Search NASA⌕ Search

SEARCH · Search NASA

Results for “High Performance Storage Systems”

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 217 records · Page 12

Parallel peak pruning for scalable SMP contour tree computation

As data sets grow to exascale, automated data analysis and visualisation are increasingly important, to intermediate human understanding and to reduce demands on disk storage via in situ analysis. Trends in architecture of high performance computing systems necessitate analysis algorithms to make effective use of combinations of massively multicore and distributed systems. One of the principal analytic tools is the contour tree, which analyses relationships between contours to identify features of more than local importance. Unfortunately, the predominant algorithms for computing the contour tree are explicitly serial, and founded on serial metaphors, which has limited the scalability of this form of analysis. While there is some work on distributed contour tree computation, and separately on hybrid GPU-CPU computation, there is no efficient algorithm with strong formal guarantees on performance allied with fast practical performance. Here in this paper, we report the first shared SMP algorithm for fully parallel contour tree computation, withfor-mal guarantees of O(lgnlgt) parallel steps and O(n lgn) work, and implementations with up to 10x parallel speed up in OpenMP and up to 50x speed up in NVIDIA Thrust.

97 MATHEMATICS AND COMPUTING↗

Scalable Contour Tree Computation by Data Parallel Peak Pruning

As data sets grow to exascale, automated data analysis and visualization are increasingly important, to intermediate human understanding and to reduce demands on disk storage via in situ analysis. Trends in architecture of high performance computing systems necessitate analysis algorithms to make effective use of combinations of massively multicore and distributed systems. One of the principal analytic tools is the contour tree, which analyses relationships between contours to identify features of more than local importance. Unfortunately, the predominant algorithms for computing the contour tree are explicitly serial, and founded on serial metaphors, which has limited the scalability of this form of analysis. While there is some work on distributed contour tree computation, and separately on hybrid GPU-CPU computation, there is no efficient algorithm with strong formal guarantees on performance allied with fast practical performance. Furthermore, we report the first shared SMP algorithm for fully parallel contour tree computation, with formal guarantees of O(lg V lg t) parallel steps and O(V lg V) work for data with V samples and t contour tree supernodes, and implementations with more than 30× parallel speed up on both CPU using TBB and GPU using Thrust and up 70× speed up compared to the serial sweep and merge algorithm.

97 MATHEMATICS AND COMPUTING↗

Assessment of commercially available and experimental hydrogen electrodes

NASA Lewis Research Center is currently involved in advanced cell component development for nickel-hydrogen cells and batteries. Long life, high energy density, improved performance and reliability are required for energy storage systems in future space missions. Commercially available as well as experimental hydrogen electrodes were assessed and copared to the state-of-the-art hydrogen electrode that is currently being used in nickel-hydrogen batteries. These electrodes were evaluated by scanning electron microscopy and standard electrochemical polarization measurements. Production variables such as Teflon content and platinum catalyst loading were considered in order to assess various hydrogen electrods with regard to the different electrode manufacturing processes.

Charleston, J. A.↗

Assessment of commercially available and experimental hydrogen electrodes

NASA Lewis Research Center is currently involved in advanced cell component development for nickel-hydrogen cells and batteries. Long life, high energy density, improved performance and reliability are required for energy storage systems in future space missions. Commercially available as well as experimental hydrogen electrodes were assessed and compared to the state-of-the-art hydrogen electrode that is currently being used in nickel-hydrogen batteries. These electrodes were evaluated by scanning electron microscopy and standard electrochemical polarization measurements. Production variables such as Teflon content and platinum catalyst loading were considered in order to assess various hydrogen electrodes with regard to the different electrode manufacturing processes.

Charleston, Jo Ann↗

So ware-Defined Network Solutions for Science Scenarios: Performance Testing Framework and Measurements

High-performance scientific work flows utilize supercomputers, scientific instruments, and large storage systems. Their executions require fast setup of a small number of dedicated network connections across the geographically distributed facility sites. We present Software-Defined Network (SDN) solutions consisting of site daemons that use dpctl, Floodlight, ONOS, or OpenDaylight controllers to set up these connections. The development of these SDN solutions could be quite disruptive to the infrastructure, while requiring a close coordination among multiple sites; in addition, the large number of possible controller and device combinations to investigate could make the infrastructure unavailable to regular users for extended periods of time. In response, we develop a Virtual Science Network Environment (VSNE) using virtual machines, Mininet, and custom scripts that support the development, testing, and evaluation of SDN solutions, without the constraints and expenses of multi-site physical infrastructures; furthermore, the chosen solutions can be directly transferred to production deployments. By complementing VSNE with a physical testbed, we conduct targeted performance tests of various SDN solutions to help choose the best candidates. In addition, we propose a switching response method to assess the setup times and throughput performances of different SDN solutions, and present experimental results that show their advantages and limitations.

