Search

High performance computing (HPC) workflows are undergoing tumultuous changes, including an explosion in size and complexity. Despite these changes, most batch job systems still use slow, centralized schedulers. Generalized hierarchical scheduling (GHS) solves many of the challenges that face modern workflows, but GHS has not been widely adopted in HPC. A major difficulty that hinders adoption is the lack of a performance model to aid in configuring GHS for optimal performance on a given application. We propose an analytical performance model of GHS, and we validate our proposed model with four different applications on a moderately-sized system. Our validation shows that our model is extremely accurate at predicting the performance of GHS, explaining 98.7% of the variance (i.e., an R2 statistic of 0.987). Our results also support the claim that GHS overcomes scheduling throughput problems; we measured throughput improvements of up to 270× on our moderately-sized system. We then apply our performance model to a pre-exascale system, where our model predicts throughput improvements of four orders of magnitude and provides insight into optimally configuring GHS on next generation systems.

This poster presents the first results of an interdisciplinary project aiming to develop and share sustainable knowledge necessary to analyze, understand, and use published scientific results to advance reproducibility in multi-messenger astrophysics. Specifically, the project targets breakthrough work associated with the First M87 Event Horizon Telescope (EHT) and delivers recommendations on how the published results of the first black hole can be effectively reproduced. The project has the potential to advance new discovery in multi-messenger astrophysics by providing guidance for generalizing methods and findings from use cases.

Scientific breakthroughs in biomolecular methods and improvements in hardware technology have shifted from a single long-running simulation to a large set of shorter simulations running simultaneously, called an ensemble. In an ensemble, each independent simulation is usually coupled with several analyses that apply identical or distinct algorithms on data produced by the corresponding simulation. Today, In situ methods are used to analyze large volumes of data generated by scientific simulations at runtime. This work studies the execution of ensemble-based simulations paired with In situ analyses using in-memory staging methods. Because simulations and analyses forming an ensemble typically run concurrently, deploying an ensemble requires efficient co-location-aware strategies, making sure the data flow between simulations and analyses that form an In situ workflow is efficient. Using an ensemble of molecular dynamics In situ workflows with multiple simulations and analyses, we first show that collecting traditional metrics such as makespan, instructions per cycle, memory usage, or cache miss ratio is not sufficient to characterize the complex behaviors of ensembles. Thus, we propose a method to evaluate the performance of ensembles of workflows that captures resource usage (efficiency), resource allocation, and component placement. Experimental results demonstrate that our proposed method can effectively capture the performance of different component placements in an ensemble. By evaluating different co-location scenarios, our performance indicator demonstrates improvements of up to four orders of magnitude when co-locating simulation and coupled analyses within a single computational host.

Nowadays, railway infrastructure designers rely heavily on computer simulators and expert systems to model, analyze and evaluate potential deployments prior to their installation. This paper presents the railway power consumption simulator model (RPCS), a cloud-based model for the design, simulation and evaluation of railway electric infrastructures. This model integrates the parameters of an infrastructure within a search engine that generates and evaluates a set of simulations to achieve optimal designs, according to a given set of objectives and restrictions. The knowledge of the domain is represented as an ontology that translates the elements in the infrastructure into an electric circuit, which is simulated to obtain a wide range of electric metrics. In order to support the execution of thousands of scenarios in a scalable, efficient and fault-tolerant manner, this paper introduces an architecture to deploy the model in a cloud environment, and a dimensioning model to find the types and number of instances that maximize performance while minimizing the externalization costs. The resulting model is applied to a particular case study, allowing the execution of over one thousand concurrent experiments in a virtual cluster on the Amazon Elastic Compute Cloud. This work has been partially funded under the grant TIN2013-41350-P of the Spanish Ministry of Economics and Competitiveness, and the COST Action IC1305 ”Network for Sustainable Ultrascale Computing Platforms” (NESUS).

