Spatiotemporal graph neural networks (ST-GNNs) are powerful tools for modeling spatial and temporal data dependencies. However, their applications have been limited primarily to small-scale datasets because of memory constraints. While distributed training offers a solution, current frameworks lack support for spatiotemporal models and overlook the properties of spatiotemporal data. Informed by a scaling study on a large-scale workload, we present PyTorch Geometric Temporal Index (PGT-I), an extension to PyTorch Geometric Temporal that integrates distributed data parallel training and two novel strategies: index-batching and distributed-index-batching. Our index techniques exploit spatiotemporal structure to construct snapshots dynamically at runtime, significantly reducing memory overhead, while distributed-index-batching extends this approach by enabling scalable processing across multiple GPUs. Our techniques enable the first-ever training of an ST-GNN on the entire PeMS dataset without graph partitioning, reducing peak memory usage by up to 89% and achieving up to a 11.78x speedup over standard DDP with 128 GPUs.

Workflows are critical for scientific discovery. However, the sophistication, heterogeneity, and scale of workflows make building, testing, and optimizing them increasingly challenging. Furthermore, their complexity and heterogeneity make performance reproducibility hard. In this paper, we propose workflow mini-apps as a tool to address the challenges in building and testing workflows while controlling the fidelity of representing real-world workflows. Workflow mini-apps are deployed and run on various HPC systems and architectures without workflow-specific constraints. We offer insight into their design and implementation, providing an analysis of their performance and reproducibility. Workflow mini-apps thus advance the science of workflows by providing simple, portable, and managed (fidelity) representations of otherwise complex and difficult-to-control real workflows.

Performance anomaly in High Performance Computing (HPC) can be defined as run-to-run variation of an application in repeated runs with the same set of configuration parameters. Such variations can occur for myriad reasons, including contention for shared resources such as the network and dynamic data distribution across application processes. Traditionally HPC researchers focus on real-time anomaly detection using different Machine Learning (ML) methods. These popular methods, such as auto-encoder, limit finding anomalous event patterns during training time. On top of that, in HPC, performance data are stored in tabular format. Though gradient-based methods have already proved their significant improvement over classification tasks, they explicitly use feature-feature relationships, ignoring the potential sample-sample relationship. To fill this gap, we build a performance anomaly classification technique leveraging the potential graph-based representation learning. We hypothesize that a meaningful and robust representation considering the sample-sample relationship for the given tabular datasets will improve the downstream anomaly classification technique. We conduct our experiment on 5 HPC datasets and 6 ML datasets. Our empirical study proves that graph-based anomaly classification outperforms the gradient-based approaches in 6 out of 11 experiments. We also explain how anomaly decisions are made inside the performance graph.

Scientific computing communities increasingly run their experiments using complex data- and compute-intensive workflows that utilize distributed and heterogeneous architectures targeting numerical simulations and machine learning, often executed on the Department of Energy Leadership Computing Facilities (LCFs). We argue that a principled, systematic approach to implementing FAIR principles at scale, including fine-grained metadata extraction and organization, can help with the numerous challenges to performance reproducibility posed by such workflows. We extract workflow patterns, propose a set of tools to manage the entire life cycle of performance metadata, and aggregate them in an HPC-ready framework for reproducibility (RECUP). We describe the challenges in making these tools interoperable, preliminary work, and lessons learned from this experiment.

Engineering higher education increasingly produces data in the volume, variety, velocity, and need for veracity such that the output of the research is considered “Big Data”. While engineering faculty members do conceive of and direct the research producing this data, there may be gaps in faculty members' knowledge in training graduate and undergraduate research assistants in the management of Big Data. The project described herein details the development of a Big Data education module for a group of graduate researchers and undergraduate research assistants in Electrical and Computer Engineering. This project has the following objectives: to document and describe current data management practices; to identify gaps in knowledge that need to be addressed in order for research assistants to successfully manage Big Data; and to create curricular interventions to address these gaps. This paper details the motivation, relevant literature, research methodology, curricular intervention, and pilot presentation of the module. Results indicate that, generally, students involved in Big Data projects need comprehensive introduction to the topic, which will be most effective when contextualized to the work that they are performing in the research or classroom environment.

Current methods for monitoring the security of large-scale commodity clusters tend to treat these clusters as nothing more than collections of independent nodes. As such, the techniques used to secure these clusters have, for the most part, been adaptations of techniques developed for securing and monitoring enterprise computing environments. We have previously proposed the idea of monitoring the security-state of large-scale commodity clusters by examining their emergent properties, that is, properties that are only visible when one ceases to look at a cluster as a collection of disparate nodes and begins to look at the properties of the cluster as a whole. We show that by correlating the open network ports observed on cluster nodes with other emergent properties - such as active processes and the contents of important system files - security analysts can make insightful observations that can greatly restrict the actions that an attacker can carry out undetected.

Understanding the Earth's climate system and how it might be changing is a preeminent scientific challenge. Global climate models are used to simulate past, present, and future climates, and experiments are executed continuously on an array of distributed supercomputers. The resulting data archive, spread over several sites, currently contains upwards of 100 TB of simulation data and is growing rapidly. Looking toward mid-decade and beyond, we must anticipate and prepare for distributed climate research data holdings of many petabytes. The Earth System Grid (ESG) is a collaborative interdisciplinary project aimed at addressing the challenge of enabling management, discovery, access, and analysis of these critically important datasets in a distributed and heterogeneous computational environment. The problem is fundamentally a Grid problem. Building upon the Globus toolkit and a variety of other technologies, ESG is developing an environment that addresses authentication, authorization for data access, large-scale data transport and management, services and abstractions for high-performance remote data access, mechanisms for scalable data replication, cataloging with rich semantic and syntactic information, data discovery, distributed monitoring, and Web-based portals for using the system.

In the emerging world of Grid Computing, shared computational, data, other distributed resources are becoming available to enable scientific advancement through collaborative research and collaboratories. This paper describes the increasing role of ontologies in the context of Grid Computing for obtaining, comparing and analyzing data. We present ontology entities and a declarative model that provide the outline for an ontology of scientific information. Relationships between concepts are also given. The implementation of some concepts described in this ontology is discussed within the context of the Earth System Grid II (ESG)[1].