An Improved GPU-Based Ray-Shooting Code For Gravitational Microlensing

TL;DR

This paper introduces an optimized GPU-based inverse ray-shooting algorithm for gravitational microlensing, significantly reducing computation time while maintaining accuracy, through geometric and interpolation improvements.

Contribution

The authors developed a novel GPU-accelerated ray-shooting method with a rectangular lens plane and interpolation, achieving 100x speedup over previous codes for high-resolution microlensing maps.

Findings

Speed increased by about 100 times for large lens numbers.

High-resolution maps up to 10,000^2 pixels are computed two orders faster.

Method maintains high accuracy despite acceleration.

Abstract

We present an improved inverse ray-shooting code based on GPUs for generating microlensing magnification maps. In addition to introducing GPUs for acceleration, we put the efforts in two aspects: (i) A standard circular lens plane is replaced by a rectangular one to reduce the number of unnecessary lenses as a result of an extremely prolate rectangular image plane. (ii) Interpolation method is applied in our implementation which has achieved an significant acceleration when dealing with large number of lenses and light rays required by high resolution maps. With these applications, we have greatly reduced the running time while maintaining high accuracy: the speed has been increased by about 100 times compared with ordinary GPU based IRS code and GPU-D code when handling large number of lenses. If encountered the high resolution situation up to $10000^2$ pixels, resulting in almost $10^{11}$ light rays, the running time can also be reduced by two orders of magnitude.