Search NASA⌕ Search

SEARCH · Search NASA

Results for “Applicability”

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 325 records · Page 18
All sourcesNASA NTRSDOE OSTI
NASA NTRS2015

Layered Thermal Insulation Systems for Industrial and Commercial Applications

From the high performance arena of cryogenic equipment, several different layered thermal insulation systems have been developed for industrial and commercial applications. In addition to the proven areas in cold-work applications for piping and tanks, the new Layered Composite Insulation for Extreme Environments (LCX) has potential for broader industrial use as well as for commercial applications. The LCX technology provides a unique combination of thermal, mechanical, and weathering performance capability that is both cost-effective and enabling. Industry applications may include, for example, liquid nitrogen (LN2) systems for food processing, liquefied natural gas (LNG) systems for transportation or power, and chilled water cooling facilities. Example commercial applications may include commercial residential building construction, hot water piping, HVAC systems, refrigerated trucks, cold chain shipping containers, and a various consumer products. The LCX system is highly tailorable to the end-use application and can be pre-fabricated or field assembled as needed. Product forms of LCX include rigid sheets, semi-flexible sheets, cylindrical clam-shells, removable covers, or flexible strips for wrapping. With increasing system control and reliability requirements as well as demands for higher energy efficiencies, thermal insulation in harsh environments is a growing challenge. The LCX technology grew out of solving problems in the insulation of mechanically complex cryogenic systems that must operate in outdoor, humid conditions. Insulation for cold work includes equipment for everything from liquid helium to chilled water. And in the middle are systems for LNG, LN2, liquid oxygen (LO2), liquid hydrogen (LH2) that must operate in the ambient environment. Different LCX systems have been demonstrated for sub-ambient conditions but are capable of moderately high temperature applications as well.

thermal conductivity↗
NASA NTRS2022

Application Table: A Bridge Connecting the Designing “With-The-Material” and “The-Material” Paradigms

Over the last few decades, advances in high-performance computing, new material characterization methods, and, more recently, an emphasis on integrated computational materials engineering (ICME) have been a catalyst for multiscale modeling and simulation-based design of materials and structures in the aerospace industry. In 2016 NASA sponsored a 2040 Vision study (which appeared in 2018) to define the potential 25-year future state required for integrated multiscale modeling of materials and systems (e.g., load-bearing structures) to accelerate the pace and reduce the expense of innovation in future aerospace and aeronautical systems. The study envisions a cyber-physical-social ecosystem comprised of experimentally verified and validated (V & V) computational models, tools, and techniques, along with the associated digital tapestry, that impacts the entire supply chain to enable cost-effective, rapid, and revolutionary design of “fit-for-purpose” materials, components, and systems. Consequently, the development of a robust information management system that incorporates (across the full life cycle) both experimental (real data) and virtual data resulting from the application of various simulation tools (at single or multiple length scales), therefore enabling the virtual design and optimization of materials throughout their processing – internal structure – property – performance envelope, has become critical. This need is also fueled by the demands for higher efficiency in material testing; consistency, quality, and traceability of data; product design; engineering analysis; as well as control of access to proprietary or sensitive information. This is particularly true when attempting to merge ICME practices with recent additive manufacturing technology which will enable production of the resulting 2040 Vision material and structural designs. At NASA Glenn Research Center we are exploring the future of material science through the use of novel characterization methodologies, high performance computing, and recently an emphasis on integrated computational materials engineering (ICME). Herein, recent efforts to incorporate an Application Table within NASA Glenn Research Center’s ICME Granta MI database is presented. The goal is to provide a place where material and structural application information/requirements can be linked so as to marry the “design the-material” and the “design-with-material” paradigms and thereby enable application-driven design and optimization of materials and structures by providing a central location that links material processing at various length scales to the application’s performance requirements. This paper discusses the specifics of this Application Table as well as best practices and key principles for the development of a robust materials information management system to enable the 2040 Vision integrated materials and structures ecosystem. Furthermore, it presents the intended role of the Application Table in the future of ICME design of “fit-for-purpose” materials, showing the need for a well-established framework that can successfully bridge the gap between the design “the material” and design “with-the-material” paradigms.

