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 433 records · Page 24

Toward Improved Support for Loosely Coupled Large Scale Simulation Workflows

High-performance computing (HPC) workloads are increasingly leveraging loosely coupled large scale simula- tions. Unfortunately, most large-scale HPC platforms, including Cray/ALPS environments, are designed for the execution of long-running jobs based on coarse-grained launch capabilities (e.g., one MPI rank per core on all allocated compute nodes). This assumption limits capability-class workload campaigns that require large numbers of discrete or loosely coupled simulations, and where time-to-solution is an untenable pacing issue. This paper describes the challenges related to the support of fine-grained launch capabilities that are necessary for the execution of loosely coupled large scale simulations on Cray/ALPS platforms. More precisely, we present the details of an enhanced runtime system to support this use case, and report on initial results from early testing on systems at Oak Ridge National Laboratory.

Ensemble computing.↗

Synthetic Proxy Infrastructure for Task Evaluation

The Synthetic Proxy Infrastructure for Task Evaluation is a proxy application designed to support application developers in gauging the performance of various task granularities when determining how best to utilize task based programming models.The infrastructure is designed to provide examples of common communication patterns with a synthetic workload intended to provide performance data to evaluate programming model and platform overheads for the purpose of determining task granularity for task decomposition purposes. This is presented as a reference implementation of a proxy application with run-time configurable input and output task dependencies ranging from an embarrassingly parallel scenario to patterns with stencil-like dependencies upon their nearest neighbors. Once all, if any, inputs are satisfied each task will execute a synthetic workload (a simple DGEMM of in this case) of varying size and output all, if any, outputs to the next tasks.The intent is for this reference implementation to be implemented as a proxy app in different programming models so as to provide the same infrastructure and to allow for application developers to simulate their own communication needs to assist in task decomposition under various models on a given platform.

Junghans, Christoph↗

Balancing computation and communication power in power constrained clusters

Systems, apparatuses, and methods for balancing computation and communication power in power constrained environments. A data processing cluster with a plurality of compute nodes may perform parallel processing of a workload in a power constrained environment. Nodes that finish tasks early may be power-gated based on one or more conditions. In some scenarios, a node may predict a wait duration and go into a reduced power consumption state if the wait duration is predicted to be greater than a threshold. The power saved by power-gating one or more nodes may be reassigned for use by other nodes. A cluster agent may be configured to reassign the unused power to the active nodes to expedite workload processing.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Integration of Titan supercomputer at OLCF with ATLAS Production System

The PanDA (Production and Distributed Analysis) workload management system was developed to meet the scale and complexity of distributed computing for the ATLAS experiment. PanDA managed resources are distributed worldwide, on hundreds of computing sites, with thousands of physicists accessing hundreds of Petabytes of data and the rate of data processing already exceeds Exabyte per year. While PanDA currently uses more than 200,000 cores at well over 100 Grid sites, future LHC data taking runs will require more resources than Grid computing can possibly provide. Additional computing and storage resources are required. Therefore ATLAS is engaged in an ambitious program to expand the current computing model to include additional resources such as the opportunistic use of supercomputers. In this paper we will describe a project aimed at integration of ATLAS Production System with Titan supercomputer at Oak Ridge Leadership Computing Facility (OLCF). Current approach utilizes modified PanDA Pilot framework for job submission to Titan's batch queues and local data management, with lightweight MPI wrappers to run single node workloads in parallel on Titan's multi-core worker nodes. It provides for running of standard ATLAS production jobs on unused resources (backfill) on Titan. The system already allowed ATLAS to collect on Titan millions of core-hours per month, execute hundreds of thousands jobs, while simultaneously improving Titans utilization efficiency. We will discuss the details of the implementation, current experience with running the system, as well as future plans aimed at improvements in scalability and efficiency.

Megino, F. Barreiro↗

ANALYSIS OF COMMUNICATION PERFORMANCE DEGRADATION OF THE RADIATION TRANSPORT CODE PIDOTS ON HIGH-UTILIZATION, MULTI-USER HPC SYSTEMS

The PIDOTS radiation transport code implements a spatially decomposed Integral Transport Matrix Method (ITMM) solver, which is intended to fully utilize the capabilities of modern, massively parallel high-performance computing (HPC) systems. While the code shows promising results, there was also an unexpected loss of parallel efficiency on the test systems as the number of participating processors grew and the parallelization grain size got finer. We seek to identify and characterize the communication-latency based effects that contribute to this slowdown. Through the creation of a high-level, parameterized representation of the workload of the code, the communication methodology was identified as the likely reason. From there, low-level, InfiniBand communication performance data measured on the Falcon HPC at Idaho National Laboratory (INL) was used to produce a discrete-event model of the communication scheme. The data, as well as the model, show that infrequent, large spikes in send/receive latency drive an unexpectedly substantial increase in projected runtime of a code. Furthermore, these effects are more pronounced under the high-utilization, scattered-workload environment of Falcon. Based on results from the model, it can be shown that a high-communication volume, small message-size regime can easily lead to slowdowns of ~5-10x, when compared to ideal results, as the processor count increases.

