Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “bottleneck analysis”

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 181 records · Page 10
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Extracting structural motifs from pair distribution function data of nanostructures using explainable machine learning

Characterization of material structure with X-ray or neutron scattering using e.g. Pair Distribution Function (PDF) analysis most often rely on refining a structure model against an experimental dataset. However, identifying a suitable model is often a bottleneck. Recently, automated approaches have made it possible to test thousands of models for each dataset, but these methods are computationally expensive and analysing the output, i.e. extracting structural information from the resulting fits in a meaningful way, is challenging. Our Machine Learning based Motif Extractor (ML-MotEx) trains an ML algorithm on thousands of fits, and uses SHAP (SHapley Additive exPlanation) values to identify which model features are important for the fit quality. We use the method for 4 different chemical systems, including disordered nanomaterials and clusters. ML-MotEx opens for a type of modelling where each feature in a model is assigned an importance value for the fit quality based on explainable ML.

36 MATERIALS SCIENCE↗
DOE OSTI2016

OrfM: a fast open reading frame predictor for metagenomic data

Finding and translating stretches of DNA lacking stop codons is a task common in the analysis of sequence data. However, the computational tools for finding open reading frames are sufficiently slow that they are becoming a bottleneck as the volume of sequence data grows. This computational bottleneck is especially problematic in metagenomics when searching unassembled reads, or screening assembled contigs for genes of interest. Here, we present OrfM, a tool to rapidly identify open reading frames (ORFs) in sequence data by applying the Aho–Corasick algorithm to find regions uninterrupted by stop codons. Benchmarking revealed that OrfM finds identical ORFs to similar tools (‘GetOrf’ and ‘Translate’) but is four-five times faster. While OrfM is sequencing platform-agnostic, it is best suited to large, high quality datasets such as those produced by Illumina sequencers.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2019

Load-balanced sparse MTTKRP on GPUs

Sparse matricized tensor times Khatri-Rao product (MT- TKRP) is one of the most computationally expensive kernels in sparse tensor computations. This work focuses on optimizing the MTTKRP for floating point operations, storage, and scalability. We begin by identifying the performance bottlenecks in directly extending the state-of-the-art CSF (compressed sparse fiber) formats from CPUs to GPUs. Our detailed analysis over the recently proposed formats shows that the lower bounds on storage and flop counts can vary significantly depending on the structure of the sparse tensor. To address this, we propose a load balanced, computation and storage-efficient scheme, HYB, which combines the best of COO (coordinate), CSF and CSL (compressed slice). With these enhancements, our GPU framework significantly out- performs the current formats on both CPU and GPU platforms.

Nisa, Israt↗
DOE OSTI2022

Towards a Stronger Foundation: Digitizing Commercial Buildings with Brick to Enable Portable Advanced Applications

Most large commercial buildings have digital controls for their heating, ventilation, and air-conditioning (HVAC) and lighting systems with the potential to implement advanced control strategies and data analytics. However, advanced control strategies and data analytics are rarely deployed at scale due to non-standard naming conventions and heterogenous building configurations. Semantic metadata standards, like Brick, show promise to proliferate these applications across many buildings, but they have not been widely adopted by industry due to barriers such as perceived risk and unfamiliarity with the technology. This paper describes the workflow we established and evaluated while using it to develop over ten Brick models of existing buildings. Through this process, we observed that digitizing existing commercial buildings is a cost and labor-intensive effort in which understanding the buildings’ data streams is the major bottleneck. Yet, we conclude this investment is worthwhile since various use case applications such as fault detection and diagnostics, thermal comfort analysis, and HVAC control optimization can utilize the same Brick model. The paper also explores the challenges and lessons learned we encountered while creating these data models, such as: 1) difficulties in finding metadata descriptions and relationships for existing buildings; 2) handling missing concepts in the schema needed to model a building; 3) lack of guidance on how to structure the data model or how much detail to include; 4) unfamiliarity with technologies, which makes the learning curve steep for applications developers. Finally, we also describe future directions for semantic metadata research and development to make such transformative technologies more accessible to practitioners.

