The Community for Technology Leaders
Proceedings of the 22nd International Conference on Parallel Architectures and Compilation Techniques (2000)
Philadelphia, Pennsylvania
Oct. 15, 2000 to Oct. 19, 2000
ISSN: 1089-795X
ISBN: 0-7695-0622-4
pp: 249
Kang Su Gatlin , University of California at San Diego
Larry Carter , University of California at San Diego
ABSTRACT
The Fast Fourier Transform (FFT) is one of the most important algorithms in computational science, accounting for large amounts of computing time. One major problem with modern FFT implementations is that they poorly scale to large problem. As the problem size increases, stride and associativity effects play a larger role. The result is a severe drop-off in performance. We use architecture-cognizance, a method for exploiting the interaction between architecture, compiler, and algorithm, to create a more scalable FFT package based on FFTW. Experiments validate our approach on four architectures: two generations of HPs (PA-8000 and 8500), an IBM POWER2, and a DEC Alpha 21164a. Performance increases of up to 65% are obtained.
INDEX TERMS
memory hierarchy, cache, TLB, divide-and-conquer, compiler optimization, runtime systems, feedback, ILP, associativity, registers
CITATION
Kang Su Gatlin, Larry Carter, "Faster FFTs via Architecture-Cognizance", Proceedings of the 22nd International Conference on Parallel Architectures and Compilation Techniques, vol. 00, no. , pp. 249, 2000, doi:10.1109/PACT.2000.888349
95 ms
(Ver 3.3 (11022016))