Register Efficient Dynamic Memory Allocator for GPUs

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 k‐d tree data st...

Full description

Saved in:
Bibliographic Details
Published in:Computer graphics forum Vol. 34; no. 8; pp. 143 - 154
Main Authors: Vinkler, M., Havran, V.
Format: Journal Article
Language:English
Published: Oxford Blackwell Publishing Ltd 01.12.2015
Subjects:
Analysis
Architecture (computers)
Buildings
Central processing units
Computer graphics
Computer memory
CPUs
CUDA
D.1.3 [Programming Techniques]: Concurrent Programming Parallel programming D.3.3 [Programming Languages]: Language Constructs and Features Dynamic storage management D.4.2 [Operating Systems]: Storage Management Allocation/deallocation strategies
dynamic memory allocation
Dynamic structural analysis
Dynamic tests
Dynamics
GPU
Hardware
many‐core architecture
Memory management
Studies
Workload
ISSN:0167-7055, 1467-8659
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 k‐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 k‐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.
Bibliography:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:0167-7055
1467-8659
DOI:10.1111/cgf.12666