New URL for NEMO forge!   http://forge.nemo-ocean.eu

Since March 2022 along with NEMO 4.2 release, the code development moved to a self-hosted GitLab.
This present forge is now archived and remained online for history.
WorkingGroups/HPC/Mins_sub_2018_06_21 (diff) – NEMO

Changes between Version 1 and Version 2 of WorkingGroups/HPC/Mins_sub_2018_06_21


Ignore:
Timestamp:
2018-06-25T13:29:42+02:00 (4 years ago)
Author:
mocavero
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • WorkingGroups/HPC/Mins_sub_2018_06_21

    v1 v2  
    66== 1.   Mixed-precision (BSC) == 
    77  
    8 Oriol presented the methodology implemented to test the impact of numerical precision in NEMO. An automatic tool to implement the Reduced Precision Emulator to a computational model has been presented, as well as the tests on groups of variables in order to identify which variables can use less precision without affecting the numerical accuracy. Tests have been performed on NEMO 3.6 GYRE1 and showed that only ~10% of the variables need double precision. 
     8Oriol presented the methodology implemented to test the impact of numerical precision in NEMO. An automatic tool to implement the Reduced Precision Emulator to a computational model has been presented, as well as the tests on groups of variables in order to identify which variables can use less precision without affecting the numerical accuracy. Tests have been performed on NEMO 3.6 GYRE1 and showed that only ~10% of the variables need double precision (see attached slides) 
    99 
    1010Open questions and future plan: need to test the approach on high-resolution (eddy resolving scale) and to evaluate the error. Which is the tolerance to safely use reduced precision? 
     
    1313== 2.   NEMO-DSL (STFC)   == 
    1414 
    15 Andy presented the light-DSL approach designed to apply DSL in NEMO. An interface to the PSyclone tool has been implemented in order to apply PSyclone transformations without impacting on the NEMO coding structure rules. The approach would allow to introduce the OpenACC parallelisation through a workflow based on two steps: processing the NEMO code to create an internal representation compliant to the PSyclone tool, manipulating the intermediate code to perform PSyclone transformations.  
     15Andy presented the light-DSL approach designed to apply DSL in NEMO. An interface to the PSyclone tool has been implemented in order to apply PSyclone transformations without impacting on the NEMO coding structure rules. The approach would allow to introduce the OpenACC parallelisation through a workflow based on two steps: processing the NEMO code to create an internal representation compliant to the PSyclone tool, manipulating the intermediate code to perform PSyclone transformations (see attached slides) 
    1616 
    1717Open questions and future plan: considering the integration of optimisations for CPUs 
     
    2020== 3.   Benchmark setup (CERFACS-CNRS)   == 
    2121 
    22 Eric presented the NEMO benchmark implemented to identify the main bottlenecks to the scalability. Some results on the BENCH-1 on Intel Broadwell system at Meteo-France have been shown comparing the reference simulation (without MPI collectives) with the pseudo double size halo and no-communication experiments. The trend of the time spent waiting for communications and for computation load imbalance has been analysed.      
     22Eric presented the NEMO benchmark implemented to identify the main bottlenecks to the scalability. Some results on the BENCH-1 on Intel Broadwell system at Meteo-France have been shown comparing the reference simulation (without MPI collectives) with the pseudo double size halo and no-communication experiments. The trend of the time spent waiting for communications and for computation load imbalance has been analysed (see attached slides) 
    2323 
    2424Open questions and future plan: extension of the tests to high-resolution configurations