Materials↗
NASA NTRSDate not supplied

Leveraging Existing Satellite Precipitation Missions for AOS Applications Development

The Atmosphere Observing System (AOS) seeks to explore fundamental questions of how interconnections between aerosols, clouds and precipitation impact our weather and climate, addressing real-world challenges to benefit society. AOS will provide key information to enhance the communities’ ability to improve weather and air quality forecasting today, seasonal to sub-seasonal changes in the near future, and societal challenges resulting from climate change in the decades to come. A fundamental component of the AOS mission is ensuring that applications are considered to the greatest extent possible in mission design.As a result, the Applications Impact Team (AIT) was implemented to address this objective.The overarching goal of the AIT is to help improve the capacity for transitioning science to applications to make it possible to more quickly and effectively inform decisions that will directly benefit society. We seek to maximize AOS benefit to impact decisions through early engagement in the mission development phase in order to prepare stakeholders to apply observations as soon as AOS mission data becomes available.To support these efforts, we leverage existing mission applications activities and initiatives, such as NASA’s GPM and TROPICS missions, to form a framework to enhance precipitation applications for AOS. Engaging with existing missions helps identify and understand data needs, gaps and opportunities for current and future stakeholders, determine what precipitation data products are of highest value and use, and helps connect stakeholders with current mission data that can serve as AOS proxy data, among others. In this presentation, we provide an overview of AOS AIT activities and initiatives and highlight how existing satellite precipitation missions and their applications activities can play a critical role in AOS applications development during mission design.

Andrea Portier↗
NASA NTRSDate not supplied

Application Table: A Bridge Connecting the Designing “With-the-Material” and “the-Material”

Over the last few decades, advances in high-performance computing, new material characterization methods, and, more recently, an emphasis on integrated computational materials engineering (ICME) have been a catalyst for multiscale modeling and simulation-based design of materials and structures in the aerospace industry. In 2016 NASA sponsored a 2040 Vision study (which appeared in 2018) to define the potential 25-year future state required for integrated multiscale modeling of materials and systems (e.g., load-bearing structures) to accelerate the pace and reduce the expense of innovation in future aerospace and aeronautical systems. The study envisions a cyber-physical-social ecosystem comprised of experimentally verified and validated (V & V) computational models, tools, and techniques, along with the associated digital tapestry, that impacts the entire supply chain to enable cost-effective, rapid, and revolutionary design of “fit-for-purpose” materials, components, and systems. Consequently, the development of a robust information management system that incorporates (across the full life cycle) both experimental (real data) and virtual data resulting from the application of various simulation tools (at single or multiple length scales), therefore enabling the virtual design and optimization of materials throughout their processing – internal structure – property – performance envelope, has become critical. This need is also fueled by the demands for higher efficiency in material testing; consistency, quality, and traceability of data; product design; engineering analysis; as well as control of access to proprietary or sensitive information. This is particularly true when attempting to merge ICME practices with recent additive manufacturing technology which will enable production of the resulting 2040 Vision material and structural designs. At NASA Glenn Research Center we are exploring the future of material science through the use of novel characterization methodologies, high performance computing, and recently an emphasis on integrated computational materials engineering (ICME). Herein, recent efforts to incorporate an Application Table within NASA Glenn Research Center’s ICME Granta MI database is presented. The goal is to provide a place where material and structural application information/requirements can be linked so as to marry the “design the-material” and the “design-with-material” paradigms and thereby enable application-driven design and optimization of materials and structures by providing a central location that links material processing at various length scales to the application’s performance requirements. This paper discusses the specifics of this Application Table as well as best practices and key principles for the development of a robust materials information management system to enable the 2040 Vision integrated materials and structures ecosystem. Furthermore, it presents the intended role of the Application Table in the future of ICME design of “fit-for-purpose” materials, showing the need for a well-established framework that can successfully bridge the gap between the design “the material” and design “with-the-material” paradigms.

Materials↗
NASA NTRSDate not supplied

A new template for developing C++ applications in NASA's Core Flight System

In this presentation, we will demonstrate an example Core Flight System (cFS) application written in C++, compatible with the Draco releases of the Core Flight Executive (cFE) and NASA Operating System Abstraction Layer (OSAL). The application boilerplate, supporting library, and associated generation script were recently developed and licensed under the permissive Apache License 2.0 with the goal of easing the cFS app development with C++. The design and features of this application will be presented, including a higher-level interface for interactions with the cFE software bus pipes, tables, and event services. Data structures are provided for centralized telecommand and telemetry parsing which isolates bookkeeping of message components from the calling code in an application's core logic. Specific advantages of writing a cFS application in C++ will be shown, including easier avoidance of symbol collisions via namespaces, expanded compile-time checks via constant expressions, default initialization for data structures, null safety via references, improved syntax for operating on multi-dimensional arrays, and reliable serialization of enumerations via enumeration classes. Special considerations needed for integrating a C++ application will be identified, including function linkage, exceptions, and stack unwinding. Evidence for the usefulness of this template will be discussed in the context of development of a flight software application used for interfacing with a solid-state data recorder.

