Investigating Portability in Chapel for Tree-Based Optimization on GPU-Powered Clusters

The Top500 list features supercomputers powered by accelerators from different vendors. This variety brings, along with the heterogeneity challenge, both the code and performance portability challenges. In this context, Chapel’s native GPU support comes as a solution for code portability between different vendors. In this paper, we investigate the viability of using the Chapel high-productivity language as a tool to achieve both code and performance portability in large-scale tree-based search. As a case study, we implemented a distributed backtracking for solving permutation combinatorial problems. Extensive experiments conducted on big N-Queens problem instances, using up to 512 NVIDIA GPUs and 1024 AMD GPUs on Top500 supercomputers, reveal that it is possible to scale on the two different systems using the same tree-based search written in Chapel. This trade-off results in a performance decrease of less than \(10\%\) for the biggest problem instances.