Roa, Carlos Duarte↗
DOE OSTI2016

The construction of arbitrary order ERKN methods based on group theory for solving oscillatory Hamiltonian systems with applications

In general, extended Runge–Kutta–Nyström (ERKN) methods are more effective than traditional Runge–Kutta–Nyström (RKN) methods in dealing with oscillatory Hamiltonian systems. However, the theoretical analysis for ERKN methods, such as the order conditions, the symplectic conditions and the symmetric conditions, becomes much more complicated than that for RKN methods. Therefore, it is a bottleneck to construct high-order ERKN methods efficiently. In this paper, we first establish the ERKN group Ω for ERKN methods and the RKN group G for RKN methods, respectively. We then rigorously show that ERKN methods are a natural extension of RKN methods, that is, there exists an epimorphism η of the ERKN group Ω onto the RKN group G. This epimorphism gives a global insight into the structure of the ERKN group by the analysis of its kernel and the corresponding RKN group G. Meanwhile, we establish a particular mapping φ of G into Ω so that each image element is an ideal representative element of the congruence class in Ω. Furthermore, an elementary theoretical analysis shows that this map φ can preserve many structure-preserving properties, such as the order, the symmetry and the symplecticity. From the epimorphism η together with its section φ, we may gain knowledge about the structure of the ERKN group Ω via the RKN group G. In light of the theoretical analysis of this paper, we obtain high-order structure-preserving ERKN methods in an effective way for solving oscillatory Hamiltonian systems. Numerical experiments are carried out and the results are very promising, which strongly support our theoretical analysis presented in this paper.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

PET-FBA: A lightweight enzyme allocation and thermodynamics-constrained flux analysis approach to explore Escherichia coli metabolic adaptation to intracellular acidification

Escherichia coli employs diverse strategies to adapt to acidic environments that disrupt enzyme activity and the thermodynamic feasibility of essential reactions. To understand the impact of pH stress on cell metabolism, we present the PET-FBA (pH-, Enzyme protein allocation-, and Thermodynamics-constrained Flux Balance Analysis) framework. PET-FBA extends genome-scale modeling by integrating enzyme protein costs and reaction Gibbs free energy changes. Additionally, by incorporating pH-dependent enzyme kinetics in response to intracellular acidification, this framework enables the simulation of E. coli's metabolic adjustments across varying external pH levels. The model's accuracy is validated by comparing in silico growth simulations with experimental measurements under both anaerobic and aerobic conditions, as well as in silico gene knockouts of essential genes. By explicitly incorporating pH effects, our model accurately replicates the metabolic shift towards lactate production as the primary fermentation product at low pH in anaerobic conditions. This shift is only predicted when enzyme kinetics are dynamically adjusted as a function of pH. Further analysis revealed that this shift can be attributed to the reduced protein efficiency of the acetyl-CoA branch compared to lactate dehydrogenase under acidic stress, which then becomes crucial for maintaining NAD regeneration and cell growth at low pH. Furthermore, we identified strategies for enhancing cell growth under acidic anaerobic conditions by improving the enzyme activity of lactate dehydrogenase and pyruvate formate lyase, which increases NAD production efficiency and reduces enzyme protein allocation costs. Designed as a lightweight yet versatile framework, PET-FBA enables efficient genome-scale metabolic analysis. Using E. coli as a model system, our framework provides a systematic approach to understanding metabolic responses to environmental stress, pinpointing key metabolic bottlenecks, and identifying potential targets for strain optimization.

42 ENGINEERING↗
DOE OSTI2022

Understanding of bacterial lignin extracellular degradation mechanisms by Pseudomonas putida KT2440 via secretomic analysis

Abstract Background Bacterial lignin degradation is believed to be primarily achieved by a secreted enzyme system. Effects of such extracellular enzyme systems on lignin structural changes and degradation pathways are still not clearly understood, which remains as a bottleneck in the bacterial lignin bioconversion process. Results This study investigated lignin degradation using an isolated secretome secreted by Pseudomonas putida KT2440 that grew on glucose as the only carbon source. Enzyme assays revealed that the secretome harbored oxidase and peroxidase/Mn 2+ -peroxidase capacity and reached the highest activity at 120 h of the fermentation time. The degradation rate of alkali lignin was found to be only 8.1% by oxidases, but increased to 14.5% with the activation of peroxidase/Mn 2+ -peroxidase. Gas chromatography–mass spectrometry (GC–MS) and two-dimensional 1 H– 13 C heteronuclear single-quantum coherence (HSQC) NMR analysis revealed that the oxidases exhibited strong C–C bond ( β-β , β -5, and β -1) cleavage. The activation of peroxidases enhanced lignin degradation by stimulating C–O bond ( β -O-4) cleavage, resulting in increased yields of aromatic monomers and dimers. Further mass spectrometry-based quantitative proteomics measurements comprehensively identified different groups of enzymes particularly oxidoreductases in P. putida secretome, including reductases, peroxidases, monooxygenases, dioxygenases, oxidases, and dehydrogenases, potentially contributed to the lignin degradation process. Conclusions Overall, we discovered that bacterial extracellular degradation of alkali lignin to vanillin, vanillic acid, and other lignin-derived aromatics involved a series of oxidative cleavage, catalyzed by active DyP-type peroxidase, multicopper oxidase, and other accessory enzymes. These results will guide further metabolic engineering design to improve the efficiency of lignin bioconversion. Graphical Abstract

