GPU accelerated computation of fast spectral transforms

• Published in: Facta universitatis. Series Electronics and energetics Vol. 24; no. 3; pp. 483 - 499
• Main Authors: Gajic, Dusan, Stankovic, Radomir
• Format: Journal Article
• Language: English
• Published: 2011
• ISSN: 0353-3670; 2217-5997
• DOI: 10.2298/FUEE1103483G

This paper discusses techniques for accelerated computation of several fast
spectral transforms on graphics processing units (GPUs) using the Open
Computing Language (OpenCL). We present a reformulation of fast algorithms
which takes into account peculiar properties of transforms to make them
suitable for the GPU implementation. A special attention is paid to the
organization of computations, memory transfer reductions, impact of integer
and Boolean arithmetic, different structure of algorithms, etc. Performance
of the GPU implementations is compared with the classical C/C++
implementations for the central processing unit (CPU). Experiments confirm
that, even though the spectral transforms considered involve only simple
arithmetic, significant speedups are achieved by implementing the algorithms
in OpenCL and performing them on the GPU.
nema