Register Efficient Dynamic Memory Allocator for GPUs
No Thumbnail Available
Date
2015
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Copyright © 2015 The Eurographics Association and John Wiley & Sons Ltd.
Abstract
We compare five 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 past and we add one with a real workload, where dynamic memory allocation is used in building the ‐d 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.We compare five 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 past and we add one with a real workload, where dynamic memory allocation is used in building the ‐d 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.
Description
@article{10.1111:cgf.12666,
journal = {Computer Graphics Forum},
title = {{Register Efficient Dynamic Memory Allocator for GPUs}},
author = {Vinkler, M. and Havran, V.},
year = {2015},
publisher = {Copyright © 2015 The Eurographics Association and John Wiley & Sons Ltd.},
DOI = {10.1111/cgf.12666}
}