arXiv subjects

Stephen Hudson

Publications and source records attributed to Stephen Hudson.

4 recordsLinked to original sources

arXiv2024

Workflows Community Summit 2024: Future Trends and Challenges in Scientific Workflows

The Workflows Community Summit gathered 111 participants from 18 countries to discuss emerging trends and challenges in scientific workflows, focusing on six key areas: time-sensitive workflows, AI-HPC convergence, multi-facility workflows, heterogeneous HPC environments, user experience, and FAIR computational workflows. The integration of AI and exascale computing has revolutionized scientific workflows, enabling higher-fidelity models and complex, time-sensitive processes, while introducing challenges in managing heterogeneous environments and multi-facility data dependencies. The rise of large language models is driving computational demands to zettaflop scales, necessitating modular, adaptable systems and cloud-service models to optimize resource utilization and ensure reproducibility. Multi-facility workflows present challenges in data movement, curation, and overcoming institutional silos, while diverse hardware architectures require integrating workflow considerations into early system design and developing standardized resource management tools. The summit emphasized improving user experience in workflow systems and ensuring FAIR workflows to enhance collaboration and accelerate scientific discovery. Key recommendations include developing standardized metrics for time-sensitive workflows, creating frameworks for cloud-HPC integration, implementing distributed-by-design workflow modeling, establishing multi-facility authentication protocols, and accelerating AI integration in HPC workflow management. The summit also called for comprehensive workflow benchmarks, workflow-specific UX principles, and a FAIR workflow maturity model, highlighting the need for continued collaboration in addressing the complex challenges posed by the convergence of AI, HPC, and multi-facility research environments.

cs.DC↗

arXiv2024

Portable, heterogeneous ensemble workflows at scale using libEnsemble

libEnsemble is a Python-based toolkit for running dynamic ensembles, developed as part of the DOE Exascale Computing Project. The toolkit utilizes a unique generator--simulator--allocator paradigm, where generators produce input for simulators, simulators evaluate those inputs, and allocators decide whether and when a simulator or generator should be called. The generator steers the ensemble based on simulation results. Generators may, for example, apply methods for numerical optimization, machine learning, or statistical calibration. libEnsemble communicates between a manager and workers. We overview the unique characteristics of libEnsemble as well as current and potential interoperability with other packages in the workflow ecosystem. We highlight libEnsemble's dynamic resource features: libEnsemble can detect system resources, such as available nodes, cores, and GPUs, and assign these in a portable way. These features allow users to specify the number of processors and GPUs required for each simulation; and resources will be automatically assigned on a wide range of systems, including Frontier, Aurora, and Perlmutter. Such ensembles can include multiple simulation types, some using GPUs and others using only CPUs, sharing nodes for maximum efficiency. We also describe the benefits of libEnsemble's generator--simulator coupling, which easily exposes to the user the ability to cancel, and portably kill, running simulations based on models that are updated with intermediate simulation output. We demonstrate libEnsemble's capabilities, scalability, and scientific impact via a Gaussian process surrogate training problem for the longitudinal density profile at the exit of a plasma accelerator stage. The study uses gpCAM for the surrogate model and employs either Wake-T or WarpX simulations, highlighting efficient use of resources that can easily extend to exascale.

cs.DC↗

arXiv2022

Comparison of Multiobjective Optimization Methods for the LCLS-II Photoinjector

Particle accelerators are among some of the largest science experiments in the world and can consist of thousands of components with a wide variety of input ranges. These systems can easily become unwieldy optimization problems during design and operations studies. Starting in the early 2000s, searching for better beam dynamics configurations became synonymous with heuristic optimization methods in the accelerator physics community. Genetic algorithms and particle swarm optimization are currently the most widely used. These algorithms can take thousands of simulation evaluations to find optimal solutions for one machine prototype. For large facilities such as the Linac Coherent Light Source (LCLS) and others, this equates to a limited exploration of many possible design configurations. In this paper, the LCLS-II photoinjector is optimized with three optimization algorithms. All optimizations were started from both a uniform random and Latin hypercube sample. In all cases, the optimizations started from Latin hypercube samples outperformed optimizations started from uniform samples. All three algorithms were able to optimize the photoinjector, with the model-based methods approximating the Pareto front in fewer simulation evaluations. This work, in combination with previous optimization observations, indicates objective penalties have a strong impact on the efficiency of such methods. In general, we recommend heuristic methods for initial optimizations and model-based methods when information about the objective space is available.

physics.acc-ph↗

arXiv2021

libEnsemble: A Library to Coordinate the Concurrent Evaluation of Dynamic Ensembles of Calculations

Almost all applications stop scaling at some point; those that don't are seldom performant when considering time to solution on anything but aspirational/unicorn resources. Recognizing these tradeoffs as well as greater user functionality in a near-term exascale computing era, we present libEnsemble, a library aimed at particular scalability- and capability-stretching uses. libEnsemble enables running concurrent instances of an application in dynamically allocated ensembles through an extensible Python library. We highlight the structure, execution, and capabilities of the library on leading pre-exascale environments as well as advanced capabilities for exascale environments and beyond.

cs.DC↗