Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “high performance computation”

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 1,423 records · Page 79

ChatMPI: LLM-Driven MPI Code Generation for HPC Workloads

The Message Passing Interface (MPI) standard plays a crucial role in enabling scientific applications for parallel computing and is an essential component in high-performance computing (HPC). However, implementing MPI code manually—especially applying a proper domain decomposition and communication pattern—is a challenging and error-prone task. We present ChatMPI, an AI assistant for MPI parallelization of sequential C codes. In our analysis, we focus on testing six essential HPC workloads, which are based on Basic Linear Algebra Subprograms levels 1, 2, and 3 as well as sparse, stencil, and iterative operations. We analyze the process of creating ChatMPI by using the ChatHPC library. This lightweight large language model (LLM)–based infrastructure enables HPC experts to efficiently create and supervise trustworthy AI capabilities for critical HPC software tasks. We study the data required for training (fine-tuning) ChatMPI to generate parallel codes that not only use MPI syntax correctly but also apply HPC techniques to reduce memory communication and maximize performance by using proper work decomposition. With a relatively small training dataset composed of a few dozen prompts and fewer than 15 minutes of fine-tuning on one node equipped with two NVIDIA H100 GPUs, ChatMPI elevates trustworthiness for MPI code generation of current LLMs (e.g., Code Llama, ChatGPT-4o and ChatGPT 5). Additionally, we evaluate the performance of the MPI codes generated by ChatMPI in comparison with the ones generated by ChatGPT-4o and ChatGPT-5. The codes generated by ChatMPI provide up to a 4 × boost in performance by using better problem decomposition, communication patterns, and HPC techniques (e.g., communication avoiding).

Valero Lara, Pedro [ORNL] (ORCID:0000000214794310)↗

Mojo Application Monitoring Tool Suite

Mojo is a software tool suite that can be used to monitor the progress of compute jobs on Linux Clusters and other high-performance computing platforms. Mojo is designed to allow system administrators to monitor the health and progress of computing jobs, and to allow users to view the progress and status of their own jobs. The facilities provided include the ability to notify users of job "hangs", and to take an automated action (e.g killing the job) when something goes wrong. These operations can lead to a more efficient use of scarce resources.

Ballance, Robert↗

Computational Science at Los Alamos National Laboratory (Rev. 1) [Slides]

High Performance Computing (HPC) enables problem solving at the grandest scales, on the most complex challenges that face humanity. The problems often tackled by scientific computing are: Very complex; Cool; Using the fastest, most powerful supercomputers on the planet; Often important, impactful, effecting real lives.

97 MATHEMATICS AND COMPUTING↗

AI-Driven Accelerated Inclusion Analysis for Energy Efficient Steelmaking (Final CRADA Report)

This was a collaborative effort between Lawrence Livermore National Security, LLC (LLNS) as manager and operator of Lawrence Livermore National Laboratory (LLNL) and ArcelorMittal USA Research LLC (“ArcelorMittal” as the Participant), to use scanning electron microscopy (SEM) images, computer vision and machine learning methods, and high-performance computing to accelerate the inclusion analysis process of liquid steel so that new methods can be used for near-real time process control on the shop floor.

36 MATERIALS SCIENCE↗

Properties of Electronic Materials

This final technical report summarizes the research conducted under DOE Grant DE-SC0002623, "Properties of Electronic Materials," led by Principal Investigator Shengbai Zhang at Rensselaer Polytechnic Institute. Over the 16-year period, the project employed first-principles computational methods to investigate the structural, electronic, and dynamic properties of a wide range of electronic materials, with applications in energy technologies, optoelectronics, and data storage. Key areas included topological insulators, phase-change materials, graphene and two-dimensional systems, perovskites for photovoltaics, defect engineering in semiconductors, kagome lattices, and ultrafast carrier dynamics. The research resulted in 115 peer-reviewed publications, advancing fundamental understanding of material behaviors at the atomic scale and contributing to innovations in renewable energy, memory devices, and quantum materials. Findings have implications for improving energy efficiency, developing lead-free solar cells, and enabling high-speed data processing. The work has trained numerous graduate students and postdocs, fostering the next generation of computational materials scientists. The original goals were to develop theoretical models and computational tools to predict and optimize electronic properties of materials for energy applications. All objectives were accomplished, with no major departures from planned methodologies. Challenges in computational scaling were addressed through access to high-performance computing resources.

