On the use of programmable hardware and reduced numerical precision in earth‐system modeling
Open Access
- 18 September 2015
- journal article
- research article
- Published by American Geophysical Union (AGU) in Journal of Advances in Modeling Earth Systems
- Vol. 7 (3), 1393-1408
- https://doi.org/10.1002/2015ms000494
Abstract
Programmable hardware, in particular Field Programmable Gate Arrays (FPGAs), promises a significant increase in computational performance for simulations in geophysical fluid dynamics compared with CPUs of similar power consumption. FPGAs allow adjusting the representation of floating‐point numbers to specific application needs. We analyse the performance‐precision trade‐off on FPGA hardware for the two‐scale Lorenz '95 model. We scale the size of this toy model to that of a high performance computing application in order to make meaningful performance tests. We identify the minimal level of precision at which changes in model results are not significant compared with a maximal precision version of the model and find that this level is very similar for cases where the model is integrated for very short or long intervals. It is therefore a useful approach to investigate model errors due to rounding errors for very short simulations (e.g. 50 time steps) to obtain a range for the level of precision that can be used in expensive long‐term simulations. We also show that an approach to reduce precision with increasing forecast time, when model errors are already accumulated, is very promising. We show that a speed‐up of 1.9 times is possible in comparison to FPGA simulations in single precision if precision is reduced with no strong change in model error. The single‐precision FPGA setup shows a speed‐up of 2.8 times in comparison to our model implementation on two six‐core CPUs for large model setups.Keywords
Funding Information
- ERC Grant
- European Union Seventh Framework Programme (318521)
- UK EPSRC
- Maxeler University Programme
- HiPEAC NoE
- Xilinx
This publication has 26 references indexed in Scilit:
- A statistically accurate modified quasilinear Gaussian closure for uncertainty quantification in turbulent dynamical systemsPhysica D: Nonlinear Phenomena, 2013
- Stochastic parametrizations and model uncertainty in the Lorenz ’96 systemPhilosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2013
- Data-based stochastic subgrid-scale parametrization: an approach using cluster-weighted modellingPhilosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2012
- Runge-Kutta methods with minimum storage implementationsJournal of Computational Physics, 2010
- Toward Seamless Prediction: Calibration of Climate Change Projections Using Seasonal ForecastsBulletin of the American Meteorological Society, 2008
- Predictability – a problem partly solvedPublished by Cambridge University Press (CUP) ,2006
- Energy Aware Computing through Probabilistic Switching: A Study of LimitsIEEE Transactions on Computers, 2005
- Effects of stochastic parametrizations in the Lorenz '96 systemQuarterly Journal of the Royal Meteorological Society, 2005
- A local ensemble Kalman filter for atmospheric data assimilationTellus A: Dynamic Meteorology and Oceanography, 2004
- Compiler transformations for high-performance computingACM Computing Surveys, 1994