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 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
DOE OSTI2018

Wide Bandgap Semiconductor Opportunities in Power Electronics

The report objective is to explore the Wide Bandgap (WBG) Power Electronics (PE) market, applications, and potential energy savings in order to identify key areas where further resources and investments of the U.S. Department of Energy’s Office of Energy Efficiency and Renewable Energy (DOE EERE) would have the most impact on U.S. competiveness. After considering the current market, several potential near-term application areas were identified as having significant market and energy savings potential with respect to clean energy applications: (1) data centers (uninterruptible power supplies and server power supplies); (2) renewable energy generation (photovoltaic-solar and wind); (3) motor drives (industrial, commercial and residential); (4) rail traction; and, (5) hybrid and electric vehicles (traction and charging). After the initial explorative analyses, it became clear that, SiC, not GaN, would be the principal WBG power device material for the chosen markets in the near future. Therefore, while GaN is discussed when appropriate, this report focuses on SiC devices, other WBG applications (e.g., solid-state transformers, combined heat and power, medical, and wireless power), the GaN market, and GaN specific applications (e.g., LiDAR, 5G) will be explored at a later date. In addition to the market, supply and value chain analyses addressed in Section 1 of this report, a SWOT (Strength, Weakness, Opportunity, Threat) analysis and potential energy savings analysis was conducted for each application area to identify the major potential WBG application area(s) with a U.S. competitiveness opportunity in the future.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2024

OASIS: Offsetting Active Reconstruction Attacks in Federated Learning

Federated Learning (FL) has garnered significant attention for its potential to protect user privacy while enhancing model training efficiency. For that reason, FL has found its use in various domains, from health care to industrial engineering, especially where data cannot be easily exchanged due to sensitive information or privacy laws. However, recent research has demonstrated that FL protocols can be easily compromised by active reconstruction attacks executed by dishonest servers. These attacks involve the malicious modification of global model parameters, allowing the server to obtain a verbatim copy of users' private data by inverting their gradient updates. Tackling this class of attack remains a crucial challenge due to the strong threat model. In this paper, we propose a defense mechanism, namely OASIS, based on image augmentation that effectively counteracts active reconstruction attacks while preserving model performance. We first uncover the core principle of gradient inversion that enables these attacks and theoretically identify the main conditions by which the defense can be robust regardless of the attack strategies. We then construct our defense with image augmentation showing that it can undermine the attack principle. Comprehensive evaluations demonstrate the efficacy of the defense mechanism highlighting its feasibility as a solution.

deep neural networks↗
DOE OSTI2014

Next Generation Environmentally-Friendly Driving Feedback Systems Research and Development

The objective of this project is to design, develop, and demonstrate a next-generation, federal safety- and emission-complaint driving feedback system that can be deployed across the existing vehicle fleet and improve fleet average fuel efficiency by at least 2%. The project objective was achieved with the driving feedback system that encourages fuel-efficient vehicle travel and operation through: 1) Eco-Routing Navigation module that suggests the most fuel-efficient route from one stop to the next, 2) Eco-Driving Feedback module that provides sensible information, recommendation, and warning regarding fuel-efficient vehicle operation, and 3) Eco-Score and Eco-Rank module that provides a means for driving performance tracking, self-evaluation, and peer comparison. The system also collects and stores vehicle travel and operation data, which are used by Algorithm Updating module to customize the other modules for specific vehicles and adapts them to specific drivers over time. The driving feedback system was designed and developed as an aftermarket technology that can be retrofitted to vehicles in the existing fleet. It consists of a mobile application for smart devices running Android operating system, a vehicle on-board diagnostics connector, and a data server. While the system receives and utilizes real-time vehicle and engine data from the vehicle’s controller area network bus through the vehicle’s on-board diagnostic connector, it does not modify or interfere with the vehicle’s controller area network bus, and thus, is in compliance with federal safety and emission regulations. The driving feedback system was demonstrated and then installed on 45 vehicles from three different fleets for field operational test. These include 15 private vehicles of the general public, 15 pickup trucks of the California Department of Transportation that are assigned to individual employees for business use, and 15 shuttle buses of the Riverside Transit Agency that are used for paratransit service. Detailed vehicle travel and operation data including route taken, driving speed, acceleration, braking, and the corresponding fuel consumption, were collected both before and during the test period. The data analysis results show that the fleet average fuel efficiency improvements for the three fleets with the use of the driving feedback system are in the range of 2% to 9%. The economic viability of the driving feedback system is high. A fully deployed system would require capital investment in smart device ($150-$350) and on-board diagnostics connector ($50-$100) as well as paying operating costs for wireless data plan and subscription fees ($20-$30 per month) for connecting to the data server and receiving various system services. For individual consumers who already own a smart device (such as smartphone) and commercial fleets that already use some kind of telematics services, the costs for deploying this driving feedback system would be much lower.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2024

