Efficient Parallel FFTs for Different Computational Models
نویسنده
چکیده
We select the Fast Fourier Transfrom (FFT) to demonstrate a methodology for deriving the optimal parallel algorithm according to predetermined performance metrics, within a computational model. Following the vector space framework for parallel permutations, we provide a speci cation language to capture the algorithm, derive the optimal parallel FFT speci cation, compute the arithmetic, memory, communication and load{balance complexity metrics, apply the analytical performance evaluation to PRAM, LPRAM, BSP and LogP computational models, and compare with actual performance results.
منابع مشابه
Eecient Parallel Ffts for Diierent Computational Models Eecient Parallel Ffts for Diierent Computational Models
We select the Fast Fourier Transfrom (FFT) to demonstrate a methodology for deriving the optimal parallel algorithm according to predetermined performance metrics, within a computational model. Following the vector space framework for parallel permutations, we provide a speciication language to capture the algorithm, derive the optimal parallel FFT speciication, compute the arithmetic, memory, ...
متن کامل3D FFTs on HPCx
Fast Fourier Transforms (FFTs) are an essential part of many scientific codes: from Molecular Dynamics to Climate Modelling. It is, therefore, evident that HPCx requires efficient methods for performing FFTs and related calculations. This study compares the performance of the two main FFT libraries on HPCx: IBM’s ESSL/PESSL and FFTW. Both serial and parallel (distributedmemory only) 3D complex-...
متن کاملFast Fourier Transform BYLINE
A fast Fourier transform (FFT) is an efficient algorithm to compute the discrete Fourier transform (DFT) of an input vector. Efficient means that the FFT computes the DFT of an n-element vector in O(n logn) operations in contrast to the O(n2) operations required for computing the DFT by definition. FFTs exist for any vector length n and for real and higher-dimensional data. Parallel FFTs have b...
متن کاملPerforming Out-of Core FFTs on Parallel Disk Systems
The Fast Fourier Transform (FFT) plays a key role in many areas of computational science and engineering. Although most one-dimensional FFT problems can be solved entirely in main memory, some important classes of applications require out-of-core techniques. For these, use of parallel I/O systems can improve performance considerably. This paper shows how to perform one-dimensional FFTs using a ...
متن کاملEfficient FFTs on IRAM
Computing Fast Fourier Transforms (FFTs) is notoriously difficult on conventional general-purpose architectures because FFTs require high memory bandwidth and strided memory accesses. Since FFTs are important in signal processing, several DSPs have hardware support for performing FFTs; moreover, some DSPs are designed solely for the purpose of computing FFTs and related transforms. In this pape...
متن کامل