Spiral: A Generator for Platform-Adapted Libraries of Signal Processing Alogorithms
- 1 February 2004
- journal article
- other
- Published by SAGE Publications in The International Journal of High Performance Computing Applications
- Vol. 18 (1) , 21-45
- https://doi.org/10.1177/1094342004041291
Abstract
SPIRAL is a generator for libraries of fast software implementations of linear signal processing transforms. These libraries are adapted to the computing platform and can be re-optimized as the hardware is upgraded or replaced. This paper describes the main components of SPIRAL: the mathematical framework that concisely describes signal transforms and their fast algorithms; the formula generator that captures at the algorithmic level the degrees of freedom in expressing a particular signal processing transform; the formula translator that encapsulates the compilation degrees of freedom when translating a specific algorithm into an actual code implementation; and, finally, an intelligent search engine that finds within the large space of alternative formulas and implementations the “best” match to the given computing platform. We present empirical data that demonstrate the high performance of SPIRAL generated code.Keywords
This publication has 24 references indexed in Scilit:
- Automating the modeling and optimization of the performance of signal transformsIEEE Transactions on Signal Processing, 2002
- Optimizing Sparse Matrix Computations for Register Reuse in SPARSITYPublished by Springer Nature ,2001
- Automatic Performance Tuning in the UHFFT LibraryPublished by Springer Nature ,2001
- Algorithms for Discrete Fourier Transform and ConvolutionPublished by Springer Nature ,1997
- A methodology for designing, modifying, and implementing Fourier transform algorithms on various architecturesCircuits, Systems, and Signal Processing, 1990
- The discreteW transformApplied Mathematics and Computation, 1985
- Simple FFT and DCT algorithms with reduced number of operationsSignal Processing, 1984
- Fast algorithms for the discrete W transform and for the discrete Fourier transformIEEE Transactions on Acoustics, Speech, and Signal Processing, 1984
- The design of optimal DFT algorithms using dynamic programmingIEEE Transactions on Acoustics, Speech, and Signal Processing, 1983
- An algorithm for the machine calculation of complex Fourier seriesMathematics of Computation, 1965