Title :
An experimental GPU global memory performance estimation and optimization
Author :
Junfeng Zhu ; Gang Chen ; Keliang Zhang ; Baifeng Wu
Author_Institution :
Inst. of Comput. Sci. & Technol., Fudan Univ., Shanghai, China
Abstract :
The enormous computational power available in modern graphics processing units (GPUs) has enabled the widely use of them for general-purpose applications. However, manual development of high-performance parallel codes for GPUs is still very challenging. In order for improving GPGPU application performance by efficiently using GPU global memory, we extend the polyhedral model to capture memory access patterns inside the source programs. We determine the global memory accesses are coalesced or not. We also estimate the memory performance of a GPGPU kernel, with the purpose of eliminating the uncoalesced global memory accesses. Experimental results show that that the present global memory performance model can estimate the global memory performance of these two applications relative accurately and the present global memory optimization methods can significantly improve performance.
Keywords :
graphics processing units; optimisation; storage management; GPGPU application performance; GPGPU kernel; GPU global memory performance estimation; general-purpose applications; global memory access; global memory optimization; graphics processing units; high-performance parallel codes; memory access patterns; polyhedral model; Arrays; Computational modeling; Graphics processing unit; Instruction sets; Memory management; Optimization; GPGPU; GPU; memory model; performance estimation; performance optimization;
Conference_Titel :
Systems and Informatics (ICSAI), 2012 International Conference on
Conference_Location :
Yantai
Print_ISBN :
978-1-4673-0198-5
DOI :
10.1109/ICSAI.2012.6223155