Search NASA⌕ Search

SEARCH · Search NASA

Results for “computer system performance”

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 1,315 records · Page 73
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

buhito

buhito is a Python library for graph analysis and machine learning. Graphs can represent networks with objects as nodes and their relationships as edges. buhito focuses on graphlet methods that study graphs through enumerating their component subgraphs to enable interpretable and fast models of complex systems. The package provides tools for different algorithmic designs for computing, analyzing, and applying graphlets to research problems such as machine learning, data compression, and anomaly detection in graph-structured data. A central feature is performing decomposition data analysis on graphs for machine learning models. Implemented in Python and built upon open-source scientific libraries such as NetworkX, NumPy, and SciPy, buhito provides high-performance methods for researchers exploring the mathematical and computational foundations of graphlet analysis applicable to systems of different sizes.

Pimonova, Yulia↗
DOE OSTI2019

Parallel Computing for Massive Dynamic Contingency Analysis

The first step towards running PSLF in a high-performance computing (HPC) environment was porting PSLF to the Linux operating system from the current shipping target of MS Windows. The target machine was the LLNL Quartz system which is a Linux cluster configured for large parallel jobs. It has 2,688 batch nodes with Dual Socket Intel E5-2695 v4 (Broadwell) CPUs with 18 cores each, with a total of 344,064 GB of memory, each node having 128 GB of memory. Nodes are connected with an Intel Omni-Path 100 GB/s interconnect. Quartz runs the Tri-Laboratory Operating System Software (TOSS) that includes Red Hat Enterprise Linux (RHEL) distribution used on the LLNL HPC machines.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

Accelerating Quantum Technologies Through Fermilab SRF Expertise

Industry forecast of exponential growth in quantum computing power still predicts that transformative applications are decades away. System performance is limited by decoherence and requires 5-10x the number of physical qubits per effective qubit.

43 PARTICLE ACCELERATORS↗
DOE OSTI2012

Experiences with High-Level Programming Directives for Porting Applications to GPUs

HPC systems now exploit GPUs within their compute nodes to accelerate program performance. As a result, high-end application development has become extremely complex at the node level. In addition to restructuring the node code to exploit the cores and specialized devices, the programmer may need to choose a programming model such as OpenMP or CPU threads in conjunction with an accelerator programming model to share and manage the difference node resources. This comes at a time when programmer productivity and the ability to produce portable code has been recognized as a major concern. In order to offset the high development cost of creating CUDA or OpenCL kernels, directives have been proposed for programming accelerator devices, but their implications are not well known. In this paper, we evaluate the state of the art accelerator directives to program several applications kernels, explore transformations to achieve good performance, and examine the expressiveness and performance penalty of using high-level directives versus CUDA. We also compare our results to OpenMP implementations to understand the benefits of running the kernels in the accelerator versus CPU cores.

43 PARTICLE ACCELERATORS↗
DOE OSTI2019

Harnessing the power of supercomputers using the PanDA Pilot 2 in the ATLAS Experiment

The unprecedented computing resource needs of the ATLAS experiment at LHC have motivated the Collaboration to become a leader in exploiting High Performance Computers (HPCs). To meet the requirements of HPCs, the PanDA system has been equipped with two new components; Pilot 2 and Harvester, that were designed with HPCs in mind. While Harvester is a resource-facing service which provides resource provisioning and workload shaping, Pilot 2 is responsible for payload execution on the resource. The presentation focuses on Pilot 2, which is a complete rewrite of the original PanDA Pilot used by ATLAS and other experiments for well over a decade. Pilot 2 has a flexible and adaptive design that allows for plugins to be defined with streamlined workflows. In particular, it has plugins for specific hardware infrastructures (HPC/GPU clusters) as well as for dedicated workflows defined by the needs of an experiment. Examples of dedicated HPC workflows are discussed in which the Pilot either uses an MPI application for processing fine-grained event level service under the control of the Harvester service or acts like an MPI application itself and runs a set of job in an assemble. In addition to describing the technical details of these workflows, results are shown from its deployment on Titan (OLCF) and other HPCs in ATLAS.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

