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 73 records · Page 4

FY 2008 Annual Progress Report for Advanced Vehicle Technology Analysis and Evaluation Activities and Heavy Vehicle Systems Optimization Program

AVTAE provides an overarching vehicle systems perspective in support of the technology R&D activities of DOE’s VT and Hydrogen, Fuel Cells & Infrastructure Technologies (HFCIT) Programs. AVTAE uses analytical and empirical tools to model and simulate potential vehicle systems, validate component performance in a systems context, verify and benchmark emerging technology, and validate computer models. Hardware-in-theloop testing allows components to be controlled in an emulated vehicle environment. Laboratory testing then provides measurement of progress toward VT technical goals and eventual validation of DOE-sponsored technologies at the Advanced Powertrain Research Facility for light- and medium-duty vehicles and at the ReFUEL Facility for heavy-duty vehicles. For this sub-program to be successful, extensive collaboration with the technology development activities within the VT and HFCIT Programs is required for both analysis and testing.

33 ADVANCED PROPULSION SYSTEMS↗

Benchmarking high performance computing architectures with CMS’ skeleton framework

Here, in 2012 CMS evaluated which underlying concurrency technology would be the best to use for its multi-threaded framework. The available technologies were evaluated on the high throughput computing systems dominating the resources in use at that time. A skeleton framework benchmarking suite that emulates the tasks performed within a CMSSW application was used to select Intel’s Thread Building Block library, based on the measured overheads in both memory and CPU on the different technologies benchmarked. In 2016 CMS will get access to high performance computing resources that use new many core architectures; machines such as Cori Phase 1&2, Theta, Mira. Because of this we have revived the 2012 benchmark to test it’s performance and conclusions on these new architectures. This talk will discuss the results of this exercise.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Parallel Computation of Coupled Cluster Hyperpolarizabilities

Static hyperpolarizabilities of five benchmark systems (hydrogen fluoride, water, acetonitrile, chloroform and para-nitroaniline) are calculated with large basis sets using coupled-cluster response theory and compared to five common DFT methods. These results reveal which methods and basis sets are appropriate for nonlinear optical studies for different types of molecules and provide a means for estimating errors from the quantum chemical approximation when including vibrational contributions or solvent effects at the QM/MM level. The largest calculation reported, which was for 72 electrons in 812 functions at C2v symmetry, took only a few hours on 256 nodes demonstrating that even larger calculations are quite feasible using modern supercomputers.

08 HYDROGEN↗

Investigations into validation of plutonium solutions for criticality safety analysis

Plutonium solution chemistry is among the most complex of all the elements in the periodic table. Under acidic conditions up to four different oxidation states can be present in significant amounts in a single solution. From the perspective of nuclear criticality safety, accurate information regarding the concentration of plutonium and other constituents in solution must be well-known in order to correctly model plutonium solution systems for analysis. This requires knowledge of the solution system along with the ability to make accurate assumptions and predictions of the chemical and physical properties of the solution system. If neutron transport methods are used to assess subcriticality in a nuclear criticality safety analysis, the models must be compared with benchmark experiments which are similar and the suitability of the computer code system must be quantified. This paper describes some investigations undertaken to support the validation of plutonium solution systems for nuclear criticality safety analysis and how the Whisper sensitivity/uncertainty (S/U) tool can provide information to support validation of such systems. Case study results for various solution systems such as aqueous plutonium nitrate, aqueous plutonium chloride and hypothetical metal-water mixture are presented. (authors)

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Compressed Optimization of Device Architectures for Semiconductor Quantum Devices

Recent advances in nanotechnology have enabled researchers to manipulate small collections of quantum-mechanical objects with unprecedented accuracy. In semiconductor quantum-dot qubits, this manipulation requires controlling the dot orbital energies, the tunnel couplings, and the electron occupations. These properties all depend on the voltages placed on the metallic electrodes that define the device, the positions of which are fixed once the device is fabricated. While there has been much success with small numbers of dots, as the number of dots grows, it will be increasingly useful to control these systems with as few electrode voltage changes as possible. Here, we introduce a protocol, which we call the "compressed optimization of device architectures" (CODA), in order both to efficiently identify sparse sets of voltage changes that control quantum systems and to introduce a metric that can be used to compare device designs. As an example of the former, we apply this method to simulated devices with up to 100 quantum dots and show that CODA automatically tunes devices more efficiently than other common nonlinear optimizers. To demonstrate the latter, we determine the optimal lateral scale for a triple quantum dot, yielding a simulated device that can be tuned with small voltage changes on a limited number of electrodes.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Using Hybrid Model OpenSHMEM + CUDA to Implement the SHOC Benchmark Suite

