SPL: A language and compiler for DSP algorithms

We discuss the design and implementation of a compiler that translates form ulas representing signal processing transforms into efficient C or Fortran programs. The formulas are represented in a language that we call SPL, an a cronym from Signal Processing Language. The compiler is a component of the SPIRAL system which makes use of formula transformations and intelligent se arch strategies to automatically generate optimized digital signal processi ng (DSP) libraries. After a discussion of the translation and optimization techniques implemented in the compiler, we use SPL formulations of the fast Fourier transform (FFT) to evaluate the compiler. Our results show that SP IRAL, which can be used to implement many classes of algorithms, produces p rograms that perform as well as "hard-wired" systems like FFTW.