Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “CORI SYSTEM”

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 37 records · Page 2

Design and implementation of I/O performance prediction scheme on HPC systems through large-scale log analysis

Abstract Large-scale high performance computing (HPC) systems typically consist of many thousands of CPUs and storage units used by hundreds to thousands of users simultaneously. Applications from large numbers of users have diverse characteristics, such as varying computation, communication, memory, and I/O intensity. A good understanding of the performance characteristics of each user application is important for job scheduling and resource provisioning. Among these performance characteristics, I/O performance is becoming increasingly important as data sizes rapidly increase and large-scale applications, such as simulation and model training, are widely adopted. However, predicting I/O performance is difficult because I/O systems are shared among all users and involve many layers of software and hardware stack, including the application, network interconnect, operating system, file system, and storage devices. Furthermore, updates to these layers and changes in system management policy can significantly alter the I/O behavior of applications and the entire system. To improve the prediction of the I/O performance on HPC systems, we propose integrating information from several different system logs and developing a regression-based approach to predict the I/O performance. Our proposed scheme can dynamically select the most relevant features from the log entries using various feature selection algorithms and scoring functions, and can automatically select the regression algorithm with the best accuracy for the prediction task. The evaluation results show that our proposed scheme can predict the write performance with up to 90% prediction accuracy and the read performance with up to 99% prediction accuracy using the real logs from the Cori supercomputer system at NERSC.

97 MATHEMATICS AND COMPUTING↗

Options Impacting the Electric System of the Future (ESF); NREL (National Renewable Energy Laboratory)

As utilities are faced with adapting to new technologies, technology and policy due diligence are necessary to ensure the development of a future grid that brings greater value to utilities and their consumers. This presentation explores the different kinds of future directions the power industry could consider to create, discussing key components necessary for success. It will also discuss the practical application and possible strategies for utilities and innovators to implement smart technologies that will enable an ultimate ‘intelligent’ grid capable of two-way communication, interoperability, and greater efficiency and system resiliency.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Tuning HDF5 subfiling performance on parallel file systems

Subfiling is a technique used on parallel file systems to reduce locking and contention issues when multiple compute nodes interact with the same storage target node. Subfiling provides a compromise between the single shared file approach that instigates the lock contention problems on parallel file systems and having one file per process, which results in generating a massive and unmanageable number of files. In this paper, we evaluate and tune the performance of recently implemented subfiling feature in HDF5. In specific, we explain the implementation strategy of subfiling feature in HDF5, provide examples of using the feature, and evaluate and tune parallel I/O performance of this feature with parallel file systems of the Cray XC40 system at NERSC (Cori) that include a burst buffer storage and a Lustre disk-based storage. We also evaluate I/O performance on the Cray XC30 system, Edison, at NERSC. Our results show performance benefits of 1.2X to 6X performance advantage with subfiling compared to writing a single shared HDF5 file. We present our exploration of configurations, such as the number of subfiles and the number of Lustre storage targets to storing files, as optimization parameters to obtain superior I/O performance. Based on this exploration, we discuss recommendations for achieving good I/O performance as well as limitations with using the subfiling feature.

97 MATHEMATICS AND COMPUTING↗

Time reversal symmetry breaking and odd viscosity in active fluids: Green–Kubo and NEMD results

Active fluids, which are driven at the microscale by non-conservative forces, are known to exhibit novel transport phenomena due to the breaking of time reversal symmetry. Recently, Epstein and Mandadapu [arXiv:1907.10041 (2019)] obtained Green-Kubo relations for the full set of viscous coefficients governing isotropic chiral active fluids, including the so-called odd viscosity, invoking Onsager's regression hypothesis for the decay of fluctuations in active non-equilibrium steady states. In this Communication, we test these Green-Kubo relations using molecular dynamics simulations of a canonical model system consisting of actively torqued dumbbells. We find the resulting odd and shear viscosity values from the Green-Kubo relations to be in good agreement with values measured independently through non-equilibrium molecular dynamics flow simulations. This provides a test of the Green-Kubo relations and lends support to the application of the Onsager regression hypothesis in relation to viscous behaviors of active matter systems.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Communication—Analysis of Thick Co-Extruded Cathodes for Higher-Energy-and-Power Lithium-Ion Batteries

3-dimensional (3D) electrode architectures have been explored as a means to decouple power and energy trade-offs in thick battery electrodes. Limited work has been published which systematically examines the impact of these architectures at the pouch cell level. This paper conducts an analysis on the potential capacity gains that can be realized with thick co-extruded electrodes in a pouch cell. Moreover, our findings show that despite lower active material composition for each cathode layer, the effective gain in thickness and active material loading enables pouch cell capacity gains greater than 10% with a Lithium Nickel Manganese Cobalt Oxide (NMC) materials system.

