Search NASA⌕ Search

SEARCH · Search NASA

Results for “server efficiency”

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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2014

Web-based, GPU-accelerated, Monte Carlo simulation and visualization of indirect radiation imaging detector performance

Purpose: Monte Carlo simulations play a vital role in the understanding of the fundamental limitations, design, and optimization of existing and emerging medical imaging systems. Efforts in this area have resulted in the development of a wide variety of open-source software packages. One such package, hybridMANTIS, uses a novel hybrid concept to model indirect scintillator detectors by balancing the computational load using dual CPU and graphics processing unit (GPU) processors, obtaining computational efficiency with reasonable accuracy. In this work, the authors describe two open-source visualization interfaces, webMANTIS and visualMANTIS to facilitate the setup of computational experiments via hybridMANTIS. Methods: The visualization tools visualMANTIS and webMANTIS enable the user to control simulation properties through a user interface. In the case of webMANTIS, control via a web browser allows access through mobile devices such as smartphones or tablets. webMANTIS acts as a server back-end and communicates with an NVIDIA GPU computing cluster that can support multiuser environments where users can execute different experiments in parallel. Results: The output consists of point response and pulse-height spectrum, and optical transport statistics generated by hybridMANTIS. The users can download the output images and statistics through a zip file for future reference. In addition, webMANTIS provides a visualization window that displays a few selected optical photon path as they get transported through the detector columns and allows the user to trace the history of the optical photons. Conclusions: The visualization tools visualMANTIS and webMANTIS provide features such as on the fly generation of pulse-height spectra and response functions for microcolumnar x-ray imagers while allowing users to save simulation parameters and results from prior experiments. The graphical interfaces simplify the simulation setup and allow the user to go directly from specifying input parameters to receiving visual feedback for the model predictions.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2017

Structural insights into the interaction of the conserved mammalian proteins GAPR-1 and Beclin 1, a key autophagy protein

Mammalian Golgi-associated plant pathogenesis-related protein 1 (GAPR-1) is a negative autophagy regulator that binds Beclin 1, a key component of the autophagosome nucleation complex. Beclin 1 residues 267–284 are required for binding GAPR-1. Here, sequence analyses, structural modeling, mutagenesis combined with pull-down assays, X-ray crystal structure determination and small-angle X-ray scattering were used to investigate the Beclin 1–GAPR-1 interaction. Five conserved residues line an equatorial GAPR-1 surface groove that is large enough to bind a peptide. A model of a peptide comprising Beclin 1 residues 267–284 docked onto GAPR-1, built using the CABS-dock server, indicates that this peptide binds to this GAPR-1 groove. Mutation of the five conserved residues lining this groove, H54A/E86A/G102K/H103A/N138G, abrogates Beclin 1 binding. The 1.27 Å resolution X-ray crystal structure of this pentad mutant GAPR-1 was determined. Comparison with the wild-type (WT) GAPR-1 structure shows that the equatorial groove of the pentad mutant is shallower and more positively charged, and therefore may not efficiently bind Beclin 1 residues 267–284, which include many hydrophobic residues. Both WT and pentad mutant GAPR-1 crystallize as dimers, and in each case the equatorial groove of one subunit is partially occluded by the other subunit, indicating that dimeric GAPR-1 is unlikely to bind Beclin 1. SAXS analysis of WT and pentad mutant GAPR-1 indicates that in solution the WT forms monomers, while the pentad mutant is primarily dimeric. Thus, changes in the structure of the equatorial groove combined with the improved dimerization of pentad mutant GAPR-1 are likely to abrogate binding to Beclin 1.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Adaptive stabilization of quantum circuits executed on unstable devices

Conventional computers have evolved to device components that demonstrate failure rates of 10 −17 or less, while current quantum computing devices typically exhibit error rates of 10 −2 or greater. This raises concerns about the reliability and reproducibility of the results obtained from quantum computers. The problem is highlighted by experimental observation that today’s NISQ devices are inherently unstable. Remote quantum cloud servers typically do not provide users with an ability to calibrate the device themselves. Using inaccurate characterization data for error mitigation can have devastating impact on reproducibility. In this study, we investigate if one can infer the critical channel parameters dynamically from the noisy binary output of the executed quantum circuit and use it to improve program stability. An open question however is how well does this methodology scale. We discuss the efficacy and efficiency of our adaptive algorithm using canonical quantum circuits such as the uniform superposition circuit. Our metric of performance is the Hellinger distance between the post-stabilization observations and the reference (ideal) distribution.