Settlemyer, Bradley↗

Technical assessment of cryo-compressed hydrogen storage tank systems for automotive applications.

On-board and off-board performance and cost of cryo-compressed hydrogen storage are assessed and compared to the targets for automotive applications. The on-board performance of the system and high-volume manufacturing cost were determined for liquid hydrogen refueling with a single-flow nozzle and a pump that delivers liquid H{sub 2} to the insulated cryogenic tank capable of being pressurized to 272 atm. The off-board performance and cost of delivering liquid hydrogen were determined for two scenarios in which hydrogen is produced by central steam methane reforming (SMR) or by central electrolysis. The main conclusions are that the cryo-compressed storage system has the potential of meeting the ultimate target for system gravimetric capacity, mid-term target for system volumetric capacity, and the target for hydrogen loss during dormancy under certain conditions of minimum daily driving. However, the high-volume manufacturing cost and the fuel cost for the SMR hydrogen production scenario are, respectively, 2-4 and 1.6-2.4 times the current targets, and the well-to-tank efficiency is well short of the 60% target specified for off-board regenerable materials.

08 HYDROGEN↗

A New Lamination and doping Concepts for Enhanced Li – S Battery Performance

Lithium ion batteries (LIBs) clearly dominated the area of high-energy storage systems for the past decade with significant research and development activity focused on the development of cathode and anode materials to maximize the specific energy storage, stability, and cycle life of the batteries. However, with the increasing demand in the EV industry for low cost, low weight, and high-energy storage batteries to meet the EV everywhere grand challenge, the current focus of research has shifted towards the development of lithium sulfur batteries (LSB) owing to the high theoretical specific capacity exhibited by sulfur compared to other cathode materials currently available. Li–S battery shows a theoretical capacity of 1675 mAh/g corresponding to the formation of Li2S which makes sulfur a promising electrode to replace the layered transition metal oxides (~150 mAh/g) and LiFePO4 (~170 mAh/g) hitherto deployed in present LIB systems. Moreover, the abundance of sulfur in the earth’s crust makes it a more economical and highly attractive proposition compared to currently existing cathodes. Despite advantages of sulfur, the existing Li-S battery technology display poor cyclability, low coulombic efficiency (CE) and very low cycle life due to the following issues: 1. Polysulfide (PS) dissolution; 2. Sluggish kinetics of PS to Li2S conversion; 3. High PS diffusivity in the electrolyte; 4. Insulating nature or poor conductivity of sulfur/Li2S; 5. Volumetric expansion/contraction of sulfur; 6. Shuttling of PS along with Li+. These issues result in loss of sulfur causing mechanical disintegration, surface passivation of both anode and cathode, thereby decreasing the specific capacity and columbic efficiency (CE). Present generation sulfur cathodes also show low specific storage capacity, very poor charging rates and low loading densities. Research is needed to overcome the issues impeding Li-S battery technology development.

25 ENERGY STORAGE↗

Active Storage with Analytics Capabilities and I/O Runtime System for Petascale Systems

Computational scientists must understand results from experimental, observational and computational simulation generated data to gain insights and perform knowledge discovery. As systems approach the petascale range, problems that were unimaginable a few years ago are within reach. With the increasing volume and complexity of data produced by ultra-scale simulations and high-throughput experiments, understanding the science is largely hampered by the lack of comprehensive I/O, storage, acceleration of data manipulation, analysis, and mining tools. Scientists require techniques, tools and infrastructure to facilitate better understanding of their data, in particular the ability to effectively perform complex data analysis, statistical analysis and knowledge discovery. The goal of this work is to enable more effective analysis of scientific datasets through the integration of enhancements in the I/O stack, from active storage support at the file system layer to MPI-IO and high-level I/O library layers. We propose to provide software components to accelerate data analytics, mining, I/O, and knowledge discovery for large-scale scientific applications, thereby increasing productivity of both scientists and the systems. Our approaches include 1) design the interfaces in high-level I/O libraries, such as parallel netCDF, for applications to activate data mining operations at the lower I/O layers; 2) Enhance MPI-IO runtime systems to incorporate the functionality developed as a part of the runtime system design; 3) Develop parallel data mining programs as part of runtime library for server-side file system in PVFS file system; and 4) Prototype an active storage cluster, which will utilize multicore CPUs, GPUs, and FPGAs to carry out the data mining workload.

97 MATHEMATICS AND COMPUTING↗

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↗

Multilevel resistive information storage and retrieval

The present invention relates to resistive random-access memory (RRAM or ReRAM) systems, as well as methods of employing multiple state variables to form degenerate states in such memory systems. The methods herein allow for precise write and read steps to form multiple state variables, and these steps can be performed electrically. Such an approach allows for multilevel, high density memory systems with enhanced information storage capacity and simplified information retrieval.

