Write a Blog >>
ICFP 2019
Sun 18 - Fri 23 August 2019 Berlin, Germany
Sun 18 Aug 2019 10:50 - 11:16 at Reindeer - Orthogonal Bases Chair(s): Gabriele Keller

The Fast Fourier Transform is a well-known algorithm used in many high-performance applications, ranging from signal processing to convolutional neural networks.

In this paper, we encode FFTs by building high-level abstractions based on a set of functional parallel patterns in the Lift language. Abstractions are derived from and closely resemble mathematical definitions for FFTs. We leverage the Lift performance-portable code generator to generate high performing GPU code for FFTs. No FFT-specific patterns are required for this, showing the expressive power of the generic parallel patterns used in Lift.

Our experimental results show that our approach achieves performance close to or better than AMD’s OpenCL implementation clFFT on two different models of GPU, but that Nvidia’s highly optimized cuFFT implementation still performs better on their GPUs.

Sun 18 Aug

Displayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change

10:50 - 12:10
Orthogonal BasesFHPNC at Reindeer
Chair(s): Gabriele Keller Utrecht University
Generating Efficient FFT GPU Code with Lift
Bastian Köpcke University of Münster, Michel Steuwer University of Glasgow, Sergei Gorlatch
Link to publication DOI Pre-print File Attached
Lazy Evaluation in Infinite-Dimensional Function Spaces with Wavelet Basis
Olivier Verdier , Justus Sagemüller Western Norway University of Applied Sciences
Link to publication Pre-print
Functional Approach to Acceleration of Monte Carlo Simulation for American Option Pricing (extended abstract)
Wojciech Michal Pawlak University of Copenhagen, Denmark, Martin Elsman University of Copenhagen, Denmark, Cosmin Oancea University of Copenhagen, Denmark
Link to publication