An FFT performance model for optimizing general-purpose processor architecture

DOI10.1007/S11390-011-0186-ZzbMATH Open1280.68075OpenAlexW2023873579MaRDI QIDQ2434553FDOQ2434553

Authors Ling Li, Yunji Chen, Dao-Fu Liu, Cheng Qian, Weiwu Hu

Publication date 6 February 2014

Published in Journal of Computer Science and Technology (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s11390-011-0186-z

zbMATH Keywords

DMAfast Fourier transform (FFT)general-purpose processor (GPP)performance prediction modelvector unit

Mathematics Subject Classification ID

Performance evaluation, queueing, and scheduling in the context of computer systems (68M20) Computer system organization (68M99)

Recommendations

• Four easy ways to a faster FFT
• Modified FFTs for Fused Multiply-Add Architectures
• Compiler Construction
• A low-memory-access length-adaptive architecture for \(2^n\)-point FFT
• scientific article; zbMATH DE number 1756129

Cites work

• 10.1162/jmlr.2003.3.4-5.887
• An Algorithm for the Machine Calculation of Complex Fourier Series
• Parallelization and Performance Analysis of the Cooley–Tukey FFT Algorithm for Shared-Memory Architectures

Cited in

(2)

• Fixed-Point Analysis and Parameter Optimization of the Radix-<formula formulatype="inline"><tex Notation="TeX">$2^{k}$</tex> </formula> Pipelined FFT Processor
• Hybrid Wordlength Optimization Methods of Pipelined FFT Processors

Describes a project that uses

Uses Software

• FFTW

This page was built for publication: An FFT performance model for optimizing general-purpose processor architecture

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2434553)