The Community for Technology Leaders
2012 41st International Conference on Parallel Processing Workshops (2012)
Pittsburgh, PA, USA USA
Sept. 10, 2012 to Sept. 13, 2012
ISSN: 1530-2016
ISBN: 978-1-4673-2509-7
pp: 612-613
ABSTRACT
In this paper we present a library for shared-memory dynamic allocation and bank-conflict free accesses for NVIDIA GPUs. The system allows an order of magnitude faster pointer chasing operations for small and medium sized arrays.
INDEX TERMS
Plasmas, Instruction sets, Indexes, Kernel, Resource management, Graphics processing unit, Libraries
CITATION

R. Farivar and R. H. Campbell, "Plasma: Shared Memory Dynamic Allocation and Bank-Conflict-Free Access in GPUs," 2012 41st International Conference on Parallel Processing Workshops(ICPPW), Pittsburgh, PA, USA USA, 2012, pp. 612-613.
doi:10.1109/ICPPW.2012.94
93 ms
(Ver 3.3 (11022016))