36 MATERIALS SCIENCE↗

A Geometry Based Infra-Structure for Computational Analysis and Design

The computational steps traditionally taken for most engineering analysis suites (computational fluid dynamics (CFD), structural analysis, heat transfer and etc.) are: (1) Surface Generation -- usually by employing a Computer Assisted Design (CAD) system; (2) Grid Generation -- preparing the volume for the simulation; (3) Flow Solver -- producing the results at the specified operational point; (4) Post-processing Visualization -- interactively attempting to understand the results. For structural analysis, integrated systems can be obtained from a number of commercial vendors. These vendors couple directly to a number of CAD systems and are executed from within the CAD Graphical User Interface (GUI). It should be noted that the structural analysis problem is more tractable than CFD; there are fewer mesh topologies used and the grids are not as fine (this problem space does not have the length scaling issues of fluids). For CFD, these steps have worked well in the past for simple steady-state simulations at the expense of much user interaction. The data was transmitted between phases via files. In most cases, the output from a CAD system could go to Initial Graphics Exchange Specification (IGES) or Standard Exchange Program (STEP) files. The output from Grid Generators and Solvers do not really have standards though there are a couple of file formats that can be used for a subset of the gridding (i.e. PLOT3D data formats). The user would have to patch up the data or translate from one format to another to move to the next step. Sometimes this could take days. Specifically the problems with this procedure are:(1) File based -- Information flows from one step to the next via data files with formats specified for that procedure. File standards, when they exist, are wholly inadequate. For example, geometry from CAD systems (transmitted via IGES files) is defined as disjoint surfaces and curves (as well as masses of other information of no interest for the Grid Generator). This is particularly onerous for modern CAD systems based on solid modeling. The part was a proper solid and in the translation to IGES has lost this important characteristic. STEP is another standard for CAD data that exists and supports the concept of a solid. The problem with STEP is that a solid modeling geometry kernel is required to query and manipulate the data within this type of file. (2) 'Good' Geometry. A bottleneck in getting results from a solver is the construction of proper geometry to be fed to the grid generator. With 'good' geometry a grid can be constructed in tens of minutes (even with a complex configuration) using unstructured techniques. Adroit multi-block methods are not far behind. This means that a million node steady-state solution can be computed on the order of hours (using current high performance computers) starting from this 'good' geometry. Unfortunately, the geometry usually transmitted from the CAD system is not 'good' in the grid generator sense. The grid generator needs smooth closed solid geometry. It can take a week (or more) of interaction with the CAD output (sometimes by hand) before the process can begin. One way Communication. (3) One-way Communication -- All information travels on from one phase to the next. This makes procedures like node adaptation difficult when attempting to add or move nodes that sit on bounding surfaces (when the actual surface data has been lost after the grid generation phase). Until this process can be automated, more complex problems such as multi-disciplinary analysis or using the above procedure for design becomes prohibitive. There is also no way to easily deal with this system in a modular manner. One can only replace the grid generator, for example, if the software reads and writes the same files. Instead of the serial approach to analysis as described above, CAPRI takes a geometry centric approach. This makes the actual geometry (not a discretized version) accessible to all phases of the analysis. The connection to the geometry is made through an Application Programming Interface (API) and NOT a file system. This API isolates the top-level applications (grid generators, solvers and visualization components) from the geometry engine. Also this allows the replacement of one geometry kernel with another, without effecting these top-level applications. For example, if UniGraphics is used as the CAD package then Parasolid (UG's own geometry engine) can be used for all geometric queries so that no solid geometry information is lost in a translation. This is much better than STEP because when the data is queried, the same software is executed as used in the CAD system. Therefore, one analyzes the exact part that is in the CAD system. CAPRI uses the same idea as the commercial structural analysis codes but does not specify control. Software components of the CAD system are used, but the analysis suite, not the CAD operator, specifies the control of the software session. This also means that the license issues (may be) minimized and individuals need not have to know how to operate a CAD system in order to run the suite.

Haimes, Robert↗

Understanding the Impact of Interconnect Failures on System Operation

Hardware failures are inevitable on large high performance computing systems. Faults or performance degradations in the high-speed network can reduce the entire system s performance. Since the introduction of the Gemini interconnect, Cray systems have become resilient to many networking faults that were fatal in their previous generation systems. These new network reliability and resiliency features have enabled higher uptimes on Cray systems by allowing them to continue running with reduced network performance. Oak Ridge National Laboratory has developed a set of user-level diagnostics that stresses the high-speed network and searches for components that are not performing as expected. Nearest-neighbor bandwidth tests check every network chip and network link in the system. Additionally, performance counters stored on the network ASIC s memory mapped registers (MMRs) are used to better understand the state of the network. Applications have also been characterized under various suboptimal network conditions to better understand what impact network problems have on user codes.

