Accelerating Adaptive IDW Interpolation Algorithm on a Single GPU

TL;DR

This paper presents GPU-accelerated versions of the adaptive IDW interpolation algorithm, significantly improving computational speed, especially in single precision, through shared memory optimization and data layout strategies.

Contribution

It introduces two GPU implementations of AIDW, compares their performance, and demonstrates substantial speedups over CPU versions, highlighting the effects of data layout and precision.

Findings

Naive GPU version achieves ~270x speedup in single precision.

Tiled GPU version achieves ~400x speedup in single precision.

Performance gains are minimal in double precision, with only ~8x speedup.

Abstract

This paper focuses on the design and implementing of GPU-accelerated Adaptive Inverse Distance Weighting (AIDW) interpolation algorithm. The AIDW is an improved version of the standard IDW, which can adaptively determine the power parameter according to the spatial points distribution pattern and achieve more accurate predictions than those by IDW. In this paper, we first present two versions of the GPU accelerated AIDW, the naive version without profiting from shared memory and the tiled version taking advantage of shared memory. We also implement the naive version and the tiled version using the data layouts, Structure of Arrays (AoS) and Array of aligned Structures (AoaS), on single and double precision. We then evaluate the performance of the GPU-accelerated AIDW by comparing it with its original CPU version. Experimental results show that: on single precision the naive version and the tiled version can achieve the speedups of approximately 270 and 400, respectively. In addition, on single precision the implementations using the layout SoA are always slightly faster than those using layout AoaS. However, on double precision, the speedup is only about 8; and we have also observed that: (1) there are no performance gains obtained from the tiled version against the naive version; and (2) the use of SoA and AoaS does not lead to significant differences in computational efficiency.