Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “high performance computing systems”

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 1,297 records · Page 72

An Optimizing Compiler for Petascale I/O on Leadership-Class Architectures

In high-performance computing (HPC), parallel I/O architectures usually have very complex hierarchies with multiple layers that collectively constitute an I/O stack, including high-level I/O libraries such as PnetCDF and HDF5, I/O middleware such as MPI-IO, and parallel file systems such as PVFS and Lustre. Our DOE project explored automated instrumentation and compiler support for I/O intensive applications. Our project made significant progress towards understanding the complex I/O hierarchies of high-performance storage systems (including storage caches, HDDs, and SSDs), and designing and implementing state-of-the-art compiler/runtime system technology that targets I/O intensive HPC applications that target leadership class machine. This final report summarizes the major achievements of the project and also points out promising future directions Two new sections in this report compared to the previous report are IOGenie and SSD/NVM-specific optimizations.

97 MATHEMATICS AND COMPUTING↗

Insights From the Software Design of a Multiphysics Multicomponent Scientific Code

Using simulations for scientific discovery requires that the software used in the simulations undergoes a rigorous design and development process similar to that of the lab instruments in the experimental sciences. To devise a good design methodology, it is critical to understand the requirements, constraints, and challenges. Furthermore, this article describes insights from the long-term stewardship of a multiphysics multicomponent software, FLASH, that was designed more than 20 years ago for astrophysics, now serves multiple communities, and has been successful in adapting to the changing world of high-performance computing.

97 MATHEMATICS AND COMPUTING↗

Timely Result-Data Offloading for Improved HPC Center Scratch Provisioning and Serviceability

Modern High-Performance Computing (HPC) centers are facing a data deluge from emerging scientific applications. Supporting large data entails a significant commitment of the highthroughput center storage system, scratch space. However, the scratch space is typically managed using simple purge policies, without sophisticated end-user data services to balance resource consumption and user serviceability. End-user data services such as offloading are performed using point-to-point transfers that are unable to reconcile center s purge and users delivery deadlines, unable to adapt to changing dynamics in the end-toend data path and are not fault-tolerant. Such inefficiencies can be prohibitive to sustaining high performance. In this paper, we address the above issues by designing a framework for the timely, decentralized offload of application result data. Our framework uses an overlay of user-specified intermediate and landmark sites to orchestrate a decentralized fault-tolerant delivery. We have implemented our techniques within a production job scheduler (PBS) and data transfer tool (BitTorrent). Our evaluation using both a real implementation and supercomputer job log-driven simulations show that: the offloading times can be significantly reduced (90.4% for a 5 GB data transfer); the exposure window can be minimized while also meeting center-user Service Level Agreements.

99 GENERAL AND MISCELLANEOUS↗

DenKv: Addressing Design Trade-offs of Key-value Stores for Scientific Applications

High-performance computing (HPC) facilities have employed flash-based storage tier near to compute nodes to absorb high I/O demand by HPC applications during periodic system-level checkpoints. To accelerate these checkpoints, proxy-based distributed key-value stores (PD-KVS) gained particular attention for their flexibility to support multiple backends and different network configurations. PD-KVS rely internally on monolithic KVS, such as LevelDB or RocksDB, to exploit the KV interface and query support. However, PD-KVS are unaware of the high redundancy factor in checkpoint data, which can be up to GBs to TBs, and therefore, tend to generate high write and space amplification on these storage layers. In this paper, we propose DenKv which is deduplication-extended node-local LSM-tree-based KVS. DenKv employs asynchronous partially inline dedup (APID) and aims to maintain the performance characteristics of LSM-tree-based KVS while reducing the write and space amplification problems. We implemented DenKv atop BlobDB and showed that our proposed solution maintains performance while reducing write amplification up to 2× and space amplification by 4× on average.

Khan, Awais↗

Advanced co-simulation for computer-aided process design and optimization of fossil energy systems with carbon capture

In this paper, we describe recent progress toward developing an Advanced Process Engineering Co-Simulator (APECS) for use in computer-aided design and optimization of fossil energy systems with carbon capture. The APECS system combines process simulation with multiphysicsbased equipment simulations, such as those based on computational fluid dynamics. These co-simulation capabilities enable design engineers to optimize overall process performance with respect to complex thermal and fluid flow phenomena arising in key plant equipment items. This paper also highlights ongoing co-simulation R&D activities in areas such as reduced order modeling, knowledge management, stochastic analysis and optimization, and virtual plant co-simulation. Continued progress in co-simulation technology— through improved integration, solution, deployment, and analysis —will have profound positive impacts on the design and optimization of high-efficiency, near-zero emission fossil energy systems.

97 MATHEMATICS AND COMPUTING↗

Designing a Scalable Fault Tolerance Model for High Performance Computational Chemistry: A Case Study with Coupled Cluster Perturbative Triples

In the last couple of decades, the massive computational power provided by the most modern supercomputers has resulted in simulation of higher order computational chem- istry methods, previously considered intractable. As the system sizes continue to increase, computational chemistry domain continues to escalate this trend using parallel comput- ing with programming models such as Message Passing Interface (MPI) and Partitioned Global Address Space (PGAS) programming models such as Global Arrays. The ever increasing scale of these supercomputers comes at a cost of reduced mean time between failures, currently in the order of days, and projected to be in the order of hours for up- coming extreme scale systems. While traditional disk based checkpointing methods are ubiquitous for storing intermediate solutions, they suffer from high overhead of writing and recovering from checkpoints. In practice, checkpointing itself often brings the system down. Clearly, methods beyond checkpointing are imperative to handling the aggravating issue of reducing MTBF. In this paper, we address this challenge by designing and im- plementing an efficient fault tolerant version of coupled cluster method with NWChem, using in memory data redundancy. We present the challenges associated with our de- sign including efficient data storage model, maintenance of at least one consistent data copy and the recovery process. Our performance evaluation without faults shows that the current design exhibits negligible overhead. In the presence of a fault, the proposed design incurs negligible overhead in comparison to the state of the art implementation without faults.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Development of experimental and computational frameworks to predict subcooled flow boiling in the LANL Isotope Production Facility

Cooling is crucial to maintain the integrity of target systems in isotope production facilities. At Los Alamos National Laboratory (LANL)’s Isotope Production Facility (IPF), multiple encapsulated targets are stacked and irradiated in tandem with a 100 MeV, ~250μA proton beam. To facilitate effective heat removal, these stacked targets are separated and cooled via a series of water channels. At these beam currents, this high-energy proton beam heats the target system, likely initiating subcooled flow boiling in the cooling channels. However, in-beam monitoring of the IPF target system is not possible due to the extreme radiation environment, and the necessarily significant shielding. To better understand high-power target performance, we developed ex-situ experimental and computational frameworks to predict the behavior of subcooled flow boiling at IPF. Subcooled flow boiling experiments on Inconel 625 samples under IPF conditions (2 bar pressure, 10 GPM flow rate (i.e., 2249 kg/m 2 /s), 85 K subcooling) revealed that IPF's average operating power is at the early stage of boiling with a heat transfer coefficient of 48,000 W/m 2 /s. The proposed modeling framework enables us to predict a complete boiling curve, i.e., single-phase heat transfer, onset of nucleate boiling, two-phase heat transfer, and critical heat flux (CHF), with specification of input boiling parameters up to intermediate heat flux levels. The estimated CHF under IPF conditions is 5.2 MW/m 2 . Experimental data under reduced conditions (2 bar pressure, 1.5 GPM flow rate (i.e., 337 kg/m 2 /s), 45 K subcooling) served as validation cases for the computational modeling. This computational model can be further extended to more complicated systems replicating the real IPF configuration, for instance, to study void distribution as a function of the incident proton beam profile and coolant velocity profile of multiple cooling channels. Finally, the proposed experimental and computational frameworks provide a means to better understand cooling systems in the isotope production facilities at different accelerators, where in-beam monitoring of the cooling process is not available.

