Search NASA⌕ Search

SEARCH · Search NASA

Results for “Performance portability”

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 127 records · Page 7

ECP libraries and tools: An overview

The Exascale Computing Project (ECP) Software Technology and Co-Design teams addressed the growing complexities in high-performance computing (HPC) by developing scalable software libraries and tools that leverage exascale system capabilities. As we enter the exascale era, the need for reusable, optimized software solutions that can handle the unique challenges posed by these systems becomes increasingly important. The primary challenges the ECP teams faced were to create software libraries and tools that are performant on exascale architectures and portable and usable across diverse hardware platforms. Efforts addressed issues related to concurrent execution, memory management, and the integration of heterogeneous computing resources, such as GPUs from multiple vendors. The ECP’s strategy involved a structured development process encompassing the creation, optimization, and deployment of software in collaboration with industry, academia, and national laboratories. The project was organized into several technical areas: co-design of domain-specific suites with target applications, programming models and runtimes, development tools, mathematical libraries, data and visualization tools, and software ecosystem and delivery mechanisms. ECP has successfully developed a large portfolio of software libraries and tools that demonstrate significant improvements in performance and scalability on exascale systems. These products have been integrated into the Department of Energy’s computing facilities, supporting various scientific applications and ensuring robust performance across different hardware setups. ECP advancements in software development for exascale computing highlight the importance of a collaborative and adaptive approach to handling next-generation HPC systems complexities. The lessons learned emphasize the need for continuous engagement with end-users and vendors, and the importance of maintaining a balance between innovation and practical implementation. Future efforts will focus on ensuring scalability, keeping pace with rapid hardware advancements, and further enhancing the interoperability and usability of the software ecosystem. In conclusion, subsequent articles in this special issue provide in-depth discussions and case studies into specific library and tool efforts.

97 MATHEMATICS AND COMPUTING↗

IRIS-MEMFLOW: Data Flow-Enabled Portable Memory Orchestration in IRIS Runtime for Diverse Heterogeneity

Task-based programming models and execution paradigms provide a means to decompose a computation by expressing it as a graph in which each node represents a specific computation operating on memory objects and the edges define the dependencies in the execution flow. In this execution model, independent nodes in the graph can be executed concurrently in different computing devices, making it suitable for heterogeneous systems in which computing devices with different architectures coexist. However, careful memory orchestration across heterogeneous devices is needed because copies of the same memory object may reside in multiple devices during execution. Manually ensuring such an orchestration is quite challenging. Not only must an application developer guard against race conditions, but they must also optimize data movement between the host and devices because unnecessary data movement significantly impacts performance. To mitigate these challenges, we enhance the IRIS heterogeneous runtime and introduce IRIS-MEMFLOW–a data flow–enabled portable memory abstraction for seamlessly orchestrating memory in diverse heterogeneous computing environments. By using data-flow analysis, IRIS-MEMFLOW guards against race conditions while multiple heterogeneous devices access memory objects. IRIS-MEMFLOW also optimizes data movement between the host and devices without manual intervention. As a result, IRIS provides improved programming productivity, performance, and portability for multidevice heterogeneous executions in high-performance computing and cloud systems that run diverse architectures from different vendors. The efficacy of IRIS-MEMFLOW is evaluated through experiments that show its capability in terms of programming productivity, multidevice heterogeneity, portability, and low overhead versus the state of the art.

Monil, M. A. H. [ORNL] (ORCID:0000000334194037)↗

Summer Internship Report: ARA2 Benchmarking

Over the past decade, the RISC-V Instruction Set Architecture (ISA) has emerged as a significant player in both academic and industrial processor design due to its open-source nature, modular extension system, and versatility across domains ranging from microcontrollers to high-performance computing (HPC). One of its most important recent advancements is the RISC-V Vector Extension (RVV), which enables explicit data-level parallelism through vector registers and vectorized instructions. Unlike traditional SIMD (Single Instruction, Multiple Data) architectures that fix vector lengths at design time, RVV uses the concept of VLEN (vector register length) as a hardware-independent parameter and allows software to adapt dynamically to the available vector width. This flexible approach ensures portability across implementations while enabling scalable performance. The ARA2 core is a parameterizable RISC-V vector processor developed at the Integrated Systems Lab at ETH Zürich and the University of Bologna. Designed as a tightly-coupled accelerator to a scalar RISC-V core, ARA2 implements the RVV 1.0 specification and offers tunable architectural parameters such as the number of vector lanes, VLEN, and cache sizes.