Dominick Allen↗
DOE OSTI2023

Blockchain applicability framework

Technology related to blockchain cybersecurity solutions and a blockchain applicability framework is disclosed. In one example of the disclosed technology, a system is configured to receive parameters for a blockchain candidate application and evaluate the parameters to determine a recommendation for types of blockchain to apply to the candidate application. The recommendation may be based on an evaluation of the parameters to determine a level of applicability of blockchain usage, a level of applicability of one or more blockchain privacy types, and a level of applicability of one or more blockchain consensus types. The system may be configured to calculate an overall percentage distribution of the levels of applicability and to output an indication of the overall percentage distribution.

Gourisetti, Sri Nikhil Gupta↗
DOE OSTI2020

Sonochemical synthesis of carbon dots, mechanism, effect of parameters, and catalytic, energy, biomedical and tissue engineering applications

Carbon-based nanomaterials are gaining more and more interest because of their wide range of applications. In this study, carbon dots (CDs) have shown exclusive interest due to unique and novel physicochemical, optical, electrical, and biological properties. Since their discovery, CDs became a promising material for wide range of research applications from energy to biomedical and tissue engineering applications. At same time several new methods have been developed for the synthesis of CDs. Compared to many of these methods, the sonochemical preparation is a green method with advantages such as facile, mild experimental conditions, green energy sources, and feasibility to formulate CDs and doped CDs with controlled physicochemical properties and lower toxicity. In the last five years, the sonochemically synthesized CDs were extensively studied in a wide range of applications. In this review, we discussed the sonochemical assisted synthesis of CDs, doped CDs and their nanocomposites. In addition to the synthetic route, we will discuss the effect of various experimental parameters on the physicochemical properties of CDs; and their applications in different research areas such as bioimaging, drug delivery, catalysis, antibacterial, polymerization, neural tissue engineering, dye absorption, ointments, electronic devices, lithium ion batteries, and supercapacitors. This review concludes with further research directions to be explored for the applications of sonochemical synthesized CDs.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Understanding the use of message passing interface in exascale proxy applications

The Exascale Computing Project (ECP) focuses on the development of future exascale-capable applications. Most ECP applications use the message passing interface (MPI) as their parallel programming model with mini-apps serving as proxies. This paper explores the explicit usage of MPI in such ECP proxy applications. We empirically analyze 14 proxy applications from the ECP Proxy Apps Suite. We use the MPI profiling interface (PMPI) to collect MPI usage patterns in ECP proxy apps. Our analysis shows that a small subset of features from MPI is commonly used in the proxies of exascale-capable applications, even when they reference third-party libraries. Overall, this study is intended to provide a better understanding of the use of MPI in current exascale applications. The findings can help focus software investments made for exascale systems in the MPI middleware including optimization, fault-tolerance, tuning, and hardware-offload.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

SOMA: Observability, monitoring, and in situ analytics for exascale applications

With the rise of exascale systems and large, data-centric workflows, the need to observe and analyze high performance computing (HPC) applications during their execution is becoming increasingly important. HPC applications are typically not designed with online monitoring in mind, therefore, the observability challenge lies in being able to access and analyze interesting events with low overhead while seamlessly integrating such capabilities into existing and new applications. We explore how our service-based observation, monitoring, and analytics (SOMA) approach to collecting and aggregating both application-specific diagnostic data and performance data addresses these needs. Furthermore, we present our SOMA framework and demonstrate its viability with LULESH, a hydrodynamics proxy application. Then we focus on Astaroth, a multi-GPU library for stencil computations, highlighting the integration of the TAU and APEX performance tools and SOMA for application and performance data monitoring.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Multiphysics for nuclear energy applications using a cohesive computational framework

