Code generators for automatic tuning of numerical kernels: Experiences with FFTW (position paper)

DOI10.1007/3-540-45350-4_14MaRDI QIDQ4472545zbMATH OpenFDO

Authors Richard Vuduc, James Demmel

Publication date 4 August 2004

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL http://link.springer.de/link/service/series/0558/bibs/1924/19240190.htm

Mathematics Subject Classification ID

Numerical methods for discrete and fast Fourier transforms (65T50) General topics in the theory of software (68N01)

Recommendations

• Automatically tuned FFTs for BlueGene/L's double FPU
• Compiler Construction
• Automatic performance tuning in the UHFFT library
• Statistical models for automatic performance tuning
• SPIRAL and beyond: automatic derivation and optimization of DSP algorithms and more

Cited in

(7)

• FFTW
• Automatic performance tuning in the UHFFT library
• Statistical models for automatic performance tuning
• Automatic parallel library generation for general-size modular FFT algorithms
• SPIRAL and beyond: automatic derivation and optimization of DSP algorithms and more
• A Rewriting System for the Vectorization of Signal Transforms
• Automatically tuned FFTs for BlueGene/L's double FPU

Describes a project that uses

Uses Software

• BLAS
• PHiPAC

This page was built for publication: Code generators for automatic tuning of numerical kernels: Experiences with FFTW (position paper)

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4472545)