A Feasibility Study on Porting the Community Land Model onto Accelerators Using Openacc
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2014, Vol 5, Issue 12
Abstract
As environmental models (such as Accelerated Climate Model for Energy (ACME), Parallel Reactive Flow and Transport Model (PFLOTRAN), Arctic Terrestrial Simulator (ATS), etc.) became more and more complicated, we are facing enormous challenges regarding to porting those applications onto hybrid computing architecture. OpenACC emerges as a very promising technology, therefore, we have conducted a feasibility analysis on porting the Community Land Model (CLM), a terrestrial ecosystem model within the Community Earth System Models (CESM)). Specifically, we used automatic function testing platform to extract a small computing kernel out of CLM, then we apply this kernel into the actually CLM dataflow procedure, and investigate the strategy of data parallelization and the benefit of data movement provided by current implementation of OpenACC. Even it is a non-intensive kernel, on a single 16-core computing node, the performance (based on the actual computation time using one GPU) of OpenACC implementation is 2.3 time faster than that of OpenMP implementation using single OpenMP thread, but it is 2.8 times slower than the performance of OpenMP implementation using 16 threads. On multiple nodes, MPI_OpenACC implementation demonstrated very good scalability on up to 128 GPUs on 128 computing nodes. This study also provides useful information for us to look into the potential benefits of “deep copy” capability and “routine” feature of OpenACC standards. We believe that our experience on the environmental model, CLM, can be beneficial to many other scientific research programs who are interested to porting their large scale scientific code using OpenACC onto high-end computers, empowered by hybrid computing architecture.
Authors and Affiliations
D. Wang, W. Wu, F. Winkler, O. Hernandez
Keywords
Related Articles
- EP ID EP100184
- DOI 10.14569/IJACSA.2014.051203
- Views 119
- Downloads 0
New Modified RLE Algorithms to Compress Grayscale Images with Lossy and Lossless Compression
New modified RLE algorithms to compress grayscale images with lossy and lossless compression, depending on the probability of repetition of pixels in the image and the pixel values to reduce the size of the encoded data...
Automatic Pavement Cracks Detection using Image Processing Techniques and Neural Network
Feature extraction methods and subsequent neural network performances were used in this research to impose proper assessment for distressed roads for a case study area in the North of Jordan. Object recognition method wa...
Design of Miniaturized Multiband Microstrip Patch Antenna using Defected Ground Structure
The recent developments in communication and antenna engineering demands compact and multiband antennas. Microstrip antenna is one of the most useful antennas for wireless communication because of its inherent features l...
Face Recognition System Based on Different Artificial Neural Networks Models and Training Algorithms
Face recognition is one of the biometric methods that is used to identify any given face image using the main features of this face. In this research, a face recognition system was suggested based on four Artificial Neur...
Analysis of the Emotions’ Brainwaves
Currently in Peru, patients with degenerative diseases, such as Amyotrophic Lateral Sclerosis (ALS) have lost of communication ability. Many researchers’ papers that establish basic communication system for these patient...