With the recent development of advanced numerical algorithms, software design, and low-cost high-performance computer hardware, reliance on coupled multiphysics to predict the behavior of complex physical systems is beginning to become standard practice. This is especially true in nuclear energy applications where strong nonlinear interdependencies exist between reactor physics, radiation transport, multi-scale nuclear fuels performance, thermal fluids, etc. Resolving these nonlinear dependencies requires choices in multiphysics software approaches. Two main multiphysics modeling and simulation approaches have emerged. The first is based upon "code coupling" where disparate physics codes of different software design, code languages, and spatial and temporal integration schemes are coupled together with relatively complex data passing interfaces. The second multiphysics software approach is to employ a "cohesive" framework where all physics applications are developed with a common software design, i.e., data structures, syntax, input format, integrated spatial and temporal discretization schemes, etc. In this paper we present the Multiphysics Object-Oriented Simulation Environment (MOOSE) development and runtime framework and describe the framework's cohesive modeling and simulation multiphysics approach. Then, a "cohesive-like" extension of the MOOSE framework is presented where MOOSE-based physics software applications are efficiently coupled to non-MOOSE (external) physics codes to form multiphysics applications using MOOSE's unique interface capabilities. Finally, several examples of MOOSE's cohesive and cohesive-like multiphysics applications will be demonstrated. These multiphysics demonstrations will incorporate both MOOSE-based applications and external codes, including Nek5000, RELAP-7, TRACE, BISON, and Pronghorn.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2022

Shape-Controlled Synthesis of Copper Nanocrystals for Plasmonic, Biomedical, and Electrocatalytic Applications

As a metal that can occur in nature in the elemental form, copper (Cu) has been used by humans since ca. 8000 BC. With most properties matching those of Ag and Au, Cu has played a more significant role in commercial applications owing to its much higher (the 25th among all elements) abundance in Earth’s crust and thus more affordable price. In addition to its common use as a conductor of heat and electricity, it is a constituent of various metal alloys for hardware, coins, strain gauges, and thermocouples. Bulk Cu is also widely utilized as a building material. When downsized to the nanoscale, Cu and Cu-based structures have found widespread use in applications ranging from electronics to optoelectronics, plasmonics, catalysis, sensing, and biomedicine. Besides Ag and Au, for example, Cu is another metal known for its localized surface plasmon resonance (LSPR) in the visible and near-infrared regions when prepared as nanocrystals. As a potential replacement for indium–tin oxide (ITO) films, polymer coatings containing Cu nanowires are strong candidates for the fabrication of transparent and flexible electrodes key to touchscreen display and related applications. The commercial catalysts for water–gas shift and gas detoxification reactions are also based on Cu nanoparticles. Most recently, Cu nanocrystals have attracted considerable interest for their superior selectivity toward hydrocarbons and multicarbon species during the electrochemical reduction of CO 2 . The success of all these applications critically depends on our ability to control the shape and surface structure of the nanocrystals. Relative to Ag and Au, it is more challenging to generate Cu-based nanocrystals using colloidal methods due to its lower reduction potential and greater vulnerability to oxidation. Here, in this account, we discuss recent progress in the colloidal synthesis of Cu nanocrystals with controlled shapes for plasmonic, biomedical, and catalytic applications. With glucose serving as a reducing agent, Cu nanocrystals bearing a twinned or single-crystal structure can be synthesized using an aqueous system with the assistance of hexadecylamine (HDA). In this synthetic protocol, HDA not only passivates the surface to protect the nanocrystals from oxidation but also manipulates the reduction kinetics of Cu(II) precursor through coordination and an increase of solution pH. Typical products include nanocubes and penta-twinned nanowires whose surfaces are dominated by {100} facets. When seeds produced either in situ or ex situ are introduced, Cu-based nanocrystals featuring a singly twinned, core–shell, or Janus structure can be readily synthesized. Aside from segmented structures, Cu-based alloys with various noble metals can be synthesized through coreduction or a galvanic replacement reaction with preformed Cu nanocrystals. By controlling the size and/or shape of Cu nanocrystals, their LSPR peaks can be tuned into the near-infrared region, making them promising candidates for optical imaging contrast enhancement and photothermal treatment. The inclusion of the 64 Cu isotope makes them immediately useful in positron emission tomography and thus image-guided therapy. The surface structure, elemental distribution, and valence state of Cu-based nanocrystals can all be tailored to augment their electrocatalytic performance. It is hoped that this Account will inspire more studies into the development of rational methods capable of producing Cu-based nanocrystals with diverse and well-controlled shapes, internal structures, and compositions for a broader range of applications.