97 MATHEMATICS AND COMPUTING↗

Bridging semantics, control specifications and assessment: A library for scalable demand flexibility controls

There is growing recognition that Demand Flexibility (DF) can play a major role in enhancing grid reliability, with building control applications emerging as key enablers for DF. However, the traditional approach to deploying new control applications in buildings, including those for DF, remains largely manual and tailored to individual buildings, making it difficult to scale. While research efforts have explored semantics-driven portability, DF controls specification, and assessment approaches, these initiatives are fragmented and limited in scope. This paper proposes a novel methodology, grounded in design science research, to integrate these elements and create a comprehensive DF controls library for both industry and academia. This approach is applied to develop the Demand FLEXibility controls LIBrary using Semantics (DFLEXLIBS), an extensible open-source library that provides DF controls for HVAC systems in Python. DFLEXLIBS enables portable, easy-to-deploy controls that abstract building-specific data points, facilitating assessment across diverse buildings. DFLEXLIBS features nine different control applications, and it is successfully implemented and tested across four virtual and two real buildings, bridging the gap between semantics-driven portability, DF controls specification, and rigorous performance assessment. Its benefits are measured by a reusability ratio greater than 90% and a functional overlap ratio of around 70% for the most common functions used in the library, significantly reducing time for deploying new controls.

Controls library↗

Evaluating Application Characteristics for GPU Portability Layer Selection

GPUs have become the dominant source of computing power for high performance computing and are increasingly being used across the High Energy Physics computing landscape for a wide variety of tasks. Though NVIDIA is currently the main provider of GPUs, AMD and Intel are rapidly increasing their market share. As a result, programming using a vendor-specific language such as CUDA can significantly reduce deployment choices. There are a number of portability layers such as Kokkos, Alpaka, SYCL, OpenMP and std::par that permit execution on a broad range of GPU and CPU architectures, significantly increasing the flexibility of application programmers. However, each of these portability layers has its own characteristics, performing better at some tasks and worse at others, or placing limitations on aspects of the application. In this presentation, we report on a study of application and kernel characteristics that can influence the choice of a portability layer and show how each layer handles these characteristics. We have analyzed representative heterogeneous applications from CMS (patatrack and p2r), DUNE (Wire-Cell Toolkit), and ATLAS (FastCaloSim) to identify key application characteristics that have different behaviors for the various portability technologies. Using these results, developers can make more informed decisions on which GPU portability technology is best suited to their application.

Atif, Mohammad [Brookhaven]↗

Examples of X-Ray Characterization Techniques in Energy Storage Research

Lithium-ion batteries have revolutionized the portable electronics and transportation sectors. Their performance is often critically dependent on the crystal structures of the anode and cathode electrode materials, which must enable the transport and reversible storage of lithium ions into and out of the lattice. Because lithium is a low-Z element, characterization of materials for lithium-ion batteries can be particularly challenging. Regardless, X-ray techniques enable analysis of material structures to better understand how battery materials perform and degrade, particularly when combined with other materials characterization and electrochemical characterization techniques. While X-ray techniques are most often used in battery research for phase identification of crystal structures, X-ray characterization techniques are also used for a wide variety of other purposes. I will discuss several examples from my research with various collaborators on several projects that highlight the impact that X-ray characterization techniques can have on battery research. The first example will focus on low-temperature microwave-assisted solvothermal synthesis of vanadium-doped LiFePO4 cathode materials for lithium-ion batteries. (1,2) Through a combination of electrochemical and materials characterization, we determined that low temperature synthesis resulted in metastable phases that enabled incorporation of higher dopant levels than resulting from high-temperature synthesis of thermodynamically stable phases. Rietveld refinement of X-ray diffraction data enabled understanding of how lattice parameters changed with doping levels and synthesis temperature. X-ray absorption near edge spectroscopy enabled understanding of the vanadium and iron oxidation states to confirm how vacancies in the structure caused by doping were charge compensated. This was important to understand because the literature suggests doping can improve LiFePO4 electrical conductivity, which improves battery charge and discharge rates. The second example will focus on understanding residual strain in lithium metal anodes. Lithium-ion batteries typically use graphite anodes, but the charge-storage capacity can be theoretically improved ~10x by using lithium metal as the anode material instead. However, lithium anodes suffer from growth of high-aspect-ratio features, such as dendrites, that can pierce nanoporous polymer separators and lead to short circuits and fires. External pressure is commonly applied to cells to enable better morphological control. We hypothesized that applied pressure may promote strain and possibly work hardening during electrochemical cycling, which motivated us to look for evidence of residual strain in lithium metal cycled under applied pressure using X-ray diffraction and sin2(..psi..) analysis. We found that lithium electrodeposited under high pressure exhibited in-plane compressive strain and that that lithium electrodeposited under low pressure did not. (3) The residual strain that accompanies electrodeposition under high pressure may lead to work hardening, which may explain how a soft metal like lithium can puncture separators and why higher pressure does not always decrease short circuits. (4-6) References: 1) Harrison, K. L.; Manthiram, A. Microwave-Assisted Solvothermal Synthesis and Characterization of Metastable LiFe1- x (VO) x PO4 Cathodes. Inorganic chemistry 2011, 50(8), 3613-3620. 2) Harrison, K. L.; Bridges, C. A.; Paranthaman, M. P.; Segre, C. U.; Katsoudas, J.; Maroni, V. A.; Idrobo, J. C.; Goodenough, J. B.; Manthiram, A. Temperature Dependence of Aliovalent-Vanadium Doping in LiFePO4 Cathodes. Chemistry of Materials 2013, 25(5), 768-781. 3) Rodriguez, M. A.; Harrison, K. L.; Goriparti, S.; Griego, J. J.; Boyce, B. L.; Perdue, B. R. Use of a Be-Dome Holder for Texture and Strain Characterization of Li Metal Thin Films via Sin2 (..psi..) Methodology. Powder Diffraction 2020, 35(2), 89-97. 4) Jungjohann, K. L.; Gannon, R. N.; Goriparti, S.; Randolph, S. J.; Merrill, L. C.; Johnson, D. C.; Zavadil, K. R.; Harris, S. J.; Harrison, K. L. Cryogenic Laser Ablation Reveals Short-Circuit Mechanism in Lithium Metal Batteries. ACS Energy Letters 2021, 6(6), 2138-2144. 5) Harrison, K. L.; Merrill, L. C.; Long, D. M.; Randolph, S. J.; Goriparti, S.; Christian, J.; Warren, B.; Roberts, S. A.; Harris, S. J.; Perry, D. L. Cryogenic Electron Microscopy Reveals That Applied Pressure Promotes Short Circuits in Li Batteries. Iscience 2021, 24(12). 6) Harrison, K. L.; Goriparti, S.; Merrill, L. C.; Long, D. M.; Warren, B.; Roberts, S. A.; Perdue, B. R.; Casias, Z.; Cuillier, P.; Boyce, B. L. Effects of Applied Interfacial Pressure on Li-Metal Cycling Performance and Morphology in 4 M LiFSI in DME. ACS Applied Materials & Interfaces 2021, 13(27), 31668-31679.