Convergence between high-performance computing (HPC) and big data analytics (BDA) is currently an established research area that has spawned new opportunities for unifying the platform layer and data abstractions in these ecosystems. This work presents an architectural model that enables the interoperability of established BDA and HPC execution models, reflecting the key design features that interest both the HPC and BDA communities, and including an abstract data collection and operational model that generates a unified interface for hybrid applications. This architecture can be implemented in different ways depending on the process- and data-centric platforms of choice and the mechanisms put in place to effectively meet the requirements of the architecture. The Spark-DIY platform is introduced in the paper as a prototype implementation of the architecture proposed. It preserves the interfaces and execution environment of the popular BDA platform Apache Spark, making it compatible with any Spark-based application and tool, while providing efficient communication and kernel execution via DIY, a powerful communication pattern library built on top of MPI. Later, Spark-DIY is analyzed in terms of performance by building a representative use case from the hydrogeology domain, EnKF-HGS. This application is a clear example of how current HPC simulations are evolving toward hybrid HPC-BDA applications, integrating HPC simulations within a BDA environment. This work was supported in part by the Spanish Ministry of Economy, Industry and Competitiveness under Grant TIN2016-79637-P(toward Unification of HPC and Big Data Paradigms), in part by the Spanish Ministry of Education under Grant FPU15/00422 TrainingProgram for Academic and Teaching Staff Grant, in part by the Advanced Scientific Computing Research, Office of Science, U.S.Department of Energy, under Contract DE-AC02-06CH11357, and in part by the DOE with under Agreement DE-DC000122495,Program Manager Laura Biven.

Today's scientific applications are increasingly relying on a variety of data sources, storage facilities, and computing infrastructures, and there is a growing demand for data analysis and visualization for these applications. In this context, exploiting Big Data frameworks for scientific computing is an opportunity to incorporate high-level libraries, platforms, and algorithms for machine learning, graph processing, and streaming; inherit their data awareness and fault-tolerance; and increase productivity. Nevertheless, limitations exist when Big Data platforms are integrated with an HPC environment, namely poor scalability, severe memory overhead, and huge development effort. This paper focuses on a popular Big Data framework -Apache Spark- and proposes an architecture to support the integration of highly scalable MPI block-based data models and communication patterns with a map-reduce-based programming model. The resulting platform preserves the data abstraction and programming interface of Spark, without conducting any changes in the framework, but allows the user to delegate operations to the MPI layer. The evaluation of our prototype shows that our approach integrates Spark and MPI efficiently at scale, so end users can take advantage of the productivity facilitated by the rich ecosystem of high-level Big Data tools and libraries based on Spark, without compromising efficiency and scalability.

Performance evaluation is crucial to understanding the behavior of scientific workflows. In this study, we target an emerging type of workflow, called in situ workflows. These workflows tightly couple components such as simulation and analysis to improve overall workflow performance. To understand the tradeoffs of various configurable parameters for coupling these heterogeneous tasks, namely simulation stride, and component placement, separately monitoring each component is insufficient to gain insights into the entire workflow behavior. Through an analysis of the state-of-the-art research, we propose a lightweight metric, derived from a defined in situ step, for assessing resource usage efficiency of an in situ workflow execution. By applying this metric to a synthetic workflow, which is parameterized to emulate behaviors of a molecular dynamics simulation, we explore two possible scenarios (Idle Simulation and Idle Analyzer) for the characterization of in situ workflow execution. In addition to preliminary results from a recently published study [11] , we further exploit the proposed metric to evaluate a practical in situ workflow with a real molecular dynamics application, i.e., GROMACS. Experimental results show that the in transit placement (analytics on dedicated nodes) sustains a higher frequency for performing in situ analysis compared to the helper-core configuration (analytics co-allocated with simulation).