25 ENERGY STORAGE↗

Using OFI libfabric on Cori/Edison

These are slides from a presentation during an NERSC site visit to Los Alamos National Laboratory. The following topics are covered: building/installing libfabric, OpenMPI using libfabric, MPICH using libfabric, Open SHMEM (Sandia), other applications, and what is next. The next steps are: get a libfabric 1.4 out, it would be nice to have libfabric 1.4 installed in system space on Cori, add libfabric modules on Cori, might be a good idea to have a SLURM PMI module to simplify its use when building/using Open MPI and MPICH built to use libfabric, and upgrade Edison to CLE 5.2 UP04 or newer.

97 MATHEMATICS AND COMPUTING↗

MPAS-Ocean NESAP Status Report

NESAP performance improvements on MPAS-Ocean have resulted in a 5% to 7% speed-up on each of the examined systems including Cori-KNL, Cori-Haswell, and Edison. These tests were configured to emulate a production workload by using 128 nodes and a high-resolution ocean domain. Overall, the gap between standard and many-core architecture performance has been narrowed, but Cori-KNL remains considerably under-performing relative to Edison. NESAP code alterations affected 600 lines of code, and most of these improvements will benefit other MPAS codes (sea ice, land ice) that are also components within ACME. Modifications are fully tested within MPAS. Testing in ACME across many platforms is underway, and must be completed before the code is merged. In addition, a ten-year production ACME global simulation was conducted on Cori-KNL in late 2016 with the pre-NESAP code in order to test readiness and configurations for scientific studies. Next steps include assessing performance across a range of nodes, threads per node, and ocean resolutions on Cori-KNL.

54 ENVIRONMENTAL SCIENCES↗

A survey of life support system automation and control

The level of automation and control necessary to support advanced life support systems for use in the manned space program is steadily increasing. As the length and complexity of manned missions increase, life support systems must be able to meet new space challenges. Longer, more complex missions create new demands for increased automation, improved sensors, and improved control systems. It is imperative that research in these key areas keep pace with current and future developments in regenerative life support technology. This paper provides an overview of past and present research in the areas of sensor development, automation, and control of life support systems for the manned space program, and it discusses the impact continued research in several key areas will have on the feasibility, operation, and design of future life support systems.

Finn, Cory K.↗

Optimizing the performance of reactive molecular dynamics simulations for many-core architectures

Reactive molecular dynamics simulations are computationally demanding. Reaching spatial and temporal scales where interesting scientific phenomena can be observed requires efficient and scalable implementations on modern hardware. In this article, we focus on optimizing the performance of the widely used LAMMPS/ReaxC package for many-core architectures. As hybrid parallelism allows better leverage of the increasing on-node parallelism, we adopt thread parallelism in the construction of bonded and nonbonded lists and in the computation of complex ReaxFF interactions. To mitigate the I/O overheads due to large volumes of trajectory data produced and to save users the burden of post-processing, we also develop a novel in situ tool for molecular species analysis. We analyze the performance of the resulting ReaxC-OMP package on two different architectures: (i) Mira, an IBM Blue Gene/Q system and (ii) Cori-II, a Cray XC-40 sytem with Knights Landing processors. For Pentaerythritol tetranitrate (PETN) systems of sizes ranging from 32 thousand to 16.6 million particles, we observe speedups in the range of 1.5-4.5x. We observe sustained performance improvements for up to 262,144 cores (1,048,576 processes) of Mira and a weak scaling efficiency of 91.5% in large simulations containing 16.6 million particles. Finally, the in situ molecular species analysis tool incurs only insignificant overheads across various system sizes and runs configurations.

97 MATHEMATICS AND COMPUTING↗

A Case For Intra-rack Resource Disaggregation in HPC

The expected halt of traditional technology scaling is motivating increased heterogeneity in high-performance computing (HPC) systems with the emergence of numerous specialized accelerators. As heterogeneity increases, so does the risk of underutilizing expensive hardware resources if we preserve today’s rigid node configuration and reservation strategies. This has sparked interest in resource disaggregation to enable finer-grain allocation of hardware resources to applications. However, there is currently no data-driven study of what range of disaggregation is appropriate in HPC. To that end, we perform a detailed analysis of key metrics sampled in NERSC’s Cori, a production HPC system that executes a diverse open-science HPC workload. In addition, we profile a variety of deep-learning applications to represent an emerging workload. We show that for a rack (cabinet) configuration and applications similar to Cori, a central processing unit with intra-rack disaggregation has a 99.5% probability to find all resources it requires inside its rack. In addition, ideal intra-rack resource disaggregation in Cori could reduce memory and NIC resources by 5.36% to 69.01% and still satisfy the worst-case average rack utilization.

