The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.01 - Jan.-June (2014 vol.13)
pp: 49-52
Yunlong Xu , , School of Electronic and Information Engineering, Xi'an, China
Rui Wang , , School of Computer Science and Engineering, Beijing, China
Nilanjan Goswami , ECE Department, University of Florida, Gainesville, USA
Tao Li , ECE Department, University of Florida, Gainesville, USA
Depei Qian , , School of Electronic and Information Engineering, Xi'an, China
ABSTRACT
To make applications with dynamic data sharing among threads benefit from GPU acceleration, we propose a novel software transactional memory system for GPU architectures (GPU-STM). The major challenges include ensuring good scalability with respect to the massively multithreading of GPUs, and preventing livelocks caused by the SIMT execution paradigm of GPUs. To this end, we propose (1) a hierarchical validation technique and (2) an encounter-time lock-sorting mechanism to deal with the two challenges, respectively. Evaluation shows that GPU-STM outperforms coarse-grain locks on GPUs by up to 20×.
INDEX TERMS
SIMD Processors, Multicore Processors, Parallel Programming, Run-time Environments,SIMD Processors, Multicore Processors, Parallel Programming, Run-time Environments
CITATION
Yunlong Xu, Rui Wang, Nilanjan Goswami, Tao Li, Depei Qian, "Software Transactional Memory for GPU Architectures", IEEE Computer Architecture Letters, vol.13, no. 1, pp. 49-52, Jan.-June 2014, doi:10.1109/L-CA.2013.4
74 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool