Engineering Papers⌕ Search

SEARCH · Engineering Papers

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 379 records · Page 21
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

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)↗
DOE OSTI2023

Accelerating the Lagrangian Particle Tracking in Hydrologic Modeling to Continental-Scale

Unprecedented climate change and anthropogenic activities have induced increasing ecohydrological problems, which have motivated the development of large-scale modeling for solutions. Water age/quality is as important as water quantity for understanding the water cycle. However, current scientific progress in tracking water parcels at large-scale with high spatiotemporal resolutions is far behind that in water balance/quantity owing to the lack of powerful tools. EcoSLIM is a particle tracking model that works with the hydrologic model ParFlow-CLM, which couples surface-subsurface hydrology with land surface processes. Here, we demonstrate a parallel framework to accelerate EcoSLIM to continental-scale on a distributed, multi-GPU platform with CUDA-Aware MPI. In tests from catchment-, to regional-, and then to continental-scale using 25-million to 1.6-billion particles, EcoSLIM shows significant speedup and excellent parallel performance. The parallel framework is portable to atmospheric and oceanic particle tracking models, where parallelization is inadequate and a standard parallel framework is absent. Parallelized EcoSLIM is a promising tool to accelerate our understanding of the terrestrial water cycle and the upscaling of subsurface hydrology to Earth system models.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

DSPS: Differentiable stellar population synthesis

ABSTRACT Models of stellar population synthesis (SPS) are the fundamental tool that relates the physical properties of a galaxy to its spectral energy distribution (SED). In this paper, we present DSPS: a python package for SPS. All of the functionality in DSPS is implemented natively in the JAX library for automatic differentiation, and so our predictions for galaxy photometry are fully differentiable, and directly inherit the performance benefits of JAX, including portability onto GPUs. DSPS also implements several novel features, such as i) a flexible empirical model for stellar metallicity that incorporates correlations with stellar age, ii) support for the Diffstar model that provides a physically-motivated connection between the star formation history of a galaxy (SFH) and the mass assembly of its underlying dark matter halo. We detail a set of theoretical techniques for using autodiff to calculate gradients of predictions for galaxy SEDs with respect to SPS parameters that control a range of physical effects, including SFH, stellar metallicity, nebular emission, and dust attenuation. When forward modelling the colours of a synthetic galaxy population, we find that DSPS can provide a factor of 5 speed-up over standard SPS codes on a CPU, and a factor of 300-400 on a modern GPU. When coupled with gradient-based techniques for optimization and inference, DSPS makes it practical to conduct expansive likelihood analyses of simulation-based models of the galaxy–halo connection that fully forward model galaxy spectra and photometry.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

Evaluating CUDA Portability with HIPCL and DPCT

HIPCL is expanding the scope of the CUDA portability route from an AMD platform to an OpenCL platform. In the meantime, the Intel DPC++ Compatibility Tool (DPCT) is migrating a CUDA program to a data parallel C++ (DPC++) program. Towards the goal of portability enhancement, we evaluate the performance of the CUDA applications from Rodinia, SHOC, and proxy applications ported using HIPCL and DPCT on Intel GPUs. After profiling the ported programs, we aim to understand their performance gaps, and optimize codes converted by DPCT to improve their performance. The open-source repository for the CUDA, HIP, and DPCT programs will be useful for the development of a translator.

