Search NASA⌕ Search

SEARCH · Search NASA

Results for “computer system benchmarking”

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 1,477 records · Page 82

Analytical harmonic vibrational frequencies with VV10-containing density functionals: Theory, efficient implementation, and benchmark assessments

VV10 is a powerful nonlocal density functional for long-range correlation that is used to include dispersion effects in many modern density functionals, such as the meta-generalized gradient approximation (mGGA), B97M-V, the hybrid GGA, ωB97X-V, and the hybrid mGGA, ωB97M-V. While energies and analytical gradients for VV10 are already widely available, this study reports the first derivation and efficient implementation of the analytical second derivatives of the VV10 energy. The additional compute cost of the VV10 contributions to analytical frequencies is shown to be small in all but the smallest basis sets for recommended grid sizes. Here, this study also reports the assessment of VV10-containing functionals for predicting harmonic frequencies using the analytical second derivative code. The contribution of VV10 to simulating harmonic frequencies is shown to be small for small molecules but important for systems where weak interactions are important, such as water clusters. In the latter cases, B97M-V, ωB97M-V, and ωB97X-V perform very well. The convergence of frequencies with respect to the grid size and atomic orbital basis set size is studied, and recommendations are reported. Finally, scaling factors to allow comparison of scaled harmonic frequencies with experimental fundamental frequencies and to predict zero-point vibrational energy are presented for some recently developed functionals (including r2SCAN, B97M-V, ωB97X-V, M06-SX, and ωB97M-V).

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Performance and energy impact of OpenMP runtime configurations on power constrained systems

Energy consumption of an application has attained the same vitality as execution time in current HPC systems, primarily due to the massive energy consumption of these systems and consequently substantial energy bills. This fact forced software developers as well as hardware vendors to put an extensive focus on energy consumption. This focus becomes even more crucial in power constrained systems, where the amount of power dedicated to applications is limited. In such systems, finding the optimal balance between execution time and energy consumption has a significant impact on utilizing these systems efficiently. A programming model is a necessary layer where optimizations can be applied to find the optimal balance. OpenMP is a standard programming model for intra-node parallelism. In this paper, we give a detailed analysis of how to optimize the execution time and energy consumption of an OpenMP application using the OpenMP runtime environment at different power levels. We studied twenty-eight OpenMP parallel regions from five NAS Parallel Benchmark (NPB) applications. Based on the study, we show that for a given power level, a suitable selection of OpenMP runtime parameters can improve the execution time and energy consumption of a parallel region up to 67% and 72%, respectively. We also show that these fine-grained improvements resulted in up to 26% of execution time and 38% of energy consumption improvement for a given OpenMP application. We finally observed that optimizing the energy consumption behavior alone across all power levels regardless of execution time behavior can lead to an additional energy consumption improvement of up to 55%. However, this improvement comes at the expense of execution time.

97 MATHEMATICS AND COMPUTING↗

A Fundamentally New Coupled Approach to Contact Mechanics via the Dirichlet‐Neumann Schwarz Alternating Method

Contact phenomena are crucial for understanding the behavior of mechanical systems. However, existing computational approaches for simulating mechanical contact often face numerical challenges, such as inaccurate physical predictions, energy conservation errors, and unwanted oscillations. Here, we introduce an alternative technique for simulating dynamic contact based on the non‐overlapping Schwarz alternating method, originally developed for domain decomposition. In multibody contact scenarios, this method treats each body as a separate, non‐overlapping domain and prevents interpenetration using an alternating Dirichlet–Neumann iterative process. This approach has a strong theoretical foundation, eliminates the need for contact constraints, and offers flexibility, making it ideal for multiscale and multiphysics applications. We conducted a numerical comparison between the Schwarz method and traditional methods, such as the Lagrange multiplier and penalty methods, focusing on a benchmark impact problem. Our results indicate that the Schwarz alternating method outperforms traditional methods in several key areas: it provides more accurate predictions for various measurable quantities and demonstrates exceptional energy conservation capabilities. To address unwanted oscillations in contact velocities and forces, we explored various algorithms and stabilization techniques, ultimately opting for the naïve‐stabilized Newmark scheme for its simplicity and effectiveness. Additionally, we validated the efficiency of the Schwarz method in a three‐dimensional impact problem, highlighting its inherent capacity to accommodate different mesh topologies, time‐integration schemes, and time steps for each interacting body.