97 MATHEMATICS AND COMPUTING↗

Adaptive Learning for Concept Drift in Application Performance Modeling

Supervised learning is a promising approach for modeling the performance of applications running on large HPC systems. A key assumption in supervised learning is that the training and testing data are obtained under the same conditions. However, in production HPC systems these conditions might not hold because the conditions of the platform can change over time as a result of hardware degradation, hardware replacement, software upgrade, and configuration updates. These changes could alter the data distribution in a way that affects the accuracy of the predictive performance models and render them less useful; this phenomenon is referred to as concept drift. Ignoring concept drift can lead to suboptimal resource usage and decreased efficiency when those performance models are deployed for tuning and job scheduling in production systems. To address this issue, we propose a concept-drift-aware predictive modeling approach that comprises two components: (1) an online Bayesian changepoint detection method that can automatically identify the location of events that lead to concept drift in near-real time and (2) a moment-matching transformation inspired by transfer learning that converts the training data collected before the drift to be useful for retraining. We use application input/output performance data collected on Cori, a production supercomputing system at the National Energy Research Scientific Computing Center, to demonstrate the effectiveness of our approach. The results show that concept-drift-aware models obtain significant improvement in accuracy; the median absolute error of the best-performing Gaussian process regression improved by 58.8% when the proposed approaches were used.

adaptive learning↗

Design and implementation of dynamic I/O control scheme for large scale distributed file systems

In this paper, we have analyzed the input/output (I/O) activities of Cori, which is a high-performance computing system at the National Energy Research Scientific Computing Center at Lawrence Berkeley National Laboratory. Our analysis results indicate that most users do not adjust storage configurations but rather use the default settings. In addition, owing to the interference from many applications running simultaneously, the performance varies based on the system status. To configure file systems autonomously in complex environments, we developed DCA-IO, a dynamic distributed file system configuration adjustment algorithm that utilizes the system log information to adjust storage configurations automatically. Our scheme aims to improve the application performance and avoid interference from other applications without user intervention. Moreover, DCA-IO uses the existing system logs and does not require code modifications, an additional library, or user intervention. To demonstrate the effectiveness of DCA-IO, we performed experiments using I/O kernels of real applications in both an isolated small-sized Lustre environment and Cori. Our experimental results shows that our scheme can improve the performance of HPC applications by up to 263% with the default Lustre configuration.

97 MATHEMATICS AND COMPUTING↗

Solar Photovoltaic Financing: Residential Sector Deployment

This report presents the information that homeowners and policy makers need to facilitate PV financing at the residential level. The full range of cash payments, bill savings, and tax incentives is covered, as well as potentially available solar attribute payments. Traditional financing is also compared to innovative solutions, many of which are borrowed from the commercial sector. Together, these mechanisms are critical for making the economic case for a residential PV installation, given its high upfront costs. Unfortunately, these programs are presently limited to select locations around the country. By calling attention to these innovative initiatives, this report aims to help policy makers consider greater adoption of these models to benefit homeowners interested installing a residential PV system.

14 SOLAR ENERGY↗

System Design Techniques for Reducing the Power Requirements of Advanced life Support Systems

The high power requirement associated with overall operation of regenerative life support systems is a critical Z:p technological challenge. Optimization of individual processors alone will not be sufficient to produce an optimized system. System studies must be used in order to improve the overall efficiency of life support systems. Current research efforts at NASA Ames Research Center are aimed at developing approaches for reducing system power and energy usage in advanced life support systems. System energy integration and energy reuse techniques are being applied to advanced life support, in addition to advanced control methods for efficient distribution of power and thermal resources. An overview of current results of this work will be presented. The development of integrated system designs that reuse waste heat from sources such as crop lighting and solid waste processing systems will reduce overall power and cooling requirements. Using an energy integration technique known as Pinch analysis, system heat exchange designs are being developed that match hot and cold streams according to specific design principles. For various designs, the potential savings for power, heating and cooling are being identified and quantified. The use of state-of-the-art control methods for distribution of resources, such as system cooling water or electrical power, will also reduce overall power and cooling requirements. Control algorithms are being developed which dynamically adjust the use of system resources by the various subsystems and components in order to achieve an overall goal, such as smoothing of power usage and/or heat rejection profiles, while maintaining adequate reserves of food, water, oxygen, and other consumables, and preventing excessive build-up of waste materials. Reductions in the peak loading of the power and thermal systems will lead to lower overall requirements. Computer simulation models are being used to test various control system designs.

Finn, Cory↗

Optimizing fusion PIC code performance at scale on Cori Phase 2

In this paper we present the results of optimizing the performance of the gyrokinetic full-f fusion PIC code XGC1 on the Cori Phase Two Knights Landing system. The code has undergone substantial development to enable the use of vector instructions in its most expensive kernels within the NERSC Exascale Science Applications Program. We study the single-node performance of the code on an absolute scale using the roofline methodology to guide optimization efforts. We have obtained 2x speedups in single node performance due to enabling vectorization and performing memory layout optimizations. On multiple nodes, the code is shown to scale well up to 4000 nodes, near half the size of the machine. We discuss some communication bottlenecks that were identified and resolved during the work.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