97 MATHEMATICS AND COMPUTING↗

Distributed metadata servers in a file system with separate metadata servers for file metadata and directory metadata

A file system is provided having a plurality of distributed metadata servers with separate metadata servers for file metadata and directory metadata. An exemplary distributed metadata storage system comprises a plurality of compute nodes, wherein at least one compute node comprises a file system client that generates a directory metadata request and/or a file metadata request; a plurality of directory metadata servers to serve directory metadata in response to a given directory metadata request; and a plurality of file metadata servers to serve file metadata in response to a given file metadata request. The plurality of directory metadata servers are distinct from the plurality of file metadata servers. The compute nodes optionally comprise an object client that requests object data from an object store system. The number of directory metadata servers and the number of file metadata servers are optionally determined independently to balance for different workloads, and can be dynamically readjusted for evolving workloads.

97 MATHEMATICS AND COMPUTING↗

Cache utilization and eviction based on allocated priority tokens

A system, method, and computer program product are provided for providing prioritized access for multithreaded processing. The method includes the steps of allocating threads to process a workload and assigning a set of priority tokens to at least a portion of the threads. Access to a resource, by each one of the threads, is based on the priority token assigned to the thread and the threads are executed by a multithreaded processor to process the workload.

Johnson, Daniel Robert↗

OpenCGRA: An Open-Source Unified Framework for Modeling,Testing, and Evaluating CGRAs

Coarse-grained reconfigurable arrays (CGRAs),loosely defined as arrays of functional units (e.g, adder, sub-tractor, multiplier, divider, or larger multi-operation units, butsmaller than a general-purpose core) interconnected through aNetwork-on-Chip, provide higher flexibility than domain-specificASIC accelerators while offering increased hardware efficiencywith respect to fine-grained reconfigurable devices, such as FieldProgrammable Gate Arrays (FPGAs). The fast evolving fieldsof machine learning and edge computing, which are seeing acontinuous flow of novel algorithms and larger models, makeCGRAs ideal target architectures to allow domain specializationwithout loosing too much generality. They also generally offerquicker and more effective reconfigurability than FPGAs, po-tentially allowing adaptation during actual algorithm execution,and implement a dataflow programming paradigm that adaptswell to these emerging workloads. Designing and generating aCGRA, however, still requires to define the type and number ofthe specific functional units, implement their interconnect andthe network topology, and perform its simulation and validation,given a variety of workloads of interest.In this paper, we propose OpenCGRA, a Python-based unifiedframework that integrates generation, modeling, testing and eval-uation for CGRAs. OpenCGRA is the first open-source integratedframework able to support the full top-to-bottom design flow forspecializing and implementing CGRAs: modeling at different ab-straction levels (functional level, cycle level, register-transfer level),generation, simulation, testing at different granularities (unit test-ing, integration testing, property-based testing), and characteriza-tion (area, power, and timing). OpenCGRAs will be made availableon GitHub.

CGRA, synthesis↗

CSB-RNN: A Faster-Than-Realtime RNN Acceleration Framework with Compressed Structured Blocks

Recurrent Neural Networks (RNN) is widely applied to temporal sequence analysis, where real-time performance is usually in demand. However, RNN suffers a heavy computational workload as the model comes with a large weight matrix. To alleviate the pain, model compression (pruning) schemes have been proposed for RNN that pruning the redundant (near-zero) weight-values. On the one hand, the non-structured pruning methods achieve a considerable pruning rate while bringing the computational irregularity, which is un-friendly to parallel-hardware. On the other hand, the existing structured pruning methods consider the hardware parallelism; However, they suffer a poor pruning rate due to the restrict constraints on pruning structure. This paper presents CSB-RNN, an optimized full-stack RNN framework with the novel compressed structured block (CSB) technique. The CSB-pruned RNN model comes with both fine-granularity that benefits the pruning rate and regular structure that facilitates the hardware-parallelism. Further, we propose a novel hardware architecture for inferencing the CSB-pruned model. Different from conventional parallel hardware, this architecture solves the block-workload imbalance issue and achieves an over 95% hardware utilization. With the experiments on 10 RNN models in 5 application domains, the CSB-RNN realizes 7×-20× lossless compression and up to 50× acceptable lossy-compression, which is 2×-7× to the prior art. With the addition of the novel hardware, the compressed-RNN inference reaches a super real-time latency of 10-400µs with FPGA implementation.