Schwarz alternating method↗

Iso-Energy-Efficiency: An Approach to Power Constrained Parallel Computation

Future large scale high performance supercomputer systems require high energy efficiency to achieve exaflops computational power and beyond. Despite the need to understand energy efficiency in high-performance systems, there are few techniques to evaluate energy efficiency at scale. In this paper, we propose a system level iso-energy-efficiency model to analyze, evaluate and predict energy-performance of data intensive parallel applications with various execution patterns running on large scale power-aware clusters. Our analytical model can help users explore the effects of machine and application dependent characteristics on system energy efficiency and isolate efficient ways to scale system parameters (e.g. processor count, CPU power/frequency, workload size and network bandwidth) to balance energy use and performance. We derive our iso-energy-efficiency model and apply it to the NAS Parallel Benchmarks on two power-aware clusters. Our results indicate that the model accurately predicts total system energy consumption within 5% error on average for parallel applications with various execution and communication patterns. We demonstrate effective use of the model for various application contexts and in scalability decision-making.

Song, Shuaiwen↗

An Analysis Framework for Investigating the Trade-offs Between System Performance and Energy Consumption in a Heterogeneous Computing Environment

Rising costs of energy consumption and an ongoing effort for increases in computing performance are leading to a significant need for energy-efficient computing. Before systems such as supercomputers, servers, and datacenters can begin operating in an energy-efficient manner, the energy consumption and performance characteristics of the system must be analyzed. In this paper, we provide an analysis framework that will allow a system administrator to investigate the tradeoffs between system energy consumption and utility earned by a system (as a measure of system performance). We model these trade-offs as a bi-objective resource allocation problem. We use a popular multi-objective genetic algorithm to construct Pareto fronts to illustrate how different resource allocations can cause a system to consume significantly different amounts of energy and earn different amounts of utility. We demonstrate our analysis framework using real data collected from online benchmarks, and further provide a method to create larger data sets that exhibit similar heterogeneity characteristics to real data sets. This analysis framework can provide system administrators with insight to make intelligent scheduling decisions based on the energy and utility needs of their systems.

Friese, Ryan↗

Performance Analysis of Memory Transfers and GEMM Subroutines on NVIDIA Tesla GPU Cluster

Commodity clusters augmented with application accelerators are evolving as competitive high performance computing systems. The Graphical Processing Unit (GPU) with a very high arithmetic density and performance per price ratio is a good platform for the scientific application acceleration. In addition to the interconnect bottlenecks among the cluster compute nodes, the cost of memory copies between the host and the GPU device have to be carefully amortized to improve the overall efficiency of the application. Scientific applications also rely on efficient implementation of the BAsic Linear Algebra Subroutines (BLAS), among which the General Matrix Multiply (GEMM) is considered as the workhorse subroutine. In this paper, they study the performance of the memory copies and GEMM subroutines that are critical to port the computational chemistry algorithms to the GPU clusters. To that end, a benchmark based on the NetPIPE framework is developed to evaluate the latency and bandwidth of the memory copies between the host and the GPU device. The performance of the single and double precision GEMM subroutines from the NVIDIA CUBLAS 2.0 library are studied. The results have been compared with that of the BLAS routines from the Intel Math Kernel Library (MKL) to understand the computational trade-offs. The test bed is a Intel Xeon cluster equipped with NVIDIA Tesla GPUs.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Data-driven analysis to understand GPU hardware resource usage of optimizations

