DocumentCode :
1955056
Title :
ScatterAlloc: Massively parallel dynamic memory allocation for the GPU
Author :
Steinberger, Markus ; Kenzel, Michael ; Kainz, Bernhard ; Schmalstieg, Dieter
Author_Institution :
Inst. for Comput. Graphics & Vision, Graz Univ. of Technol., Graz, Austria
fYear :
2012
fDate :
13-14 May 2012
Firstpage :
1
Lastpage :
10
Abstract :
In this paper, we analyze the special requirements of a dynamic memory allocator that is designed for massively parallel architectures such as Graphics Processing Units (GPUs). We show that traditional strategies, which work well on CPUs, are not well suited for the use on GPUs and present the thorough design of ScatterAlloc, which can efficiently deal with hundreds of requests in parallel. Our allocator greatly reduces collisions and congestion by scattering memory requests based on hashing. We analyze ScatterAlloc in terms of allocation speed, data access time and fragmentation, and compare it to current state-of-the-art allocators, including the one provided with the NVIDIA CUDA toolkit. Our results show, that ScatterAlloc clearly outperforms these other approaches, yielding speed-ups between 10 to 100.
Keywords :
graphics processing units; parallel architectures; resource allocation; storage management; GPU; NVIDIA CUDA toolkit; ScatterAlloc; allocation speed; data access time; fragmentation; graphics processing units; hashing; massively parallel dynamic memory allocation; memory request scattering; parallel architectures; Dynamic scheduling; Graphics processing unit; Instruction sets; Kernel; Memory management; Resource management; GPU; dynamic memory allocation; hashing; massively parallel;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Innovative Parallel Computing (InPar), 2012
Conference_Location :
San Jose, CA
Print_ISBN :
978-1-4673-2632-2
Electronic_ISBN :
978-1-4673-2631-5
Type :
conf
DOI :
10.1109/InPar.2012.6339604
Filename :
6339604
Link To Document :
بازگشت