The increasing amounts of data related to the execution of scientific workflows has raised awareness of their shift towards parallel data-intensive problems. In this paper, we deliver our experience combining the traditional high-performance computing and grid-based approaches with Big Data analytics paradigms, in the context of scientific ensemble workflows. Our goal was to assess and discuss the suitability of such data-oriented mechanisms for production-ready workflows, especially in terms of scalability. We focused on two key elements in the Big Data ecosystem: the data-centric programming model, and the underlying infrastructure that integrates storage and computation in each node. We experimented with a representative MPI-based iterative workflow from the hydrology domain, EnKF-HGS, which we re-implemented using the Spark data analysis framework. We conducted experiments on a local cluster, a private cloud running OpenNebula, and the Amazon Elastic Compute Cloud (AmazonEC2). The results we obtained were analysed to synthesize the lessons we learned from this experience, while discussing promising directions for further research. This work was supported by the Spanish Ministry of Economics and Competitiveness grant TIN-2013-41350-P, the IC1305 COST Action “Network for Sustainable Ultrascale Computing Platforms” (NESUS), and the FPU Training Program for Academic and Teaching Staff Grant FPU15/00422 by the Spanish Ministry of Education .

Nowadays there is a raising interest in bridging the gap between Big Data application models and data-intensive HPC. This work explores the effects that Big Data-inspired paradigms could have in current scientific applications through the evaluation of a real-world application from the hydrology domain. This evaluation led to experience that portrayed the key aspects of the HPC and Big Data paradigms that made them successful in their respective worlds. With this information, we established a research roadmap to build a platform suitable for HPC hybrid applications, with a focus on efficient data management and fault-tolerance.

The computational complexity and the constantly increasing amount of input data for scientific computing models is threatening their scalability. In addition, this is leading towards more data-intensive scientific computing, thus rising the need to combine techniques and infrastructures from the HPC and big data worlds. This paper presents a methodological approach to cloudify generalist iterative scientific workflows, with a focus on improving data locality and preserving performance. To evaluate this methodology, it was applied to an hydrological simulator, EnKF-HGS. The design was implemented using Apache Spark, and assessed in a local cluster and in Amazon Elastic Compute Cloud (EC2) against the original version to evaluate performance and scalability.

Many scientific areas make extensive use of computer simulations to study complex real-world processes. These computations are typically very resource-intensive and present scalability issues as experiments get larger even in dedicated clusters, since these are limited by their own hardware resources. Cloud computing raises as an option to move forward into the ideal unlimited scalability by providing virtually infinite resources, yet applications must be adapted to this new paradigm. This process of converting and/or migrating an application and its data in order to make use of cloud computing is sometimes known as cloudifying the application. We propose a generalist cloudification method based in the MapReduce paradigm to migrate scientific simulations into the cloud to provide greater scalability. We analysed its viability by applying it to a real-world railway power consumption simulatior and running the resulting implementation on Hadoop YARN over Amazon EC2. Our tests show that the cloudified application is highly scalable and there is still a large margin to improve the theoretical model and its implementations, and also to extend it to a wider range of simulations. We also propose and evaluate a multidimensional analysis tool based on the cloudified application. It generates, executes and evaluates several experiments in parallel, for the same simulation kernel. The results we obtained indicate that out methodology is suitable for resource intensive simulations and multidimensional analysis, as it improves infrastructure’s utilization, efficiency and scalability when running many complex experiments. This work has been partially funded under the grant TIN2013-41350-P of the Spanish Ministry of Economics and Competitiveness, and the COST Action IC1305 "Network for Sustainable Ultrascale Computing Platforms" (NESUS).

Many scientific areas make extensive use of computer simulations to study complex real-world processes. These computations are typically very resource-intensive and present scalability issues as experiments get larger, even in dedicated clusters since they are limited by their own hardware resources. Cloud computing raises as an option to move forward into the ideal unlimited scalability by providing virtually infinite resources, yet applications must be adapted to this new paradigm. We propose a generalist cloudification method based in the MapReduce paradigm to migrate numerical simulations into the cloud to provide greater scalability. We analysed its viability by applying it to a real-world simulation and running the resulting implementation on Hadoop YARN over Amazons EC2. Our tests show that the cloudified application is highly scalable and there is still a large margin to improve the theoretical model and its implementations, and also to extend it to a wider range of simulations.