Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Performance Gap”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

10 Years Later: Cloud Computing is Closing the Performance Gap

Can cloud computing infrastructures provide HPC-competitive performance for scientific applications broadly? Despite prolific related literature, this question remains open. Answers are crucial for designing future systems and democratizing high-performance computing. We present a multi-level approach to investigate the performance gap between HPC and cloud computing, isolating different variables that contribute to this gap. Our experiments are divided into (i) hardware and system microbenchmarks and (ii) user application proxies. The results show that today’s high-end cloud computing can deliver HPC-competitive performance not only for computationally intensive applications, but also for memory- and communication-intensive applications – at least at modest scales – thanks to the high-speed memory systems and interconnects and dedicated batch scheduling now available on some cloud platforms.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Understanding the Performance Gap between Polycrystalline and Single-Crystal Nickel-Rich Layered Oxide Cathodes

Singe-crystal (SC) nickel-rich layered oxide cathodes, composed of boundary-free particles with high tap density, offer significant advantages in volumetric energy density and mechanical strength compared with polycrystalline (PC) cathode materials. However, as the nickel content increases (≥80%), SC Ni-rich cathodes often suffer from faster performance degradation than PC cathodes of the same composition, and the underlying causes of this discrepancy remain poorly understood. Herein, we reveal the distinct Ni redox behaviors that govern the electrochemical performance of SC and PC Ni-rich cathodes using multiscale and operando characterization techniques. Our results indicate that the increasingly heterogeneous Ni oxidation process in SC cathodes leads to the additional irreversible oxygen redox activity that deteriorates both the mechanical and chemical structures. In contrast, PC cathodes, despite with more pronounced surface reconstruction, exhibit greater chemomechanical stability due to homogeneous redox reactions during charging. Consequently, we find that bulk degradation, more than surface reactions, ultimately leads to fast capacity decay of SC Ni-rich cathodes during cycling. In conclusion, this work offers a comprehensive view on the impact of Ni redox evolutions on the chemomechanical stability in Ni-rich layered oxide cathodes, providing new insights into the longstanding performance gap between SC and PC cathodes, and guiding the rational design of Ni-rich cathode architectures.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Understanding Performance Portability of Bioinformatics Applications in SYCL on an NVIDIA GPU

Our goal is to have a better understanding of performance portability of SYCL kernels on a GPU. Toward this goal, we migrate representative kernels in bioinformatics applications from CUDA to SYCL, evaluate their performance on an NVIDIA GPU, and explain the performance gaps through performance profiling and analyses. We hope that the findings provide valuable feedback to the development of the SYCL ecosystem.

Jin, Zheming↗
DOE OSTI2025

A Study of Performance Portability of Low-bit Fused Matrix-Vector Multiplication Kernels in SYCL

Understanding the causes of performance gaps between a portable programming model and a vendor-specific programming model is important for improving performance portability. This paper studies performance portability of low-bit fused general matrix-vector multiplication kernels in SYCL on vendors’ graphics processing units (GPUs). This work introduces the use case, explains the kernel implementations in detail, evaluates the performance of the CUDA, HIP, and SYCL kernels on datacenter, desktop, and laptop GPUs, and investigates the causes of performance gaps. The results show that loop unrolling, kernel dispatch overhead, and sum reduction contribute to the gaps.

Jin, Zheming [ORNL] (ORCID:000000027197780X)↗
DOE OSTI2025

CAFE AU LAIT: Compute-Aware Federated Augmented Low-Rank AI Training

Federated finetuning is crucial for unlocking the knowledge embedded in pretrained Large Language Models (LLMs) when data are geographically distributed across clients. Unlike finetuning with data from a single institution, federated finetuning allows collaboration across multiple institutions, enabling the utilization of diverse and decentralized datasets while preserving data privacy. Given the high computing costs of LLM training and the emphasis on energy efficiency in Federated Learning (FL), Low-Rank Adaptation (LoRA) has emerged as a widely adopted algorithm due to its significantly reduced number of trainable parameters. However, this assumes that all data silos have the necessary computing resources to compute local updates of LLMs. Nevertheless, in practice, the computing resources across clients are highly heterogeneous: while some may have access to hundreds of GPUs, others might have limited or no GPU access. Recently, federated finetuning using synthetic data has been proposed, allowing clients to participate in a collaborative training run without training LLMs locally. However, our experimental results reveal a performance gap between models trained using synthetic data and those trained using local updates. Motivated by the observed heterogeneity in computing resources and the performance gap, we propose a novel two-stage algorithm that leverages the storage and computing capabilities of a strong server. In the first stage, under the coordination of the strong server, clients with limited computing resources collaborate to generate synthetic data, which is transferred to and stored on the strong server. In the second stage, the strong server uses this synthetic data on behalf of the resource-constrained clients to perform federated LoRA finetuning alongside clients with sufficient computing resources. This approach ensures that all clients can participate in the finetuning process. Experimental results demonstrate that incorporating local updates from even a small fraction of clients improves performance compared to using synthetic data for all clients. Furthermore, we incorporate the Gaussian mechanism in both stages to guarantee client-level differential privacy.