This work describes the process of porting the Scalable HeterOgeneous Computing (SHOC) benchmark suite from the hybrid MPI + CUDA implementation to OpenSHMEM + CUDA. SHOC includes a wide variety of benchmark kernels used to measure accelerator performance in both single node and cluster configurations. The hybrid model implementation attempts to place all major computation on accelerator devices, and uses MPI to synchronize and aggregate results. In some cases, MPI Groups are used to gradually reduce the number of accelerators used for computation as the problem size drops. Porting this behavior to OpenSHMEM required implementing several synchronizing collective operations, and using SHMEM teams to replace MPI Group functionality. Benchmark results on a Cray XK7 system with one GPU per compute node show that SHMEM performance is equal to MPI performance in these hybrid tasks. These results and porting experience show that using OpenSHMEM for accelerator devices benefits from adding functionality for synchronization and teams, and would further benefit from adding support for communication within accelerator kernels.

97 MATHEMATICS AND COMPUTING↗

Advanced Vehicle Technology Analysis and Evaluation Activities and Heavy Vehicle Systems Optimization Program (2008 Annual Progress Report)

AVTAE provides an overarching vehicle systems perspective in support of the technology R&D activities of DOE’s VT and Hydrogen, Fuel Cells & Infrastructure Technologies (HFCIT) Programs. AVTAE uses analytical and empirical tools to model and simulate potential vehicle systems, validate component performance in a systems context, verify and benchmark emerging technology, and validate computer models. Hardware-in-theloop testing allows components to be controlled in an emulated vehicle environment. Laboratory testing then provides measurement of progress toward VT technical goals and eventual validation of DOE-sponsored technologies at the Advanced Powertrain Research Facility for light- and medium-duty vehicles and at the ReFUEL Facility for heavy-duty vehicles. For this sub-program to be successful, extensive collaboration with the technology development activities within the VT and HFCIT Programs is required for both analysis and testing. Analytical results of this sub-program are used to estimate national benefits and/or impacts of DOE-sponsored technology development.

33 ADVANCED PROPULSION SYSTEMS↗

The ESIF-HPC-2 Benchmark Suite: Preprint

We describe the development of the ESIF-HPC-2 benchmark suite, a collection of kernel and application benchmark codes for measuring computational and I/O performance from single nodes to full HPC systems that was used for acceptance testing in our recent HPC procurement. The configurations of the benchmarks used for our system is presented. We also describe a set of 'dimensions' that can be used to classify benchmarks and assess coverage of a suite systematically. The collection is offered cost-free as a GitHub repository for general usage and further development.

97 MATHEMATICS AND COMPUTING↗

Effect of Inlet Throttling on Thermohydraulic Instability in a Large Scale Waterbased RCCS: A System-Level Analysis with RELAP5-3D

This paper presents results from system -level modeling of a water -based reactor cavity cooling system using RELAP5-3D. The computational model is benchmarked with experimental data from a half -scale RCCS test facility at Argonne National Laboratory. The model prediction is first compared with a two-phase oscillatory baseline experimental case where mixed accuracy is obtained. The model shows reasonable prediction of mass flow rate, pressure, and temperature but significant overprediction of void fraction. The model prediction is then compared with a fault case where the inlet of the risers is gradually reduced using a throttling valve. As the valve is closed, the model is able to predict some major flow phenomena observed in the experiment such as the dampening of oscillations, the reintroduction of oscillations, as well as boiling, flashing, and geysering in the risers. However, the timeline of these events are not well captured by the model. The model is also used to investigate the evolution of flow regime in the chimney. This work highlights that the semiempirical constitutive relations used in RELAP-3D could have a strong influence on the accuracy of the model in two-phase oscillatory flows.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Increased Fidelity and Associated Computational cost of Detailed Integral Experiment Benchmarks [Slides]

It does not seem like the system is significantly more sensitive to diameters of components near the center of the core. Intuitively it is, but was not detectable with simulations run to a Monte Carlo k eff uncertainty of 0.00002. The system is more sensitive to heights of components near the center of the core. Most (if not all) Zeus style benchmarks have perturbed core component heights individually.