batteries↗

Portable Parallel Algorithms and Frameworks for Exascale Graph Analytics

Graphs (or networks) are a tool used to model the interactions among various entities. Efficiently processing large graphs has recently attracted significant attention due to the applications of graphs in various domains, such as biology, chemistry, and cyber-security. Analyzing the structure and properties of these graphs is an important component of many scientific computing pipelines. With the explosion in the volume of data, graphs have become very large and can contain hundreds of billions of vertices and trillions of edges. Therefore, it is crucial to develop high-performance methods to enable graph analysis to be done quickly and energy-efficiently. Furthermore, these solutions should be highly parallel in order to take advantage of modern parallel machines. However, designing efficient solutions is not enough. With the wide variety of computing environments available, each with different programmability and performance characteristics, it is necessary to develop solutions that are portable in terms of both performance (i.e., provide theoretical guarantees) and programmability (i.e., provide high level abstractions).

97 MATHEMATICS AND COMPUTING↗

Fabrication of metal-organic framework thin films for luminescent sensing applications

Metal−organic frameworks (MOFs) have emerged as an exciting material class due to their nearly infinite design space: an inexhaustible combination of metal centers, organic linkers, and reaction conditions may be leveraged to obtained desired optical, physical, and chemical properties. This rich synthetic diversity enables properties such as pore dimensions and functionality to be rationally tailored for highly selective and sensitive detection of target analytes. Luminescent MOF-based sensors in particular offer advantages including low cost, portability, and ease-of-use. Often, performance is maximized by utilizing the luminescent MOF in thin film form, for example by integrating the film onto an optical fiber, yet the synthesis of high-quality MOF thin films often requires tedious, expensive, and/or slow approaches. Here, we demonstrate a rapid, simple strategy for growing copper MOFs using metal oxide templates; the concept is first demonstrated with a well-studied system, copper-1,3,5-benznetricarboxylate (Cu-BTC). Variables such as the choice of solvent, pH, and the choice of the copper salt anion all govern thin film quality. We then extend this method to synthesize a solvent and metal-responsive copper MOF that is particularly effective at detecting aluminum, an economically critical metal, at trace concentrations using a fully portable luminescence spectrometer. Taken together, this work demonstrates a convenient, versatile, and sustainable method for developing high quality MOF thin film-based optical sensors.

Crawford, Scott↗

MUPPET: An automated OpenMP mutation testing framework for performance optimization

MUPPET is a tool for OpenMP programs that identifies program modifications, called mutations, aimed at improving program performance. Existing performance optimization techniques, including profiling-based and auto-tuning techniques, fail to indicate program modifications at the source level thus preventing their portability across compilers. MUPPET aims to help HPC developers reason about performance defects and missed opportunities to improve performance at the source code level.

Parasyris, Konstantinos↗

Accelerating Application Bulk Synchronous Writes in HPC Environments

High-bandwidth storage tiers are becoming more common for their capability to absorb high-rate, bursty I/Os. Notably, the designs of these fast storage tiers differ from system to system. The variation of these layers and non-uniform methods of access can pose chal- lenges for applications seeking to run at multiple HPC facilities. Therefore, in this work, we present Spectral, a rapid-output ab- straction library to accelerate application, bulk-synchronous writes on HPC systems. We design Spectral to enable applications to use high-bandwidth storage, such as node-local storage and dis- tributed, write-caches (e.g., burst buffers) transparently without requiring modifications to the application or file system source code. The key idea is to allow applications to spend most of the time performing productive work and to not require any source code changes for maximum portability on different HPC archi- tectures. Spectral internally re-routes write-only files through available, high-performance I/O resources before ultimately mi- grating them to the shared global parallel file system. For instance, on Summit, Spectral transparently places application outputs on node-local storage and then utilizes asynchronous migration to the center-wide GPFS file system. We evaluate Spectral on the Summit HPC system (1024 nodes) using the IOR benchmark and real scientific applications. Spectral shows linear performance scaling, improving application write performance by over an order of magnitude when compared to GPFS.