Fast spark-detection system for GEM detectors

The sPHENIX experiment is currently under commissioning at the Relativistic Heavy Ion Collider (RHIC) at Brookhaven National Lab (BNL). The Time Projection Chamber (TPC) serves as a tracking detector for the experiment. The sPHENIX TPC uses a stack of four Gas Electron Multipliers (GEMs) as a gain stage in a reduced ion back-flow configuration. To mitigate the damaging effects of sparks in the GEMs, an online spark monitoring system was created. Once the system detects a spark in a GEM stack, the voltages across the GEMs in that stack can be lowered to prevent further sparking without affecting the gain and efficiency of the other modules. Spark signals are coupled out of the GEM stack by a pick-off capacitor attached to the bottom of the bottom GEM. Custom PCBs convert the oscillatory spark signal into a mono-polar pulse that is then digitized. The software then saves the waveform in a server and uses experimentally derived thresholds to determine how to react. As a result, the system has so far proven to be effective at improving the stability of the TPC and preventing damaging events while collecting cosmic ray data.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2022

A New Integrated Analysis Suite for Fast-Ion Study in KSTAR

Here, an integrated workflow for fast-ion analysis was developed by adapting the One Modeling Framework for Integrated Task (OMFIT) workflow manager to support a standard and unified analysis platform for KSTAR users. The newly established analysis suite offers a graphical user interface–based workflow to enable users to readily access and handle experimental data archived in various data formats and servers. Further, users can analyze the data by importing modules designed for conducting certain tasks, such as profile fitting, equilibrium reconstruction, and postprocessing of tokamak data. The procedures for preparing the inputs for fast-ion simulations are streamlined by a common workflow manager, which enables the parallel processing of various tasks to efficiently analyze large fast-ion datasets. The OMFIT platform comprises a flexible Python-based application that enables users to freely manipulate the Python scripts for applications that are unavailable in the standard workflow. The framework also offers mapping tools to translate the output data into the Integrated Modeling and Analysis Suite format to maintain application compatibility for future ITER burning plasma experiments.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2018

Belle II Conditions Database

The Belle II experiment at KEK is preparing for taking first collision data in early 2018. For the success of the experiment it is essential to have information about varying conditions available to systems worldwide in a fast and efficient manner that is straightforward for both the user and maintainer. The Belle II Conditions Database was designed to make maintenance as easy as possible. To this end, a HTTP REST service was developed with industry-standard tools such as Swagger for the API interface development, Payara for the Java EE application server, and the Hazelcast in-memory data grid for support of scalable caching as well as transparent distribution of the service across multiple sites. On the client side, the online and offline software has to be able to obtain conditions data from the Belle II Conditions Database in a robust and reliable way under very different situations. As such the client side interface to the Belle II Conditions Database has been designed with a variety of access mechanisms which allow the software to be used with and without an internet connection. Different methods to access the payload information are implemented to allow for a high level of customization per site and to simplify testing of new payloads locally. Changes to the conditions data are usually handled transparently but users can actively check whether an object has changed or register callback functions to be called whenever a conditions data object is updated. In addition a command line user interface has been developed to simplify inspection and modification of the database contents.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Securing Federated Learning Against Active Reconstruction Attacks

Federated Learning (FL) has amassed notable attention for its ability to preserve user privacy while emphasizing the retainment of model training efficiency. Due to this potential, FL has been integrated in many domains, such as healthcare, finance, law, and industrial engineering, where data cannot be easily exchanged due to sensitive information and strict privacy laws. However, current research has indicated that FL protocols are easily compromised by active data reconstruction attacks employed by actively dishonest servers. The malicious modification of global model parameters allows an actively dishonest server to obtain a direct copy of users’ private data via gradient inversion. Here, this class of attacks is highly underexplored and continues to be a major challenge due to the intense threat model. In this paper, we propose OASIS as a scalable and modality-agnostic defense based on data augmentation that counteracts active data reconstruction attacks while preserving model performance. To generalize our defense, we uncover the intuition behind gradient inversion that enables these attacks and theoretically establish the conditions by which the defense can be considered robust regardless of attack design. From this, we formulate our defense with data augmentation that illustrates its ability to undermine the attack principle. We evaluate OASIS on five real-world datasets–two image-based (ImageNet and CIFAR100) and three text-based (Wikitext, Stack Overflow, and Shakespeare)–which span diverse uses cases such as vision tasks and language modeling. Comprehensive evaluations on these datasets exhibit the efficacy of OASIS and highlight its feasibility as a solution.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