09 BIOMASS FUELS↗
DOE OSTI2017

Bacteriophage Tail-Tube Assembly Studied by Proton-Detected 4D Solid-State NMR

Obtaining unambiguous resonance assignments remains a major bottleneck in solid-state NMR studies of protein structure and dynamics. Particularly for supramolecular assemblies with large subunits (>150 residues), the analysis of crowded spectral data presents a challenge, even if three-dimensional (3D) spectra are used. Here, we present a proton-detected 4D solid-state NMR assignment procedure that is tailored for large assemblies. The key to recording 4D spectra with three indirect carbon or nitrogen dimensions with their inherently large chemical shift dispersion lies in the use of sparse non-uniform sampling (as low as 2 %). As a proof of principle, we acquired 4D (H)COCANH, (H)CACONH, and (H)CBCANH spectra of the 20 kDa bacteriophage tail-tube protein gp17.1 in a total time of two and a half weeks. These spectra were sufficient to obtain complete resonance assignments in a straightforward manner without use of previous solution NMR data.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2019

Performance optimization, modeling and analysis of sparse matrix-matrix products on multi-core and many-core processors

Sparse matrix-matrix multiplication (SpGEMM) is a computational primitive that is widely used in areas ranging from traditional numerical applications to recent big data analysis and machine learning. Although many SpGEMM algorithms have been proposed, hardware specific optimizations for multi- and many-core processors are lacking and a detailed analysis of their performance under various use cases and matrices is not available. In this work, we firstly identify and mitigate multiple bottlenecks with memory management and thread scheduling on Intel Xeon Phi (Knights Landing or KNL). Specifically targeting many-core processors, we develop a hash-table-based algorithm and optimize a heap-based shared-memory SpGEMM algorithm. We examine their performance together with other publicly available codes. Different from the literature, our evaluation also includes use cases that are representative of real graph algorithms, such as multi-source breadth-first search or triangle counting. Our hash-table and heap-based algorithms are showing significant speedups from libraries in the majority of the cases while different algorithms dominate the other scenarios with different matrix size, sparsity, compression factor and operation type. We wrap up in-depth evaluation results and make a recipe to give the best SpGEMM algorithm for target scenario. We build the performance model for hash-table and heap-based algorithms, which supports the recipe. A critical finding is that hash-table-based SpGEMM gets a significant performance boost if the nonzeros are not required to be sorted within each row of the output matrix. Finally, we integrate our implementations into a large-scale protein clustering code named HipMCL, accelerating its SpGEMM kernel by up to 10X and achieving an overall performance boost for the whole HipMCL application by 2.6X.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Battery Energy Storage Scenario Analyses Using the Lithium-Ion Battery Resource Assessment (LIBRA) Model

Meeting aggressive carbon emission goals will entail widespread deployment of renewable sources of electricity. Because these sources are variable, there is a need to develop scalable energy storage technologies. The U.S. Department of Energy is supporting efforts to increase U.S. manufacturing and recycling capabilities for LIBs and to decrease costs of stationary storage batteries. Many factors influence the domestic manufacturing and cost of stationary storage batteries, including availability of critical raw materials (lithium, cobalt, and nickel), competition from various demand sectors (consumer electronics, vehicles, and battery energy storage), resource recovery (recycling), government policies, and learning in the industry, among other factors. Understanding how these factors interact and identifying synergies and bottlenecks is important for developing effective strategies for the LIB stationary energy storage system. We developed the Lithium-Ion Battery Resource Analysis (LIBRA) model as a tool to help stakeholders better understand the following types of questions: What are the roles of R&D, industrial learning, and scaling of demand in lowering the cost of battery energy storage system production? How do the intersections between the EV and stationary storage sectors affect the battery supply chain? For various stationary storage and EV penetration scenarios, what volumes of critical materials might be required and what role can resource recovery play? What does expected demand for both EVs and stationary storage portend for mineral resources and overall mineral scarcity? The LIBRA model is developed using a System dynamics (SD) modeling approach to represent interactions across the segments of the battery materials supply chain. System dynamics models can capture the complex interactions and feedback between the various system components that influence supply and demand. The LIBRA model is comprised of several interacting modules that represent specific portions of the LIB supply chain. The model tracks the buildout of the domestic LIB industry over time (2020 - 2050) and in the context of competing demands for raw materials, recycling, and markets for LIBs. The LIBRA model represents major systemic feedback loops and delays across the supply chain. This report provides a complete documentation for the LIBRA model, including model assumptions, data, scenario analysis results, and sensitivity analysis of the model's input space.