42 ENGINEERING↗

Enforcing End-to-end I/O Policies for Scientific Workflows using Software-Defined Storage Resource Enclaves

Data-intensive knowledge discovery requires scientific applications to run concurrently with analytics and visualization codes executing in situ for timely output inspection and knowledge extraction. Consequently, I/O pipelines of scientific workflows can be long and complex because they comprise many stages of analytics across different layers of the I/O stack of high-performance computing systems. Performance limitations at any I/O layer or stage can cause an I/O bottleneck resulting in greater than expected end-to-end I/O latency. In this paper, we present the design and implementation of a novel data management infrastructure called Software-Defined Storage Resource Enclaves (SIREN) at system level to enforce end-to-end policies that dictate an I/O pipeline's performance. SIREN provides an I/O performance interface for users to specify the desired storage resources in the context of in-situ analytics. If suboptimal performance of analytics is caused by an I/O bottleneck when data are transferred between simulations and analytics, schedulers in different layers of the I/O stack automatically provide the guaranteed lower bounds on I/O throughput. Lastly, our experimental results demonstrate that SIREN provides performance isolation among scientific workflows sharing multiple storage servers across two I/O layers (burst buffer and parallel file systems) while maintaining high system scalability and resource utilization.

97 MATHEMATICS AND COMPUTING↗

Conditioning of BPM pickup signals for operations of the Duke storage ring with a wide range of single-bunch current

The Duke storage ring is a dedicated driver for the storage ring based oscillator free-electron lasers (FELs), and the High Intensity Gamma-ray Source (HIGS). Furthermore, it is operated with a beam current ranging from about 1 mA to 100 mA per bunch for various operations and accelerator physics studies. High performance operations of the FEL and γ-ray source require a stable electron beam orbit, which has been realized by the global orbit feedback system. As a critical part of the orbit feedback system, the electron beam position monitors (BPMs) are required to be able to precisely measure the electron beam orbit in a wide range of the single-bunch current. However, the high peak voltage of the BPM pickups associated with high single-bunch current degrades the performance of the BPM electronics, and can potentially damage the BPM electronics. A signal conditioning technique using low pass filters is developed to reduce the peak voltage to protect the BPM electronics, and to make the BPMs capable of working with a wide range of single-bunch current. Simulations and electron beam based tests are performed. The results show that the Duke storage ring BPM system is capable of providing precise orbit measurements to ensure highly stable FEL and HIGS operations.

43 PARTICLE ACCELERATORS↗

Scalable I/O Systems via Node-Local Storage: Approaching 1 TB/sec File I/O

In the race to PetaFLOP-speed supercomputing systems, the increase in computational capability has been accompanied by corresponding increases in CPU count, total RAM, and storage capacity. However, a proportional increase in storage bandwidth has lagged behind. In order to improve system reliability and to reduce maintenance effort for modern large-scale systems, system designers have opted to remove node-local storage from the compute nodes. Today's multi-TeraFLOP supercomputers are typically attached to parallel file systems that provide only tens of GBs/s of I/O bandwidth. As a result, such machines have access to much less than 1GB/s of I/O bandwidth per TeraFLOP of compute power, which is below the generally accepted limit required for a well-balanced system. In a many ways, the current I/O bottleneck limits the capabilities of modern supercomputers, specifically in terms of limiting their working sets and restricting fault tolerance techniques, which become critical on systems consisting of tens of thousands of components. This paper resolves the dilemma between high performance and high reliability by presenting an alternative system design which makes use of node-local storage to improve aggregate system I/O bandwidth. In this work, we focus on the checkpointing use-case and present an experimental evaluation of the Scalable Checkpoint/Restart (SCR) library, a new adaptive checkpointing library that uses node-local storage to significantly improve the checkpointing performance of large-scale supercomputers. Experiments show that SCR achieves unprecedented write speeds, reaching a measured 700GB/s of aggregate bandwidth on 8,752 processors and an estimated 1TB/s for a similarly structured machine of 12,500 processors. This corresponds to a speedup of over 70x compared to the bandwidth provided by the 10GB/s parallel file system the cluster uses. Further, SCR can adapt to an environment in which there is wide variation in performance or capacity among the individual node-local storage elements.

