Domain-specific library generation for parallel software and hardware platforms
Franchetti, F.
Voronenko, Y.
Milder, P.A.
Chellappa, S.
Telgarsky, M.R.
Hao Shen
D'Alberto, P.
de Mesmay, F.
Hoe, J.C.
Moura, J.M.F.
Piischel, M.
Carnegie Mellon Univ., Pittsburg, PA;
This paper appears in: Parallel and Distributed Processing, 2008. IPDPS 2008. IEEE International Symposium on
Publication Date: 14-18 April 2008
On page(s): 1-5
Location: Miami, FL,
ISSN: 1530-2075
ISBN: 978-1-4244-1693-6
INSPEC Accession Number: 10025278
Digital Object Identifier: 10.1109/IPDPS.2008.4536398
Current Version Published: 2008-06-03
Abstract
We overview a library generation framework called Spiral. For the domain of linear transforms, Spiral automatically generates implementations for parallel platforms including SIMD vector extensions, multicore processors, field-programmable gate arrays (FPGAs) and FPGA accelerated processors. The performance of the generated code is competitive with the best available hand-written libraries.
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