Shi, Runbin↗

The Rucio File Catalog in DIRAC implemented for Belle II

DIRAC and Rucio are two standard pieces of software widely used in the HEP domain. DIRAC provides Workload and Data Management function- alities, among other things, while Rucio is a dedicated, advanced Distributed Data Management system. Many communities that already use DIRAC have expressed their interest in using DIRAC for Workload Management in combi- nation with Rucio for Data Management. In this paper, we describe the integra- tion of the Rucio File Catalog into DIRAC that was initially developed for the Belle II collaboration.

97 MATHEMATICS AND COMPUTING↗

m-CUBES An efficient and portable implementation of multi-dimensional integration for gpus

The task of multi-dimensional numerical integration is frequently encountered in physics and other scientific fields, e.g., in modeling the effects of systematic uncertainties in physical systems and in Bayesian parameter estimation. Multi-dimensional integration is often time-prohibitive on CPUs. Efficient implementation on many-core architectures is challenging as the workload across the integration space cannot be predicted a priori. We propose m-Cubes, a novel implementation of the well-known Vegas algorithm for execution on GPUs. Vegas transforms integration variables followed by calculation of a Monte Carlo integral estimate using adaptive partitioning of the resulting space. m-Cubes improves performance on GPUs by maintaining relatively uniform workload across the processors. As a result, our optimized Cuda implementation for Nvidia GPUs outperforms parallelization approaches proposed in past literature. We further demonstrate the efficiency of m-Cubes by evaluating a six-dimensional integral from a cosmology application, achieving significant speedup and greater precision than the CUBA library's CPU implementation of VEGAS. We also evaluate m-Cubes on a standard integrand test suite. m-Cubes outperforms the serial implementations of the Cuba and GSL libraries by orders of magnitude speedup while maintaining comparable accuracy. Our approach yields a speedup of at least 10 when compared against publicly available Monte Carlo based GPU implementations. In summary, m-Cubes can solve integrals that are prohibitively expensive using standard libraries and custom implementations. A modern C++ interface header-only implementation makes m-Cubes portable, allowing its utilization in complicated pipelines with easy to define stateful integrals. Compatibility with non-Nvidia GPUs is achieved with our initial implementation of m-Cubes using the Kokkos framework.

Sakiotis, Ioannis↗

Basin-Wide Approaches to Hydropower Licensing

This presentation summarizes findings from a 2020 NREL technical report including the FERC relicensing process for non-federal hydropower projects, analyzes FERC-licensed projects with license expiration dates from 2018-2037, discusses FERC's authority to coordinate license terms of hydropower projects within a shared river basin and provides basin-wide case studies and considerations to hydropower relicensing. In the United States there are 1,043 active FERC-licensed hydroelectric projects with a total capacity of 56,097 MW. Of those, 647 with a total capacity of 21,870 MW have license expiration dates from 2018-2037. The expected workload in conjunction with the time, cost, and complexity associated with issuing a single new license has led to initiatives that aim to increase the efficiency of the relicensing process. Federal and state regulators and licensees in California, Maine, New York, and Wisconsin have begun to develop approaches to look at hydropower relicensing as part of a larger system - a river basin. These basin-wide approaches seek to coordinate different stages of the relicensing process for multiple projects at the same time. The goal of these basin-wide approaches is to increase the efficiency of the relicensing process and allow for a more comprehensive analysis of the cumulative impacts of the projects within the basin. These innovative approaches to relicensing could also reduce the workload for regulators and costs associated with relicensing. This presentation discusses some of the findings from the Basin-wide Approaches to Hydropower Relicensing: Case Studies and Considerations including a summary of the key considerations for the FERC relicensing process for non-federal hydropower projects, key findings from the analysis of FERC-licensed projects with license expiration dates from 2018-2037, discusses FERC's authority to coordinate license terms of hydropower projects within a shared river basin and provides basin-wide case studies and considerations to hydropower relicensing.

basin-wide↗

Scalable load balancing for massively parallel distributed Monte Carlo particle transport

In order to run computer simulations efficiently on massively parallel computers with hundreds of thousands or millions of processors, care must be taken that the calculation is load balanced across the processors. Examining the workload of every processor leads to an unscalable algorithm, with run time at least as large as O(N), where N is the number of processors. We present a scalable load balancing algorithm, with run time 0(log(N)), that involves iterated processor-pair-wise balancing steps, ultimately leading to a globally balanced workload. We demonstrate scalability of the algorithm up to 2 million processors on the Sequoia supercomputer at Lawrence Livermore National Laboratory. (authors)

