Influence of the compiler on multi-CPU performance of WRFv3

Langkamp, Thomas

doi:10.5194/gmdd-4-547-2011

Cited by 6 publications

(7 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With a recent refactor of legacy code, GEOS-Chem now compiles with all major versions of the GNU Fortran compiler (GEOS-Chem 2018c). Although some models like WRF are found to be significantly slower with GNU compilers than with Intel compilers (Langkamp 2011;Siuta et al 2016), for GEOS-Chem we find that switching to the GNU compiler decreases performance by only 5% (GEOS-Chem 2018d), in part due to a sustained effort to only bring hardware-independent and compiler-agonistic optimizations into the GEOS-Chem main code branch.…”

Section: Open-source Softwarementioning

confidence: 71%

Enabling Immediate Access to Earth Science Models through Cloud Computing: Application to the GEOS-Chem Model

Zhuang

Jacob

Gaya

et al. 2019

Bulletin of the American Meteorological Society

View full text Add to dashboard Cite

Cloud computing platforms can provide fast and easy access to complex Earth science models and large datasets. This article presents a mature capability for running the GEOS-Chem global 3D model of atmospheric chemistry on the Amazon Web Services (AWS) cloud. GEOS-Chem users at any experience level can get immediate access to the latest, standard version of the model in a preconfigured software environment with all needed meteorological and other input data, and they can analyze model output data easily within the cloud using Python tools in Jupyter notebooks. Users with no prior knowledge of cloud computing are provided with easy-to-follow, step-by-step instructions. They can learn how to complete a demo project in less than one hour, and from there they can configure and submit their own simulations. The cloud is particularly attractive for beginning and occasional users who otherwise may need to spend substantial time configuring a local computing environment. Heavy users with their own local clusters can also benefit from the cloud to access the latest standard model and datasets, share simulation configurations and results, benchmark local simulations, and respond to surges in computing demand. Software containers allow GEOS-Chem and its software environment to be moved smoothly between cloud platforms and local clusters, so that the exact same simulation can be reproduced everywhere. Because the software requirements and workflows tend to be similar across Earth science models, the work presented here provides general guidance for porting models to cloud computing platforms in a user-accessible way.

show abstract

Section: Open-source Softwarementioning

confidence: 71%

Enabling Immediate Access to Earth Science Models through Cloud Computing: Application to the GEOS-Chem Model

Zhuang

Jacob

Gaya

et al. 2019

Bulletin of the American Meteorological Society

View full text Add to dashboard Cite

show abstract

“…From Table I it is clear that the CPIs for the Intel and AMD 48-core CPUs and the GPU are very similar; furthermore, Langkamp [22] found very little difference in the WRF MPI performance when compiled using gfortran and the PGI compiler on an AMD Opteron 2384 system. So, using the 48-core AMD system as our reference, we can compare the compute performance of our kernel with that of the original kernel parallelized using MPI.…”

Section: Discussionmentioning

confidence: 98%

An analysis of the feasibility and benefits of GPU/multicore acceleration of the Weather Research and Forecasting model

