Publication | Open Access
Digital Signal Processing Using Stream High Performance Computing
50
Citations
8
References
2015
Year
Wireless CommunicationsEngineeringRadio FrequencyRadio CommunicationMulti-rate Signal ProcessingComputer ArchitectureData Streaming ArchitectureGraphics Processing UnitsParallel ComputingInstrumentationStream ProcessingDual PolarizationRadio EngineeringAntennaComputer EngineeringComputer ScienceRadio TelescopeRadio PropagationSignal ProcessingParallel ProgrammingLarge Aperture Experiment
A “large-N” correlator that makes use of Field Programmable Gate Arrays and Graphics Processing Units has been deployed as the digital signal processing system for the Long Wavelength Array station at Owens Valley Radio Observatory (LWA-OV), to enable the Large Aperture Experiment to Detect the Dark Ages (LEDA). The system samples a [Formula: see text][Formula: see text]MHz baseband and processes signals from 512 antennas (256 dual polarization) over a [Formula: see text][Formula: see text]MHz instantaneous sub-band, achieving 16.8[Formula: see text]Tops[Formula: see text]s[Formula: see text] and 0.236 Tbit[Formula: see text]s[Formula: see text] throughput in a 9[Formula: see text]kW envelope and single rack footprint. The output data rate is 260 MB[Formula: see text]s[Formula: see text] for 9-s time averaging of cross-power and 1[Formula: see text]s averaging of total power data. At deployment, the LWA-OV correlator was the largest in production in terms of N and is the third largest in terms of complex multiply accumulations, after the Very Large Array and Atacama Large Millimeter Array. The correlator’s comparatively fast development time and low cost establish a practical foundation for the scalability of a modular, heterogeneous, computing architecture.
| Year | Citations | |
|---|---|---|
Page 1
Page 1