With heterogeneous systems, the number of GPUs per chip increases to provide computational capabilities for solving science at a nanoscopic scale. However, low utilization for single GPUs defies the need to invest more money in expensive accelerators. Although related work develops optimizations to improve application performance, none studies how these optimizations impact hardware resource usage or average GPU utilization. Here, this paper takes a data-driven analysis approach in addressing this gap by (1) characterizing how hardware resource usage affects device utilization, execution time, or both, (2) presenting a multiobjective metric to identify important application-device interactions that can be optimized to improve device utilization and application performance jointly, (3) studying hardware resource usage behaviors of several optimizations for a benchmark application, and finally (4) identifying optimization opportunities for several scientific proxy applications based on their hardware resource usage behaviors. Furthermore, we demonstrate the applicability of our methodology by applying the identified optimizations to a proxy application, which improves the execution time, device utilization, and power consumption by up to 29.6%, 5.3% and 26.5% respectively.

Computer science↗

Wireless Sensor Instrumentation for Distributed Sensing in Ground-Test Facilities

Wireless sensors have a number of advantages over wired sensors for flexible or temporary diagnostic deployment in a field or lab setting. Relative to wireless alternatives, traditional wired systems encounter limitations including spatial and weight constraints, maintenance costs, and signal integrity in high-noise environments. Ground-test facilities often face these challenges and cause increase down-time costs and failure of data integrity. This paper describes the development and implementation of flexible wireless sensor boards for applications within ground-test facilities using different network architectures. These boards implement state-of-the- art STM32 microprocessor chips for high-speed data acquisition and computational power. Additionally, the design integrates long-range radio transceivers with power output of +20dBm, easily reaching 2 km range, while maintaining high interference immunity and minimizing current consumption. The wireless sensor boards were implemented to demonstrate performance through benchmark testing and by taking distributed electrically-isolated measurements on a high-voltage lab apparatus while using different network architectures. Although this test case is in a laboratory setting, this network architecture could be easily repurposed for various other forms of monitoring.

Wireless Sensor Network↗

Resolved Resonance Region Analysis of 206 Pb, 207 Pb, and 208 Pb for Next Generation Lead-Cooled Fast Systems

Recently, great interest has been generated in using lead as a coolant for fast neutron systems and as a result it is important to investigate the ENDF/B-VIII.0 isotopic evaluations that comprise stable le ad. To this end, resonance parameters for 206 Pb, 207 Pb, and 208 Pb were re-evaluated because their resolved reso­nance regions extend beyond 0.5 MeV meaning resonance parameters used in reconstructing cross sections and elastic scattering angular distributions impact fast systems. The impact of resonance parameters is demon­strated by the differences between the evaluations in predicting experimental results from the fully modeled RPI Quasi-Differential Scattering Experiment via MCNPv6.2. In addition, MCNP KCODE calculations of lead-sensitive fast spectra critical benchmarks showed variations of keff on average of 400 pcm, caused solely from differences in elastic scattering angular distributions in 208 Pb. Re-evaluation entailed fitting data with the program SAMMY.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Experimental validation benchmark data for CFD of transient convection from forced to natural with flow reversal on a vertical flat plate

Transient convection has been investigated experimentally for the purpose of providing Computational Fluid Dynamics (CFD) validation benchmark data. A specialized facility for validation benchmark experiments called the Rotatable Buoyancy Tunnel was used to acquire thermal and velocity measurements of flow over a smooth, vertical heated plate. The initial condition was forced convection downward with subsequent transition to mixed convection, ending with natural convection upward after a flow reversal. Data acquisition through the transient was repeated for ensemble-averaged results. With simple flow geometry, validation data were acquired at the benchmark level. All boundary conditions (BCs) were measured and their uncertainties quantified. Temperature profiles on all four walls and the inlet were measured, as well as as-built test section geometry. Inlet velocity profiles and turbulence levels were quantified using Particle Image Velocimetry. System Response Quantities (SRQs) were measured for comparison with CFD outputs and include velocity profiles, wall heat flux, and wall shear stress. Extra effort was invested in documenting and preserving the validation data. Details about the experimental facility, instrumentation, experimental procedure, materials, BCs, and SRQs are made available through this paper. As a result, the latter two are available for download and the other details are included in this work.