Wang, Jiayi [ORNL]↗
DOE OSTI2019

Performance Exploration Through Optimistic Static Program Annotations

Compilers are limited by the static information directly or indirectly encoded in the program. Low-level languages, such as C/C++, are considered problematic as their weak type system and relaxed memory semantic allows for various, sometimes non-obvious, behaviors. Since compilers have to preserve the program semantics for all program executions, the existence of exceptional behavior can prevent optimizations that the developer would consider valid and might expect. Analyses to guarantee the absence of disruptive and unlikely situations are consequently an indispensable part of an optimizing compiler. However, such analyses have to be approximative and limited in scope as global and exact solutions are infeasible for any non-trivial program. In this paper, we present an automated tool to measure the effectmissing static information has on the optimizations applied to a given program. The approach generates an optimistically optimized program version which, compared to the original, defines a performance gap that can be closed by better compiler analyses and selective static program annotations. Our evaluation on six already tuned proxy applications for high-performance codes shows speedups of up to 20.6%. This clearly indicates that static uncertainty limits performance. At the same time, we observed that compilers are often unable to utilize additional static information. Thus, manual annotation of all correct static information is therefore not only error prone but also mostly redundant.

Auto Tuning↗
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 OSTI2023

Understanding Performance Portability of SYCL Kernels: A Case Study with the All-Pairs Distance Calculation in Bioinformatics on GPUs

SYCL is a portable programming model. Toward the goal of a better understanding of performance portability of SYCL kernels on GPUs, we select a bioinformatics kernel for computing the all-pairs distance as a case study. After migrating the kernel from CUDA to HIP and SYCL, we evaluate the performance of the CUDA, HIP, and SYCL kernels on NVIDIA V100 and AMD MI210 GPUs. We analyze the GPU instructions from the kernels to explain performance gaps between SYCL and CUDA/HIP. We hope that the findings are valuable for improving performance portability of SYCL.

Jin, Zheming↗
DOE OSTI2025

ORNL Design Engineering Library: Validated Thermoelectric Digital Twins

Radioisotope thermoelectric generators (RTGs) serve a crucial role in supplying thermal and electrical energy for reliable and long-duration power in remote and extreme environments. The thermal energy is provided by the decay of radioisotopes and is converted into electrical energy using the steady-state thermoelectric process by exploiting the Seebeck effect. Maintaining a thermal gradient through the material is necessary to drive current production. Modern predictive multi-physics tools are able to effectively describe the complex and strongly coupled phenomena needed for accurate model-based system engineering efforts needed to develop higher performing RTGs. Experimental validation of model simulations is essential to confirm the accuracy, reliability, and applicability of predictive multiphysics tools. Validation fosters confidence among users, helps meet regulatory requirements, and contributes to the ongoing improvement of simulation techniques, ultimately leading to better, safer, and more efficient designs and processes. Validated models can then be used as digital twins and can be interrogated to understand and quantify the performance gaps between theoretical and physical systems. These insights can be used to build higher performing systems.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2021

Installation Quality Framework: Investment Return Approach for Energy Savings on Building Product Installation

A case study was conducted on 44 residential homes using both traditional house wrap and ZIP System systems to measure the overall airtightness and compare estimated energy usages. The labor, material, and overhead and profit (O&P) costs were analyzed and used to determine the optimal choice for long-term benefits in terms of cost and performance. The impact of insulation installation is considered a key factor in improving the strategy of reducing energy consumption. Improved installation practices can affect the airtightness of common wall assemblies to reduce the building energy performance gaps and provide insight on how to allocate resources better. A framework was developed to analyze operational costs and building energy performance to address how installation quality is a factor in the return of investment in building construction for heating and cooling systems within the thermal envelope. With this methodology, aggressive energy performance goals will be met while balancing the tradeoff between installation techniques and building systems efficiency based on the introduced probabilistic investment return (PIR) metric.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2019

Evaluating Burst Buffer Placement in HPC Systems

Burst buffers (BBs) are increasingly exploited in contemporary supercomputers to bridge the performance gap between compute and storage systems. The design of BBs, particularly the placement of these devices and the underlying network topology, impacts both performance and cost. As the cost of other components such as memory and accelerators is increasing, it is becoming more important that HPC centers provision BBs tailored to their workloads.This work contributes a provisioning system to provide accurate, multi-tenant simulations that model realistic application and storage workloads from HPC systems. The framework aids HPC centers in modeling their workloads against multiple network and BB configurations rapidly. In experiments with our framework, we provide a comparison of representative Oak Ridge Leadership Computing Facility (OLCF) I/O workloads against multiple BB designs. We analyze the impact of these designs on latency, I/O phase lengths, contention for network and storage devices, and choice of network topology.

