Title :
Parallelism and Auto-Tuner of Irregular Iteration in Reservoir Simulation
Author :
Zhang, Ji-Lin ; Zhu, Li-Ting ; Wan, Jian ; Jiang, Cong-Feng
Author_Institution :
Dept. of Comput. Sci. & Technol., Hangzhou Dianzi Univ., Hangzhou, China
Abstract :
In the field of reservoir numerical simulation, irregular iteration problem is one of the most important reasons to affect the efficiency of large-scale computing. Memory access patterns can´t be determined at compiler-time, which brings us difficulties to parallel. This library uses Inspector/Executor model based on distributed clusters, and improves parallel efficiency utilizing alternate tiling technology. Besides, we get the optimal efficiency by auto-tuner, which can find the right parameters. Finally, numerical results on CLUSTER show that the method has a good parallel efficiency as well as scalability, and the auto-tuner possesses practicality to a certain extent.
Keywords :
digital simulation; geophysics computing; graph theory; hydrocarbon reservoirs; iterative methods; parallel algorithms; CLUSTER; DII-I/E parallel algorithm; Inspector-Executor model; alternate tiling technology; auto-tuner; distributed clusters; irregular iteration problem; large-scale computing; matrix graph; memory access pattern; optimal efficiency; parallel efficiency; parallelism; reservoir numerical simulation; Algorithm design and analysis; Clustering algorithms; Parallel processing; Partitioning algorithms; Program processors; Schedules; Tiles; Irregular Iteration; auto-tuner; parallel computing; tiling;
Conference_Titel :
Computer, Consumer and Control (IS3C), 2012 International Symposium on
Conference_Location :
Taichung
Print_ISBN :
978-1-4673-0767-3
DOI :
10.1109/IS3C.2012.21