Cray↗

DRAGON: breaking GPU memory capacity limits with direct NVM access

Heterogeneous computing with accelerators is growing in importance in high performance computing (HPC). Recently, application datasets have expanded beyond the memory capacity of these accelerators, and often beyond the capacity of their hosts. Meanwhile, nonvolatile memory (NVM) storage has emerged as a pervasive component in HPC systems because NVM provides massive amounts of memory capacity at affordable cost. Currently, for accelerator applications to use NVM, they must manually orchestrate data movement across multiple memories and this approach only performs well for applications with simple access behaviors. To address this issue, we developed DRAGON, a solution that enables all classes of GP-GPU applications to transparently compute on terabyte datasets residing in NVM. DRAGON leverages the page-faulting mechanism on the recent NVIDIA GPUs by extending capabilities of CUDA Unified Memory (UM). Our experimental results show that DRAGON transparently expands memory capacity and obtain additional speedups via automated I/O and data transfer overlapping.

Markthub, Pak↗

Intelligently-Automated Facilities Expansion with the HEPCloud Decision Engine

The next generation of High Energy Physics experiments are expected to generate exabytes of data---two orders of magnitude greater than the current generation. In order to reliably meet peak demands, facilities must either plan to provision enough resources to cover the forecasted need, or find ways to elastically expand their computational capabilities. Commercial cloud and allocation-based High Performance Computing (HPC) resources both have explicit and implicit costs that must be considered when deciding when to provision these resources, and to choose an appropriate scale. In order to support such provisioning in a manner consistent with organizational business rules and budget constraints, we have developed a modular intelligent decision support system (IDSS) to aid in the automatic provisioning of resources---spanning multiple cloud providers, multiple HPC centers, and grid computing federations.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Parameter Determination of the Non-Local Granular Fluidity Model for Wood Chips by Comparison to Well-Defined Experimental Flow Systems

Unlike simple liquids and gases, the bulk flow and transport of granular materials remain poorly understood by physicists and pose many problems for engineers in designing and operating bulk-solids handling equipment. Discrete element methods (DEM) are currently considered the state-of-the-art for simulating the flow of granular materials, but DEM is limited in system size to about a few million particles due to high computational costs, even when run on current high-performance computing architectures. Continuum models are needed to simulate the flows of bulk solids in industrial-scale vessels and equipment, e.g., grain silos and coal-ash disposal piles. The focus of this work is the so-called nonlocal granular fluidity (NLGF) model that has been previously shown to reproduce observed nonlocal behaviors that arise when granular phenomena occur on length scales that are near the scale of the system geometry, e.g., the jamming of hopper outlets and the stop-height of piles on inclines [PNAS, 110(17), 6730-6735]. We have implemented the NLGF constitutive model in OpenFOAM CFD software, performed simulations of well-defined flow systems, and compared the results to experimental data. Experimental systems include a ring-shear tester, pile formation, flow on an incline, and discharge of a hopper. The tested material was loblolly pine wood chips that were milled and sieved to a size range of roughly 0.05-0.25 inches in diameter. The NLGF model parameters were tuned to achieve reasonable agreement between simulation and experimental results. Further, we evaluate the mapping between measurable material properties (bulk friction angle, particle-particle friction, compressibility, grain diameter, etc.) with NLGF model parameters, some of which have direct analogs (friction parameters and grain diameter) while others are constructs of the model (nonlocal amplitude and timescale of fluidity evolution).

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

INL Poster - Juan Barrera Salazar

Generation IV nuclear reactors introduce several advantages and benefits in terms of safety and efficiency when compared with their predecessors from previous generation. This is due, among many things, to the use of innovative forms of fuel and coolant, different from the conventional ones used in the last decades. Given that these upcoming designs utilize emerging technologies, the related instrumentation is also in the process of being developed; therefore, it is necessary to establish the sensitivity requirements and the effects of uncertainty on different properties of the components and elements of the reactor designs. This report presents the results of simulations that quantify the impacts of the uncertainties of four thermophysical properties of the refrigerant salt (LiF-BeF2) for the Kairos Power benchmark model (g-FHR) for steady state making use of the Sobol’ method through polynomial chaos surrogate modeling. The properties of the salt to which uncertainty was evaluated were density, dynamic viscosity, thermal conductivity and heat capacity. This study was carried out using the Griffin/Pronghorn multiphysics model under the computational resources of the Idaho National Laboratory (INL) High Performance Computing (HPC). The results indicate a weak dependence of the uncertainty of thermal conductivity on the quantities of core pressure drop and core outlet temperature.