Dasgupta, Samudra↗
DOE OSTI2023

OCTOKV: An Agile Network-Based Key-Value Storage System with Robust Load Orchestration

In this paper, we propose OctoKV, an innovative network-based key-value storage system. OctoKV addresses the repetitive address translation overhead associated with traditional key-value stores running on file systems on the client side. To mitigate this overhead, we implemented the key-value store on the server side using NVMe-oF and a user-level NVMe driver. In particular, we employed fine-grained resource monitoring and load balancing based on heuristics to optimize I/O performance. OctoKV is deployed on a Linux cluster with Intel SPDK. The extensive evaluation shows that OctoKV achieves lower I/O response times in comparison to traditional approaches where key-value stores run on the client side. Also, the proposed load balancing strategies efficiently enhance I/O response times by equally distributing the workload from overloaded cores to other cores.

Khan, Awais↗
DOE OSTI2018

I/O load balancing for big data HPC applications

High Performance Computing (HPC) big data problems require efficient distributed storage systems. However, at scale, such storage systems often experience load imbalance and resource contention due to two factors: the bursty nature of scientific application I/O; and the complex I/O path that is without centralized arbitration and control. For example, the extant Lustre parallel file system-that supports many HPC centers-comprises numerous components connected via custom network topologies, and serves varying demands of a large number of users and applications. Consequently, some storage servers can be more loaded than others, which creates bottlenecks and reduces overall application I/O performance. Existing solutions typically focus on per application load balancing, and thus are not as effective given their lack of a global view of the system. In this paper, we propose a data-driven approach to load balance the I/O servers at scale, targeted at Lustre deployments. To this end, we design a global mapper on Lustre Metadata Server, which gathers runtime statistics from key storage components on the I/O path, and applies Markov chain modeling and a minimum-cost maximum-flow algorithm to decide where data should be placed. Evaluation using a realistic system simulator and a real setup shows that our approach yields better load balancing, which in turn can improve end-to-end performance.

Paul, Arnab K.↗
DOE OSTI2022

Emerging Threats and Technology Investigation: Industrial Internet of Things - Risk and Mitigation for Nuclear Infrastructure

Industries supporting the global nuclear infrastructure striving for cost savings, expansions in efficiency, and convenience are likely to adopt components (e.g., hardware, software) that comprise the Internet of Things (IoT) and Industrial Internet of Things (IIoT). These devices offer potential improvements along with security challenges. Modern conveniences achieved through application of technology have propagated through society in the form of interconnected devices, from doorbells to microwave ovens, commonly referred to as IoT. IoT devices are often Internet-connected devices that are designed to send data back to a cloud-based server, where a smart phone application then presents device status and control options. Home-based IoT applications carry a different set of risks when compared to a business or security environment, where there is also a history of convenience and interconnection. Industrial settings have long relied on specifically designed Supervisory Control and Data Acquisition (SCADA) systems for process control where IIoT devices are intended to inform business decisions and augment traditional processes. A recent National Institute of Standards and Technology (NIST) report provides a distinction between process control and IIoT in that traditional process control is not replaced by IIoT, but rather IIoT devices are intended to enhance industrial processes through additional monitoring of various sensors and application of data analytics models using artificial intelligence (AI) and machine learning (ML) (Fagan, Marron, et al. 2021) (Ross, et al. 2021).

