Heterogeneous workflows represent a promising approach for overcoming traditional application performance limitations and to accelerate scientific insight on high-performance computing (HPC) platforms. As HPC platforms grow in size and complexity, managing and optimizing workflow resources while maximizing scientific output assumes vital importance. Optimal workflow resource allocation requires high-quality and timely information about the state of the hardware resources, the status of the pending tasks, the performance of the tasks that have already been executed, and the current status of the workflow itself. A robust performance observability framework that captures and delivers this information can fundamentally improve the quality of decision-making within the workflow system, setting the stage for the adaptive execution of workflow tasks. We propose the use of SOMA, a service-based performance observability framework for such HPC workflows. With the RADICAL-Pilot runtime system as a development vehicle, SOMA demonstrates that service-based architectures coupled with an appropriate data model can serve the performance monitoring needs of large-scale ensemble workflows in a low-overhead fashion. Effective observability of workflow performance requires exporting, storing, and analyzing several types of performance data from across the application and workflow software stacks. Our study finds significant benefits in integrating observability frameworks as first-class citizens within an HPC workflow software stack. In this paper, we demonstrate how SOMA can simultaneously observe the performance states of the individual tasks, system hardware, and the workflow as a whole. Such information can then be employed to calculate better resource allocation and task configuration.

Summary With the rise of exascale systems and large, data‐centric workflows, the need to observe and analyze high performance computing (HPC) applications during their execution is becoming increasingly important. HPC applications are typically not designed with online monitoring in mind, therefore, the observability challenge lies in being able to access and analyze interesting events with low overhead while seamlessly integrating such capabilities into existing and new applications. We explore how our service‐based observation, monitoring, and analytics (SOMA) approach to collecting and aggregating both application‐specific diagnostic data and performance data addresses these needs. We present our SOMA framework and demonstrate its viability with LULESH, a hydrodynamics proxy application. Then we focus on Astaroth, a multi‐GPU library for stencil computations, highlighting the integration of the TAU and APEX performance tools and SOMA for application and performance data monitoring.

Distributed data storage services tailored to specific applications have grown popular in the high-performance computing (HPC) community as a way to address I/O and storage challenges. These services offer a variety of specific interfaces, semantics, and data representations. They also expose many tuning parameters, making it difficult for their users to find the best configuration for a given workload and platform. To address this issue, we develop a novel variational-autoencoder-guided asynchronous Bayesian optimization method to tune HPC storage service parameters. Our approach uses transfer learning to leverage prior tuning results and use a dynamically updated surrogate model to explore the large parameter search space in a systematic way. We implement our approach within the DeepHyper open-source framework, and apply it to the autotuning of a high-energy physics workflow on Argonne's Theta supercomputer. We show that our transfer-learning approach enables a more than 40 x search speedup over random search, compared with a 2.5 x to 10 x speedup when not using transfer learning. Additionally, we show that our approach is on par with state-of-the-art autotuning frameworks in speed and outperforms them in resource utilization and parallelization capabilities.

The importance of ensemble computing is well established. However, executing ensembles at scale introduces interesting performance fluctuations that have not been well investigated. In this paper, we trace our experience uncovering performance fluctuations of ensemble applications (primarily constituting a workflow of GROMACS tasks), and unsuccessful attempts, so far, at trying to discern the underlying cause(s) of performance fluctuations. Is the failure to discern the causative or contributing factors a failure of capability? Or imagination? Do the fluctuations have their genesis in some inscrutable aspect of the system or software? Does it warrant a fundamental reassessment and rethinking of how we assume and conceptualize performance reproducibility? Answers to these questions are not straightforward, nor are they immediate or obvious. We conclude with a discussion about the performance of ensemble applications and ruminate over the implications for how we define and measure application performance.

Inline and in transit visualization are popular in situ visualization models for high performance computing (HPC) applications. Inline visualization is invoked through a library call on the HPC application (simulation), while in transit methods invoke a visualization module running on in transit resources. In transit methods can offer better efficiency than inline by running the visualization at a lower concurrency level than the simulation. State-of-the-art in transit schemes are limited to employing a dedicated in transit resource for every simulation. The resulting idle time on the in transit resource can severely limit the cost savings over inline methods. This research proposes SERVIZ, an in transit visualization service that can be shared amongst multiple simulations to reduce idle time, thereby efficiently using in transit resources. SERVIZ achieves cost savings of up to 26% over inline and up to$4\mathbf{x}$reduction in idle time compared to a dedicated in transit implementation.