99 GENERAL AND MISCELLANEOUS↗

Use of HSM with Relational Databases

Hierarchical storage management (HSM) systems have evolved to become a critical component of large information storage operations. They are built on the concept of using a hierarchy of storage technologies to provide a balance in performance and cost. In general, they migrate data from expensive high performance storage to inexpensive low performance storage based on frequency of use. The predominant usage characteristic is that frequency of use is reduced with age and in most cases quite rapidly. The result is that HSM provides an economical means for managing and storing massive volumes of data. Inherent in HSM systems is system managed storage, where the system performs most of the work with minimum operations personnel involvement. This automation is generally extended to include: backup and recovery, data duplexing to provide high availability, and catastrophic recovery through use of off-site storage.

Breeden, Randall↗

Chameleon: An Adaptive Wear Balancer for Flash Clusters

NAND flash-based Solid State Devices (SSDs) offer the desirable features of high performance, energy efficiency, and fast growing capacity. Thus, the use of SSDs is increasing in distributed storage systems. A key obstacle in this context is that the natural unbalance in distributed I/O workloads can result in wear imbalance across the SSDs in a distributed setting. This, in turn can have significant impact on the reliability, performance, and lifetime of the storage deployment. Extant load balancers for storage systems do not consider SSD wear imbalance when placing data, as the main design goal of such balancers is to extract higher performance. Consequently, data migration is the only common technique for tackling wear imbalance, where existing data is moved from highly loaded servers to the least loaded ones. In this paper, we explore an innovative holistic approach, Chameleon, that employs data redundancy techniques such as replication and erasure-coding, coupled with endurance-aware write offloading, to mitigate wear level imbalance in distributed SSD-based storage. Chameleon aims to balance the wear among different flash servers while meeting desirable objectives of: extending life of flash servers; improving I/O performance; and avoiding bottlenecks. Evaluation with a 50 node SSD cluster shows that Chameleon reduces the wear distribution deviation by 81% while improving the write performance by up to 33%.

Zhao, Nannan↗

Development and Performance Evaluation of High Temperature Concrete for Thermal Energy Storage for Solar Power Generation

Thermal energy can be stored by the mechanism of sensible or latent heat or heat from chemical reactions. Sensible heat is the means of storing energy by increasing the temperature of the solid or liquid. Since the concrete as media cost per kWh thermal is $1, this seems to be a very economical material to be used as a TES. This research is focused on extending the concrete TES system for higher temperatures (500 °C to 600 °C) and increasing the heat transfer performance using novel construction techniques. To store heat at high temperature special concretes are developed and tested for its performance. The storage capacity costs of the developed concrete is in the range of $0.91-$3.02/kWh thermal . Two different storage methods are investigated. In the first one heat is transported using molten slat through a stainless steel tube and heat is transported into concrete block through diffusion. The cost of the system is higher than the targeted DOE goal of $15/kWht hermal . The increase in cost of the system is due to stainless steel tube to transfer the heat from molten salt to the concrete blocks.The other method is a one-tank thermocline system in which both the hot and cold fluid occupy the same tank resulting in reduced storage tank volume. In this model, heated molten salt enters the top of the tank which contains a packed bed of quartzite rock and silica sand as the thermal energy storage (TES) medium. The single-tank storage system uses about half the salt that is required by the two-tank system for a required storage capacity. This amounts to a significant reduction in the cost of the storage system. The single tank alternative has also been proven to be cheaper than the option which uses large concrete modules with embedded heat exchangers. Using computer models optimum dimensions are determined to have an round trip efficiency of 84%. Additionally, the cost of the structured concrete thermocline configuration provides the TES capacity cost of $33.80$/kWh thermal compared with $30.04/kWhthermal for a packed-bed thermocline (PBTC) configuration and $46.11/kWh thermal for a two-tank liquid configuration.

14 SOLAR ENERGY↗

Server-side Log Data Analytics for I/O Workload Characterization and Coordination on Large Shared Storage Systems

Inter-application I/O contention and performance interference have been recognized as severe problems. In this work, we demonstrate, through measurement from Titan (world s No. 3 supercomputer), that high I/O variance co-exists with the fact that individual storage units remain under-utilized for the majority of the time. This motivates us to propose AID, a system that performs automatic application I/O characterization and I/O-aware job scheduling. AID analyzes existing I/O traffic and batch job history logs, without any prior knowledge on applications or user/developer involvement. It identifies the small set of I/O-intensive candidates among all applications running on a supercomputer and subsequently mines their I/O patterns, using more detailed per-I/O-node traffic logs. Based on such auto- extracted information, AID provides online I/O-aware scheduling recommendations to steer I/O-intensive applications away from heavy ongoing I/O activities. We evaluate AID on Titan, using both real applications (with extracted I/O patterns validated by contacting users) and our own pseudo-applications. Our results confirm that AID is able to (1) identify I/O-intensive applications and their detailed I/O characteristics, and (2) significantly reduce these applications I/O performance degradation/variance by jointly evaluating out- standing applications I/O pattern and real-time system l/O load.

Liu, Y.↗