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗
DOE OSTI2019

UPS: Unified PMU-Data Storage System to Enhance T+D PMU Data Usability

The emerging distribution-level phasor measurement unit (D-PMU) is expected to play an important role in enhancing distribution system observability and situational-awareness. It is a demanding yet challenging task to develop advanced D-PMU data management and analytics tools to improve D-PMU data usability and further promote D-PMU projects deployment. This paper focuses on D-PMU data processing and storage. It presents a brief review of existing D-PMU data storage systems and points out their limitations on high-performance, flexibility, and scalability. To overcome the limitations, a unified PMU-data storage system (UPS) is proposed. Specifically, a unified I/O interface between storage servers and computing jobs is developed to effectively reduce the overhead of managing various computing jobs and data analytics over multiple storage infrastructures; and PMUCache with PMUCache partitioning and PMUCache replacement algorithms are designed to support in-situ data processing and shared distributed data storage and further serve the computing jobs/queries with different Quality of Service (QoS) requirements. Through a series of experiments, it is demonstrated that UPS achieves high performance on fast and big data processing and storage, and efficiently increases the flexibility and scalability of PMU data management systems.

42 ENGINEERING↗
DOE OSTI2025

Using Apptainer in a Pilot-based Distributed Workload

GlideinWMS is a pilot and pressure-based workload manager for distributed scientific computing. Many experiments like CMS and Fermilab’s Neutrino experiments use it to provision elastic clusters for their analysis and simulations, split into close to a million concurrent jobs. Most user jobs require containers, and the pilots use Apptainer to set up the desired platform. For the pilots that run as regular batch jobs, Apptainer is safer, lighter, and easier to use than other containerization solutions. Many images used by the pilots are expanded SIF images distributed via the CernVM-FS: this combination is very efficient. At Fermilab, for example, we store on GitHub Dockerfiles that mimic the platform in the worker nodes of local clusters. GitHub workflows build and push the images to Docker Hub, and a service periodically pulls and converts them to the expanded SIF images in the CernVM-FS, so the scientists can find a familiar environment everywhere. Apptainer has also been used to run services inside the pilot jobs, like benchmarks that characterize the worker node being used, or a Triton Inference Server that allows sharing a GPU with all the jobs that run in parallel on a node.

Mambelli, Marco [Fermilab] (ORCID:0000000294892681↗
DOE OSTI2020

Streaming Data Reorganization at Scale with DeltaFS Indexed Massive Directories

We report complex storage stacks providing data compression, indexing, and analytics help leverage the massive amounts of data generated today to derive insights. It is challenging to perform this computation, however, while fully utilizing the underlying storage media. This is because, while storage servers with large core counts are widely available, single-core performance and memory bandwidth per core grow slower than the core count per die. Computational storage offers a promising solution to this problem by utilizing dedicated compute resources along the storage processing path. We present DeltaFS Indexed Massive Directories (IMDs), a new approach to computational storage. DeltaFS IMDs harvest available (i.e., not dedicated) compute, memory, and network resources on the compute nodes of an application to perform computation on data. We demonstrate the efficiency of DeltaFS IMDs by using them to dynamically reorganize the output of a real-world simulation application across 131,072 CPU cores. DeltaFS IMDs speed up reads by 1,740x while only slightly slowing down the writing of data during simulation I/O for in situ data processing.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Graph Neural Network-based Tracking as a Service

Recent studies have shown promising results for track finding in dense environments using Graph Neural Network (GNN)-based algorithms. However, GNN-based track finding is computationally slow on CPUs, necessitating the use of coprocessors to accelerate the inference time. Additionally, the large input graph size demands a large device memory for efficient computation, a requirement not met by all computing facilities used for particle physics experiments, particularly those lacking advanced GPUs. Furthermore, deploying the GNN-based track-finding algorithm in a production environment requires the installation of all dependent software packages, exclusively utilized by this algorithm. These computing challenges must be addressed for the successful implementation of GNN-based track-finding algorithm into production settings. In response, we introduce a ``GNN-based tracking as a service'' approach, incorporating a custom backend within the NVIDIA Triton inference server to facilitate GNN-based tracking. This paper presents the performance of this approach using the Perlmutter supercomputer at NERSC.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2018