CPU and memory efficient coherent mode decomposition for the partially coherent x-ray simulations

In this work, the method of the Coherent Mode Decomposition (CMD) is applied to numerical wave propagation calculations for partially-coherent X-rays, using the Fourier optics and compatible methods. Its CPU and memory efficiency is discussed in various cases of the wavefront at the source and the beam waist. With the absence of the quadratic phase terms, the required sampling density of the electric fields is effectively reduced. The problem size is thus moderate and the method is feasible to be implemented on a single-node CPU server. In other cases, the same argument holds with proper treatments of the quadratic phase terms. Tests on CMD and the modes propagation are done for the case of the Coherent Hard X-ray beamline of the National Synchrotron Light Source II, using the Synchrotron Radiation Workshop software. We observe a few hundred or less dominant decomposed modes that resemble the electric fields converge to the wavefront intensity at a high accuracy of over 99%.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Emerging Jets Search, Triton Server Deployment, and Track Quality Development: Machine Learning Applications in High Energy Physics

Machine learning is becoming prevalent in high energy physics, with numerous applications in physics analyses and event reconstruction showing great improvements compared to traditional computing methods. This thesis studies three projects which each propose new avenues for machine learning applications within the high energy physics CMS experiment located at CERN. In the first project, a search for a dark matter signal called “emerging jets” is performed, using graph neural networks to greatly increase sensitivity to the signal’s signature within the data. The result of this dark matter search sets the most stringent exclusion limits to date on theoretical emerging jet models. Motivated by inefficiencies encountered when processing the emerging jet graph neural network at Fermi National Accelerator Laboratory’s computing centers, the second project re-optimizes the computing centers for machine learning inference. This re-optimization uses NVIDIA Triton Inference Servers to process users’ analysis code heterogeneously, therefore achieving high processing throughput and decreasing user time-to-insight. The last project focuses on an upgrade to the CMS experiment’s real-time event selection system which improves physics object reconstruction under harsh processing conditions. A boosted decision tree is used to quickly and efficiently quantify a reconstructed particle’s “track quality” in order to remove particle tracks reconstructed erroneously. In summary, this thesis will not only present examples of how high energy physics can greatly benefit by leveraging machine learning techniques for physics analysis and reconstruction, but will also provide guidance on how the field can prepare for the inevitable increase in machine learning applications.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

HPC Campaign Management: Remote data access with user-defined error bound using ADIOS and ZFP

Remote access to large-scale scientific datasets, like those generated by combustion simulations or other high-performance computing (HPC) applications, presents a significant challenge. Downloading entire datasets is often impractical due to their size and the bandwidth limitations of typical networks. To address this challenge, we propose a novel approach that enables efficient remote access to large datasets distributed across multiple facilities. Our method enables technologies to download only the data values of a select variable, in a select region of interest, to a user-defined accuracy. For this purpose, we extended the ADIOS IO library to provide read functions with user-defined accuracy, a remote data server that understands multidimensional selections of specific variables, steps and accuracy from an ADIOS dataset, and which uses lossy compression on the remote site to reduce the data to be transferred back to the client. In addition, our extension of the ADIOS library collects metadata from multiple datasets in small files called Campaign Archives, which can be shared among project participants on any HPC, cloud or laptop, and which can easily facilitate the discovery of content and pointers to the data location as well as remote access to the data by local tools as if data was local. This feature called Campaign Management, enables a group of scientists to manage related datasets stored in multiple files, across multiple facilities as if it was in a single file/database. We demonstrate the effectiveness of our approach using a 1.5 TB dataset from the S3D combustion simulation on Frontier at the Oak Ridge Leadership Facility. Even a single variable from this dataset, at 64 GB, is too large to be processed on a standard laptop. We show two different reading patterns for 2D plots and 3D visualization, with careful settings that a scientist studying combustion data would do and show that running the same Python scripts on Frontier directly takes comparable time than running them on the local laptop with remote access to the data on Frontier.