GENTANGLE: integrated computational design of gene entanglements

The design of two overlapping genes in a microbial genome is an emerging technique for adding more reliable control mechanisms in engineered organisms for increased stability. The design of functional overlapping gene pairs is a challenging procedure, and computational design tools are used to improve the efficiency to deploy successful designs in genetically engineered systems. GENTANGLE (Gene Tuples ArraNGed in overLapping Elements) is a high-performance containerized pipeline for the computational design of two overlapping genes translated in different reading frames of the genome. This new software package can be used to design and test gene entanglements for microbial engineering projects using arbitrary sets of user-specified gene pairs.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2018

Speculation and replication in temperature accelerated dynamics

Accelerated Molecular Dynamics (AMD) is a class of MD-based algorithms for the long-time scale simulation of atomistic systems that are characterized by rare-event transitions. Temperature-Accelerated Dynamics (TAD), a traditional AMD approach, hastens state-to-state transitions by performing MD at an elevated temperature. Recently, Speculatively-Parallel TAD (SpecTAD) was introduced, allowing the TAD procedure to exploit parallel computing systems by concurrently executing in a dynamically generated list of speculative future states. Although speculation can be very powerful, it is not always the most efficient use of parallel resources. In this paper, we compare the performance of speculative parallelism with a replica-based technique, similar to the Parallel Replica Dynamics method. A hybrid SpecTAD approach is also presented, in which each speculation process is further accelerated by a local set of replicas. Finally and overall, this work motivates the use of hybrid parallelism whenever possible, as some combination of speculation and replication is typically most efficient.

36 MATERIALS SCIENCE↗
DOE OSTI2021

The FMO-DFTB Method

Although the fragment molecular orbital (FMO) method enables electronic structure calculations with near-linear scaling behavior with respect to system size, the computational cost of ab initio methods typically employed in conjunction with FMO is still prohibitive for routine calculations of very large systems or long timescale molecular dynamics simulations. We, therefore, combined the FMO and density-functional tight-binding (DFTB) method, which is one of the emerging semi-empirical quantum chemical methods, and have demonstrated that FMO-DFTB is capable of performing geometry optimizations for systems containing up to one million atoms using limited computational resources. In this chapter, we will review the basics of the DFTB method first before introducing FMO-DFTB, focusing on the relationship with density functional theory and other FMO methodologies. We also demonstrate the latest scalings of FMO-DFTB2 and DFTB3 using three-dimensional water clusters, showing that the most favorable scaling is O(N1.16). Applications of FMO-DFTB to various systems are briefly summarized, and an outlook to future applications is provided.

Nishimoto, Yoshio↗
DOE OSTI2025

Advanced System Thermal Fluids Solver Development for SAM

This work summarizes a feasibility study on testing numerical algorithms that are suitable and efficient for advanced system analysis code development under the mutli-physics framework, MOOSE. The key is the implementation of a high-order one-dimensional staggered-grid finite volume method (SG-FVM), and its direct interaction with the linear/nonlinear solver, PETSc. Leveraging the existing capabilities of the SAM code, significant code coverages were established in the finite volume method code. This in turn allows for a suite of test problems with different problem sizes and levels of complexity to be used to quantify the performance improvement of the finite volume method code. As evidently shown in this study, the implemented SG-FVM demonstrated superior performance improvement against a direct finite element method implementation through MOOSE for the wide range of selected problems. On two computer systems, the speedup was observed to be significant, with at least one order of magnitude of solving time reduction. In addition, for a complex reactor model, transient simulation was performed using the finite volume method code, the results of which agree very well with the reference results from the finite element method code. Overall, this study demonstrates a successful feasibility study on the proposed numerical algorithms and software structure to support advanced system analysis tool development. In this work, short-term priority development and testing items were identified, and long-term code adoption and integration plans were made for the eventual deployment of the finite volume method in the SAM code.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2014

SU-E-T-47: Application of the Repair-Misrepair-Fixation RBE Model to Describe the Results of High Resolution Proton Irradiation Cell Survival Experiments

