Packaging HEP Heterogeneous Mini-apps for Portable Benchmarking and Facility Evaluation on Modern HPCs
Mohammad Atif, Pengfei Ding, Ka Hei Martin Kwok, Charles Leggett
TL;DR
The paper tackles the challenge of evaluating and deploying heterogeneous HEP workloads on diverse, evolving HPCs. It presents turn-key deployment strategies for two representative mini-apps: p2r using Spack and FastCaloSim using containerization, enabling cross-platform benchmarking. Key contributions include a Spack-based build system for p2r with explicit backend variants and an external-packages mechanism, plus a CI-driven container workflow for FastCaloSim with automated performance tracking. The approach enables reproducible, scalable benchmarking and facility evaluation, informing resource allocation and hardware procurement decisions.
Abstract
High Energy Physics (HEP) experiments are making increasing use of GPUs and GPU dominated High Performance Computer facilities. Both the software and hardware of these systems are rapidly evolving, creating challenges for experiments to make informed decisions as to where they wish to devote resources. In its first phase, the High Energy Physics Center for Computational Excellence (HEP-CCE) produced portable versions of a number of heterogeneous HEP mini-apps, such as \ptor, FastCaloSim, Patatrack and the WireCell Toolkit, that exercise a broad range of GPU characteristics, enabling cross platform and facility benchmarking and evaluation. However, these mini-apps still require a significant amount of manual intervention to deploy on a new facility. We present our work in developing turn-key deployments of these mini-apps, where by means of containerization and automated configuration and build techniques such as Spack, we are able to quickly test new hardware, software, environments and entire facilities with minimal user intervention, and then track performance metrics over time.