Jin, Zheming↗
DOE OSTI2024

Common Approach to Molten Salt Reactor Safety Evaluation [Slides]

The presentation describes the necessary elements of developing a common approach to molten salt reactor (MSR) safety adequacy evaluation. Developing a common approach to establishing adequate safety for MSRs could substantially decrease the developer risks. However, safety adequacy is intimately associated with reactor licensing which is an element with national sovereignty. No reactor class has a common, portable international license. The advantageous performance characteristics of MSRs can be leveraged to decrease the cost and time necessary to develop reasonable confidence of adequate safety. Adequate safety can be demonstrated though either accident prevention or mitigation. MSR have characteristics that may make accident mitigation a preferable safety adequacy evaluation approach. Adequate quality as well as a thorough understanding of accident progression validated through separate and integral effects testing remains central to any safety adequacy demonstration method.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2022

GASNet-EX RMA Communication Performance on Recent Supercomputing Systems

Partitioned Global Address Space (PGAS) programming models, typified by systems such as Unified Parallel C (UPC) and Fortran coarrays, expose one-sided Remote Memory Access (RMA) communication as a key building block for High Performance Computing (HPC) applications. Architectural trends in supercomputing make such programming models increasingly attractive, and newer, more sophisticated models such as UPC++, Legion and Chapel that rely upon similar communication paradigms are gaining popularity. GASNet-EX is a portable, open-source, high-performance communication library designed to efficiently support the networking requirements of PGAS runtime systems and other alternative models in emerging exascale machines. The library is an evolution of the popular GASNet communication system, building upon 20 years of lessons learned. We present microbenchmark results which demonstrate the RMA performance of GASNet-EX is competitive with MPI implementations on four recent, high-impact, production HPC systems. These results are an update relative to previously published results on older systems. The networks measured here are representative of hardware currently used in six of the top ten fastest supercomputers in the world, and all of the exascale systems on the U.S. DOE road map.

Hargrove, Paul H↗
DOE OSTI2025

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↗
DOE OSTI2020

Epithermal Neutron Resonance Analysis Using a Compact D-T Generator

Nuclear material identification and isotopic composition analysis are important capabilities for safeguards and the verification of nuclear arms control and nonproliferation treaties. Epithermal neutron resonance imaging has been proposed for spent fuel assay measurements, and the development of a mobile neutron imaging system could provide such a tool for on-site applications. This technique is highly sensitive to isotopes of interest for safeguards applications (e.g. 235,238 U, 238,239,240 Pu) and yields unique transmission spectra for a target containing actinides and some mid- and high-Z elements. Paired with a position-sensitive neutron detector, such a system could provide spatial information of the target isotopic composition. Recent progress in the development of high intensity neutron sources could make mobile epithermal neutron imaging designs increasingly feasible to serve as a tool for nuclear inspectors. In this work, Monte Carlo (MC) simulations were performed to further optimize a previous design for an epithermal neutron resonance-based analysis apparatus using a D-T portable neutron generator. Additionally, experimental work is being performed to test the feasibility of this method. The MC simulations of moderation time distributions for different moderator compositions and thicknesses were measured to provide a multi-group correction for neutron time-of-flight energy reconstruction.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2026

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↗
DOE OSTI2026

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]↗
DOE OSTI2020

Detecting Phase-Resolved Magnetization Dynamics by Magneto-Optic Effects at 1550 nm Wavelength

We demonstrate the detection of phase-resolved magnetization dynamics with combinatorial magneto-optic Kerr and Faraday effects. The method uses a continuous-wave laser that is amplitude-modulated at the spin dynamic frequencies, and thus allows for coherent tracking of the spin dynamics, akin a “lock-in” type measurement. In particular, our method, using a single 1550-nmwavelength, probes simultaneously the ferromagnetic resonance of Y 3 Fe 5 O 12 (YIG) and Permalloy (Py = Ni 80 Fe 20 ) in a YIG-Pyhetero structure. The fiber-based magneto-optic components also have the advantage of being made into a compact, tabletop or even portable system with yet robust measurement performances. We believe that our method will be found useful in studying hybrid quantum magnonic systems and/or investigating phase-resolved spin dynamics in nanomagnet structures involving both ferromagnetic insulators and metals.

