Please use this identifier to cite or link to this item:
Main Title: Automatic Data Layout Optimizations for GPUs
Author(s): Kofler, Klaus
Cosenza, Biagio
Fahringer, Thomas
Type: Conference Object
Language Code: en
Abstract: Memory optimizations have became increasingly important in order to fully exploit the computational power of modern GPUs. The data arrangement has a big impact on the performance, and it is very hard for GPU programmers to identify a well-suited data layout. Classical data layout transformations include grouping together data fields that have similar access patterns, or transforming Array-of-Structures (AoS) to Structure-of-Arrays (SoA). This paper presents an optimization infrastructure to automatically determine an improved data layout for OpenCL programs written in AoS layout. Our framework consists of two separate algorithms: The first one constructs a graph-based model, which is used to split the AoS input struct into several clusters of fields, based on hardware dependent parameters. The second algorithm selects a good per-cluster data layout (e.g., SoA, AoS or an intermediate layout) using a decision tree. Results show that the combination of both algorithms is able to deliver higher performance than the individual algorithms. The layouts proposed by our framework result in speedups of up to 2.22, 1.89 and 2.83 on an AMD FirePro S9000, NVIDIA GeForce GTX 480 and NVIDIA Tesla k20m, respectively, over different AoS sample programs, and up to 1.18 over a manually optimized program.
Issue Date: 2015
Date Available: 4-Jun-2018
DDC Class: 004 Datenverarbeitung; Informatik
Subject(s): GPU
data layout
graph-based model
Proceedings Title: Euro-Par 2015: Parallel Processing. Euro-Par 2015. (Lecture Notes in Computer Science, vol 9233)
Publisher: Springer
Publisher Place: Berlin ; Heidelberg ; New York, NY
Publisher DOI: 10.1007/978-3-662-48096-0_21
Page Start: 263
Page End: 274
ISBN: 978-3-662-48096-0
ISSN: 0302-9743
Appears in Collections:FG Architektur eingebetteter Systeme » Publications

Files in This Item:
File Description SizeFormat 
KoflerEUROPAR15.pdf1.1 MBAdobe PDFThumbnail

Items in DepositOnce are protected by copyright, with all rights reserved, unless otherwise indicated.