The detection of gravitational waves (GWs) from binary neutron stars (BNSs) with possible telescope follow-ups opens a window to ground-breaking discoveries in the field of multi-messenger astronomy. With the improved sensitivity of current and future GW detectors, more BNS detections are expected. Therefore, enhancing low-latency GW search algorithms to achieve rapid speed, high accuracy, and low computational cost is essential. One innovative solution to reduce latency is to embed machine learning (ML) methods in heterogeneous computing systems. In this work, we evaluate the performance, time, energy, and economic cost of our model across CPU, GPU, and FPGA platforms, showcasing its potential for deployment in real-time gravitational wave detection pipelines. Furthermore, we discuss our main challenges and setbacks during the process.

Associated Links

• Presentation Slides (PDF)
• Presentation Slides (PPTX)
• Indico Agenda