42 ENGINEERING↗

Verifying MCNP Models of the TEX High 240 Plutonium Benchmark

Computational modeling programs are invaluable tools that allow us to understand systems, safely develop new processes, and make reliable predictions about future designs. However, the effectiveness of these codes is limited by the degree to which their parameters match the real world. In the field of nuclear engineering, cross section data is one of these vital parameters. Accurate cross section data on important fissile and fissionable isotopes promotes the design of safer and more efficient fabrication, transportation, storage, and stockpiling of nuclear fuel. Unfortunately, there are knowledge gaps in data on key isotopes. In 2011, a multinational meeting hosted by the US Department of Energy Nuclear Criticality Safety Program ranked the priority of certain cross section data needs. In response, Lawrence Livermore National Lab (LLNL) designed the Thermal and Epithermal eXperiment (TEX) series of benchmark experiments. Benchmark experiments are used to validate current cross section data. They validate data by comparing the results of an actual experiment to the predicted results from a computational model. The data a benchmark applies to depends on the isotope and energy range the experiment’s neutron multiplication factor ( k eff ) is most sensitive to. The development and testing of the TEX High 240 Plutonium Benchmark will help validate 240 Pu cross section data. The configuration and materials of this benchmark are designed to be most sensitive to 240 Pu's intermediate energy range (from 0.625 ev to 100 keV ). MCNP® models of the assembly have been developed by LLNL and the results have been written in the final design report. In order for the discrepancies between benchmark models and experiments to be attributed to cross section inaccuracies, the accuracy of the models needs to be verified. The goal of this project is to verify of the results of LLNL's modeling by creating a new set of MCNP models and comparing the results.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Power Signature Analysis of the SPECpower_ssj2008 Benchmark

As the power consumption of a server system becomes a mainstream concern in enterprise environments, understanding the system's power behavior at varying utilization levels provides us a key to select appropriate energy-efficiency optimizations. In this work, we present an in-depth analysis of 177 SPECpower_ssj2008 results published between 2007--2010 to understand the changes of server's power behavior over time. In particular, we identified simple nonlinear functions appropriate for modeling the power behavior of today's, aggressively power-managed, machines. We consider this work as an important first step towards developing capability for power signature analysis of a high-end computer system.

99 GENERAL AND MISCELLANEOUS↗

A design methodology for domain-optimized power-efficient supercomputing

As power has become the pre-eminent design constraint for future HPC systems, computational efficiency is being emphasized over simply peak performance. Recently, static benchmark codes have been used to find a power efficient architecture. Unfortunately, because compilers generate sub-optimal code, benchmark performance can be a poor indicator of the performance potential of architecture design points. Therefore, we present hardware/software cotuning as a novel approach for system design, in which traditional architecture space exploration is tightly coupled with software auto-tuning for delivering substantial improvements in area and power efficiency. We demonstrate the proposed methodology by exploring the parameter space of a Tensilica-based multi-processor running three of the most heavily used kernels in scientific computing, each with widely varying micro-architectural requirements: sparse matrix vector multiplication, stencil-based computations, and general matrix-matrix multiplication. Results demonstrate that co-tuning significantly improves hardware area and energy efficiency - a key driver for next generation of HPC system design.

97 MATHEMATICS AND COMPUTING↗

High fidelity nuclear energy system optimization towards an environmentally benign, sustainable, and secure energy source.

