Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Workload”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 73 records · Page 4

Quantum Computing Technology Roadmaps and Capability Assessment for Scientific Computing - An analysis of use cases from the NERSC workload

The National Energy Research Scientific Computing Center (NERSC), as the high-performance computing (HPC) facility for the Department of Energy’s Office of Science, recognizes the essential role of quantum computing in its future mission. In this report, we analyze the NERSC workload and identify materials science, quantum chemistry, and high-energy physics as the science domains and application areas that stand to benefit most from quantum computers. These domains jointly make up over 50% of the current NERSC production workload, which is illustrative of the impact quantum computing could have on NERSC’s mission going forward. We perform an extensive literature review and determine the quantum resources required to solve classically intractable problems within these science domains. This review also shows that the quantum resources required have consistently decreased over time due to algorithmic improvements and a deeper understanding of the problems. At the same time, public technology roadmaps from a collection of ten quantum computing companies predict a dramatic increase in capabilities over the next five to ten years. Our analysis reveals a significant overlap emerging in this time frame between the technological capabilities and the algorithmic requirements in these three scientific domains. We anticipate that the execution time of large-scale quantum workflows will become a major performance parameter and propose a simple metric, the Sustained Quantum System Performance (SQSP), to compare system-level performance and throughput for a heterogeneous workload.

97 MATHEMATICS AND COMPUTING↗

Parallel Particle Advection Bake-Off for Scientific Visualization Workloads

There are multiple algorithms for parallelizing particle advection for scientific visualization workloads. While many previous studies have contributed to the understanding of individual algorithms, our study aims to provide a holistic understanding of how algorithms perform relative to each other on various workloads. To accomplish this, we consider four popular parallelization algorithms and run a “bake-off” study (i.e., an empirical study) to identify the best matches for each. The study includes 216 tests, going to a concurrency of up to 8192 cores and considering data sets as large as 34 billion cells with 300 million particles. Overall, our study informs three important research questions: (1) which parallelization algorithms perform best for a given workload?, (2) why?, and (3) what are the unsolved problems in parallel particle advection? In terms of findings, we find that the seeding box is the most important factor in choosing the best algorithm, and also that there is a significant opportunity for improvement in execution time, scalability, and efficiency.

Pugmire, Dave↗

The WorkQueue project: A task queue for the CMS workload management system

We present the development and first experience of a new component (termed WorkQueue) in the CMS workload management system. This component provides a link between a global request system (Request Manager) and agents (WMAgents) which process requests at compute and storage resources (known as sites). These requests typically consist of creation or processing of a data sample (possibly terabytes in size). Unlike the standard concept of a task queue, the WorkQueue does not contain fully resolved work units (known typically as jobs in HEP). This would require the WorkQueue to run computationally heavy algorithms that are better suited to run in the WMAgents. Instead the request specifies an algorithm that the WorkQueue uses to split the request into reasonable size chunks (known as elements). An advantage of performing lazy evaluation of an element is that expanding datasets can be accommodated by having job details resolved as late as possible. The WorkQueue architecture consists of a global WorkQueue which obtains requests from the request system, expands them and forms an element ordering based on the request priority. Each WMAgent contains a local WorkQueue which buffers work close to the agent, this overcomes temporary unavailability of the global WorkQueue and reduces latency for an agent to begin processing. Elements are pulled from the global WorkQueue to the local WorkQueue and into the WMAgent based on the estimate of the amount of work within the element and the resources available to the agent. WorkQueue is based on CouchDB, a document oriented NoSQL database. The WorkQueue uses the features of CouchDB (map/reduce views and bi-directional replication between distributed instances) to provide a scalable distributed system for managing large queues of work. The project described here represents an improvement over the old approach to workload management in CMS which involved individual operators feeding requests into agents. This new approach allows for a system where individual WMAgents are transient and can be added or removed from the system as needed.

Ryu, S.↗

Early Evaluation of Fugaku A64FX Architecture Using Climate Workloads

The Energy Exascale Earth System Model (E3SM) Project is an ongoing, state-of-the-science Earth system modeling, simulation, and prediction project that targets efficient utilization of U.S. Department of Energy’s (DOE) supercomputers to meet the science needs of the nation and the mission needs of DOE. This work focuses on our early evaluation of the A64FX architecture on Fugaku supercomputer using E3SM benchmarks. We will present results that track hardware trends, facilitate architecture comparison and the specific impact on our workload using an atmospheric model benchmark. We have two variants of the code written in Fortran and C++/Kokkos respectively which were used to collect data on a variety of CPU and GPU platforms. Furthermore, we have conducted a comparative evaluation of the compilers on the A64FX architecture and found GNU to be the best performer for our workload. Our experience so far indicates that Fugaku/A64FX shows promising energy efficiency (performance/Watt) with further performance gains possible through architecture-aware optimization efforts.

