The Fastest Fourier Transform in the West (MIT-LCS-TR-728)

نویسندگان

  • Matteo Frigo
  • Steven G. Johnson
چکیده

This paper describes FFTW, a portable C package for computing the oneand multidimensional complex discrete Fourier transform (DFT). FFTW is typically faster than all other publicly available DFT software, including the well-known FFTPACK and the code from Numerical Recipes. More interestingly, FFTW is competitive with or better than proprietary, highly-tuned codes such as Sun’s Performance Library and IBM’s ESSL library. FFTW implements the Cooley-Tukey fast Fourier transform, and is freely available on the Web at http://theory.lcs.mit.edu/ ̃fftw. Three main ideas are the keys to FFTW’s performance. First, the computation of the transform is performed by an executor consisting of highly-optimized, composable blocks of C code called codelets. Second, at runtime, a planner finds an efficient way (called a ‘plan’) to compose the codelets. Through the planner, FFTW adapts itself to the architecture of the machine it is running on. Third, the codelets are automatically generated by a codelet generator written in the Caml Light dialect of ML. The codelet generator produces long, optimized, unreadable code, which is nevertheless easy to modify via simple changes to the generator.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Data - sparse matrix computations Lecture 2 : FFT - The Fast Fourier Transform Lecturer : Anil Damle

It is without a doubt, one crucial piece of the toolbox of numerical methods. The FFT or Fast Fourier Transform is a fast algorithm used to compute the Discrete Fourier Transform. It is one of the most common discrete transforms used today. Note: While many other algorithms used throughout this course can be coded up for use in other projects, you shouldn’t attempt to do this with the FFT. The ...

متن کامل

Architecture independent short vector FFTs

This paper introduces a SIMD vectorization for FFTW—the “fastest Fourier transform in the west” by Matteo Frigo and Steven Johnson. The new method leads to an architecture independent short vector SIMD FFT vectorization that utilizes the architecture adaptivity of FFTW. It is based on special FFT kernels (up to size 64 and more) that are utilized by FFTW to compute the whole transform. This vec...

متن کامل

Detecting buried channels using linear least square RGB color stacking method based on deconvolutive short time Fourier transform

Buried channels are one of the stratigraphic hydrocarbon traps. They are often filled with a variety of porous and permeable sediments so they are important in the exploration of oil and gas reservoirs. In reflection seismic data, high-frequency components are sensitive to the channel thickness, whereas, low-frequency components are sensitive to the channel infill materials. Therefore, decompos...

متن کامل

DFT Performance Prediction in FFTW

Fastest Fourier Transform in the West (FFTW) is an adaptive FFT library that generates highly efficient Discrete Fourier Transform (DFT) implementations. It is one of the fastest FFT libraries available and it outperforms many adaptive or hand-tuned DFT libraries. Its success largely relies on the huge search space spanned by several FFT algorithms and a set of compiler generated C code (called...

متن کامل

Fourier Transforms for the BlueGene/L Communication Network

A computational kernel of particular importance for many scientific applications is the Fast Fourier Transform (FFT) of multi-dimensional data. A fundamental challenge is the design and implementation of such parallel numerical algorithms to utilise efficiently thousands of nodes. The BlueGene/L is a massively parallel high performance computer organised as a three-dimensional torus of compute ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1997