Open AccessIdentifying attributes of GPU programs for difficulty evaluation
Author(s) -
Dale Tristram,
Karen Bradshaw
Publication year - 2014
Publication title -
south african computer journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.227
H-Index - 6
eISSN - 2313-7835
pISSN - 1015-7999
DOI - 10.18489/sacj.v53i0.195
Subject(s) - computer science , general purpose computing on graphics processing units , acceleration , cuda , parallelism (grammar) , parallel computing , graphics , computation , graphics processing unit , algorithm , computer graphics (images) , physics , classical mechanics
General-purpose computation on graphics processing units (GPGPU) has great potential to accelerate many scientific models and algorithms. However, some problems are considerably more difficult to accelerate than others, and it may be challenging for those new to GPGPU to ascertain the difficulty of accelerating a particular problem. Through what was learned in the acceleration of three problems, problem attributes have been identified that can assist in the evaluation of the difficulty of accelerating a problem on a GPU. The identified attributes are a problem's available parallelism, inherent parallelism, synchronisation requirements, and data transfer requirements. We envisage that with further development, these attributes could form the foundation of a difficulty classification system that could be used to determine whether GPU acceleration is practical for a candidate GPU acceleration problem, aid in identifying appropriate techniques and optimisations, and outline the required GPGPU knowledge.