Khetawat, Harsh↗
DOE OSTI2024

Nonlinear encoding in diffractive information processing using linear optical materials

Nonlinear encoding of optical information can be achieved using various forms of data representation. Here, we analyze the performances of different nonlinear information encoding strategies that can be employed in diffractive optical processors based on linear materials and shed light on their utility and performance gaps compared to the state-of-the-art digital deep neural networks. For a comprehensive evaluation, we used different datasets to compare the statistical inference performance of simpler-to-implement nonlinear encoding strategies that involve, e.g., phase encoding, against data repetition-based nonlinear encoding strategies. We show that data repetition within a diffractive volume (e.g., through an optical cavity or cascaded introduction of the input data) causes the loss of the universal linear transformation capability of a diffractive optical processor. Therefore, data repetition-based diffractive blocks cannot provide optical analogs to fully connected or convolutional layers commonly employed in digital neural networks. However, they can still be effectively trained for specific inference tasks and achieve enhanced accuracy, benefiting from the nonlinear encoding of the input information. Our results also reveal that phase encoding of input information without data repetition provides a simpler nonlinear encoding strategy with comparable statistical inference accuracy to data repetition-based diffractive processors. Our analyses and conclusions would be of broad interest to explore the push-pull relationship between linear material-based diffractive optical systems and nonlinear encoding strategies in visual information processors.

42 ENGINEERING↗
DOE OSTI2021

Component Modeling, Co-Optimization, and Trade-Space Evaluation (FY2021 Annual Progress Report)

This project is intended to support the development of new traction drive systems that meet the targets of 100 kW/L for power electronics and 50 kW/L for electric machines with reliable operation to 300,000 miles. To meet these goals, new designs must be identified that make use of state-of-the-art and next-generation electronic materials and design methods. Designs must exploit synergies between components, for example converters designed for high-frequency switching using wide band gap devices and ceramic capacitors. This project includes: (1) a survey of available technologies; (2) the development of design tools that consider the converter volume and performance; (3) exercising the design software to evaluate performance gaps and predict the impact of certain technologies and design approaches, i.e. GaN semiconductors, ceramic capacitors, and select topologies; and (4) building and testing hardware prototypes to validate models and concepts. Early instantiations of the design tools enable co-optimization of the power module and passive elements and provide some design guidance; later instantiations will enable the co-optimization of inverter and machine. Prototype testing begins with evaluation of simpler conversion topologies (i.e. the half-bridge boost converter) and progresses with fabrication of prototype inverter drives.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2022

Reduced order modeling for flow and transport problems with Barlow Twins self-supervised learning

Abstract We propose a unified data-driven reduced order model (ROM) that bridges the performance gap between linear and nonlinear manifold approaches. Deep learning ROM (DL-ROM) using deep-convolutional autoencoders (DC–AE) has been shown to capture nonlinear solution manifolds but fails to perform adequately when linear subspace approaches such as proper orthogonal decomposition (POD) would be optimal. Besides, most DL-ROM models rely on convolutional layers, which might limit its application to only a structured mesh. The proposed framework in this study relies on the combination of an autoencoder (AE) and Barlow Twins (BT) self-supervised learning, where BT maximizes the information content of the embedding with the latent space through a joint embedding architecture. Through a series of benchmark problems of natural convection in porous media, BT–AE performs better than the previous DL-ROM framework by providing comparable results to POD-based approaches for problems where the solution lies within a linear subspace as well as DL-ROM autoencoder-based techniques where the solution lies on a nonlinear manifold; consequently, bridges the gap between linear and nonlinear reduced manifolds. We illustrate that a proficient construction of the latent space is key to achieving these results, enabling us to map these latent spaces using regression models. The proposed framework achieves a relative error of 2% on average and 12% in the worst-case scenario (i.e., the training data is small, but the parameter space is large.). We also show that our framework provides a speed-up of $$7 \times 10^{6}$$ 7 × 10 6 times, in the best case, and $$7 \times 10^{3}$$ 7 × 10 3 times on average compared to a finite element solver. Furthermore, this BT–AE framework can operate on unstructured meshes, which provides flexibility in its application to standard numerical solvers, on-site measurements, experimental data, or a combination of these sources.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