97 MATHEMATICS AND COMPUTING↗

Performance improvement and human resources transition management in D and D projects - 15440

Power generation and other nuclear facilities production is mainly characterized by stable working environment, with continuous efforts for improvement based on previous achievements, constant workload, foreseeable and established organizational hierarchy; and generation of cash. In contrary to normal production - when phasing down the facility for final shutdown, decommissioning and dismantling - one has to manage a new, highly dynamic working environment, with decreasing workload, new skills required; and consumption of cash. The key to successful transition is to recognize the need for establishing an explicit performance improvement program with an effective change management process in order to address this profound evolution as early as possible in the project. AREVA owns and operates large nuclear material processing facilities. This includes the responsibility for their end of life up to final Decommissioning and Dismantling (D and D). Faced with this transitional challenge, AREVA took example from well-known management methods (Lean Management, 6 Sigma, TPM...) successfully applied by the non-nuclear production industry with the corresponding philosophy of Operational Excellence. These methods were adapted to the specifics of nuclear decommissioning projects. Furthermore, specific computerized tools were developed to assist managers in implementing measures for re-deploying, re-training and re-qualifying personnel as well as re-organizing the work structure while maintaining safety and social consensus. Significant improvements in the dismantling works as well as in the management of generated waste were achieved early after start of the implementation of the performance improvement programs. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Effects of adaptive automation on operator-system performance - 103

Adaptive automation (AA) is the dynamic, real-time change in the degree of automation in response to situational changes. AA systems are being developed in many industries, including for nuclear power plant applications. AA is a promising means of mitigating human performance issues that often arise in highly automated systems. The purpose of this Nuclear Regulatory Commission study was to characterize important AA design features, define the effects of AA on performance, examine the human factors engineering (HFE) guidance available to design and evaluate AA systems, and identify research and development needs. In general, we found that AA improves task performance and situation awareness (SA) while managing workload. Although the research is limited, AA also supports operator recognition of automation failure and recovery. Research on human-system interfaces has identified principles showing promise for supporting SA, including failure detection, and limiting workload. Research further suggests that AA systems are both more effective, and less disruptive and distracting, when they follow rules of interaction similar to those used by human crewmembers. Our general conclusion about the HFE guidance available to designers and reviewers is that it is limited and has not kept pace with automation technology. We discuss several research and development needs that will help support a better understanding of where and how AA should be used and support the development of more comprehensive guidance for AA safety reviews. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Operating displays - new concept: high performance displays - 118

New control rooms in Nuclear Power Plants using digital Distributed Control System (DCS) operated with software displays, are providing thousands of signals to the operating crew. When an event happens, the Flood of information provided to operators could obscure the initiator event increasing the operator response time, work load and complicating the selection of the actions to be performed. There are some initiatives that are trying to minimize the 'avalanche effect' as the alarm engineering filtering and prioritization or diagnostic displays. Likewise, new control rooms are lost the availability to know the plant status just with a quick glance to the panel indicators. Regarding Small Modular Reactors, where in some cases four operators should monitor and control twelve reactors, these problems are even more significant. The challenge is to find a solution, based on current digital systems, that supply information to operators in order to prevent events and take early actions to minimize or avoid any unexpected incident. In order to minimize human errors, Tecnatom has developed a specific set of displays, called 'High Performance Displays' (HPD) based on objectives, work environment limitation, and non-anticipated events. These displays are being design following the HFE standards: applying the NUREG-0711 elements to identify the information that they have to content and the NUREG-0700 to design the interface. The function of these displays is monitoring the plant situation in a way that the operators are able to recognize any potential event at a simple glance but controlling thousands of signals through pattern recognition, symmetries, regular polygons and colors. The objective of the HPD is to provide an integrated function minimizing the tunnel effect and reduce the workload during the diagnosis phase. Moreover, HPD enhance operators to take the right actions to anticipate the response to any event, even avoiding it, if possible This paper analyzes how HPD's have been design as well as presents the results of a preliminary validation of their capabilities. The preliminary validation is a reduce validation in a full scope simulator running two representative scenarios of abnormal and emergency operation. The analysis is focused on the first stage of the event, i.e. the detection phase, HPD's have been installed in a generic full scope simulator of a nuclear power plant, digital controlled. Both scenarios have been performed by two different operator crews. The first operator shift has worked with the conventional human machine interface, that is, displays similar to the ones currently installed in existing nuclear power plant with digital control. The second crew, reproduce the same scenarios but with HPD available. The studio collects preliminary data in order to compare results, draw lesson learned from the experience to improve HPD design, and find solutions in terms of reducing human errors, human workload, and increase the availability of the plant. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Human Performance Measures for the Evaluation of Nuclear Power Plant Control Room Interfaces: A Systematic Review - 265

