Auto-tuning of fast fourier transform on graphics processors (original) (raw)

Proceedings of the 16th ACM symposium on Principles and practice of parallel programming - PPoPP '11, 2011

Abstract

We present an auto-tuning framework for FFTs on graphics processors (GPUs). Due to complex design of the memory and compute subsystems on GPUs, the performance of FFT kernels over the range of possible input parameters can vary widely. We generate several variants for ...

Brandon Lloyd hasn't uploaded this paper.

Let Brandon know you want this paper to be uploaded.

Ask for this paper to be uploaded.