Purpose: To develop a system to rapidly and accurately calculate RBE with the repair-misrepair-fixation (RMF) model for proton therapy data sets and to evaluate its effectiveness in modeling RBE for cell survival experiments performed with the H460 cell line for a range of proton LET. Methods: A system for using the Monte Carlo Damage Simulation (MCDS) software with high performance computing was developed. Input for the MCDS software for a range of proton energies in increments of 0.1 MeV was generated and simulated. The output data were then used to determine doseaveraged quantities for the RMF model based on equivalently binned proton energy spectra. The method was applied to calculate RBE at 50% survival for experimental cell survival data. Experimental data were obtained using a system which allowed for the accumulation of cell survival data at known values of dose-averaged proton LETs at a range of doses. RBE was calculated based directly on a Cs-137 reference experiment and, additionally, according to fitted values of the θ and κ terms of the RMF model. Results: Dose-averaged RMF model quantities were calculated using the HPC system. Compared to experimental RBE determined using a Cs-137 irradiation as a reference, the RBE from the model differed by at most 49%. RBE based on the fitted values of θ and κ differed by at most 18% for the highest LET. Conclusion: A system for rapidly generating data necessary to calculate RBE with the RMF model has been developed. For the H460 cell line, the RMF model could not reproduce the experimentally determined RBE based solely on the photon reference data. Fitting of the θ and κ terms of the RMF model indicates that their values increase for proton LET exceeding approximately 10 keV/µm. NIH Program Project Grant P01CA021239.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2017

Performance Characterization of De Novo Genome Assembly on Leading Parallel Systems.

De novo genome assembly is one of the most important and challenging computational problems in modern genomics; further, it shares algorithms and communication patterns important to other graph analytic and irregular applications. Unlike simulations, it has no floating point arithmetic and is dominated by small memory transactions within and between computing nodes. In this work, we focus on the highly scalable HipMer assembler and identify the dominant algorithms and communication patterns, also using microbenchmarks to capture the workload. We evaluate HipMer on a variety of platforms from the latest HPC systems to ethernet clusters. HipMer performs well on all single node systems, including the Xeon Phi manycore architecture. Given large enough problems, it also demonstrates excellent scaling across nodes in an HPC system, but requires a high speed network with low overhead and high injection rates. Our results shed light on the architectural features that are most important for achieving good parallel efficiency on this and related problems.

Ellis, Marquita↗
DOE OSTI2019

Adaptive Learning for Concept Drift in Application Performance Modeling

Supervised learning is a promising approach for modeling the performance of applications running on large HPC systems. A key assumption in supervised learning is that the training and testing data are obtained under the same conditions. However, in production HPC systems these conditions might not hold because the conditions of the platform can change over time as a result of hardware degradation, hardware replacement, software upgrade, and configuration updates. These changes could alter the data distribution in a way that affects the accuracy of the predictive performance models and render them less useful; this phenomenon is referred to as concept drift. Ignoring concept drift can lead to suboptimal resource usage and decreased efficiency when those performance models are deployed for tuning and job scheduling in production systems. To address this issue, we propose a concept-drift-aware predictive modeling approach that comprises two components: (1) an online Bayesian changepoint detection method that can automatically identify the location of events that lead to concept drift in near-real time and (2) a moment-matching transformation inspired by transfer learning that converts the training data collected before the drift to be useful for retraining. We use application input/output performance data collected on Cori, a production supercomputing system at the National Energy Research Scientific Computing Center, to demonstrate the effectiveness of our approach. The results show that concept-drift-aware models obtain significant improvement in accuracy; the median absolute error of the best-performing Gaussian process regression improved by 58.8% when the proposed approaches were used.

adaptive learning↗
DOE OSTI2015

MCNP 2020: Preparing LANL Monte Carlo for Exascale Computer Systems (White Paper)

The MCNP Monte Carlo code for simulating particle transport is the product of over 60 years of Monte Carlo code development at LANL. MCNP is the most-used code worldwide for particle transport in nuclear systems, with over 10,000 users in dozens of application areas. At LANL, MCNP is used extensively in applications for nuclear criticality safety, stockpile stewardship, homeland security, radiological safety, experiment design and analysis, etc., and is considered a critical technology resource for national defense. MCNP is often referred to as the “gold standard” for radiation transport calculations, based on the long development history and extensive validation work. Today, however, this critical technology and its well-deserved reputation are at risk. We propose a targeted effort over the next several years to upgrade the core software portions of the MCNP code. This effort will focus on fundamental structural changes to the underlying MCNP algorithms, data storage, and code architecture. These changes will directly improve code maintainability, reduce the development time for new features, improve the code performance, and make the code more flexible and adaptable for expected future computer systems. To move forward with new computer systems and additional new features, it is vital to have a solid base.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2024