Big Data Mining for Assessing Calibration of Building Energy Models

Residential and commercial buildings in China, India, the United States (US), United Kingdom (UK), and Italy consume 39-45% of each nation's primary energy. Building energy models can be used to automatically optimize the return-on-investment for retrofits to improve a building’s energy efficiency. However, with an average of 3,000 building descriptors necessary to accurately simulate a single building, there is a market need to reduce the transaction cost for creating a more robust model for simulating every building in a city and accurately estimate savings prior to capital expenditures.We used two of the world’s fastest supercomputers, assembled unique datasets, and developed innovative algorithms for big data mining to assess different methods to create an accurate building energy model. The team has leveraged a total of eight high performance computing resources and 218 servers to analyze the best methods, metrics, and algorithms for creating an accurate building energy model beyond current industry standards necessary for private-sector financing. The project developed the world’s fastest buildings simulator, has completed over 8 million simulations totaling over 300TB, and mined this data with over 130,000 parallel artificial intelligence algorithms. This was used to quantify accuracy of AI-developed calibration algorithms with results that surpass industry standard guidelines and can identify individual building parameters to between 15% and 32% of their actual value.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2023

Self-Sustainable IoT-Based Remote Sensing Powered by Energy Harvesting Using Stacked Piezoelectric Transducer and Thermoelectric Generator

We propose a self-powered remote multi-sensing system for traffic sensing which is powered by the collective energy harvested from the mechanical vibration of the road caused by the passing vehicles and from the temperature gradient between the asphalt of the road and the soil underneath. A stacked piezoelectric transducer converts mechanical vibrations into electrical energy and a thermoelectric generator harvests the thermal energy from the thermal gradient. Electrical energy signals from the stacked piezoelectric transducer and the thermoelectric generators are converted into usable DC power to recharge the battery using AC-DC and DC-DC converters working simultaneously. The multi-sensing system comprises an embedded system with a microcontroller that acquires data from the sensors and sends the sensory data to an IoT transceiver which transmits the data as RF packets to an ethernet gateway. The gateway converts the RF packets into Internet Protocol (IP) packets and sends them to a remote server. Laboratory and road-testing results showed over 98% sensory data accuracy with the system functioning solely powered by the energy harvested from the alternative energy sources. The successful maximum transmission distance obtained between the IoT, and the gateway was approximately 1 mile, which is a considerable transmission distance achieved in an urban environment. Successful operation of the self-powered multi-sensing system under both laboratory and road conditions contributes considerably to the fields of energy harvesting and self-powered remote sensing systems. The energy flow chart and efficiency for the steps in the system were found to be mechanical power from vehicles to the energy harvester of 0.25%, stacked PZT transducer efficiency was found to be 37%, and for the TEGs the efficiency is 11%. AC-to-DC and DC-to-DC converters’ efficiencies were found to be 90% and 11%. The wireless communication RF transceiver efficiency was found to be 62.5%.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2016

Plug and Play PV Systems for American Homes

The core objectives of the Plug & Play PV Systems Project were to develop a PV system that can be installed on a residential rooftop for less than $1.50/W in 2020, and in less than 10 hours (from point of purchase to commissioning). The Fraunhofer CSE team’s approach to this challenge involved a holistic approach to system design – hardware and software – that make Plug & Play PV systems: • Quick, easy, and safe to install • Easy to demonstrate as code compliant • Permitted, inspected, and interconnected via an electronic process Throughout the three years of work during this Department of Energy SunShot funded project, the team engaged in a substantive way with inspectional services departments and utilities, manufacturers, installers, and distributors. We received iterative feedback on the system design and on ideas for how such systems can be commercialized. This ultimately led us to conceiving of Plug & Play PV Systems as a framework, with a variety of components compatible with the Plug & Play PV approach, including string or microinverters, conventional modules or emerging lightweight modules. The framework enables a broad group of manufacturers to participate in taking Plug & Play PV Systems to market, and increases the market size for such systems. Key aspects of the development effort centered on the system hardware and associated engineering work, the development of a Plug & Play PV Server to enable the electronic permitting, inspection and interconnection process, understanding the details of code compliance and, on occasion, supporting applications for modifications to the code to allow lightweight modules, for example. We have published a number of papers on our testing and assessment of novel technologies (e.g., adhered lightweight modules) and on the electronic architecture.

