Show simple item record

dc.contributor.authorVinkler, Mareken_US
dc.contributor.authorVlastimil, Havranen_US
dc.contributor.editorIngo Wald and Jonathan Ragan-Kelleyen_US
dc.date.accessioned2015-07-06T15:26:30Z
dc.date.available2015-07-06T15:26:30Z
dc.date.issued2014en_US
dc.identifier.isbn978-3-905674-60-6en_US
dc.identifier.issn2079-8679en_US
dc.identifier.urihttp://dx.doi.org/10.2312/hpg.20141090en_US
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/hpg.20141090
dc.description.abstractWe compare four existing dynamic memory allocators optimized for GPUs and show their strengths and weaknesses. In the measurements we use three generic evaluation tests proposed in the literature and add one with a real workload where dynamic memory allocation is used for building the kd-tree data structure. Following the performance analysis we propose a new dynamic memory allocator and its variants that address the limitations of the existing dynamic memory allocators. The new dynamic memory allocator uses few resources and is targeted towards large and variably sized memory allocations on massively parallel hardware architectures.en_US
dc.publisherThe Eurographics Associationen_US
dc.subjectD.1.3 [Programming Techniques]en_US
dc.subjectConcurrent Programmingen_US
dc.subjectParallel programming D.3.3 [Programming Languages]en_US
dc.subjectLanguage Constructs and Featuresen_US
dc.subjectDynamic storage management D.4.2 [Operating Systems]en_US
dc.subjectStorage Managementen_US
dc.subjectAllocation/deallocation strategiesen_US
dc.titleRegister Efficient Memory Allocator for GPUsen_US
dc.description.seriesinformationEurographics/ ACM SIGGRAPH Symposium on High Performance Graphicsen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record