Vanderbauwhede

Takemi

2015

Concurrency and Computation

View full text Add to dashboard Cite

There is a growing need for ever more accurate climate and weather simulations to be delivered in shorter timescales, in particular, to guard against severe weather events such as hurricanes and heavy rainfall. Due to climate change, the severity and frequency of such events -and thus the economic impact -are set to rise dramatically. Hardware acceleration using graphics processing units (GPUs) or Field-Programmable Gate Arrays (FPGAs) could potentially result in much reduced run times or higher accuracy simulations. In this paper, we present the results of a study of the Weather Research and Forecasting (WRF) model undertaken in order to assess if GPU and multicore acceleration of this type of numerical weather prediction (NWP) code is both feasible and worthwhile. The focus of this paper is on acceleration of code running on a single compute node through offloading of parts of the code to an accelerator such as a GPU. The governing equations set of the WRF model is based on the compressible, non-hydrostatic atmospheric motion with multi-physics processes. We put this work into context by discussing its more general applicability to multiphysics fluid dynamics codes: in many fluid dynamics codes, the numerical schemes of the advection terms are based on finite differences between neighboring cells, similar to the WRF code. For fluid systems including multi-physics processes, there are many calls to these advection routines. This class of numerical codes will benefit from hardware acceleration. We studied the performance of the original code of the WRF model and proposed a simple model for comparing multicore CPU and GPU performance. Based on the results of extensive profiling of representative WRF runs, we focused on the acceleration of the scalar advection module. We discuss the implementation of this module as a data-parallel kernel in both OpenCL and OpenMP. We show that our data-parallel kernel version of the scalar advection module runs up to seven times faster on the GPU compared with the original code on the CPU. However, as the data transfer cost between GPU and CPU is very high (as shown by our analysis), there is only a small speed-up (two times) for the fully integrated code. We show that it would be possible to offset the data transfer cost through GPU acceleration of a larger portion of the dynamics code. In order to carry out this research, we also developed an extensible software system for integrating OpenCL code into large Fortran code bases such as WRF. This is one of the main contributions of our work. We discuss the system to show how it allows the replacement of the sections of the original codebase with their OpenCL counterparts with minimal changes -literally only a few lines -to the original code. Our final assessment is that, even with the current system architectures, accelerating WRF -and hence also other, similar types of multi-physics fluid dynamics codes -with a factor of up to five times is definitely an achievable goal. Accelerating multi-physics fluid dynamics codes including NWP...

show abstract

“…The efficiency and performance in parallel programming usually were assessed by magnitude and performance indicators, using mainly the following metrics: the execution time [10], speed-up and the efficiency [15,16,21]. The execution time is the time required for the application for the development of one or more tasks in a program.…”

Section: Efficiency and Performance In Parallel Programmingmentioning

confidence: 99%

“…144 experiments were executed to obtain the execution time (t), speedup (Sn) and efficiency (En) considering three hours simulation time with a processors number from 1 to 256, the four PBL schemes (YSU, MYJ, ACM2 and BouLac) [2,4,7,8], two time step and two physics configuration and were executed according to the scheduling in the MNIII supercomputer account [10,15,16,21].…”

Section: Performance Indicators Experimentsmentioning

confidence: 99%

Planet Boundary Layer Parameterization in Weather Research and Forecasting (WRFv3.5): Assessment of Performance in High Spatial Resolution Simulations in Complex Topography of Mexico

Rocha

Pérez

Meléndez

et al. 2017

CyS

View full text Add to dashboard Cite

This paper presents the application of the Weather Research and Forecasting (WRF version 3.5) with high spatial resolution (3 and 1 km) testing four Planet Boundary Layer (PBL) schemes to the complex topography of Mexico in different numerical experiments that have tried to find the best configuration. The WRF is a Numerical Weather Prediction (NWP) model giving support for weather forecasting and modeling in Chemical Transport (CTM) or Air Quality Models as CMAQ or CHIMERE. For the above, the objectives in this work were assess the performance, the best grid parameterization, meteorological initial conditions, temporal resolution, time step and PBL schemes used in order to minimize the execution time and to show changes in speedup and efficiency. Mare Nostrum III supercomputer was used for the computational processing in the cluster. The computational performance indicators were execution time, speedup and efficiency. The sensitivity analysis was performed using the mean bias (MB) and root mean square error (RMSE) from variables obtained by WRFv3.5 such as temperature, windspeed, sea level pressure and the METAR Veracruz airport station observations. The results show that Mellor-Yamada-Janjic (MYJ) scheme was better in computational parallel execution with at least 8 processors and a time step of 18 seconds. The sensitivity analyses show that time step is not a key in the accuracy of the meteorological values obtained. It is necessary consider the lack of data in METAR stations in Mexico.

show abstract

Influence of the compiler on multi-CPU performance of WRFv3

Cited by 6 publications

References 7 publications

Enabling Immediate Access to Earth Science Models through Cloud Computing: Application to the GEOS-Chem Model

Enabling Immediate Access to Earth Science Models through Cloud Computing: Application to the GEOS-Chem Model

An analysis of the feasibility and benefits of GPU/multicore acceleration of the Weather Research and Forecasting model

Planet Boundary Layer Parameterization in Weather Research and Forecasting (WRFv3.5): Assessment of Performance in High Spatial Resolution Simulations in Complex Topography of Mexico

Contact Info

Product

Resources

About