07 ISOTOPE AND RADIATION SOURCES↗

A Parallel Graph Environment for Real-World Data Analytics Workflows

Economic competitiveness and national security depend increasingly on the insightful analysis of large data sets. The diversity of real-world data sources and analytic workflows impose challenging hardware and software requirements for parallel graph platforms. The irregular nature of graph methods is not supported well by the deep memory hierarchies of conventional distributed systems, requiring new processor and runtime system designs to tolerate memory and synchronization latencies. Moreover, the efficiency of relational table operations and matrix computations are not attainable when data is stored in common graph data structures. In this paper, we present HAGGLE, a high-performance, scalable data analytics platform. The platform’s hybrid data model supports a variety of distributed, thread-safe data structures, parallel programming constructs, and persistent and streaming data. An abstract runtime layer enables us to map the stack to conventional, distributed computer systems with accelerators. The runtime uses multithreading, active messages, and data aggregation to hide memory and synchronization latencies on large-scale systems.

Graph Analytics↗

A massively parallel semi-Lagrangian algorithm for solving the transport equation

The scalar transport equation underpins many models employed in science, engineering, technology and business. Application areas include, but are not restricted to, pollution transport, weather forecasting, video analysis and encoding (the optical flow equation), options and stock pricing (the Black-Scholes equation) and spatially explicit ecological models. Unfortunately finding numerical solutions to this equation which are fast and accurate is not trivial. Moreover, finding such numerical algorithms that can be implemented on high performance computer architectures efficiently is challenging. In this paper the authors describe a massively parallel algorithm for solving the advection portion of the transport equation. We present an approach here which is different to that used in most transport models and which we have tried and tested for various scenarios. The approach employs an intelligent domain decomposition based on the vector field of the system equations and thus automatically partitions the computational domain into algorithmically autonomous regions. The solution of a classic pure advection transport problem is shown to be conservative, monotonic and highly accurate at large time steps. Additionally we demonstrate that the algorithm is highly efficient for high performance computer architectures and thus offers a route towards massively parallel application.

54 ENVIRONMENTAL SCIENCES↗

Machine learning the metastable phase diagram of covalently bonded carbon

Abstract Conventional phase diagram generation involves experimentation to provide an initial estimate of the set of thermodynamically accessible phases and their boundaries, followed by use of phenomenological models to interpolate between the available experimental data points and extrapolate to experimentally inaccessible regions. Such an approach, combined with high throughput first-principles calculations and data-mining techniques, has led to exhaustive thermodynamic databases (e.g. compatible with the CALPHAD method), albeit focused on the reduced set of phases observed at distinct thermodynamic equilibria. In contrast, materials during their synthesis, operation, or processing, may not reach their thermodynamic equilibrium state but, instead, remain trapped in a local (metastable) free energy minimum, which may exhibit desirable properties. Here, we introduce an automated workflow that integrates first-principles physics and atomistic simulations with machine learning (ML), and high-performance computing to allow rapid exploration of the metastable phases to construct “metastable” phase diagrams for materials far-from-equilibrium. Using carbon as a prototypical system, we demonstrate automated metastable phase diagram construction to map hundreds of metastable states ranging from near equilibrium to far-from-equilibrium (400 meV/atom). We incorporate the free energy calculations into a neural-network-based learning of the equations of state that allows for efficient construction of metastable phase diagrams. We use the metastable phase diagram and identify domains of relative stability and synthesizability of metastable materials. High temperature high pressure experiments using a diamond anvil cell on graphite sample coupled with high-resolution transmission electron microscopy (HRTEM) confirm our metastable phase predictions. In particular, we identify the previously ambiguous structure of n -diamond as a cubic-analog of diaphite-like lonsdaelite phase.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Pass-efficient methods for compression of high-dimensional turbulent flow data