The impact associated with energy generation and utilization is immeasurable due to the immense, widespread, and myriad effects it has on the world and its inhabitants. The polar extremes are demonstrated on the one hand, by the high quality of life enjoyed by individuals with access to abundant reliable energy sources, and on the other hand by the global-scale environmental degradation attributed to the affects of energy production and use. Thus, nations strive to increase their energy generation, but are faced with the challenge of doing so with a minimal impact on the environment and in a manner that is self-reliant. Consequently, a revival of interest in nuclear energy has followed, with much focus placed on technologies for transmuting nuclear spent fuel. The performed research investigates nuclear energy systems that optimize the destruction of nuclear waste. In the context of this effort, nuclear energy system is defined as a configuration of nuclear reactors and corresponding fuel cycle components. The proposed system has unique characteristics that set it apart from other systems. Most notably the dedicated High-Energy External Source Transmuter (HEST), which is envisioned as an advanced incinerator used in combination with thermal reactors. The system is configured for examining environmentally benign fuel cycle options by focusing on minimization or elimination of high level waste inventories. Detailed high-fidelity exact-geometry models were developed for representative reactor configurations. They were used in preliminary calculations with Monte Carlo N-Particle eXtented (MCNPX) and Standardized Computer Analysis for Licensing Evaluation (SCALE) code systems. The reactor models have been benchmarked against existing experimental data and design data. Simulink{reg_sign}, an extension of MATLAB{reg_sign}, is envisioned as the interface environment for constructing the nuclear energy system model by linking the individual reactor and fuel component sub-models for overall analysis of the system. It also provides control over key user input parameters and the ability to effectively consolidate vital output results for uncertainty/sensitivity analysis and optimization procedures. The preliminary analysis has shown promising advanced fuel cycle scenarios that include Pressure Water Reactors Pressurized Water Reactors (PWRs), Very High Temperature Reactors (VHTRs) and dedicated HEST waste incineration facilities. If deployed, these scenarios may substantially reduce nuclear waste inventories approaching environmentally benign nuclear energy system characteristics. Additionally, a spent fuel database of the isotopic compositions for multiple design and control parameters has been created for the VHTR-HEST input fuel streams. Computational approaches, analysis metrics, and benchmark strategies have been established for future detailed studies.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

A prospect for computing in porous materials research: Very large fluid flow simulations

Properties of porous materials, abundant both in nature and industry, have broad influences on societies via, e.g. oil recovery, erosion, and propagation of pollutants. The internal structure of many porous materials involves multiple scales which hinders research on the relation between structure and transport properties: typically laboratory experiments cannot distinguish contributions from individual scales while computer simulations cannot capture multiple scales due to limited capabilities. Thus the question arises how large domain sizes can in fact be simulated with modern computers. This question is here addressed using a realistic test case; it is demonstrated that current computing capabilities allow the direct pore-scale simulation of fluid flow in porous materials using system sizes far beyond what has been previously reported. The achieved system sizes allow the closing of some particular scale gaps in, e.g. soil and petroleum rock research. Specifically, a full steady-state fluid flow simulation in a porous material, represented with an unprecedented resolution for the given sample size, is reported: the simulation is executed on a CPU-based supercomputer and the 3D geometry involves 16,3843 lattice cells (around 590 billion of them are pore sites). Using half of this sample in a benchmark simulation on a GPU-based system, a sustained computational performance of 1.77 PFLOPS is observed. These advances expose new opportunities in porous materials research. The implementation techniques here utilized are standard except for the tailored high-performance data layouts as well as the indirect addressing scheme with a low memory overhead and the truly asynchronous data communication scheme in the case of CPU and GPU code versions, respectively.

Computer Science↗

A Framework for Distributed Approximation of Moments with Higher-Order Derivatives through Automatic Differentiation

We present a framework for the distributed approximation of moments, enabling the evaluation of the uncertainty in a dynamical system. The first and second moment, mean, and variance are computed with up to third-order Taylor series expansion. The required derivatives for the expansion are generated automatically by automatic differentiation and propagated through an implicit time stepper. The computational kernels are the accumulation of the derivatives (Jacobian, Hessian, tensor) and the covariance matrix. We apply distributed parallelism to the Hessian or third-order tensor, and the user merely has to provide a function for the differential equation, thus achieving similar ease of use as Monte Carlo-based methods. We demonstrate our approach using with benchmarks on Theta, a KNL-based system at the Argonne Leadership Computing Facility.

Automatic Differentiation↗

The ESIF-HPC-2 Benchmark Suite

We describe the development of the ESIF-HPC-2 benchmark suite, a collection of kernel and application benchmark codes for measuring computational and I/O performance from single nodes to full HPC systems that was used for acceptance testing in our recent HPC procurement. The configurations of the benchmarks used for our system is presented. We also describe a set of "dimensions" that can be used to classify benchmarks and assess coverage of a suite systematically. The collection is offered cost-free as a GitHub repository for general usage and further development.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