Poster Type: ACM SRC Posters
Author: Yuya Kudo (Hokkaido University), Yuki Satake (Hokkaido University), Takeshi Fukaya (Hokkaido University), Takeshi Iwashita (Kyoto University)
Abstract: We develop a GPU-friendly variant of the symmetric successive over-relaxation (SSOR) preconditioner for efficient execution of the preconditioned conjugate gradient (PCG) method on GPUs. To avoid the forward and backward substitutions required by the original SSOR preconditioner, which constitute a major bottleneck on GPUs, we incorporate an approximate inverse of a triangular matrix appearing in the SSOR preconditioner, with a dropping strategy to reduce the cost of applying it. We demonstrate the effectiveness of the proposed SSOR variant against existing parallel SSOR variants on an NVIDIA H100 GPU. The proposed variant substantially reduces the cost of applying the preconditioner by replacing the forward and backward substitutions with SpMVs, while largely preserving the convergence improvement of SSOR. Consequently, despite the additional cost of constructing the approximate inverse, the total PCG execution time is reduced for most of the test matrices, demonstrating that the proposed approach provides an effective GPU-friendly SSOR variant.
Best Poster Finalist (BP): no
Poster: PDF
Poster Summary: PDF