Projects per year
Abstract / Description of output
Large Eddy Simulation is a critical modelling tool for the investigation of atmospheric flows, turbulence and cloud microphysics. The models used by the UK atmospheric research community are homogeneous and the latest model, MONC, is designed to run on substantial HPC systems with very high CPU core counts. In order to future proof these codes it is worth investigating other technologies and architectures which might support the communities running their codes at the exa-scale.
In this paper we present a hybrid version of MONC, where the most computationally intensive aspect is offloaded to the GPU while the rest of the functionality runs concurrently on the CPU. Developed using the directive driven OpenACC, we consider the suitability and maturity of this technology to modern Fortran scientific codes as well general software engineering techniques which aid this type of porting work. The performance of our hybrid model at scale is compared against the CPU version before considering other tuning options and making a comparison between the energy usage of the homo- and hetero-geneous versions. The result of this work is a promising hybrid model that shows performance benefits of our approach when the GPU has a significant computational workload which can not only be applied to the MONC model but also other weather and climate simulations in use by the community.
In this paper we present a hybrid version of MONC, where the most computationally intensive aspect is offloaded to the GPU while the rest of the functionality runs concurrently on the CPU. Developed using the directive driven OpenACC, we consider the suitability and maturity of this technology to modern Fortran scientific codes as well general software engineering techniques which aid this type of porting work. The performance of our hybrid model at scale is compared against the CPU version before considering other tuning options and making a comparison between the energy usage of the homo- and hetero-geneous versions. The result of this work is a promising hybrid model that shows performance benefits of our approach when the GPU has a significant computational workload which can not only be applied to the MONC model but also other weather and climate simulations in use by the community.
Original language | English |
---|---|
Title of host publication | Proceedings of the Second Workshop on Accelerator Programming using Directives |
Publisher | ACM |
ISBN (Print) | 978-1-4503-4014-4 |
DOIs | |
Publication status | Published - 2015 |
Event | WACCPD15: Second Workshop on Accelerator Programming using Directives - Austin, Texas, United States Duration: 16 Nov 2015 → … |
Workshop
Workshop | WACCPD15: Second Workshop on Accelerator Programming using Directives |
---|---|
Country/Territory | United States |
City | Austin, Texas |
Period | 16/11/15 → … |
Fingerprint
Dive into the research topics of 'A directive based hybrid met office NERC cloud model'. Together they form a unique fingerprint.Projects
- 1 Finished
Research output
- 1 Software
-
Met Office NERC Cloud model (MONC)
Brown, N. & Weiland, M., 30 Apr 2018Research output: Non-textual form › Software
Datasets
-
Met Office NERC Cloud model (MONC)
Brown, N. (Creator) & Weiland, M. (Creator), Edinburgh DataShare, 30 Apr 2018
DOI: 10.7488/ds/2343
Dataset