BuildingQA: A Benchmark for Natural Language Question Answering over Building Knowledge Graphs

Graph-based representations of building metadata using ontologies like Brick are vital for smart building applications, but querying them remains a challenge for practitioners. Knowledge Graph Question Answering (KGQA) systems, meant to retrieve answers from natural language questions, traditionally require large-scale training data, making them ill-suited for the specialized and data-scarce building domain. The advent of Large Language Models (LLMs) offers a paradigm shift, enabling zero-shot natural language querying without building/domain-specific training. Yet, there is no standardized benchmark for building-specific KGQA which can guide and validate research in this area. To address this gap, our work makes three primary contributions. First, we introduce the BuildingQA Benchmark Dataset, constructed through a multi-stage process of collecting practitioner data, augmenting it with LLMs for linguistic diversity, and curating a final set of 188 questions across 4 buildings. Second, we characterize the benchmark's complexity and ambiguity, introducing a novel method to quantify its "lexical gap" and providing a four-stage diagnostic framework for analyzing how systems fail. Third, we benchmark zero-shot LLM-powered KGQA systems to establish baseline performance and analyze their failure modes. Our evaluation reveals that top-performing systems achieve a maximum F1 score of only 0.38. This result does not indicate a failure of these powerful systems, but rather underscores the unique challenges posed by our benchmark. It demonstrates a critical performance gap, showing that current methods successful on general KGs struggle with the specific lexical and structural nuances of the building domain. BuildingQA1 thus provides the benchmark dataset and foundational analysis needed to drive the development of novel, domain-aware methods required to unlock the use of semantic data in buildings.

Mulayim, Ozan Baris↗
DOE OSTI2023

Evaluating performance and portability of high-level programming models: Julia, Python/Numba, and Kokkos on exascale nodes

We explore the performance and portability of the high-level programming models: the LLVM-based Julia and Python/Numba, and Kokkos on high-performance computing (HPC) nodes: AMD Epyc CPUs and MI250X graphical processing units (GPUs) on Frontier’s test bed Crusher system and Ampere’s Arm-based CPUs and NVIDIA’s A100 GPUs on the Wombat system at the Oak Ridge Leadership Computing Facilities. We compare the default performance of a hand-rolled dense matrix multiplication algorithm on CPUs against vendor-compiled C/OpenMP implementations, and on each GPU against CUDA and HIP. Rather than focusing on the kernel optimization per-se, we select this naive approach to resemble exploratory work in science and as a lower-bound for performance to isolate the effect of each programming model. Julia and Kokkos perform comparably with C/OpenMP on CPUs, while Julia implementations are competitive with CUDA and HIP on GPUs. Performance gaps are identified on NVIDIA A100 GPUs for Julia’s single precision and Kokkos, and for Python/Numba in all scenarios. We also comment on half-precision support, productivity, performance portability metrics, and platform readiness. We expect to contribute to the understanding and direction for high-level, high-productivity languages in HPC as the first-generation exascale systems are deployed.

Godoy, William↗
DOE OSTI2024

Effects of Rolling Reduction on Critical Current Density and Microstructure of Bi-2212 Wires

Bi-2212 Rutherford cables have been fabricated into flat racetrack coils and canted-cosine-theta dipole magnets. The performance gap between the magnets made with Rutherford cables and the “short-sample-limit” is about 30%. To better understand the influence of Rutherford cable processing on the strand performance, we studied three Bi-2212 wires with filament architectures of 37 × 18 and 55 × 18 and diameters of 0.8 and 1.0 mm. To simulate the deformation caused by cabling process, the three wires were rolled with thickness reductions ranging from 10% to 30%. The aspect ratios of rolled strands are between 1.29 and 2.05. The low aspect-ratio wire is also an interesting form for fabricating solenoid coils with higher packing density. The round and rolled strands were heat-treated under 50 bar and with maximum heat treatment temperatures of 885.5 °C and 890.5 °C. The rolling deformation reduced filament size uniformity, resulting in filament merging in fully heat-treated wires. It was found that rolling reduction reduced wire critical current density (JE) by 16 to 18%, but the JE decrease saturated at 15 to 20% of the thickness reduction. It is believed that the reduced JE results from the filament merging caused by rolling and non-uniform shrinking during overpressure heat treatment.

Bi-2212 wire↗