Automatic Performance Tuning in the UHFFT Library
نویسنده
چکیده
In this paper we describe the architecture{speci c automatic performance tuning implemented in the UHFFT library. The UHFFT library is an adaptive and portable software library for fast Fourier transforms (FFT).
منابع مشابه
Automatic Performance Tuning for Fast Fourier Transforms
In this paper we discuss architecture-specific performance tuning for fast Fourier transforms (FFTs) implemented in the UHFFT library. The UHFFT library is an adaptive and portable software library for FFTs developed by the authors. We present the optimization methods used at different levels, starting with the algorithm selection used for the library code generation and ending with the actual ...
متن کاملUHFFT: A High Performance DFT Framework
We present a framework for algorithm selection, code generation and optimization for the Fast Fourier Transform. The framework consists of two main parts – the DFT Code Generator (FftGen) and the Execution Scheduler (FftPlanner). The library generator outputs a highly optimized set of small to modest size DFT codelets written in ‘C’. The FftPlanner searches an exponential space of possible algo...
متن کاملAutomatic tuning of a behavior-based guidance algorithm for formation flight of quadrotors
This paper presents a tuned behavior-based guidance algorithm for formation flight of quadrotors. The behavior-based approach provides the basis for the simultaneous realization of different behaviors such as leader following and obstacle avoidance for a group of agents; in our case they are quadcopters. In this paper optimization techniques are utilized to tune the parameters of a behavior-bas...
متن کاملEmpirical Auto-tuning Code Generator for FFT and Trigonometric Transforms
We present an automatic, empirically tuned code genenrator for Real/Complex FFT and Trigonometric Transforms. The code generator is part of an adaptive and portable FFT computation framework UHFFT. Performance portability over varying architectures is achieved by generating highly optimized set of straight line C codelets (micro-kernel) that adapt to the microprocessor architecture. The tuning ...
متن کاملStatistical Models for Automatic Performance Tuning
Achieving peak performance from library subroutines usually requires extensive, machine-dependent tuning by hand. Automatic tuning systems have emerged in response, and they typically operate by (1) generating a large number of possible implementations of a subroutine, and (2) selecting the fastest implementation by an exhaustive, empirical search. This paper presents quantitative data that mot...
متن کامل