36 MATERIALS SCIENCE↗
DOE OSTI2021

BeeSwarm: Enabling Parallel Scaling Performance Measurement in Continuous Integration for HPC Applications

Testing is one of the most important steps in software development–it ensures the quality of software. Continuous Integration (CI) is a widely used testing standard that can report software quality to the developer in a timely manner during development progress. Performance, especially scalability, is another key factor for High Performance Computing (HPC) applications. There are many existing profiling and performance tools for HPC applications, but none of these are integrated into CI tools. In this work, we propose BeeSwarm, an HPC container based parallel scaling performance system that can be easily applied to the current CI test environments. BeeSwarm is mainly designed for HPC application developers who need to monitor how their applications can scale on different compute resources. We demonstrate BeeSwarm using a multi-physics HPC application with Travis CI, GitLab CI and GitHub Actions while using ChameleonCloud and Google Compute Engine as the compute backends. Finally, our results show that BeeSwarm can be used for scalability and performance testing of HPC applications.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Hvac: Removing I/O Bottleneck for Large-Scale Deep Learning Applications

Scientific communities are increasingly adopting deep learning (DL) models in their applications to accelerate scientific discovery processes. However, with rapid growth in the computing capabilities of HPC supercomputers, large-scale DL applications have to spend a significant portion of training time performing I/O to a parallel storage system. Previous research works have investigated optimization techniques such as prefetching and caching. Unfortunately, there exist non-trivial challenges to adopting the existing solutions on HPC supercomputers for large-scale DL training applications, which include non-performance and/or failures at extreme scale, lack of portability and generality in design, complex deployment methodology, and being limited to a specific application or dataset. To address these challenges, we propose High-Velocity AI Cache (HVAC), a distributed read-cache layer that targets and fully exploits the node-local storage or near node-local storage technology. HVAC seamlessly accelerates read I/O by aggregating node-local or near node-local storage, avoiding metadata lookups and file locking while preserving portability in the application code. We deploy and evaluate HVAC on 1,024 nodes (with over 6000 NVIDIA V100 GPUS) of the Summit supercomputer. In particular, we evaluate the scalability, efficiency, accuracy, and load distribution of HVAC compared to GPFS and XFS-on-NVMe. With four different DL applications, we observe an average 25 % performance improvement atop GPFS and 9% drop against XFS-on-NVMe, which scale linearly and are considered the performance upper bound. We envision HVAC as an important caching library for upcoming HPC supercomputers such as Frontier.

Khan, Awais↗
DOE OSTI2020

Methods and Experiences for Developing Abstractions for Data-intensive, Scientific Applications

Developing software for scientific applications that require the integration of diverse types of computing, instruments, and data present challenges that are distinct from commercial software. These applications require scale, and the need to integrate various programming and computational models with evolving and heterogeneous infrastructure. Pervasive and effective abstractions for distributed infrastructures are thus critical; however, the process of developing abstractions for scientific applications and infrastructures is not well understood. While theory-based approaches for system development are suited for well-defined, closed environments, they have severe limitations for designing abstractions for scientific systems and applications. The design science research (DSR) method provides the basis for designing practical systems that can handle real-world complexities at all levels. In contrast to theory-centric approaches, DSR emphasizes both practical relevance and knowledge creation by building and rigorously evaluating all artifacts. In this work, we show how DSR provides a well-defined framework for developing abstractions and middleware systems for distributed systems. Specifically, we address the critical problem of distributed resource management on heterogeneous infrastructure over a dynamic range of scales, a challenge that currently limits many scientific applications. We use the pilot-abstraction, a widely used resource management abstraction for high-performance, high throughput, big data, and streaming applications, as a case study for evaluating the DSR activities. For this purpose, we analyze the research process and artifacts produced during the design and evaluation of the pilot-abstraction. We find DSR provides a concise framework for iteratively designing and evaluating systems. Finally, we capture our experiences and formulate different lessons learned.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Volt/VAR Optimization (VVO) Application on GridAPPS-D Platform

There is a large increment in the distributed energy resources (DERs) installation and deployments of smart sensing devices and communication infrastructure; hence, the power distribution network is swiftly evolving from a passive network to an active network. This motivates the development of advanced applications to operate power distribution systems for higher efficiency and reliability. These advanced applications are model-based and data-driven. This requires an advanced distribution management system (ADMS) to provide required data for the optimal operation of the distribution systems by coordinating various grid controllable devices. In this paper a Volt-VAR optimization (VVO) application to coordinate the grid’s legacy and new voltage control devices for conservation voltage reduction (CVR) is deployed on the GridAPPS-D platform (an open-source platform ) for ADMS application development. The VVO application is validated for various operating conditions on using modified IEEE 8500-node distribution test feeders. Further, the application is successfully deployed on the GridAPPS-D platform.

