Presentation
Massively Parallel Bayesian Inference Framework for GPU Supercomputers: Application to Estimation of Coseismic Fault Slip
DescriptionWe present a massively parallel Bayesian inference framework for GPU supercomputers, demonstrated in coseismic fault slip estimation. Bayesian inference, a robust method for inverse analysis, often relies on Monte Carlo sampling with over 100,000 forward simulations, making large-scale applications computationally intensive. A previous state-of-the-art implementation for the CPU-based supercomputer Fugaku was unsuitable for GPUs due to numerous small, imbalanced computations. We redesigned the algorithm to enforce uniform, dense computation and employed Multi-Process Service (MPS) to maximize GPU utilization. On a single node of the GPU-based supercomputer Miyabi with an NVIDIA GH200 Grace Hopper Superchip, the method achieved 13.40 TFLOPS (20% of Tensor Cores FP64 peak) and scaled to 128 nodes with 92.3% efficiency. Compared with the original CPU implementation on Fugaku, it achieved a 42.1-fold speedup per node and reduced energy-to-solution to 18.8%. The methodology provides a general guide for porting Bayesian inference and similar applications to GPU-based environments.
Event Type
Research and ACM SRC Posters
TimeThursday, 20 November 20258:00am - 5:00pm CST
LocationSecond Floor Atrium
Archive
view
Similar Presentations