Khan, Awais↗

IRIS Reimagined: Advancements in Intelligent Runtime System for Task-Based Programming

Task-based programming models are gaining traction in scientific computing. IRIS is a portable runtime system that exploits multiple heterogeneous programming systems and can discover available resources and manage multiple diverse programming systems (e.g., CUDA, Hexagon, HIP, Level Zero, OpenCL, and OpenMP) simultaneously. It accounts for the constraints of task dependencies and provides customizable scheduling policies to map those tasks to heterogeneous devices. In this paper, we present new capabilities added to IRIS to improve its portability for heterogeneous programming, build-friendliness, and performance efficiency. The new additions include vendor-specific kernel support, a runtime system with a foreign function interface to eliminate writing wrapper or boilerplate code for heterogeneous kernels, an easy-to-use and configurable CMake-based build environment, automatic and efficient data transfers and orchestration, and the Hunter and DAGGER toolchains to evaluate IRIS’s task scheduling algorithms.

Miniskar, Narasinga Rao↗

Flexible transparent conducting electrodes unexpectedly influence MAPbI 3 film morphology and perovskite solar cell performance

Fabricating perovskite solar cells (PSCs) on plastic substrates will enable cost-effective manufacturing of lightweight and portable energy systems. Here, we study the influence of flexible transparent conductive electrodes (TCEs) on the methylammonium lead iodide (MAPbI3) film morphology and PSC performance. Three types of TCEs on polyethylene terephthalate (PET) are compared: a custom-made AgNWs/indium zinc oxide hybrid TCE and two commercial substrates with indium tin oxide (ITO) or metal/insulator/metal (MIM) as the TCE. Using the same p-i-n architecture and hole transport layer (HTL), we find that PSCs fabricated on the hybrid TCE show better performance and stability compared to those made on commercial TCEs. The PSC performance enhancement is attributed to the superior structural and optical properties of MAPbI3 film deposited on the hybrid TCE, which is explained by the surface energy difference of the HTL. While it is anticipated that solar cell performance can be affected by TCEs’ transmittance and sheet resistance as they determine light absorption and carrier transport, respectively, our finding of TCE influencing the morphology and crystallinity of MAPbI3 film, and hence PSC performance, is unexpected.

14 SOLAR ENERGY↗

Portable Tank Storage Pit Technical Documents and Associated Flooring Documents

The work performed under this section includes the surface preparation and application of protective floor coatings; furnishing all labor, materials, and equipment necessary to perform all operations in connection with the application required for satisfactory completion in accordance with the standards and practices set forth herein.

99 GENERAL AND MISCELLANEOUS↗

A bending test protocol for characterizing the mechanical performance of flexible photovoltaics

Flexible photovoltaics (PV) represents a promising research field with great potential for wearable, portable, and indoor applications. Significant progress has been made in recent years, with flexible emerging PV reporting power conversion efficiency (PCE) over 24%. Yet, there is a need for a unifying protocol to assess PV performance, compare research results, and evaluate the state- of-the-art achievements in flexible PV. In this paper, a consensus protocol is presented for measuring PCE over 1,000 bending cycles under 1% strain. Moreover, several good practice guidelines are proposed including bending procedures, flexibility testing with and without encapsulation, and ambient conditions during testing (e.g., temperature, humidity, illumination). Notably, the importance of uniform application of bending radius and the testing of parallel and perpendicular orientations of bending axis with respect to the direction of the electric current are emphasized. These recommendations aim to promote consistency in device comparison and allow for better reproducibility.