The future of high-performance computing, specifically on future Exascale computers, will presumably see memory capacity and bandwidth fail to keep pace with data generated, for instance, from massively parallel partial differential equation (PDE) systems. Current strategies proposed to address this bottleneck entail the omission of large fractions of data, as well as the incorporation of in situ compression algorithms to avoid overuse of memory. To ensure that post-processing operations are successful, this must be done in a way that a sufficiently accurate representation of the solution is stored. Moreover, in situations where the input/output system becomes a bottleneck in analysis, visualization, etc., or the execution of the PDE solver is expensive, the number of passes made over the data must be minimized. In the interest of addressing this problem, this work focuses on the utility of pass-efficient, parallelizable, low-rank, matrix decomposition methods in compressing high-dimensional simulation data from turbulent flows. Additionally, a particular emphasis is placed on using coarse representation of the data – compatible with the PDE discretization grid – to accelerate the construction of the low-rank factorization. This includes the presentation of a novel single-pass matrix decomposition algorithm for computing the so-called interpolative decomposition. The methods are described extensively and numerical experiments on two turbulent channel flow data are performed. In the first (unladen) channel flow case, compression factors exceeding 400 are achieved while maintaining accuracy with respect to first- and second-order flow statistics. In the particle-laden case, compression factors of 100 are achieved and the compressed data is used to recover particle velocities. These results show that these compression methods can enable efficient computation of various quantities of interest in both the carrier and disperse phases.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

High energy x-ray phase contrast CT using glancing-angle grating interferometers

Purpose: The authors present initial progress toward a clinically compatible x-ray phase contrast CT system, using glancing-angle x-ray grating interferometry to provide high contrast soft tissue images at estimated by computer simulation dose levels comparable to conventional absorption based CT. Methods: DPC-CT scans of a joint phantom and of soft tissues were performed in order to answer several important questions from a clinical setup point of view. A comparison between high and low fringe visibility systems is presented. The standard phase stepping method was compared with sliding window interlaced scanning. Using estimated dose values obtained with a Monte-Carlo code the authors studied the dependence of the phase image contrast on exposure time and dose. Results: Using a glancing angle interferometer at high x-ray energy (∼45 keV mean value) in combination with a conventional x-ray tube the authors achieved fringe visibility values of nearly 50%, never reported before. High fringe visibility is shown to be an indispensable parameter for a potential clinical scanner. Sliding window interlaced scanning proved to have higher SNRs and CNRs in a region of interest and to also be a crucial part of a low dose CT system. DPC-CT images of a soft tissue phantom at exposures in the range typical for absorption based CT of musculoskeletal extremities were obtained. Assuming a human knee as the CT target, good soft tissue phase contrast could be obtained at an estimated absorbed dose level around 8 mGy, similar to conventional CT. Conclusions: DPC-CT with glancing-angle interferometers provides improved soft tissue contrast over absorption CT even at clinically compatible dose levels (estimated by a Monte-Carlo computer simulation). Further steps in image processing, data reconstruction, and spectral matching could make the technique fully clinically compatible. Nevertheless, due to its increased scan time and complexity the technique should be thought of not as replacing, but as complimentary to conventional CT, to be used in specific applications.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Multileaf collimator performance monitoring and improvement using semiautomated quality control testing and statistical process control

