SearcharxivSearch

arXiv subjects

Atul Ghalame

Publications and source records attributed to Atul Ghalame.

2 recordsLinked to original sources

High-Performance Computing for SKA Transient Search: Use of FPGA based Accelerators -- a brief review

This paper presents the High-Performance computing efforts with FPGA for the accelerated pulsar/transient search for the SKA. Case studies are presented from within SKA and pathfinder telescopes highlighting future opportunities. It reviews the scenario that has shifted from offline processing of the radio telescope data to digitizing several hundreds/thousands of antenna outputs over huge bandwidths, forming several 100s of beams, and processing the data in the SKA real-time pulsar search pipelines. A brief account of the different architectures of the accelerators, primarily the new generation Field Programmable Gate Array-based accelerators, showing their critical roles to achieve high-performance computing and in handling the enormous data volume problems of the SKA is presented here. It also presents the power-performance efficiency of this emerging technology and presents potential future scenarios.

astro-ph.IM

Investigation of a Machine learning methodology for the SKA pulsar search pipeline

The SKA pulsar search pipeline will be used for real time detection of pulsars. Modern radio telescopes such as SKA will be generating petabytes of data in their full scale of operation. Hence experience-based and data-driven algorithms become indispensable for applications such as candidate detection. Here we describe our findings from testing a state of the art object detection algorithm called Mask R-CNN to detect candidate signatures in the SKA pulsar search pipeline. We have trained the Mask R-CNN model to detect candidate images. A custom annotation tool was developed to mark the regions of interest in large datasets efficiently. We have successfully demonstrated this algorithm by detecting candidate signatures on a simulation dataset. The paper presents details of this work with a highlight on the future prospects.

astro-ph.IM