25 ENERGY STORAGE↗
NASA NTRS2012

Flow Analysis Tool White Paper

Faster networks are continually being built to accommodate larger data transfers. While it is intuitive to think that implementing faster networks will result in higher throughput rates, this is often not the case. There are many elements involved in data transfer, many of which are beyond the scope of the network itself. Although networks may get bigger and support faster technologies, the presence of other legacy components, such as older application software or kernel parameters, can often cause bottlenecks. Engineers must be able to identify when data flows are reaching a bottleneck that is not imposed by the network and then troubleshoot it using the tools available to them. The current best practice is to collect as much information as possible on the network traffic flows so that analysis is quick and easy. Unfortunately, no single method of collecting this information can sufficiently capture the whole endto- end picture. This becomes even more of a hurdle when large, multi-user systems are involved. In order to capture all the necessary information, multiple data sources are required. This paper presents a method for developing a flow analysis tool to effectively collect network flow data from multiple sources and provide that information to engineers in a clear, concise way for analysis. The purpose of this method is to collect enough information to quickly (and automatically) identify poorly performing flows along with the cause of the problem. The method involves the development of a set of database tables that can be populated with flow data from multiple sources, along with an easyto- use, web-based front-end interface to help network engineers access, organize, analyze, and manage all the information.

Boscia, Nichole K.↗
DOE OSTI2021

Further engineering of R. toruloides for the production of terpenes from lignocellulosic biomass

Abstract Background Mitigation of climate change requires that new routes for the production of fuels and chemicals be as oil-independent as possible. The microbial conversion of lignocellulosic feedstocks into terpene-based biofuels and bioproducts represents one such route. This work builds upon previous demonstrations that the single-celled carotenogenic basidiomycete, Rhodosporidium toruloides , is a promising host for the production of terpenes from lignocellulosic hydrolysates. Results This study focuses on the optimization of production of the monoterpene 1,8-cineole and the sesquiterpene α-bisabolene in R. toruloides . The α-bisabolene titer attained in R. toruloides was found to be proportional to the copy number of the bisabolene synthase (BIS) expression cassette, which in turn influenced the expression level of several native mevalonate pathway genes. The addition of more copies of BIS under a stronger promoter resulted in production of α-bisabolene at 2.2 g/L from lignocellulosic hydrolysate in a 2-L fermenter. Production of 1,8-cineole was found to be limited by availability of the precursor geranylgeranyl pyrophosphate (GPP) and expression of an appropriate GPP synthase increased the monoterpene titer fourfold to 143 mg/L at bench scale. Targeted mevalonate pathway metabolite analysis suggested that 3-hydroxy-3-methyl-glutaryl-coenzyme A reductase (HMGR), mevalonate kinase (MK) and phosphomevalonate kinase (PMK) may be pathway bottlenecks are were therefore selected as targets for overexpression. Expression of HMGR, MK, and PMK orthologs and growth in an optimized lignocellulosic hydrolysate medium increased the 1,8-cineole titer an additional tenfold to 1.4 g/L. Expression of the same mevalonate pathway genes did not have as large an impact on α-bisabolene production, although the final titer was higher at 2.6 g/L. Furthermore, mevalonate pathway intermediates accumulated in the mevalonate-engineered strains, suggesting room for further improvement. Conclusions This work brings R. toruloides closer to being able to make industrially relevant quantities of terpene from lignocellulosic biomass.

09 BIOMASS FUELS↗
DOE OSTI2016

Parallel File System I/O Performance Testing On LANL Clusters

These are slides from a presentation on parallel file system I/O performance testing on LANL clusters. I/O is a known bottleneck for HPC applications. Performance optimization of I/O is often required. This summer project entailed integrating IOR under Pavilion and automating the results analysis. The slides cover the following topics: scope of the work, tools utilized, IOR-Pavilion test workflow, build script, IOR parameters, how parameters are passed to IOR, *run_ior: functionality, Python IOR-Output Parser, Splunk data format, Splunk dashboard and features, and future work.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1999