Purpose: High-quality radiation therapy using highly conformal dose distributions and image-guided techniques requires optimum machine delivery performance. In this work, a monitoring system for multileaf collimator (MLC) performance, integrating semiautomated MLC quality control (QC) tests and statistical process control tools, was developed. The MLC performance monitoring system was used for almost a year on two commercially available MLC models. Control charts were used to establish MLC performance and assess test frequency required to achieve a given level of performance. MLC-related interlocks and servicing events were recorded during the monitoring period and were investigated as indicators of MLC performance variations. Methods: The QC test developed as part of the MLC performance monitoring system uses 2D megavoltage images (acquired using an electronic portal imaging device) of 23 fields to determine the location of the leaves with respect to the radiation isocenter. The precision of the MLC performance monitoring QC test and the MLC itself was assessed by detecting the MLC leaf positions on 127 megavoltage images of a static field. After initial calibration, the MLC performance monitoring QC test was performed 3–4 times/week over a period of 10–11 months to monitor positional accuracy of individual leaves for two different MLC models. Analysis of test results was performed using individuals control charts per leaf with control limits computed based on the measurements as well as two sets of specifications of ±0.5 and ±1 mm. Out-of-specification and out-of-control leaves were automatically flagged by the monitoring system and reviewed monthly by physicists. MLC-related interlocks reported by the linear accelerator and servicing events were recorded to help identify potential causes of nonrandom MLC leaf positioning variations. Results: The precision of the MLC performance monitoring QC test and the MLC itself was within ±0.22 mm for most MLC leaves and the majority of the apparent leaf motion was attributed to beam spot displacements between irradiations. The MLC QC test was performed 193 and 162 times over the monitoring period for the studied units and recalibration had to be repeated up to three times on one of these units. For both units, rate of MLC interlocks was moderately associated with MLC servicing events. The strongest association with the MLC performance was observed between the MLC servicing events and the total number of out-of-control leaves. The average elapsed time for which the number of out-of-specification or out-of-control leaves was within a given performance threshold was computed and used to assess adequacy of MLC test frequency. Conclusions: A MLC performance monitoring system has been developed and implemented to acquire high-quality QC data at high frequency. This is enabled by the relatively short acquisition time for the images and automatic image analysis. The monitoring system was also used to record and track the rate of MLC-related interlocks and servicing events. MLC performances for two commercially available MLC models have been assessed and the results support monthly test frequency for widely accepted ±1 mm specifications. Higher QC test frequency is however required to maintain tighter specification and in-control behavior.

07 ISOTOPE AND RADIATION SOURCES↗

Ultra-thick three-dimensional interpenetrating graphene electrode architectures for high volumetric density energy storage

For electrochemical energy storage, increasing the electrode thickness is an effective approach to achieving higher energy density from a given material. However, this often compromises ion transport, leading to diminished performance. Here, in this study, we present a novel platform for fabricating complex 3D interpenetrating electrode structures via photo-polymerization 3D printing, integrated with computational structural optimization for energy storage. The platform employs an acrylate resin system infused with graphene oxide (GO), enabling high-fidelity printing of optimized porous structures and facilitating efficient electron and ion transport in ultra-thick electrodes. The optimized 3D layouts substantially enhance energy and power densities compared to conventional configurations, ensuring superior material utilization and minimal ohmic losses. Supercapacitors fabricated using this approach achieved an exceptional energy density of 4.7 Wh L−1 at a power density of 1689.0 W L−1, surpassing traditional designs. This work underscores the transformative role of structural optimization in advancing electrochemical performance and establishes a versatile pathway for developing next-generation energy storage systems with exceptional efficiency and functionality.

Wang, Zhen [University of California, Berkeley, CA↗

Runtime Scheduling Policies for Distributed Graph Algorithms

In this paper we explore scheduling and runtime system support for unordered distributed graph computations that rely on optimistic (speculative) execution. Performance of such algorithms is impacted by two competing trends: the higher degree of parallelism enabled by optimistic execution in turn requires substantial runtime support. To address the potentially high overhead and scheduling complexity introduced by the runtime, we investigate customizable scheduling policies that augment the scheduler of the underlying runtime to adapt it to a specific graph application. We present several implementations of Distributed Control (DC), a data-driven unordered approach with work prioritization and demonstrate that customizable scheduling policies result in the most efficient implementation, outperforming the well-known -stepping Single-Source Shortest Paths (SSSP) and Jones-Plassmann vertex-coloring algorithms. We apply two scheduling techniques, flow control and adaptive frequency of network progress, which allow application-level control over the balance of domain work and the runtime work. Experimental results show the benefit of such application-aware scheduling for irregular distributed graph algorithms.