14 SOLAR ENERGY↗
DOE OSTI2020

Smart Composite Pressure Vessels (SCPV) with Integrated Health Monitoring

The U.S. Department of Energy (DOE) is promoting and developing more energy efficient and environmentally friendly technologies that will enable America to use less petroleum. Hydrogen fuel cells – which directly convert the chemical energy in hydrogen to electricity with only water and heat as byproducts – are a very attractive solution that can enable this to happen. To date, DOE's efforts have culminated in commercial demonstration of on-board vehicular hydrogen storage systems that can allow for a driving range of greater than 300 miles. This requires storing 5 Kgs of hydrogen onboard a light vehicle. In order to store this quantity of hydrogen, the hydrogen gas needs to be stored in a composite overwrapped pressure vessel (COPV) at a very high internal pressure. The objective of the program was to demonstrate continuous and predictable health-monitoring of composite pressure vessels. A higher confidence in the operational safety of the vessels will lead to reduced burst factor of safety imposed by regulatory standards and hence will help reduce the structural wall thickness that drives the cost of the vessel. Highly optimized Type III (metal lined) and Type IV (polymer lined) COPVs that are manufactured using filament winding process have been designed and qualified for the above mentioned application. However, the main structural component of the COPVs is carbon fiber and the high cost of carbon fiber composite in a pressure vessel is a primary challenge in reducing the cost of gaseous hydrogen storage. Continuous and remote monitoring of structural health of the COPVs as well as optimization of the strength translation of carbon fibers have the potential to allow for reduced factor of safety, thereby reduced amount of carbon and associated cost of the vessel. In the current program, the project team including Steelhead Composites (SHC), University of Tennessee, Knoxville (UTK), Teijin Carbon America, Oak Ridge National Laboratory (ORNL) and LUNA designed, fabricated, and tested smart composite pressure vessels with integrated sensors. Iterative loops of design and testing using coupons, subscale STEB vessels and full size vessels proved that a new generation of high performance carbon fiber can be used for efficient design of Type 3 vessels for H2 storage. Novel analysis techniques were developed to predict the initiation and propagation of interlaminar damage inside the composite shell due to impact damage, a real threat in practical operation. Such an analysis scheme is typically not used in tank design but is an essential tool for health monitoring of composite vessels. Remote sensing of the key signatures of the tank’s operating parameters such as pressure, acceleration and humidity was demonstrated using a unique device that can wirelessly transmit and stream the data to a remote server. Fiber optic sensors were successfully integrated during fabrication of the tanks. These sensors provide a wealth of information regarding the structural health of the vessel when it is subsequently pressurized or subjected to impact damage. Excellent correlation was demonstrated between the fiber optic sensor and mechanical strain gage data, and between the measurements and analytical predictions.

08 HYDROGEN↗
DOE OSTI2024

AEcroscopy: A Software–Hardware Framework Empowering Microscopy Toward Automated and Autonomous Experimentation

Microscopy has been pivotal in improving the understanding of structure-function relationships at the nanoscale and is by now ubiquitous in most characterization labs. However, traditional microscopy operations are still limited largely by a human-centric click-and-go paradigm utilizing vendor-provided software, which limits the scope, utility, efficiency, effectiveness, and at times reproducibility of microscopy experiments. Here, in this work, a coupled software–hardware platform is developed that consists of a software package termed AEcroscopy (short for Automated Experiments in Microscopy), along with a field-programmable-gate-array device with LabView-built customized acquisition scripts, which overcome these limitations and provide the necessary abstractions toward full automation of microscopy platforms. The platform works across multiple vendor devices on scanning probe microscopes and electron microscopes. It enables customized scan trajectories, processing functions that can be triggered locally or remotely on processing servers, user-defined excitation waveforms, standardization of data models, and completely seamless operation through simple Python commands to enable a plethora of microscopy experiments to be performed in a reproducible, automated manner. This platform can be readily coupled with existing machine-learning libraries and simulations, to provide automated decision-making and active theory-experiment optimization to turn microscopes from characterization tools to instruments capable of autonomous model refinement and physics discovery.