Fukuda, Kenjiro↗

Portable Acceleration of CMS Computing Workflows with Coprocessors as a Service

Computing demands for large scientific experiments, such as the CMS experiment at the CERN LHC, will increase dramatically in the next decades. To complement the future performance increases of software running on central processing units (CPUs), explorations of coprocessor usage in data processing hold great potential and interest. Coprocessors are a class of computer processors that supplement CPUs, often improving the execution of certain functions due to architectural design choices. We explore the approach of Services for Optimized Network Inference on Coprocessors (SONIC) and study the deployment of this as-a-service approach in large-scale data processing. In the studies, we take a data processing workflow of the CMS experiment and run the main workflow on CPUs, while offloading several machine learning (ML) inference tasks onto either remote or local coprocessors, specifically graphics processing units (GPUs). With experiments performed at Google Cloud, the Purdue Tier-2 computing center, and combinations of the two, we demonstrate the acceleration of these ML algorithms individually on coprocessors and the corresponding throughput improvement for the entire workflow. This approach can be easily generalized to different types of coprocessors and deployed on local CPUs without decreasing the throughput performance. We emphasize that the SONIC approach enables high coprocessor usage and enables the portability to run workflows on different types of coprocessors.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Innovative approach to counterfeit and noncompliant refrigerant detection: A cost-effective, portable solution

The increasing prevalence of counterfeit and incompatible refrigerants presents significant risks to Heating, Ventilation, Air Conditioning, and Refrigeration (HVAC&R) systems, including compromised equipment performance, safety hazards, and non-compliance. This article details the development of a novel, cost-effective, and portable detection device designed to accurately verify refrigerants. The device utilizes a controlled gas sampling and analysis system within a sealed chamber, ensuring precise measurements while maintaining safety through a purging mechanism. The system features a high-sensitivity sensor integrated with an onboard control module that analyzes gas composition in real-time, providing feedback within a 2-minute duration. Laboratory validation demonstrated the device’s high accuracy (>95 % based on correct identification of compliant vs. non-compliant blends) in detecting unauthorized refrigerant blends. The projected cost of the product stands at ∼ $150, based on the retail pricing of individual components. Laboratory validation demonstrated the device’s high accuracy (>95 % for composition identification, 100 % rejection of tested counterfeit/incorrect blends) in detecting unauthorized refrigerant blends with a response time <2 min. The device correctly identified authentic R-454A/B/C blends and reliably rejected R-407F and closely related counterfeit mixtures. Key advantages include affordability, ease of use, rapid response time, and compatibility with a wide range of refrigerants. This solution supports compliance with regulatory frameworks, enhances safety in HVAC&R operations, and mitigates the risks associated with counterfeit refrigerants.

Counterfeit refrigerants↗

The Benefits and Weaknesses of Containerizing Software for HPC

Containerization technology has emerged as a transformative tool for software engineers, offering consistent development and deployment environments, simplifying dependency management, and enhancing scalability and portability across diverse systems. However, its application in High-Performance Computing (HPC) presents unique challenges, including the management of virtualization overhead, the need for efficient resource allocation, and the maintenance of optimal performance for compute-intensiv

Ho, Eric Victor [Sandia National Laboratories (SNL↗

A Novel, Low-Cost, Portable Device for Counterfeit and Noncompliant Refrigerant Detection

The increasing prevalence of counterfeit refrigerants presents significant risks to Heating, Ventilation, Air Conditioning, and Refrigeration (HVACR) systems, including compromised equipment performance, safety hazards, and environmental non-compliance. This report details the development of a novel, cost-effective, and portable detection device designed to accurately identify counterfeit refrigerants. The device utilizes a controlled gas sampling and analysis system within a sealed chamber, ensuring precise measurements while maintaining safety through a purging mechanism. The system features a high-sensitivity sensor integrated with an onboard control module that analyzes gas composition in real-time, providing users with clear visual indicators for refrigerant authenticity.Laboratory validation demonstrated the device’s high accuracy (exceeding 95%) in detecting unauthorized refrigerant blends. Key advantages include affordability, ease of use, rapid response time, and compatibility with a wide range of refrigerants. This solution supports compliance with regulatory frameworks such as the American Innovation and Manufacturing (AIM) Act, enhances safety in HVACR operations, and mitigates the risks associated with counterfeit refrigerants. Future developments will focus on expanding refrigerant detection capabilities, integrating machine learning for enhanced accuracy, implementing cost-reduction strategies to improve accessibility and market adoption, and optimizing system packaging for enhanced field portability.

99 GENERAL AND MISCELLANEOUS↗