Improvements to the Unstructured Mesh Generator MESH3D

The AIRPLANE process starts with an aircraft geometry stored in a CAD system. The surface is modeled with a mesh of triangles and then the flow solver produces pressures at surface points which may be integrated to find forces and moments. The biggest advantage is that the grid generation bottleneck of the CFD process is eliminated when an unstructured tetrahedral mesh is used. MESH3D is the key to turning around the first analysis of a CAD geometry in days instead of weeks. The flow solver part of AIRPLANE has proven to be robust and accurate over a decade of use at NASA. It has been extensively validated with experimental data and compares well with other Euler flow solvers. AIRPLANE has been applied to all the HSR geometries treated at Ames over the course of the HSR program in order to verify the accuracy of other flow solvers. The unstructured approach makes handling complete and complex geometries very simple because only the surface of the aircraft needs to be discretized, i.e. covered with triangles. The volume mesh is created automatically by MESH3D. AIRPLANE runs well on multiple platforms. Vectorization on the Cray Y-MP is reasonable for a code that uses indirect addressing. Massively parallel computers such as the IBM SP2, SGI Origin 2000, and the Cray T3E have been used with an MPI version of the flow solver and the code scales very well on these systems. AIRPLANE can run on a desktop computer as well. AIRPLANE has a future. The unstructured technologies developed as part of the HSR program are now targeting high Reynolds number viscous flow simulation. The pacing item in this effort is Navier-Stokes mesh generation.

Thomas, Scott D.↗
DOE OSTI2026

Architectural scaling tradeoffs in modular 3D bosonic quantum processors

We propose a modular three-dimensional bosonic quantum processor built from repeatable coupled-cavity modules linked by configurable interconnect networks. Using hardware-motivated graph-theoretic measures, we compare nearest-neighbor, hub-based, and hybrid architectures in terms of interconnect count, communication distance, resource concentration, and implementation complexity. Rather than identifying a universally optimal topology, our analysis shows how these architectures redistribute the costs of scaling, including wiring and port requirements, nonlocal communication distance, exposure to shared resources, routing bottlenecks, and scheduling overhead. Case studies of a \(3\times3\) processor and a larger hierarchical architecture further distinguish finite-size performance from asymptotic scaling. The resulting framework provides a systematic basis for evaluating modular three-dimensional bosonic processors and for identifying the device-level parameters required for quantitative hardware design.

Zhu, Shaojiang [Fermilab] (ORCID:0000000293180092)↗
NASA NTRS1994

Automated Scalability Analysis Tools for Message Passing Parallel Programs

In order to develop scalable parallel applications, a number of programming decisions have to be made during the development of the program. Performance tools that help in making these decisions are few, if existent. Traditionally, performance tools have focused on exposing performance bottlenecks of small-scale executions of the program. However, it is common knowledge that programs that perform exceptionally well on small processor configurations, more often than not, perform poorly when executed on larger processor configurations. Hence, new tools that predict the execution characteristics of scaled-up programs are an essential part of an application developers toolkit. In this paper we discuss important issues that need to be considered in order to build useful scalability analysis tools for parallel programs. We introduce a simple tool that automatically extracts scalability characteristics of a class of deterministic parallel programs. We show with the help of a number of results on the Intel iPSC/860, that predictions are within reasonable bounds.

Sarukkai, Sekhar R.↗
DOE OSTI2023

Few-Shot Learning Enables Population-Scale Analysis of Leaf Traits in Populus trichocarpa

Plant phenotyping is typically a time-consuming and expensive endeavor, requiring large groups of researchers to meticulously measure biologically relevant plant traits, and is the main bottleneck in understanding plant adaptation and the genetic architecture underlying complex traits at population scale. In this work, we address these challenges by leveraging few-shot learning with convolutional neural networks to segment the leaf body and visible venation of 2,906 Populus trichocarpa leaf images obtained in the field. In contrast to previous methods, our approach (a) does not require experimental or image preprocessing, (b) uses the raw RGB images at full resolution, and (c) requires very few samples for training (e.g., just 8 images for vein segmentation). Traits relating to leaf morphology and vein topology are extracted from the resulting segmentations using traditional open-source image-processing tools, validated using real-world physical measurements, and used to conduct a genome-wide association study to identify genes controlling the traits. In this way, the current work is designed to provide the plant phenotyping community with (a) methods for fast and accurate image-based feature extraction that require minimal training data and (b) a new population-scale dataset, including 68 different leaf phenotypes, for domain scientists and machine learning researchers. All of the few-shot learning code, data, and results are made publicly available.

59 BASIC BIOLOGICAL SCIENCES↗