47 OTHER INSTRUMENTATION↗
DOE OSTI2021

UEMtomaton: A Source-Available Platform to Aid in Start-up of Ultrafast Electron Microscopy Labs

The steady rise in the number of ultrafast electron microscopy (UEM) labs, in addition to the opacity and lack of detailed descriptions of current approaches that would enable point-by-point construction, has created an opportunity for sharing common methods and instrumentation for (for example) automating data acquisition to assist in efficient lab start-up and to learn about common and robust protocols. In the spirit of open sharing of methods, we provide here a description of an entry-level method and user interface (UI) for automating UEM experiments, and we provide access to the source code and scripts (source-available) for ease of implementation or as a starting reference point for those entering or seeking to enter the field (https://github.com/CEMSFlannigan/UEMtomaton/releases/tag/v1.0). Core instrumentation and physical connections in the UEM lab at Minnesota are described. Interface communication schemes consisting of duo server-client pairs between critical components – the optical delay stage and the UEM digital camera – are presented, with emphasis placed on describing the logic and communications sequence designed to conduct automated series acquisitions. An application designed and programmed with C++/CLI as Windows Forms in Microsoft Visual Studio – dubbed UEMtomaton – is also presented. Key to the UI layout is centralization of the automation tasks and establishment of communication within the software rather than by interfacing with each individual workstation. It is our hope that this note provides useful insight for current and future UEM researchers, particularly with respect to generalizability and portability of the approach to emerging labs. Here, we note that while this basic, entry-level approach is certainly not the most sophisticated or comprehensive of those currently in use, we feel there is nevertheless value in clearly communicating a proven straightforward method to hopefully lower the barrier to entry into the field.

47 OTHER INSTRUMENTATION↗
DOE OSTI2020

Evaluating Modern GPU Interconnect: PCIe, NVLink, NV-SLI, NVSwitch and GPUDirect

High performance multi-GPU computing becomes an inevitable trend due to the ever-increasing demand on computation capability in emerging domains such as deep learning, big data and planet-scale simulations. However, the lack of deep understanding on how modern GPUs can be connected and the real impact of state-of-the-art interconnect technology on multi-GPU application performance become a hurdle. In this paper, we fill the gap by conducting a thorough evaluation on five latest types of modern GPU interconnects: PCIe, NVLink-V1, NVLink-V2, NVLink-SLI and NVSwitch, from six high-end servers and HPC platforms: NVIDIA P100-DGX-1, V100-DGX-1, DGX-2, OLCF’s SummitDev and Summit supercomputers, as well as an SLI-linked system with two NVIDIA Turing RTX-2080 GPUs. Based on the empirical evaluation, we have observed four new types of GPU communication network NUMA effects: three are triggered by NVLink’s topology, connectivity and routing, while one is caused by PCIe chipset design issue. These observations indicate that, for a multi-GPU application running in a multi-GPU node, choosing the right GPU combination can impose considerable impact on GPU communication efficiency, as well as an application’s overall performance. Our evaluation can be leveraged in building practical multi-GPU performance models, which are vital for GPU task allocation, scheduling and migration in a shared environment (e.g., AI cloud and HPC centers), as well as communication-oriented performance tuning.

Performance Evaluation, GPU, Interconnect, NUMA, P↗
DOE OSTI2017

Subspace-Aware Index Codes

In this paper, we generalize the well-known index coding problem to exploit the structure in the source-data to improve system throughput. In many applications (e.g., multimedia), the data to be transmitted may lie (or can be well approximated) in a low-dimensional subspace. We exploit this low-dimensional structure of the data using an algebraic framework to solve the index coding problem (referred to as subspace-aware index coding) as opposed to the traditional index coding problem which is subspace-unaware. Also, we propose an efficient algorithm based on the alternating minimization approach to obtain near optimal index codes for both subspace-aware and -unaware cases. In conclusion, our simulations indicate that under certain conditions, a significant throughput gain (about 90%) can be achieved by subspace-aware index codes over conventional subspace-unaware index codes.

97 MATHEMATICS AND COMPUTING↗