Understanding the Impact of Synchronous, Asynchronous, and Hybrid In-Situ Techniques in Computational Fluid Dynamics Applications

TL;DR

The paper tackles IO and storage bottlenecks in CFD at Exascale by evaluating three in-situ coordination models—synchronous, asynchronous, and hybrid—across three tasks: physics-based lossy/lossless data compression, in-situ visualization, and uncertainty quantification, using Nek5000 as the CFD kernel. It employs an ADIOS2-based in-situ workflow with adaptor layers to connect Nek5000 to the in-situ tasks and presents three real-world case studies on large CPU systems, including a new physics-based lossy compression method. The results show task-dependent benefits: compression favors synchronous execution for low-overhead operation, visualization benefits from asynchronous execution to reduce MPI bottlenecks, and UQ achieves best performance in a hybrid setup that amortizes communication and balances workload. These findings provide practical guidance for selecting in-situ approaches on homogeneous CPU HPC systems and point to future work on predictive models and GPU/heterogeneous-node extensions to support exascale simulations.

Abstract

High-Performance Computing (HPC) systems provide input/output (IO) performance growing relatively slowly compared to peak computational performance and have limited storage capacity. Computational Fluid Dynamics (CFD) applications aiming to leverage the full power of Exascale HPC systems, such as the solver Nek5000, will generate massive data for further processing. These data need to be efficiently stored via the IO subsystem. However, limited IO performance and storage capacity may result in performance, and thus scientific discovery, bottlenecks. In comparison to traditional post-processing methods, in-situ techniques can reduce or avoid writing and reading the data through the IO subsystem, promising to be a solution to these problems. In this paper, we study the performance and resource usage of three in-situ use cases: data compression, image generation, and uncertainty quantification. We furthermore analyze three approaches when these in-situ tasks and the simulation are executed synchronously, asynchronously, or in a hybrid manner. In-situ compression can be used to reduce the IO time and storage requirements while maintaining data accuracy. Furthermore, in-situ visualization and analysis can save Terabytes of data from being routed through the IO subsystem to storage. However, the overall efficiency is crucially dependent on the characteristics of both, the in-situ task and the simulation. In some cases, the overhead introduced by the in-situ tasks can be substantial. Therefore, it is essential to choose the proper in-situ approach, synchronous, asynchronous, or hybrid, to minimize overhead and maximize the benefits of concurrent execution.

Figures (12)

• Figure 1: Illustration of a simulation with synchronous, asynchronous and hybrid in-situ tasks.
• Figure 2: Illustration of the workflow of a Nek5000 simulation with a synchronous in-situ task.
• Figure 3: Illustration of the workflow of a Nek5000 simulation with an asynchronous in-situ task.
• Figure 4: Illustration of the workflow of a Nek5000 simulation with a hybrid in-situ task.
• Figure 5: Slice of the velocity magnitude downstream from the bent section. a) is the original data set, while b) is the reconstruction of a field compressed with a maximum allowed error of $10^{-2}$.