42 ENGINEERING↗

Challenges and Opportunities of User-Level File Systemsfor HPC

The performance gap between magnetic disks and data processing on HPC systems has become that huge that an efficient data processing can only be achieved by introducing non-volatile memory (NVRAM) as a new storage tier. Although the benefits of hierarchical storage have been adequately demonstrated to the point that the newest leadership class HPC systems will employ burst buffers, critical questions remain for supporting hierarchical storage systems, including: How should we present hierarchical storage systems to user applications, such that they are easy to use and that application code is portable across systems? How should we manage data movement through a storage hierarchy for best performance and resilience of data? How do the particular I/O use cases mandate the way we manage data? There have been many efforts to explore this space in the form of file systems, with increasingly more implemented at the user level. This is because it is relatively easy to swap in new, specialized user-level file systems for use by applications on a case-by-case basis, as opposed to the current mainstream approach of using general-purpose, system-level file systems which may not be optimized for HPC workloads and must be installed by administrators. In contrast, file systems at the user level can be tailored for specific HPC workloads for high performance and can be used by applications without administrator intervention. Many user-level file system developers have found themselves “having to reinvent the wheel” to implement various optimizations in their file systems. Thus, a main goal of this meeting was to bring together experts in I/O performance, file systems, and storage, and collectively explore the space of current and future problems and solutions for I/O on hierarchical storage systems in order to begin a community effort in enabling user-level file system support for HPC systems. We had a lively week of learning about each other’s approaches as well as unique I/O use cases that can influence the design of a community-driven file and storage system standards. The agenda for this meeting contained talks from participants on the following high level topics: HPC storage and I/O support today; what do HPC users need for I/O; existing userlevel file system efforts; object stores and other alternative storage systems; and components for building user-level file systems. The talks were short and intended to be conversation starters for more in-depth discussions with the whole group. The participants engaged in lengthy discussions on various questions that arose from the talks including: Are we ready to program to a memory hierarchy versus block devices? Are the needs of HPC users reflected in our existing file systems and storage systems? Should we drop or keep POSIX moving forward? What do we mean when we say “user-level file system”? Do we all mean the same thing? How should the IO 500 benchmark be defined so it is fair and useful? and How are stage-in and stage-out actually going to work? The report for this seminar contains a record of the talks from the participants as well as the resulting discussions. Our hope is that the effort initiated during this seminar will result in long-term collaborations that will benefit the HPC community as a whole.

97 MATHEMATICS AND COMPUTING↗

Opportunities for Combined Heat and Power in Data Centers

Data centers represent a rapidly growing and very energy intensive activity in commercial, educational, and government facilities. In the last five years the growth of this sector was the electric power equivalent to seven new coal-fired power plants. Data centers consume 1.5% of the total power in the U.S. Growth over the next five to ten years is expected to require a similar increase in power generation. This energy consumption is concentrated in buildings that are 10-40 times more energy intensive than a typical office building. The sheer size of the market, the concentrated energy consumption per facility, and the tendency of facilities to cluster in 'high-tech' centers all contribute to a potential power infrastructure crisis for the industry. Meeting the energy needs of data centers is a moving target. Computing power is advancing rapidly, which reduces the energy requirements for data centers. A lot of work is going into improving the computing power of servers and other processing equipment. However, this increase in computing power is increasing the power densities of this equipment. While fewer pieces of equipment may be needed to meet a given data processing load, the energy density of a facility designed to house this higher efficiency equipment will be as high as or higher than it is today. In other words, while the data center of the future may have the IT power of ten data centers of today, it is also going to have higher power requirements and higher power densities. This report analyzes the opportunities for CHP technologies to assist primary power in making the data center more cost-effective and energy efficient. Broader application of CHP will lower the demand for electricity from central stations and reduce the pressure on electric transmission and distribution infrastructure. This report is organized into the following sections: (1) Data Center Market Segmentation--the description of the overall size of the market, the size and types of facilities involved, and the geographic distribution. (2) Data Center Energy Use Trends--a discussion of energy use and expected energy growth and the typical energy consumption and uses in data centers. (3) CHP Applicability--Potential configurations, CHP case studies, applicable equipment, heat recovery opportunities (cooling), cost and performance benchmarks, and power reliability benefits (4) CHP Drivers and Hurdles--evaluation of user benefits, social benefits, market structural issues and attitudes toward CHP, and regulatory hurdles. (5) CHP Paths to Market--Discussion of technical needs, education, strategic partnerships needed to promote CHP in the IT community.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