Sreepathi, Sarat↗

Power Profile Monitoring and Tracking Evolution of System-Wide HPC Workloads

The power & energy demands of HPC machines have grown significantly. Modern exascale HPC systems require tens of megawatts of combined power for computing resources and cooling facilities at full capacity. The current energy trend is not sustainable for future HPC systems, and there is a need to work toward the energy efficiency aspect of HPC performance. Energy awareness of the HPC applications at the job level is essential for running an efficient HPC system. This work aims to develop a pipeline to provide a production-level system-wide overview of the HPC workloads' power profile while handling evolving workloads exhibiting new power trends. We developed an open-set classification model for HPC jobs based on the properties of power profiles to continuously provide a system-wide holistic view of recently completed jobs. The pipeline helps continuously monitor the job-level power usage pattern of HPC and enables us to capture the new trends in applications' power behavior. We employed a comprehensive set of techniques to generate job-level data, custom-designed feature extraction methods to extract critical features from jobs' power profiles, clustering techniques powered by generative modeling, and open-set classification for identifying job profiles into known classes or an unknown set. With extensive evaluations, we demonstrate the effectiveness of each component in our pipeline. We provide an analysis of the resulting clusters that characterize the power profile landscape of the Summit supercomputer from more than 60K jobs executed in a year. The open-set classification classifies the known data sets into known classes with high accuracy and identifies unknown data noints with over 85% accuracy.

Karimi, Ahmad Maroof↗

SU-F-T-101: Insight into Dosimetry Workload and Planning Timelines: A 6 Year Review at One Institution

Purpose: To elucidate realistic clinical treatment planning workload and timelines to improve understanding for patients, payers, and other institutions involved in radiotherapy processes. Methods: A web based tool was developed using Oracle Express (Oracle Corp, Redwood City, CA) which allowed communication between the physicians and staff about the current state of the patient plan. For 6 years, all patient courses were logged and time-stamped in 22 discreet steps which detailed start and stop times for simulation, contouring, and treatment planning tasks. This data was combined with the treatment planning database (TPDB) using the Eclipse Scripting API (Varian Medical Systems, Palo Alto, CA) to cross-identify plans between the two systems. This time data was analyzed across our dosimetry staff and treatment modality. Results: In 6 years, 110,477 patient statuses were time-logged for 9683 courses of treatment using our internal software. The courses contained 8305 unique patients who were binned into one of 11 diagnosis site categories. 8253 courses could be reconciled against the TPDB using timestamp data from patient statuses. The average planning volume per dosimetrist was 375.8 ± 142.4 plans per year with the average number of planning revisions per dosimetrist of 71.0 ± 27.1 plans per year. The median treatment planning times by modality ranged from to 48.3 hours for IMRT plans 5 fields or less to 119.6 hours for IMRT with 8 or more fields. Two arc VMAT, three arc VMAT, and 3D plans median times were 89.1 hours, 113.8 hours, and 50.9 hours respectively. Conclusion: Using our web based tool, we have demonstrated the ability to quantify treatment planning timelines and workloads which could help in setting appropriate expectations for patients, payers, and hospital administration. COI: Author received monies from Varian Medical Systems for research and teaching honorarium.

60 APPLIED LIFE SCIENCES↗

Comparative I/O workload characterization of two leadership class storage clusters. In: PDSW '15 Proceedings of the 10th Parallel Data Storage Workshop

The Oak Ridge Leadership Computing Facility (OLCF) is a leader in large-scale parallel file system development, design, deployment and continuous operation. For the last decade, the OLCF has designed and deployed two large center-wide parallel file systems. The first instantiation, Spider 1, served the Jaguar supercomputer and its predecessor, Spider 2, now serves the Titan supercomputer, among many other OLCF computational resources. The OLCF has been rigorously collecting file and storage system statistics from these Spider systems since their transition to production state. In this paper we present the collected I/O workload statistics from the Spider 2 system and compare it to the Spider 1 data. Our analysis show that the Spider 2 workload is more more write-heavy I/O compared to Spider 1 (75% vs. 60%, respectively). The data also show the OLCF storage policies such as periodic purges are effectively managing the capacity resource of Spider 2. Furthermore, due to improvements in tdm_multipath and ib_srp software, we are utilizing the Spider 2 system bandwidth and latency resources more effectively. The Spider 2 bandwidth usage statistics shows that our system is working within the design specifications. However, it is also evident that our scientific applications can be more effectively served by a burst buffer storage layer. All the data has been collected by monitoring tools developed for the Spider ecosystem. We believe the observed data set and insights will help us better design the next-generation Spider file and storage system. It will also be helpful to the larger community for building more effective large-scale file and storage systems.