21 - SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLAN↗

Hot Chips and Hot Interconnects for High End Computing Systems

I will discuss several processors: 1. The Cray proprietary processor used in the Cray X1; 2. The IBM Power 3 and Power 4 used in an IBM SP 3 and IBM SP 4 systems; 3. The Intel Itanium and Xeon, used in the SGI Altix systems and clusters respectively; 4. IBM System-on-a-Chip used in IBM BlueGene/L; 5. HP Alpha EV68 processor used in DOE ASCI Q cluster; 6. SPARC64 V processor, which is used in the Fujitsu PRIMEPOWER HPC2500; 7. An NEC proprietary processor, which is used in NEC SX-6/7; 8. Power 4+ processor, which is used in Hitachi SR11000; 9. NEC proprietary processor, which is used in Earth Simulator. The IBM POWER5 and Red Storm Computing Systems will also be discussed. The architectures of these processors will first be presented, followed by interconnection networks and a description of high-end computer systems based on these processors and networks. The performance of various hardware/programming model combinations will then be compared, based on latest NAS Parallel Benchmark results (MPI, OpenMP/HPF and hybrid (MPI + OpenMP). The tutorial will conclude with a discussion of general trends in the field of high performance computing, (quantum computing, DNA computing, cellular engineering, and neural networks).

Saini, Subhash↗

Hard Disk/Solid State Drive Synergy in Support of Data-Intensive Computing [Slides]

Data-intensive applications are becoming increasingly common in high-performance computing. Examples include combustion simulation, human genome analysis, and satellite image processing. Efficient access of data sets is critical to the performance of these applications. Because of the size of the data today's economically feasible approach is to store the data files on an array of hard disks or data servers equipped with hard disks and managed by a parallel file system such as PVFS or Lustre wherein the data is striped over a (large) number of disks for high aggregate I/O throughout. With file striping, a request for a segment of logically contiguous file space is decomposed into multiple sub-requests, each to a different server. While the data unit for this striping is usually reasonably large to benefit disk efficiency, the first and/or last sub-requests can be much smaller than the striping unit if the request does not align with the striping pattern, severely compromising hard disk efficiency and thus application performance. We propose to exploit solid state drives (SSD), whose efficiency is much less sensitive to small random accesses, to enable the alignment of requests to disk with the data striping pattern. In this scheme hard disks mainly serve large, aligned, sequential requests, with SSDs serving small or unaligned requests, thus respecting the relative cost, performance, and durability characteristics of the two media, and thereby achieving synergy in performance/cost. We will describe the design of the proposed scheme, its implementation on CCS-7's Darwin cluster, and performance results.

97 MATHEMATICS AND COMPUTING↗

The OpenMC Monte Carlo particle transport code

A new Monte Carlo code called OpenMC is currently under development at the Massachusetts Institute of Technology as a tool for simulation on high-performance computing platforms. Given that many legacy codes do not scale well on existing and future parallel computer architectures, OpenMC has been developed from scratch with a focus on high performance scalable algorithms as well as modern software design practices. The present work describes the methods used in the OpenMC code and demonstrates the performance and accuracy of the code on a variety of problems.