A Novel Deep Reinforcement Learning Approach to Traffic Signal Control with Connected Vehicles

The advent of connected vehicle (CV) technology offers new possibilities for a revolution in future transportation systems. With the availability of real-time traffic data from CVs, it is possible to more effectively optimize traffic signals to reduce congestion, increase fuel efficiency, and enhance road safety. The success of CV-based signal control depends on an accurate and computationally efficient model that accounts for the stochastic and nonlinear nature of the traffic flow. Without the necessity of prior knowledge of the traffic system’s model architecture, reinforcement learning (RL) is a promising tool to acquire the control policy through observing the transition of the traffic states. In this paper, we propose a novel data-driven traffic signal control method that leverages the latest in deep learning and reinforcement learning techniques. By incorporating a compressed representation of the traffic states, the proposed method overcomes the limitations of the existing methods in defining the action space to include more practical and flexible signal phases. The simulation results demonstrate the convergence and robust performance of the proposed method against several existing benchmark methods in terms of average vehicle speeds, queue length, wait time, and traffic density.

42 ENGINEERING↗

Orion Absolute Navigation System Progress and Challenge

The absolute navigation design of NASA's Orion vehicle is described. It has undergone several iterations and modifications since its inception, and continues as a work-in-progress. This paper seeks to benchmark the current state of the design and some of the rationale and analysis behind it. There are specific challenges to address when preparing a timely and effective design for the Exploration Flight Test (EFT-1), while still looking ahead and providing software extensibility for future exploration missions. The primary onboard measurements in a Near-Earth or Mid-Earth environment consist of GPS pseudo-range and delta-range, but for future explorations missions the use of star-tracker and optical navigation sources need to be considered. Discussions are presented for state size and composition, processing techniques, and consider states. A presentation is given for the processing technique using the computationally stable and robust UDU formulation with an Agee-Turner Rank-One update. This allows for computational savings when dealing with many parameters which are modeled as slowly varying Gauss-Markov processes. Preliminary analysis shows up to a 50% reduction in computation versus a more traditional formulation. Several state elements are discussed and evaluated, including position, velocity, attitude, clock bias/drift, and GPS measurement biases in addition to bias, scale factor, misalignment, and non-orthogonalities of the accelerometers and gyroscopes. Another consideration is the initialization of the EKF in various scenarios. Scenarios such as single-event upset, ground command, and cold start are discussed as are strategies for whole and partial state updates as well as covariance considerations. Strategies are given for dealing with latent measurements and high-rate propagation using multi-rate architecture. The details of the rate groups and the data ow between the elements is discussed and evaluated.

Holt, Greg N.↗

Designing Energy Efficient Communication Runtime Systems: A View from PGAS Models

As the march to the Exascale computing gains momentum, energy consumption of supercomputers has emerged to be the critical roadblock. While architectural innovations are imperative in achieving computing of this scale, it is largely dependent on the systems software to leverage the architectural innovations. Parallel applications in many computationally intensive domains have been designed to leverage these supercomputers, with legacy two-sided communication semantics using Message Passing Interface. At the same time, Partitioned Global Address Space Models are being designed which provide global address space abstractions and one-sided communication for exploiting data locality and communication optimizations. PGAS models rely on one-sided communication runtime systems for leveraging high-speed networks to achieve best possible performance. In this paper, we present a design for Power Aware One-Sided Communication Library - PASCoL. The proposed design detects communication slack, leverages Dynamic Voltage and Frequency Scaling (DVFS) and Interrupt driven execution to exploit the detected slack for energy efficiency. We implement our design and evaluate it using synthetic benchmarks for one-sided communication primitives, Put, Get and Accumulate and uniformly non-contiguous data transfers. Our performance evaluation indicates that we can achieve significant reduction in energy consumption without performance loss on multiple one-sided communication primitives. The achieved results are close to the theoretical peak available with the experimental test bed.

