the user configuration [[BR]] ''' Science Reviewer:''' Gurvan Madec [[BR]] ''' System Reviewer:''' Gurvan Madec [[BR]] ''' Deadline:''' [[BR]] ''' Priority:''' [[BR]] ''' Depends on:''' [[BR]] ''' Principal Investigator : ''' Tomas Lovato (tomas.lovato@cmcc.it) 62 63 63 64 === '''CMCC-7 - Revise bdy structure (ROBUST-5)''' === 64 ''' Motivation:''' Generalise the structure of BDY schemes used by OPA and TOP [[BR]] ''' Status :''' [[BR]] ''' Main tasks :''' Revise the code structure of available open boundary conditions in order to have generalised schemes in one place that can be used for either active and passive tracers (like e.g. for the advection) [[BR]] ''' Science Reviewer:''' C. Ethé [[BR]] ''' System Reviewer:''' C. Ethé [[BR]] ''' Deadline:''' [[BR]] ''' Priority:''' [[BR]] ''' Depends on:''' [[BR]] ''' Principal Investigator : '''Tomas Lovato (tomas.lovato@cmcc.it)65 ''' Motivation:''' Generalise the structure of BDY schemes used by OPA and TOP [[BR]] ''' Status :''' [[BR]] ''' Main tasks :''' Revise the code structure of available open boundary conditions in order to have generalised schemes in one place that can be used for either active and passive tracers (like e.g. for the advection) [[BR]] ''' Science Reviewer:''' C. Ethé [[BR]] ''' System Reviewer:''' C. Ethé [[BR]] ''' Deadline:''' [[BR]] ''' Priority:''' [[BR]] ''' Depends on:''' [[BR]] ''' Principal Investigator : ''' Tomas Lovato (tomas.lovato@cmcc.it)