Abstract

Abstract. The planetary boundary layer (PBL) is the lowest part of the atmosphere and where its character is directly affected by its contact with the underlying planetary surface. The PBL is responsible for vertical sub-grid-scale fluxes due to eddy transport in the whole atmospheric column. It determines the flux profiles within the well-mixed boundary layer and the more stable layer above. It thus provides an evolutionary model of atmospheric temperature, moisture (including clouds), and horizontal momentum in the entire atmospheric column. For such purposes, several PBL models have been proposed and employed in the weather research and forecasting (WRF) model of which the Yonsei University (YSU) scheme is one. To expedite weather research and prediction, we have put tremendous effort into developing an accelerated implementation of the entire WRF model using graphics processing unit (GPU) massive parallel computing architecture whilst maintaining its accuracy as compared to its central processing unit (CPU)-based implementation. This paper presents our efficient GPU-based design on a WRF YSU PBL scheme. Using one NVIDIA Tesla K40 GPU, the GPU-based YSU PBL scheme achieves a speedup of 193× with respect to its CPU counterpart running on one CPU core, whereas the speedup for one CPU socket (4 cores) with respect to 1 CPU core is only 3.5×. We can even boost the speedup to 360× with respect to 1 CPU core as two K40 GPUs are applied.

Highlights

  • The science of meteorology explains observable weather events, and its application is weather forecasting

  • This study develops an efficient graphics processing unit (GPU)-based design on the Yonsei University (YSU) planetary boundary layer (PBL) scheme, which is one of the physical models in weather research and forecasting (WRF)

  • We developed the massively parallel GPU version of the YSU PBL scheme using NVIDIA Tesla K40 GPUs www.geosci-model-dev.net/8/2977/2015/

Read more

Summary

Introduction

The science of meteorology explains observable weather events, and its application is weather forecasting. The collected quantitative data about the current state of the atmosphere are used to predict future states This requires the aid of equations of fluid dynamics and thermodynamics that are based on laws of physics, chemistry, and fluid motion. To expedite weather analysis research and forecasting, we have put tremendous efforts into developing an accelerated implementation of the entire WRF model using a GPU massive parallel architecture whilst maintaining its accuracy as compared to its CPU-based implementation. This study develops an efficient GPU-based design on the Yonsei University (YSU) planetary boundary layer (PBL) scheme, which is one of the physical models in WRF. It determines the flux profiles within the well-mixed boundary layer and the more stable layer above, and provides an evolutionary model of atmospheric temperature, moisture (including clouds), and horizontal momentum in the entire atmospheric column

YSU PBL scheme
Mixed-layer diffusion
Free atmosphere diffusion
GPU device specification and basis of CUDA engine
GPU-based implementation
Premise for optimizing GPU-based YSU PBL scheme
CPU core Non-coalesced Coalesced
Optimization with more L1 cache
Optimization with scalarizing temporary arrays
Optimization with height dependence release
Impact of block size on GPU-based YSU PBL scheme
Impact of registers per thread on GPU-based YSU PBL scheme
Data transfer between CPU and GPUs
Output comparison between CPU-based and GPU-based programs
Multi-GPU implementation
Findings
Summary and future work
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.