SPIRAL: Code Generation for DSP Transforms
Markus Püschel, José M. F. Moura, Jeremy Russell Johnson et al. · Proceedings of the IEEE · 2005
Fast changing, increasingly complex, and diverse computing platforms pose central problems in scientific computing: How to achieve, with reasonable effort, portable optimal performance? We present SPIRAL, which considers this problem for the performance-critical domain of linear digital signal processing (DSP) transforms. For a specified transform, SPIRAL automatically generates high-performance code that is tuned to the given platform. SPIRAL formulates the tuning as an optimization problem and exploits the domain-specific mathematical structure of transform algorithms to implement a feedback-driven optimizer. Similar to a human expert, for a specified transform, SPIRAL "intelligently" generates and explores algorithmic and implementation choices to find the best match to the computer's microarchitecture. The "intelligence" is provided by search and learning techniques that exploit the structure of the algorithm and implementation space to guide the exploration and optimization. SPIRAL generates high-performance code for a broad set of DSP transforms, including the discrete Fourier transform, other trigonometric transforms, filter transforms, and discrete wavelet transforms. Experimental results show that the code generated by SPIRAL competes with, and sometimes outperforms, the best available human tuned transform library code.
Cited by 824 works. doi:10.1109/jproc.2004.840306
Authors
- Markus Püschel
- José M. F. Moura
- Jeremy Russell Johnson
- David Padua
- Manuela Veloso
- Bryan Singer
- Jianxin Xiong
- Franz Franchetti
- A. Gacic
- Yevgen Voronenko
- K. Chen
- Robert William Johnson
- Nick Rizzolo
References
- Genetic algorithms in search, optimization, and machine learning
- Numerical recipes in C: the art of scientific computing
- Genetic Algorithms in Search, Optimization and Machine Learning
- Numerical recipes in Pascal: the art of scientific computing
- Discrete-Time Signal Processing
- Genetic Algorithms
- The Art of Computer Programming. Volume 1: Fundamental Algorithms.
- Multirate Systems and Filter Banks
- Wavelets and filter banks
- LAPACK Users' Guide