Nuclear Science & Technology↗

PoPLAR: Portal for Petascale Lifescience Applications and Research

Background: We are focusing specifically on fast data analysis and retrieval in bioinformatics that will have a direct impact on the quality of human health and the environment. The exponential growth of data generated in biology research, from small atoms to big ecosystems, necessitates an increasingly large computational component to perform analyses. Novel DNA sequencing technologies and complementary high-throughput approaches–such as proteomics, genomics, metabolomics, and meta-genomics–drive data-intensive bioinformatics. While individual research centers or universities could once provide for these applications, this is no longer the case. Today, only specialized national centers can deliver the level of computing resources required to meet the challenges posed by rapid data growth and the resulting computational demand. Consequently, we are developing massively parallel applications to analyze the growing flood of biological data and contribute to the rapid discovery of novel knowledge. Methods: The efforts of previous National Science Foundation (NSF) projects provided for the generation of parallel modules for widely used bioinformatics applications on the Kraken supercomputer. We have profiled and optimized the code of some of the scientific community’s most widely used desktop and small-cluster-based applications, including BLAST from the National Center for Biotechnology Information (NCBI), HMMER, and MUSCLE; scaled them to tens of thousands of cores on high-performance computing (HPC) architectures; made them robust and portable to next-generation architectures; and incorporated these parallel applications in science gateways with a web-based portal. Results: This paper will discuss the various developmental stages, challenges, and solutions involved in taking bioinformatics applications from the desktop to petascale with a front-end portal for very-large-scale data analysis in the life sciences. Conclusions: This research will help to bridge the gap between the rate of data generation and the speed at which scientists can study this data. The ability to rapidly analyze data at such a large scale is having a significant, direct impact on science achieved by collaborators who are currently using these tools on supercomputers.

59 BASIC BIOLOGICAL SCIENCES↗

Applied Information Systems Research Program (AISRP). Workshop 2: Meeting Proceedings

The Earth and space science participants were able to see where the current research can be applied in their disciplines and computer science participants could see potential areas for future application of computer and information systems research. The Earth and Space Science research proposals for the High Performance Computing and Communications (HPCC) program were under evaluation. Therefore, this effort was not discussed at the AISRP Workshop. OSSA's other high priority area in computer science is scientific visualization, with the entire second day of the workshop devoted to it.

Source record↗

Multi-scale approach to the modeling of fission gas discharge during hypothetical loss-of-flow accident in gen-IV sodium fast reactor

The required technological and safety standards for future Gen IV Reactors can only be achieved if advanced simulation capabilities become available, which combine high performance computing with the necessary level of modeling detail and high accuracy of predictions. The purpose of this paper is to present new results of multi-scale three-dimensional (3D) simulations of the inter-related phenomena, which occur as a result of fuel element heat-up and cladding failure, including the injection of a jet of gaseous fission products into a partially blocked Sodium Fast Reactor (SFR) coolant channel, and gas/molten sodium transport along the coolant channels. The computational approach to the analysis of the overall accident scenario is based on using two different inter-communicating computational multiphase fluid dynamics (CMFD) codes: a CFD code, PHASTA, and a RANS code, NPHASE-CMFD. Using the geometry and time history of cladding failure and the gas injection rate, direct numerical simulations (DNS), combined with the Level Set method, of two-phase turbulent flow have been performed by the PHASTA code. The model allows one to track the evolution of gas/liquid interfaces at a centimeter scale. The simulated phenomena include the formation and breakup of the jet of fission products injected into the liquid sodium coolant. The PHASTA outflow has been averaged over time to obtain mean phasic velocities and volumetric concentrations, as well as the liquid turbulent kinetic energy and turbulence dissipation rate, all of which have served as the input to the core-scale simulations using the NPHASE-CMFD code. A sliding window time averaging has been used to capture mean flow parameters for transient cases. The results presented in the paper include testing and validation of the proposed models, as well the predictions of fission-gas/liquid-sodium transport along a multi-rod fuel assembly of SFR during a partial loss-of-flow accident. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Provisioning a Multi-Tiered Data Staging Area for Extreme-Scale Machines

Massively parallel scientific applications, running on extreme-scale supercomputers, produce hundreds of terabytes of data per run, driving the need for storage solutions to improve their I/O performance. Traditional parallel file systems (PFS) in high performance computing (HPC) systems are unable to keep up with such high data rates, creating a storage wall. In this work, we present a novel multi-tiered storage architecture comprising hybrid node-local resources to construct a dynamic data staging area for extreme-scale machines. Such a staging ground serves as an impedance matching device between applications and the PFS. Our solution combines diverse resources (e.g., DRAM, SSD) in such a way as to approach the performance of the fastest component technology and the cost of the least expensive one. We have developed an automated provisioning algorithm that aids in meeting the checkpointing performance requirement of HPC applications, by using a least-cost storage configuration. We evaluate our approach using both an implementation on a large scale cluster and a simulation driven by six-years worth of Jaguar supercomputer job-logs, and show that our approach, by choosing an appropriate storage configuration, achieves 41.5% cost savings with only negligible impact on performance.

99 GENERAL AND MISCELLANEOUS↗