42 ENGINEERING↗
DOE OSTI2025

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↗
DOE OSTI2024

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↗
DOE OSTI2023

An automated and portable method for selecting an optimal GPU frequency

Power consumption poses a significant challenge in current and emerging graphics processing unit (GPU) enabled high-performance computing systems. In modern GPUs, dynamic voltage frequency scaling (DVFS) appears to be a reliable control to regulate power consumption and performance. However, the DVFS design space is large - hence, brute-force approaches are infeasible to select the optimal frequency. Furthermore, no single frequency can be universally optimal for applications with varying computational intensities. Thus, the application's complexity and the availability of a wide range of frequency settings are a challenge in selecting the optimal frequency configuration for a given GPU workload. To that end, this paper proposes a systematic approach that consists of three steps. The feature characterization study identifies the fine-grain GPU utilization metrics that influence the power consumption and execution time of a given workload. To understand the performance, power, and energy consumption behaviors of a workload across GPU's DVFS design space, we derived analytical power and performance models using the identified fine-grain features. Here, it is shown that the same set of GPU utilization metrics can estimate both the power consumption and execution time while being agnostic of changes to frequency and input sizes. Applying a power control with the single objective of reducing power may cause performance degradation, leading to more energy consumption. A multi-objective approach is proposed to select the optimal GPU DVFS configuration for a workload that reduces power consumption with negligible degradation in performance. The evaluation was conducted using SPEC ACCEL benchmarks and three real applications - NAMD LAMMPS, and LSTM on NVIDIA GV100, GA100, and AMD MI210 GPUs. On average, real applications showed 29.6% energy savings with a performance loss of 5.2% on GA100 and 22.6% energy savings with a performance loss of 4.7% on GV100. Moreover, the proposed models are portable to real applications, GPU architectures, and vendors, and require metric collection at only the default frequency rather than all supported DVFS configurations. Additionally, we conducted a comparison between our models and the GPU assembly instructions (PTX)-based static models. The results revealed a significant reduction in the average error rates, with a decrease from 19.7% to 3.1% for power models and from 29.4% to 5.2% for performance models.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

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↗
DOE OSTI2021

A Hierarchical Task Scheduler for Heterogeneous Computing

Heterogeneous computing is one of the future directions of HPC. Task scheduling in heterogeneous computing must balance the challenge of optimizing the application performance and the need for an intuitive interface with the programming run-time to maintain programming portability. The challenge is further compounded by the varying data communication time between tasks. This paper proposes RANGER, a hardware-assisted task-scheduling framework. By integrating RISC-V cores with accelerators, the RANGER scheduling framework divides scheduling into global and local levels. At the local level, RANGER further partitions each task into fine-grained subtasks to reduce the overall makespan. At the global level, RANGER maintains the coarse granularity of the task specification, thereby maintaining programming portability. The extensive experimental results demonstrate that RANGER achieves a 12.7× performance improvement on average, while only requires 2.7% of area overhead.

Miniskar, Narasinga Rao↗
DOE OSTI2023

Novel 3D Force Sensors for a Cost-Effective 3D Force Plate for Biomechanical Analysis

Three-dimensional force plates are important tools for biomechanics discovery and sports performance practice. However, currently, available 3D force plates lack portability and are often cost-prohibitive. To address this, a recently discovered 3D force sensor technology was used in the fabrication of a prototype force plate. Thirteen participants performed bodyweight and weighted lunges and squats on the prototype force plate and a standard 3D force plate positioned in series to compare forces measured by both force plates and validate the technology. For the lunges, there was excellent agreement between the experimental force plate and the standard force plate in the X-, Y-, and Z-axes (r = 0.950–0.999, p < 0.001). For the squats, there was excellent agreement between the force plates in the Z-axis (r = 0.996, p < 0.001). Across axes and movements, root mean square error (RMSE) ranged from 1.17% to 5.36% between force plates. Although the current prototype force plate is limited in sampling rate, the low RMSEs and extremely high agreement in peak forces provide confidence the novel force sensors have utility in constructing cost-effective and versatile use-case 3D force plates.

42 ENGINEERING↗