Radio interferometric imaging refers to the construction of images on visibility data observed by radio telescope arrays. Due to the data and computation intensity, existing imaging algorithms are slow for wide field measurement. To address this problem, we propose cuGridder, a GPU-based CUDA C program that produces the same result as W-gridder, the latest CPU-based imaging algorithm, but the execution is accelerated effectively by the GPU. Our main idea is to divide the imaging workflow into a sequence of steps, including convolution, 2D FFT, 1D DFT, and correction, and parallelize each step as a GPU kernel program. Furthermore, we design a lock-free algorithm for convolution, the most expensive step in the workflow, adopt a simple yet effective mask function for the convolution, and o...[ Read more ]

Radio interferometric imaging refers to the construction of images on visibility data observed by radio telescope arrays. Due to the data and computation intensity, existing imaging algorithms are slow for wide field measurement. To address this problem, we propose cuGridder, a GPU-based CUDA C program that produces the same result as W-gridder, the latest CPU-based imaging algorithm, but the execution is accelerated effectively by the GPU. Our main idea is to divide the imaging workflow into a sequence of steps, including convolution, 2D FFT, 1D DFT, and correction, and parallelize each step as a GPU kernel program. Furthermore, we design a lock-free algorithm for convolution, the most expensive step in the workflow, adopt a simple yet effective mask function for the convolution, and optimize the memory access pattern. As a result, cuGridder outperforms the state-of-the-art CPU-based and GPU-based libraries in running time and achieves high image quality. Our code package is available at https://github.com/HLSUD/cuGridder.