Abstract:
This paper presents an evolutionary algorithm for searching for the optimal implementations of signal transforms and compares this approach against other search techniques. A single signal processing algorithm can be represented by a very large number of different but mathematically equivalent formulas. When these formulas are implemented in actual code, unfortunately their running times differ significantly. Signal processing algorithm optimization aims at finding the fastest formula. We present a new approach that successfully solves this problem, using an evolutionary stochastic search algorithm, STEER, to search through the very large space of formulas. We empirically compare STEER against other search methods, showing that it notably can find faster formulas while still only timing a very small portion of the search space. 1
Citations
|
4828
|
Genetic Algorithms
– Goldberg
- 1989
|
|
267
|
FFTW: An adaptive software architecture for the FFT
– Frigo, Johnson
- 1998
|
|
233
|
Automatically Tuned Linear Algebra Software
– Whaley, Dongarra
- 1998
|
|
154
|
Optimizing matrix multiply using PHiPAC: A portable, highperformance, ANSI C coding methodology
– Bilmes, Asanovic, et al.
- 1997
|
|
89
|
Discrete Cosine Transform
– Rao, Yip
- 1990
|
|
51
|
High-level optimization via automated statistical modeling
– Brewer
- 1995
|
|
44
|
SPL: A Language and Compiler for DSP Algorithms
– Xiong, Johnson, et al.
- 2001
|
|
37
|
Algorithm selection using reinforcement learning
– Lagoudakis, Littman
- 2000
|
|
34
|
Applications of Walsh and Related Functions
– Beauchamp
- 1984
|
|
23
|
The design of optimal DFT algorithms using dynamic programming
– Johnson, Burrus
- 1983
|
|
21
|
Fast Automatic Generation of DSP Algorithms
– Puschel, Singer, et al.
- 2001
|
|
16
|
Automatic implementation of FFT algorithms
– Auslander, Johnson, et al.
- 1996
|
|
8
|
In search of the optimal Walsh-Hadamard transform
– Johnson, Püschel
- 2000
|
|
6
|
Performance models and search methods for optimal FFT implementations
– Sepiashvili
- 2000
|
|
4
|
An investigation of Cooley-Tukey decompositions for the FFT
– Haentjens
- 2000
|
