Custom Computing Design and Implementation for Multiple Dedispersion with GPU

Pulsar searching requires a real-time coherent de-dispersion process on an enormous stream of complex voltage data. We present a many-core accelerated de-dispersion pipeline, ACDT, which exploits the custom computing design for multiple de-dispersion on GPUs. The ACDT implementation optimizes the de...

Full description

Saved in:
Bibliographic Details
Main Authors: Kong, Xiangcong, Zheng, Xiaoying, Zhu, Yongxin, Zhang, Qinrun, Huang, Ying
Format: Conference Proceeding
Language:English
Subjects:
Cloud computing
coherent dedispersion
Conferences
custom computation
GPU
Graphics processing units
pipeline
Pipelines
pulsar
Real-time systems
Switches
System-on-chip
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Pulsar searching requires a real-time coherent de-dispersion process on an enormous stream of complex voltage data. We present a many-core accelerated de-dispersion pipeline, ACDT, which exploits the custom computing design for multiple de-dispersion on GPUs. The ACDT implementation optimizes the de-dispersion by switching to on-chip shared memory, adopting customized FFT with the overlap-save method, and overlapping the computation with transfer by a two-stage pipeline. The overall performance of ACDT is improved by 2 to 4 times when multiple DMs are processed in sequential compared to the state-of-the-art CDMT package.
ISSN:2693-8928
DOI:10.1109/CSCloud-EdgeCom52276.2021.00028