Jha, Rahul↗
DOE OSTI2026

Dual Context: Leveraging Structured Application Context for Code Generation and Runtime Feature Activation via Chat Interfaces

Integrating artificial intelligence (AI) capabilities into software applications typically involves two common paths. For developers, AI assists in generating and documenting source code and other related software engineering efforts. For users, AI assists them through question-and-answer exchanges via chatbots. Both approaches have their value, but neither effectively leverages the modularity of component-based architectures that modern web application frameworks offer. We implement a proof of concept within a centralized suite of applications used for the Atmospheric Radiation Measurement (ARM) Data Center Operational Tools, where we introduce a third integration path through the ARM Context Engine (ACE). ACE is a context driven system that uses structured contextual specifications to enable Large Language Models (LLMs) to render interactive and feature-rich user interface (UI) components directly within chat responses, alongside or in place of conventional text outputs. These specifications serve two important purposes across what we call code context and UI context. Code context provides AI-assisted development tools with structured application knowledge beyond raw code, including component relationships, architectural patterns and schematic information, enabling the generation of consistent, well-structured code. UI context defines the rules for enabling and rendering component features at runtime based on the user's natural language input, allowing end users to activate capabilities such as data export, filtering, and pagination within chat responses, without requiring code changes or redeployment. We demonstrate, through a comparative evaluation against general-purpose AI chatbots, that context-driven component rendering provides interactive capabilities that text-based responses cannot replicate, including deterministic component behavior, application-consistent design language, and on-demand feature activation. A development effort comparison further shows that features that traditionally require multi-step development cycles can be activated with a single naturallanguage request. In this ongoing work, we present ACE as an emerging approach to AI integration that positions modular, well-documented software architecture as the foundation for AI-ready applications. ACE treats context as a shared resource across both development and user-facing AI, bringing cohesion to conventionally disconnected efforts, bridging developer tooling and end-user capabilities within a single framework.

Tadimeti, Vijay [ORNL]↗
DOE OSTI2021

Logically Parallel Communication for Fast MPI+Threads Applications

Supercomputing applications are increasingly adopting the MPI+threads programming model over the traditional "MPI everywhere" approach to better handle the disproportionate increase in the number of cores compared with other on-node resources. In practice, however, most applications observe a slower performance with MPI+threads primarily because of poor communication performance. Recent research efforts on MPI libraries address this bottleneck by mapping logically parallel communication, that is, operations that are not subject to MPI's ordering constraints to the underlying network parallelism. Domain scientists, however, typically do not expose such communication independence information because the existing MPI-3.1 standard's semantics can be limiting. Researchers had initially proposed user-visible endpoints to combat this issue, but such a solution requires intrusive changes to the standard (new APIs). The upcoming MPI-4.0 standard, on the other hand, allows applications to relax unneeded semantics and provides them with many opportunities to express logical communication parallelism. Here in this article, we show how MPI+threads applications can achieve high performance with logically parallel communication. Through application case studies, we compare the capabilities of the new MPI-4.0 standard with those of the existing one and user-visible endpoints (upper bound). Logical communication parallelism can boost the overall performance of an application by over 2x.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Auto-HPCnet: An Automatic Framework to Build Neural Network-based Surrogate for High-Performance Computing Applications

High-performance computing communities are increasingly adopt- ing Neural Networks (NN) as surrogate models in their applications to generate scientific insights. Replacing an execution phase in the application with NN models can bring significant performance im- provement. However, there is a lack of tools that can help domain scientists automatically apply NN-based surrogate models to HPC applications. We introduce a framework, named Auto-HPCnet, to democratize the usage of NN-based surrogates. Auto-HPCnet is the first end-to-end framework that makes past proposals for the NN-based surrogate model practical and disciplined. Auto-HPCnet introduces a workflow to address unique challenges when apply- ing the approximation, such as feature acquisition and meeting the application-specific constraint on the quality of final computation outcome. We show that Auto-HPCnet can leverage NN for a set of HPC applications and achieve 5.50× speedup on average (up to 16.8× speedup and with data preparation cost included) while meeting the application-specific constraint on the final computation quality.

Dong, Wenqian↗