Analyzing inference workloads for spatiotemporal modeling

Ensuring power grid resiliency, forecasting climate conditions, and optimization of transportation infrastructure are some of the many application areas where data is collected in both space and time. Spatiotemporal modeling is about modeling those patterns for forecasting future trends and carrying out critical decision-making by leveraging machine learning/deep learning. Once trained offline, field deployment of trained models for near real-time inference could be challenging because performance can vary significantly depending on the environment, available compute resources and tolerance to ambiguity in results. Users deploying spatiotemporal models for solving complex problems can benefit from analytical studies considering a plethora of system adaptations to understand the associated performance-quality trade-offs. To facilitate the co-design of next-generation hardware architectures for field deployment of trained models, it is critical to characterize the workloads of these deep learning (DL) applications during inference and assess their computational patterns at different levels of the execution stack. In this paper, we develop several variants of deep learning applications that use spatiotemporal data from dynamical systems. We study the associated computational patterns for inference workloads at different levels, considering relevant models (Long short-term Memory, Convolutional Neural Network and Spatio-Temporal Graph Convolution Network), DL frameworks (Tensorflow and PyTorch), precision (FP16, FP32, AMP, INT16 and INT8), inference runtime (ONNX and AI Template), post-training quantization (TensorRT) and platforms (Nvidia DGX A100 and Sambanova SN10 RDU). Overall, our findings indicate that although there is potential in mixed-precision models and post-training quantization for spatiotemporal modeling, extracting efficiency from contemporary GPU systems might be challenging. Instead, co-designing custom accelerators by leveraging optimized High Level Synthesis frameworks (such as SODA High-Level Synthesizer for customized FPGA/ASIC targets) can make workload-specific adjustments to enhance the efficiency.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2013

A Diagnoser Algorithm for Anomaly Detection in DEDS under Partial Unreliable Observations: Characterization and Inclusion in Sensor Configuration Optimizaton

Complex engineering systems have to be carefully monitored to meet demanding performance requirements, including detecting anomalies in their operations. There are two major monitoring challenges for these systems. The first challenge is that information collected from the monitored system is often partial and/or unreliable, in the sense that some occurred events may not be reported and/or may be reported incorrectly (e.g., reported as another event). The second is that anomalies often consist of sequences of event patterns separated in space and time. This paper introduces and analyzes a diagnoser algorithm that meets these challenges for detecting and counting occurrences of anomalies in engineering systems. The proposed diagnoser algorithm assumes that models are available for characterizing plant operations (via stochastic automata) and sensors (via probabilistic mappings) used for reporting partial and unreliable information. Methods for analyzing the effects of model uncertainties on the diagnoser performance are also discussed. In order to select configurations that reduce sensor costs, while satisfying diagnoser performance requirements, a sensor configuration selection algorithm developed in previous work is then extended for the proposed diagnoser algorithm. The proposed algorithms and methods are then applied to a multi-unit-operation system, which is derived from an actual facility application. Results show that the proposed diagnoser algorithm is able to detect and count occurrences of anomalies accurately and that its performance is robust to model uncertainties. Furthermore, the sensor configuration selection algorithm is able to suggest optimal sensor configurations with significantly reduced costs, while still yielding acceptable performance for counting the occurrences of anomalies.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Architecture and Performance of Perlmutter’s 35 PB ClusterStor E1000 All-Flash File System

NERSC's newest system, Perlmutter, features a 35 PB all-flash Lustre file system built on HPE Cray ClusterStor E1000. We present its architecture, early performance figures, and performance considerations unique to this architecture. We demonstrate the performance of E1000 OSSes through low-level Lustre tests that achieve over 90% of the theoretical bandwidth of the SSDs at the OST and LNet levels. We also show end-to-end performance for both traditional dimensions of I/O performance (peak bulk-synchronous bandwidth) and non-optimal workloads endemic to production computing (small, incoherent I/Os at random offsets) and compare them to NERSC's previous system, Cori, to illustrate that Perlmutter achieves the performance of a burst buffer and the resilience of a scratch file system. Finally, we discuss performance considerations unique to all-flash Lustre and present ways in which users and HPC facilities can adjust their I/O patterns and operations to make optimal use of such architectures.

Lockwood, Glenn K↗