The purpose of this study was to review the literature related to measuring human performance in the design and evaluation of the human-system interface (HSI) of nuclear power plant (NPP) control rooms and synthesize lessons learned and future directions for research and practice in this field. The design and evaluation of digital or hybrid HSI requires comprehensive measurement of human performance to ensure quality and safety of the nuclear power process control. Human factors evaluation frameworks have been proposed to guide the measurement of human performance constructs. However, there are few guides for selecting appropriate measures for those constructs. A systematic review of empirical research literature was conducted. Studies were identified through academic publication databases and grey literature searches. Eligible studies were coded and information regarding human performance measures was extracted and analyzed. A total of 80 studies met the criteria. Human performance measures extracted from the reviewed studies included measures of: behavioral performance; workload; situation awareness; human-human or human-machine cooperation; other cognitive performance indicators; and system performance. Behavioral performance (speed and accuracy), workload, and situation awareness were the most frequently measured constructs with validated and domain-specific instruments. The results of the literature review provided an overview of the human performance constructs and their corresponding measures for NPP control room HSI evaluation. These results can be used as an initial guide to establish appropriate and comprehensive measurements of human performance for such evaluations. Future directions in measure development are also discussed. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Development of Real-Time Quantitative Safety Evaluation Method for Nuclear Power Plants

Human operators involved with large process control systems such as nuclear power plants (NPPs) perform significant roles in the operation of systems. In this reason, deficiencies in human factors such as poor HSI (Human System Interface) design, procedure, and training, are significant contributing factors to NPPs incidents and accidents. In this regard, many kinds of studies including human reliability analysis (HRA), operation support system, automation, have been conducted in order to reduce human errors. Among these fields of studies, automation has its own specialty since it mainly focuses on eliminating the human error-inducing tasks to reduce human error, while other topics are primarily focusing on reducing human error by aiding human operators during operation. It is commonly believed that replacing human operators to the automated system would guarantee greater efficiency, lower workloads, and fewer human errors. However, these beliefs are not always true in large and complex systems such as NPP, since excessive automation can generate new roles for human operators, change human operators' activities in unexpected ways, and inducing 'out-of-the-loop' (OOTL) problem. Especially, although human error probability drastically increases during abnormal situations in NPP due to overload of information, high workload, and short time available for diagnosis, automation is not actively adopted since conventional machine learning techniques are neither capable nor reliable to handle overwhelmingly complex abnormal situations in NPP. Recently, newly developed 'deep learning' techniques have been actively applied to many fields, and some of these studies proved that the artificial intelligences (AI) based on deep learning techniques show better performance than that of human being. In 2015, deep Q-network (DQN) which is one of the deep learning techniques was developed and applied to train AI that automatically plays various Atari 2800 games, and this AI surpassed the human-level playing in many kind of games. Also in 2016, 'AlphaGo', which was developed by 'Google Deepmind' based on deep learning technique to play the game of Go, was defeated Se-dol Lee who is the World Go champion with score of 4:1. In the point of view that the game of Go is considered as one of the challenging area in machine learning field, it is verified that these new machine learning techniques can perform well, even better than the human being in high-complexity tasks. Previously, most of AI applications in nuclear field were focusing on supporting human operators' tasks such as diagnosis and decision making by rapid classification and prediction, based on fixed training data sets. However, it is expected that AI can be applied to solve more complicated problems (i.e. automation during abnormal states in NPP) by adopting advanced machine learning methodologies. In order to apply the automation system in NPP, firstly it is needed to evaluate the status of the plant quantitatively in real-time, since the information about which state is better (i.e. safe) or worse (i.e. unsafe) is essential for training properly working automation AI. Currently, there are several methodologies for NPP safety evaluation such as probabilistic safety assessment (PSA), safety performance indicator (SPI). However, existing methodologies are not feasible for development of automated system since they are not capable for the cases which are not included in the underlying model, not able to consider delicate changes in the NPP, and hard to evaluate in real-time. Therefore, development of new NPP safety evaluation methodology which can cover previously mentioned requirements is needed to conduct the study on NPP automation further. In this study, the concept of early warning score (EWS) in medical field was adopted to develop the methodology which can evaluate the safety level of the NPP quantitatively and in real-time. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