Vishnu, Abhinav↗

Online Event Detection in Synchrophasor Data with Graph Signal Processing

Online detection of anomalies is crucial to enhancing the reliability and resiliency of power systems. We propose a novel data-driven online event detection algorithm with synchrophasor data using graph signal processing. In addition to being extremely scalable, our proposed algorithm can accurately capture and leverage the spatio-temporal correlations of the streaming PMU data. This paper also develops a general technique to decouple spatial and temporal correlations in multiple time series. Finally, we develop a unique framework to construct a weighted adjacency matrix and graph Laplacian for product graph. Case studies with real-world, large-scale synchrophasor data demonstrate the scalability and accuracy of our proposed event detection algorithm. Compared to the state-of-the-art benchmark, the proposed method not only achieves higher detection accuracy but also yields higher computational efficiency.

Event detection↗

FY20 Proxy App Suite Release: Report for ECP Proxy App Project Milestone ADCD-504-10

Version 4.0 of the ECP Proxy App Suite is practically unchanged from the previous release. The current set of proxies has proven useful for many aspects of benchmarking and co-design and we see little reason to alter the suite. Although there have been few changes to the ECP suite, the team has been hard at work in other areas. In the area of Machine Learning (ML) we have now created a separate proxy suite dedicated to this scientific applications of ML. The suite includes: miniGAN (Generative Adversarial Networks), miniRL (Reinforcement Learning), CRADL (inline inference), Cosmoflow-Benchmark (Convolutional Neural Network), and MLPerf-DeepCam (Climate Segmentation Benchmark). Section 3 contains more information about these proxies as well as the principles that are guiding the development of the suite. We have surveyed available proxies for several application domains including Computational Fluid Dynamics, Quantum Chemistry, Quantum Computing Simulation, Molecular Dynamics, Monte Carlo Transport, and Density Functional Theory to identify gaps in proxy coverage. Several new proxy apps are either already available or will be released soon to fill these gaps. Section 4 provides full details. Finally, section 5 reports on our continued collaboration with the ECP Continuous Integration (CI) effort to use proxy apps to help identify problems and roadblocks to cross-lab CI. We have also assisted the El Capitan Center of Excellence (COE) to stand up a CI system that will be used to test releases of HPE and AMD software stacks. We hope that the COE effort can serve as a model for ECP by showing how the Proxy App Team can work with AD and ST teams identify critical features, kernels, patterns, etc. and incorporate them into a CI system that will help ensure that Frontier and Aurora will provide those needed capabilities.

97 MATHEMATICS AND COMPUTING↗

Hybrid state-space self-tuning control of uncertain linear systems

The paper presents a hybrid state-space self-tuner using a new dual-rate sampling scheme for digital adaptive control of continuous-time uncertain linear systems. A state-space-based recursive least-squares algorithm, together with a variable forgetting factor, is used for direct estimations of both the equivalent discrete-time uncertain linear system parameters and the associated discrete-time state of a continuous-time uncertain linear system from the sampled input and output data. An analogue optimal regional pole-placement design method is used for designing an optimal observer-based analogue controller. A suboptimal observer-based digital controller is then designed from the designed analogue controller using digital redesign technique. To enhance the robustness of parameter identification and state estimation algorithms, a dynamic bound for a class of uncertain bilinear parameters and a fast-rate digital controller are developed at each fast-sampling period. Also, to accommodate computation loads and computation delay for developing the advanced hybrid self-tuner, the designed analogue controller and observer gains are both updated at each slow-sampling period. This control technique has been successfully applied to benchmark control problems.

Shieh, L. S.↗