Simulation-Based Performance Prediction of HPC Applications: A Case Study of HPL

TL;DR

This paper introduces a simulation-based performance prediction method for HPC applications that accurately models hardware and software components, demonstrated through the HPL benchmark on supercomputers.

Contribution

The paper presents a hybrid simulation approach enabling fast, accurate, and low-overhead performance modeling of HPC applications at exascale, with minimal source code modifications.

Findings

Accurately predicts HPL performance with 4% error on Frontera.

Simulation takes less than five hours for large-scale HPL.

Method is scalable and applicable to TOP500 supercomputers.

Abstract

We propose a simulation-based approach for performance modeling of parallel applications on high-performance computing platforms. Our approach enables full-system performance modeling: (1) the hardware platform is represented by an abstract yet high-fidelity model; (2) the computation and communication components are simulated at a functional level, where the simulator allows the use of the components native interface; this results in a (3) fast and accurate simulation of full HPC applications with minimal modifications to the application source code. This hardware/software hybrid modeling methodology allows for low overhead, fast, and accurate exascale simulation and can be easily carried out on a standard client platform (desktop or laptop). We demonstrate the capability and scalability of our approach with High Performance LINPACK (HPL), the benchmark used to rank supercomputers in the TOP500 list. Our results show that our modeling approach can accurately and efficiently predict the performance of HPL at the scale of the TOP500 list supercomputers. For instance, the simulation of HPL on Frontera takes less than five hours with an error rate of four percent.