Podhorszki, Norbert [ORNL] (ORCID:000000019647542X↗
DOE OSTI2016

Experimental Analysis of File Transfer Rates over Wide-Area Dedicated Connections

File transfers over dedicated connections, supported by large parallel file systems, have become increasingly important in high-performance computing and big data workflows. It remains a challenge to achieve peak rates for such transfers due to the complexities of file I/O, host, and network transport subsystems, and equally importantly, their interactions. We present extensive measurements of disk-to-disk file transfers using Lustre and XFS file systems mounted on multi-core servers over a suite of 10 Gbps emulated connections with 0-366 ms round trip times. Our results indicate that large buffer sizes and many parallel flows do not always guarantee high transfer rates. Furthermore, large variations in the measured rates necessitate repeated measurements to ensure confidence in inferences based on them. We propose a new method to efficiently identify the optimal joint file I/O and network transport parameters using a small number of measurements. We show that for XFS and Lustre with direct I/O, this method identifies configurations achieving 97% of the peak transfer rate while probing only 12% of the parameter space.

Rao, Nageswara S.↗
DOE OSTI2021

Improving Data Center Energy Efficiency Through End-to-End Cooling Modeling and Optimization. Final Report

This report summarizes the development and demonstration of the three features developed for the DOE project “Improving Data Center Energy Efficiency through End-to-End Cooling Modeling and Optimization” (Award No. DE-EE0007688). The development of the three software features, Feature 1: Optimization of Cooling System Operation, Feature 2: Optimization of Airflow Management System, and Feature 3: Simultaneous Optimization of Airflow Management and Cooling Systems, are described first. Feature 1 is implemented in Phase 1 of the project and demonstrates 15% energy savings from cooling system optimization by applying the proposed retrofit solutions. Feature 2 is implemented in Phase 2 and the assessments show cooling energy-saving potential between 19.3% and 54.0%, depending on the energy-saving measures employed. In addition, investigating the energy saving potential for a hypothetical simple data center shows about 6.8% energy savings by optimizing the server load placement. Feature 3 is implemented in Phase 3 and the results show energy savings of 53.4% and 74.6% for the two partner data centers, respectively, compared to the baselines defined in Phase 1. Lastly, the project outcomes including software releases and publications are discussed.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2024

A hardware-in-the-loop (HIL) testbed for cyber-physical energy systems in smart commercial buildings

In recent years, there has been a growing trend toward the development of smart buildings that rely on cyber-physical systems (CPS) to optimize occupant comfort, safety, and energy efficiency. To ensure the reliable and efficient operation of CPS with designed control strategies, it is important to evaluate their performance under various scenarios before deploying them in the real world. This is where a Hardware-in-the-loop (HIL) testbed designed for studying sensor and control-related studies in smart buildings can be highly valuable. With the growing threat of cyber-attacks and physical faults targeting smart buildings, it is essential to ensure the security of building operations. A HIL testbed can emulate cyber-attack and physical fault scenarios, allowing researchers to develop and test threat detection and mitigation algorithms. This enables researchers to identify potential issues and optimize the algorithms in a safe and controlled environment before they are deployed in real-world settings, reducing the risk of failures that can negatively impact occupant comfort, safety, and energy efficiency. Therefore, this paper developed a HIL testbed designed for cyber-physical energy systems (e.g. buildings automation system (BAS)) in smart commercial buildings. The HIL testbed is comprised of a real-time building and Heating, Ventilation, and Air-Conditioning (HVAC) emulator using Modelica-based dynamic models, a set of BAS controllers, and a BAS computer server. The data generation capability of the HIL testbed is demonstrated by tracking normal and faulty operating data in the BAS, as well as monitoring detailed network traffic in the local BAS network. Here, this study further demonstrates the HIL testbed’s capability by conducting case studies on real-time physical fault and cyber-attack experiments using a Department of Energy (DOE) prototype commercial building. It is anticipated that the fully functional HIL testbed will be utilized for a variety of sensor and control-related studies, including but not limited to testing, developing, validating of different HVAC control strategies, fault detection & diagnosis, energy monitoring and analysis, cyber security study, etc.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2019

Data Analytics for Electrical Distribution Systems with Micro PMUs (GMLC 1.4.9 Technical Report)