Gunasekaran, Raghul↗

Tuyere: Enabling Scalable Memory Workloads for System Exploration

Memory technologies are under active development. Meanwhile, workloads on contemporary computing systems are increasing rapidly in size and diversity. Such dynamics in hardware and software further widen the gap between memory system design and performance evaluation. In this work, we propose a data-centric abstraction of high-performance computing applications for fast exploration of new memory technologies. We also provide a framework that uses a formal modeling language to describe the abstraction, automatically translates abstractions into memory traffic, and directly interfaces with cycle-accurate simulators. We evaluated the framework using 20 workloads and validated the memory traffic profile, the simulation results, and the relative memory changes of four memory technologies. Our results show that the data-centric abstraction can accurately capture application behavior adaptable to different input problems and can expedite system exploration.

Peng, Ivy Bo↗

Evaluating HPC Scheduling Strategies for Urgent Workloads

Scientific computing centers increasingly face workloads with diverse urgency requirements, driven by applications that demand rapid or even immediate execution. Appropriately configured scheduling policies can significantly improve both user satisfaction and overall cluster utilization. In this work, we present a systematic analysis of scheduler configurations under scenarios where a fraction of jobs have urgent computing needs. We evaluate multiple job scheduling simulators, develop a lightweight job-submission emulation framework, and create tools to analyze and visualize the resulting scheduling data. Our study identifies key trade-offs between responsiveness, fairness, and efficiency, and offers a set of practical scheduling configurations (particularly for Slurm) that can be tailored to HPC environments supporting mixed-urgency workloads.

Maheshwari, Ketan [ORNL] (ORCID:000000033800662X)↗

FY17 CSSE L2 Milestone Report: Analyzing Power Usage Characteristics of Workloads Running on Trinity.

This report summarizes the work performed as part of a FY17 CSSE L2 milestone to in- vestigate the power usage behavior of ASC workloads running on the ATS-1 Trinity plat- form. Techniques were developed to instrument application code regions of interest using the Power API together with the Kokkos profiling interface and Caliper annotation library. Experiments were performed to understand the power usage behavior of mini-applications and the SNL/ATDM SPARC application running on ATS-1 Trinity Haswell and Knights Landing compute nodes. A taxonomy of power measurement approaches was identified and presented, providing a guide for application developers to follow. Controlled scaling study experiments were performed on up to 2048 nodes of Trinity along with smaller scale ex- periments on Trinity testbed systems. Additionally, power and energy system monitoring information from Trinity was collected and archived for post analysis of "in-the-wild" work- loads. Results were analyzed to assess the sensitivity of the workloads to ATS-1 compute node type (Haswell vs. Knights Landing), CPU frequency control, node-level power capping control, OpenMP configuration, Knights Landing on-package memory configuration, and algorithm/solver configuration. Overall, this milestone lays groundwork for addressing the long-term goal of determining how to best use and operate future ASC platforms to achieve the greatest benefit subject to a constrained power budget.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Performance Analysis of Scientific Computing Workloads on Trusted Execution Environments

Scientific computing sometimes involves computation on sensitive data. Depending on the data and the execution environment, the HPC (high-performance computing) user or data provider may require confidentiality and/or integrity guarantees. To study the applicability of hardware-based trusted execution environments (TEEs) to enable secure scientific computing, we deeply analyze the performance impact of AMD SEV and Intel SGX for diverse HPC benchmarks including traditional scientific computing, machine learning, graph analytics, and emerging scientific computing workloads. We observe three main findings: 1) SEV requires careful memory placement on large scale NUMA machines (1x -3.4x slowdown without and 1x -1.15x slowdown with NUMA aware placement), 2) virtualization - a prerequisite for SEV - results in performance degradation for workloads with irregular memory accesses and large working sets (1x -4x slowdown compared to native execution for graph applications) and 3) SGX is inappropriate for HPC given its limited secure memory size and inflexible programming model (1.2x -126x slowdown over unsecure execution). Finally, we discuss forthcoming new TEE designs and their potential impact on scientific computing.

97 MATHEMATICS AND COMPUTING↗

Evaluating the Cloud for Capability Class Leadership Workloads

Cloud platforms offer a variety of benefits that are very appealing for a large scale HPC facility with a diverse and dynamic user base and workload set. At the same time, there is cause for concern about transitioning to the cloud. Incorporating cloud resources into existing HPC facilities or even fully transitioning to a cloud deployment poses significant challenges at the technical, organizational, and economic levels. Regardless, based on current trends it is highly likely that cloud platforms will become an integral component of many HPC centers in some form. To gain a better understanding of both the limitations and capabilities of current cloud infrastructures we evaluated the public offerings of the three leading cloud platforms (Amazon Web Services, Microsoft Azure, and Google Cloud Platform) using a selection of representative application workloads from our facility. Our findings show that while current HPC offerings are still nascent, significant progress is being made to address the present shortcomings. At the same time, significant challenges and questions remain about whether HPC cloud offerings will be able to deliver the full range of expected benefits.