High-performance computing (HPC) software is evolving to support an increasingly diverse set of applications and heterogeneous hardware architectures. As part of this evolution, the construction of scientific software has shifted from a traditional monolithic message passing interface executable model to a coupled, services-style model in which simulations run alongside a host of distributed HPC data services within the same batch job allocation. Microservices have emerged as a powerful new way to build these distributed data services through a composition model. However, performance analysis of composed microservices is a daunting challenge. It requires collecting, monitoring, aggre-gating, and exporting performance data from multiple sources. To be effective, the design of such a monitoring solution must allow for seamless integration into HPC applications and distributed services alike, be scalable, operate with a low overhead, and take advantage of the HPC platform. We propose SYMBIOMON, a monitoring service that is built by composing high-performance microservices. We describe its design and implementation within the context of the Mochi framework. SYMBIOMON combines a time-series data model with existing Mochi data services to collect, aggregate, and export performance metrics in a distributed manner. SYMBIOMON enables seamless, low-overhead monitoring and analysis of data services and HPC applications alike. Using HEPnOS, a production-quality Mochi data service, we demonstrate the use of SYMBIOMON to identify better service configurations.

Microservices are a powerful new way of building, customizing, and deploying distributed services owing to their flexibility and maintainability. Several large-scale distributed platforms have emerged to serve the growing needs of data-centric workloads and services in commercial computing. Concurrently, high-performance computing (HPC) systems and software are rapidly evolving to meet the demands of diversified applications and heterogeneity. The interplay of hardware factors, software configuration parameters, and the flexibility offered with a microservice architecture makes it nontrivial to estimate the optimal service instantiation for a given application workload. Further, this problem is exacerbated when considering that these services operate in a dynamic and heterogeneous HPC environment. An optimally integrated service can be vastly more performant than a haphazardly integrated one. Existing performance tools for HPC either fail to understand the request-response model of communication inherent to microservices or they operate within a narrow scope, limiting the insight that can be gleaned from employing them in isolation.We propose a methodology for integrated performance analysis of HPC microservices frameworks and applications called SYMBIOSYS. We describe its design and implementation within the context of the Mochi framework. This integration is achieved by combining distributed callpath profiling and tracing with a performance data exchange strategy that collects fine-grained, low-level metrics from the RPC communication library and network layers. The result is a portable, low-overhead performance analysis setup that provides a holistic profile of the dependencies among microservices and how they interact with the Mochi RPC software stack. Using HEPnOS, a production-quality Mochi data service, we demonstrate the low-overhead operation of SYMBIOSYS at scale and use it to identify the root causes of poorly performing service configurations.

Several robust performance systems have been created for parallel machines with the ability to observe diverse aspects of application execution on different hardware platforms. All of these are designed with the objective to support measurement methods that are efficient, portable, and scalable. For these reasons, the performance measurement infrastructure is tightly embedded with the application code and runtime execution environment. As parallel software and systems evolve, especially towards more heterogeneous, asynchronous, and dynamic operation, it is expected that the requirements for performance observation and awareness will change. For instance, heterogeneous machines introduce new types of performance data to capture and performance behaviors to characterize. Furthermore, there is a growing interest in interacting with the performance infrastructure for in situ analytics and policy-based control. The problem is that an existing performance system architecture could be constrained in its ability to evolve to meet these new requirements. The paper reports our research efforts to address this concern in the context of the TAU Performance System. In particular, we consider the use of a powerful plugin model to both capture existing capabilities in TAU and to extend its functionality in ways it was not necessarily conceived originally. The TAU plugin architecture supports three types of plugin paradigms: EVENT, TRIGGER, and AGENT. We demonstrate how each operates under several different scenarios. Results from larger-scale experiments are shown to highlight the fact that efficiency and robustness can be maintained, while new flexibility and programmability can be offered that leverages the power of the core TAU system while allowing significant and compelling extensions to be realized.

Electrical power has become an important design constraint in high-performance computing (HPC) systems. On future HPC machines, power is likely to be a budgeted resource and thus managed dynamically. Power management software needs to reliably measure application performance at runtime in order to respond effectively to changes in application behavior. Execution time tells us little about how the science in the application is progressing toward an application-defined end goal. To the best of our knowledge, no study has defined or categorized online application progress in the context of power management. Based on semi-structured interviews with HPC application-specialists, we define an online notion of progress-an application-specific metric that can be monitored at runtime to provide a sense of the rate at which application science is being performed. Using instrumentation, we characterize and categorize the progress of various production scientific applications and benchmarks. We propose a model of the impact of dynamic power capping on application progress. By experimental evaluation, we show that our model accurately captures the general behavior of the progress of different classes of applications under a power cap. We believe that such a model is an important first step toward the design of more dynamic power management policies for HPC systems.