This report describes how electrical utilities with residential, industrial, commercial and government customers make decisions using Data Analytics (DA) applications and discusses how OpenFMB was leveraged to share that data among disparate types of devices for DA. OpenFMB is a data standard developed by utilities for distributed communication and control of power system assets. Here we explored how OpenFMB can be used for sharing analytics and what those analytics could be for a set of representative grid devices. A review of DA applications performed by electrical utilities and customers is presented. An overview of how the testbed we used was built and configured is summarized. Several experiments which were carried out to explore the capabilities of OpenFMB alongside other data sharing mechanisms for gathering sensor measurements and sharing analytics is also discussed. And finally a comparison of OpenFMB and LBNL’s SPARK framework is summarized. Today’s electrical utilities focus on monitoring the real-time customer consumptions, offering new real-time tariff models based on customer usage habits (rewards and punishments), providing energy peak during peak load times (plan energy generation and distribution), improving the load management for transformers and power lines, and controlling the energy and grid resources efficiently. On the other hand, the DA applications for residential customers are based on modifying the customer electricity usage habit to save money, making accurate and timely decisions for electrical billing. However, the DA applications for industrial, commercial and government customers focus on creating efficient programs to improve the environmental condition (reducing CO₂ emission), developing better load forecasting for industrial and/or commercial activities. In this project, a testbed was built to explore how the OpenFMB framework can be used to distribute data among various types of representative grid edge devices. Micro PMUs (Phasor Measurement Unit) were used to collect and transmit data to an OpenPDC server alongside relays with a framework configured with a system using OpenFMB to collect and transmit data. The testbed was composed of a physical asset based on a 60 Hz AC radial power system constructed using SI-GRID components. The power system consisted of a 3-phase 14 volts line-to-ground (24 volts line-to-line) power source, three 3-phase line emulators, a programmable resistive load bank, two smart relays, two micro PMUs, and a (SCADA) and Phasor Data Concentrator (PDC) computer. This testbed configuration allowed us to perform breaker operation tests collecting data from the micro PMUs and from the relays’ sensors. During the micro PMU breaker operation tests we collected the measured and estimated fundamental voltages, currents, frequency as well as the total true, reactive and apparent power. The displacement power factor from two micro PMUs located in parallel power lines was also used. The software steps for the implementation of the Synchrophasor system are explained in detail in this report. The setting (1-2-3) and data collection (4-5) phases were performed with a free download open source software. In the setting phase, the micro PMUs were set (1), the data stream for each micro PMU was validated, and the connection and configuration files were created (2). The PDC computer was set using the connection and configuration files of the micro PMUs (3). In the data collection phase, the binary data from the micro PMUs was collected (4), and the binary data files of the micro PMUs was converted to analyze the test results (5). OpenFMB was configured to use protocol translators to read Modbus and transform the reading into the OpenFMB data model to be read for DA applications.Our experiments showed that by leveraging the OpenFMB data model and the micro PMUs together we could obtain better situational awareness of network faults, which in some cases could lead to failures in the system and would be less perceivable otherwise. For example, in one experiment the fundamental RMS current angle, and the fundamental displacement power factor (estimated by the ratio between the measured real and apparent total power) had a disturbance at the micro PMU connected to the beginning of the parallel power line because the breaker was opened without the operators or SCADA system’s knowledge, and no current was available. Based on the breaker state scenarios and micro PMU locations, the DA applications using the current angle and displacement power factor from the micro PMUs should be studied in detail to avoid a non-desired measurement that could affect the decision from the DA. Also, the sample rates for PMU, Relay and micro PMU devices were compared. The DA application improved the control and operation between the electrical utilities and their customers (residential, industrial, transportation, commercial and government). The higher the sample rate, the better the quality of the measurement for DA estimations.

42 ENGINEERING↗
DOE OSTI2017

Diving into Petascale Production File Systems through Large Scale Profiling and Analysis

As leadership computing facilities grow their storage capacity into the multi- petabyte range, the number of files and directories leap into the scale of billions. A complete profiling of such a parallel file system in a production environment presents a unique challenge. On one hand, the time, resources, and negative performance impact on production users can make regular profiling difficult. On the other hand, the result of such profiling can yield much needed understanding of the file system's general characteristics, as well as provide insight to how users write and access their data on a grand scale. This paper presents a lightweight and scalable profiling solution that can efficiently walk, analyze, and profile multi-petabyte parallel file systems. This tool has been deployed and is in regular use on very large-scale production parallel file systems at both Oak Ridge National Lab's Oak Ridge Leadership Facility (OLCF) and Lawrence Livermore National Lab's Livermore Computing (LC) facilities. We present the results of our initial analysis on the data collected from these two large-scale production systems, organized into three use cases: (1) file system snapshot and composition, (2) striping pattern analysis for Lustre, and (3) simulated storage capacity utilization in preparation for future file systems. Our analysis shows that on the OLCF file system, over 96% of user files exhibit the default stripe width, potentially limiting performance on large files by underutilizing storage servers and disks. Our simulated block analysis quantitatively shows the space overhead when doing a forklift system migration. It also reveals that due to the difference in system compositions (OLCF vs. LC), we can achieve better performance and space trade-offs by employing different native file system block sizes.