97 MATHEMATICS AND COMPUTING↗

Modeling Workloads of a Linear Electromagnetic Code for Load Balancing Matrix Assembly

This report presents our work to model the workloads of a linear electromagnetic application based on the method of moments in the frequency domain to effectively load balance the matrix assembly. This application is particularly challenging to load balance due to its lack of persistent iterative behavior, its operation under tight memory constraint (where the matrix may fill 80% of memory on each node), and the algorithmic complexity of the computational method. This report describes the first step in our work to apply an inspector-executor approach for load balancing workloads where key parameters are exposed during the inspector phase and a pre-trained model is applied to predict relative task weights for the load balancer.

97 MATHEMATICS AND COMPUTING↗

Reducing Concurrency Bottlenecks in Parallel I/O Workloads

To enable high performance parallel checkpointing we introduced the Parallel Log Structured File System (PLFS). PLFS is middleware interposed on the file system stack to transform concurrent writing of one application file into many non-concurrently written component files. The promising effectiveness of PLFS makes it important to examine its performance for workloads other than checkpoint capture, notably the different ways that state snapshots may be later read, to make the case for using PLFS in the Exascale I/O stack. Reading a PLFS file involved reading each of its component files. In this paper we identify performance limitations on broader workloads in an early version of PLFS, specifically the need to build and distribute an index for the overall file, and the pressure on the underlying parallel file system's metadata server, and show how PLFS's decomposed components architecture can be exploited to alleviate bottlenecks in the underlying parallel file system.

COMPUTER ARCHITECTURE↗

BigPanDA: PanDA Workload Management System and its Applications beyond ATLAS

Modern experiments collect peta-scale volumes of data and utilize vast, geographically distributed computing infrastructure that serves thousands of scientists around the world. Requirements for rapid, near real-time data processing, fast analysis cycles and need to run massive detector simulations to support data analysis pose special premium on efficient use of available computational resources. A sophisticated Workload Management System (WMS) is needed to coordinate the distribution and processing of data and jobs in such environment. The ATLAS experiment at CERN uses PanDA (Production and Data Analysis) Workload Management System for managing the workflow for all data processing on over 150 data centers. While PanDAcurrently uses more than 250,000 cores with a peak performance of 0.3 petaFLOPS, it runs around 2 million jobs per day on hundreds of Grid sites and serving thousands of ATLAS users. In 2017 about 1.5 exabytes of data were processed with PanDA.In 2012 BigPanDA project project was started with aim to introduce new types of computing resources into ATLAS computing infrastructure, but also to offering PanDA features to different data-intensive applications for projects and experiments outside of ATLAS and High-Energy and Nuclear Physics. In this article we will present accomplishments and discuss possible directions for future work.

Svirin, Pavlo↗

Workload-Adaptive Management of Energy-Smart Disk Storage Systems

Recent studies have identified disk storage systems as one of the major consumers of power in data centers. Many disk power management (DPM) schemes were suggested where the power consumed by disks is reduced by spinning them down during long idle periods. Spinning the disks down and up results in additional energy and response time costs. For that reason, DPM schemes are effective only if the disks experience relatively long idle periods and the scheme does not introduce a severe response time penalty. In this paper we introduce a dynamic block exchange algorithm which switches data between disks based on the observed workload such that frequently accessed blocks end up residing on a few"hot" disks thus allowing the majority of disks to experience longer idle periods. We validate the effectiveness of the algorithm with trace-driven simulations showing power savings of up to 60percent with very small response time penalties.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Full Scale Evaluation of How Task-Based Overview Displays Impact Operator Workload and Situation Awareness When in Emergency Procedure Space

Control room modernization is critical to extending the life of the 99 operating commercial nuclear power plants (NPP) within the United States. However, due to the lack of evidence demonstrating the efficiency and effectiveness of recent candidate technologies, current NPP control rooms operate without the benefit of various newer technologies now available. As nuclear power plants begin to extend their licenses to continue operating for another 20 years, there is increased interest in modernizing the control room and supplementing the existing control boards with advanced technologies. As part of a series of studies investigating the benefits of advanced control room technologies, the researchers conducted an experimental study to observe the effect of Task-Based Overview Displays (TODs) on operator workload and situation awareness (SA) while completing typical operating scenarios. Researchers employed the Situation Awareness Rating Technique (SART) and the NASA Task Load Index (TLX) as construct measures.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