Firoz, Jesun S.↗

Multi-Fidelity Stochastic Economic Dispatch for Operating Low Carbon Power Grids

Grid operators can address the inherently stochastic nature of renewables by solving a two-stage stochastic programming model that minimizes the cost of dispatch decisions while accounting for the complex grid dynamics. It is common to use a sample average approximation to estimate the expectation of the second stage costs in this model. However, the large sample count needed for numerical accuracy makes effective modeling large-scale electric grids computationally intractable. We introduce a control variate multi-fidelity estimator for the second-stage recourse that enables high quality dispatch decisions in real-time with a reduced computational burden. We obtain a hierarchy of model fidelities by linearizing the AC power flow system representation to DC power flow, and by relaxing transmission and voltage network constraints. We evaluate the performance of our proposed method on a synthetic grid with 73 buses against a deterministic baseline with persistence forecast and a high-fidelity reference. Our analysis shows a computational speed-up of 7.62x with a minimal loss in accuracy. The multi-fidelity method is well suited to fidelity combinations that use a simplified network topology in their lower fidelity model and is an attractive option for applications where accurate grid modeling needed on a limited computational budget.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Quantum simulations of excited states with active-space downfolded Hamiltonians

Many-body techniques based on the double unitary coupled cluster ansatz (DUCC) can be used to downfold electronic Hamiltonians into low-dimensional active spaces. It can be shown that the resulting dimensionality reduced Hamiltonians are amenable for quantum computing. Recent studies performed for several benchmark systems using quantum phase estimation (QPE) algorithms demonstrated that these formulations can recover a significant portion of ground-state dynamical correlation effects that stem from the electron excitations outside of the active space. These results have also been confirmed in studies of ground-state potential energy surfaces using quantum simulators. In this letter, we study the effectiveness of the DUCC formalism in describing excited states. We also emphasize the role of the QPE formalism and its stochastic nature in discovering/identifying excited states or excited-state processes in situations when the knowledge about the true configurational structure of a sought after excited state is limited or postulated (due to the specific physics driving excited-state processes of interest). In this context, we can view the QPE algorithm as an engine for verifying various hypotheses for excited-state processes and providing statistically meaningful results that correspond to the electronic state(s) with the largest overlap with a postulated configurational structure. We illustrate these ideas on examples of strongly cor- related molecular systems, characterized by small energy gaps and high density of quasi-degenerate states around the Fermi level.

quantum chemistry, quantum computing, computationa↗

Sensitivity analysis of generic deep geologic repository with focus on spatial heterogeneity induced by stochastic fracture network generation

Geologic Disposal Safety Assessment Framework is a state-of-the-art simulation software toolkit for probabilistic post-closure performance assessment of systems for deep geologic disposal of nuclear waste developed by the United States Department of Energy. This paper presents a generic reference case and shows how it is being used to develop and demonstrate performance assessment methods within the Geologic Disposal Safety Assessment Framework that mitigate some of the challenges posed by high uncertainty and limited computational resources. Variance-based global sensitivity analysis is applied to assess the effects of spatial heterogeneity using graph-based summary measures for scalar and time-varying quantities of interest. Behavior of the system with respect to spatial heterogeneity is further investigated using ratios of water fluxes. This analysis shows that spatial heterogeneity is a dominant uncertainty in predictions of repository performance which can be identified in global sensitivity analysis using proxy variables derived from graph descriptions of discrete fracture networks. New quantities of interest defined using water fluxes proved useful for better understanding overall system behavior.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