EGU2020-16204
https://doi.org/10.5194/egusphere-egu2020-16204
EGU General Assembly 2020
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

An evaluation of the mixed precision version of NEMO 4.0.1

Oriol Tintó, Stella Valentina Paronuzzi Ticco, Mario C. Acosta, Miguel Castrillo, Kim Serradell, and Francisco J. Doblas-Reyes
Oriol Tintó et al.
  • Barcelona Supercomputing Center, Earth Sciences, Barcelona, Spain (oriol.tinto@bsc.es)

One of the requirements to keep improving the science produced using NEMO is to enhance its computational performance. The interest in improving its capability to efficiently use the computational infrastructure its two-fold: on one side there are experiments that would only be possible if a certain threshold of throughput is achieved, on the other side any development that achieves an increase in efficiency would help saving resources while reducing the environmental impact of our experiments. One of the opportunities that raised interest in the last few years is the optimization of the numerical precision. Historical reasons brought many computational models to over-engineer the numerical precision: solving this miss-adjustment can payback in terms of efficiency and throughput. In this direction, a research was carried out in order to safely reduce the numerical precision in NEMO which led to a mixed-precision version of the model. The implementation has been developed following the approach proposed by Tintó et al. 2019, in which the variables that require double precision are identified automatically and the remaining ones are switched to use single-precision. The implementation will be released in 2020 and this work presents its evaluation in terms of both performance and scientific results.

How to cite: Tintó, O., Paronuzzi Ticco, S. V., Acosta, M. C., Castrillo, M., Serradell, K., and Doblas-Reyes, F. J.: An evaluation of the mixed precision version of NEMO 4.0.1, EGU General Assembly 2020, Online, 4–8 May 2020, EGU2020-16204, https://doi.org/10.5194/egusphere-egu2020-16204, 2020

Comments on the presentation

AC: Author Comment | CC: Community Comment | Report abuse

Presentation version 1 – uploaded on 06 May 2020 , no comments