Wang, Feiyi↗
DOE OSTI2024

Dual Channel Dual Staging: Hierarchical and Portable Staging for GPU-Based In-Situ Workflow

In-situ workflows have emerged as an attractive approach for addressing data movement challenges at very large scales. Since GPU-based architectures dominate the HPC landscapes, porting these in-situ workflows, and, specifically, the inter-application data exchange, to GPU-based systems can be challenging. Technologies such as GPUDirect RDMA (GDR), which is typically used for I/O in GPU applications as an optimization that circumvents the CPU overhead, can be leveraged to support bulk data exchanges between GPU applications. However, current GDR design often lacks performance portability across HPC clusters built with different hardware configurations. Furthermore, the local CPU may also be effectively used as an auxiliary communication mechanism to offload data exchanges. In this paper, we present a dual channel dual staging approach for efficient, scalable, and performance-portable inter-application data exchange for in-situ workflows. This approach exploits the data access pattern within in-situ workflows along with the inherent execution asynchrony to accelerate data exchanges and, at the same time, improve performance portability. Specifically, the dual channel dual staging method leverages both the local CPU and the remote data staging server to build a hierarchical joint staging area and uses this staging area to transform blocking inter-application bulk data exchanges into best-effort local data movements between GPU and CPU. The dual channel dual staging is implemented as a portability extension of the Dataspaces-GPU staging framework. We present an experimental evaluation of its performance, portability, and scalability using this implementation on three leadership GPU clusters. The evaluation results demonstrate that the dual channel dual staging method saves up to 75% in data-exchange time compared to host-based, GDR, and alternate portable designs, while maintaining scalability (up to 512 GPUs) and performance portability across the three platforms.

Zhang, Bo [University of Utah]↗
DOE OSTI2019

The Open High Throughput Computing Content Delivery Network

LHC experiments make extensive use of web proxy caches, especially for software distribution via the CernVM File System and for conditions data via the Frontier Distributed Database Caching system. Since many jobs read the same data, cache hit rates are high and hence most of the traffic flows efficiently over Local Area Networks. However, it is not always possible to have local web caches, particularly for opportunistic cases whereexperiments have little control over site services. The Open High Throughput Computing (HTC) Content Delivery Network (CDN), openhtc.io, aims to address this by using web proxy caches from a commercial CDN provider. Cloudflare provides a simple interface for registering DNS aliases of any web server and does reverse proxy web caching on those aliases. The openhtc.io domain is hosted on Cloudflare's free tier CDN which has no bandwidth limit and makes use of data centers throughout the world, so the average performance for clients is much improved compared to reading from CERN or a Tier 1. The load on WLCG servers is also significantly reduced. WLCG Web Proxy Auto Discovery is used to select local web caches when they are available and otherwise select openhtc.io caching. This paper describes the Open HTC CDN in detail and provides initial results from its use for LHC@Home and USCMS opportunistic computing.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2015

Motivation and Design of the Sirocco Storage System Version 1.0.

Sirocco is a massively parallel, high performance storage system for the exascale era. It emphasizes client-to-client coordination, low server-side coupling, and free data movement to improve resilience and performance. Its architecture is inspired by peer-to-peer and victim- cache architectures. By leveraging these ideas, Sirocco natively supports several media types, including RAM, flash, disk, and archival storage, with automatic migration between levels. Sirocco also includes storage interfaces and support that are more advanced than typical block storage. Sirocco enables clients to efficiently use key-value storage or block-based storage with the same interface. It also provides several levels of transactional data updates within a single storage command, including full ACID-compliant updates. This transaction support extends to updating several objects within a single transaction. Further support is provided for con- currency control, enabling greater performance for workloads while providing safe concurrent modification. By pioneering these and other technologies and techniques in the storage system, Sirocco is poised to fulfill a need for a massively scalable, write-optimized storage system for exascale systems. This is version 1.0 of a document reflecting the current and planned state of Sirocco. Further versions of this document will be accessible at http://www.cs.sandia.gov/Scalable_IO/ sirocco .

97 MATHEMATICS AND COMPUTING↗