cuInspiral: prototype gravitational waves detection pipeline fully coded on GPU using CUDA

TL;DR

This paper presents cuInspiral, a GPU-based gravitational wave detection pipeline that significantly accelerates computations using CUDA, demonstrating promising performance improvements for future gravitational wave observatories.

Contribution

The paper introduces cuInspiral, the first fully GPU-implemented binary coalescence detection pipeline, showcasing its performance and accuracy advantages over CPU-based methods.

Findings

GPU implementation achieves substantial speedup over CPU code.

The pipeline maintains high detection accuracy.

Performance results support future gravitational wave data analysis.

Abstract

In this paper we report the prototype of the first coalescing binary detection pipeline fully implemented on NVIDIA GPU hardware accelerators. The code has been embedded in a GPU library, called cuInspiral and has been developed under CUDA framework. The library contains for example a PN gravitational wave signal generator, matched filtering/FFT and detection algorithms that have been profiled and compared with the corresponding CPU code with dedicated benchmark in order to provide gain factor respect to the standard CPU implementation. In the paper we present performances and accuracy results about some of the main important elements of the pipeline, demonstrating the feasibility and the chance of obtain an impressive computing gain from these new many-core architectures in the perspective of the second and third generations of gravitational wave detectors.