WANDER: An Explainable Decision-Support Framework for HPC

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lahiry, Ankur, Banday, Banooqa, Bhattarai, Yugesh, Islam, Tanzima Z.
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911338137124864
author Lahiry, Ankur
Banday, Banooqa
Bhattarai, Yugesh
Islam, Tanzima Z.
author_facet Lahiry, Ankur
Banday, Banooqa
Bhattarai, Yugesh
Islam, Tanzima Z.
contents High-performance computing (HPC) systems expose many interdependent configuration knobs that impact runtime, resource usage, power, and variability. Existing predictive tools model these outcomes, but do not support structured exploration, explanation, or guided reconfiguration. We present WANDER, a decision-support framework that synthesizes alternate configurations using counterfactual analysis aligned with user goals and constraints. We introduce a composite trade-off score that ranks suggestions based on prediction uncertainty, consistency between feature-target relationships using causal models, and similarity between feature distributions against historical data. To our knowledge, WANDER is the first such system to unify prediction, exploration, and explanation for HPC tuning under a common query interface. Across multiple datasets WANDER generates interpretable and trustworthy, human-readable alternatives that guide users to achieve their performance objectives.
format Preprint
id arxiv_https___arxiv_org_abs_2506_04049
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WANDER: An Explainable Decision-Support Framework for HPC
Lahiry, Ankur
Banday, Banooqa
Bhattarai, Yugesh
Islam, Tanzima Z.
Performance
Artificial Intelligence
High-performance computing (HPC) systems expose many interdependent configuration knobs that impact runtime, resource usage, power, and variability. Existing predictive tools model these outcomes, but do not support structured exploration, explanation, or guided reconfiguration. We present WANDER, a decision-support framework that synthesizes alternate configurations using counterfactual analysis aligned with user goals and constraints. We introduce a composite trade-off score that ranks suggestions based on prediction uncertainty, consistency between feature-target relationships using causal models, and similarity between feature distributions against historical data. To our knowledge, WANDER is the first such system to unify prediction, exploration, and explanation for HPC tuning under a common query interface. Across multiple datasets WANDER generates interpretable and trustworthy, human-readable alternatives that guide users to achieve their performance objectives.
title WANDER: An Explainable Decision-Support Framework for HPC
topic Performance
Artificial Intelligence
url https://arxiv.org/abs/2506.04049