Investigating performance variations of an optimized GPU-ported granulometry algorithm - Archive ouverte HAL Access content directly
Conference Papers Year : 2012

Investigating performance variations of an optimized GPU-ported granulometry algorithm

Abstract

In this article, we present an optimized GPU implementation of a granulometry algorithm which is used a lot in the study of material domain. The main contribution to this algorithm is the binarization of the input data which increases throughput while reducing data allocated memory space. Also, the optimized GPU implementation brings an order of magnitude speedup compared to a CPU multi-threaded implementation. Furthermore, we investigate the reasons why GPU performance drop for different input data dimensions. Three main factors are exposed: under-exploited threads, threadblocks and streaming multiprocessors. This study should help the reader understand the tight relation that exists between the CUDA programming paradigm and the gpu architecture as well as some main bottlenecks.
Fichier principal
Vignette du fichier
DASIP_2012_final.pdf (192.33 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00787861 , version 1 (19-02-2013)

Identifiers

  • HAL Id : hal-00787861 , version 1

Cite

Vincent Boulos, Vincent Fristot, Dominique Houzet, Luc Salvo, P. Lhuissier. Investigating performance variations of an optimized GPU-ported granulometry algorithm. DASIP 2012 - Conference on Design and Architectures for Signal and Image Processing, Oct 2012, Karlsruhe, Germany. pp.1-6. ⟨hal-00787861⟩
359 View
348 Download

Share

Gmail Facebook X LinkedIn More