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 181 records · Page 10

Can I/O Variability Be Reduced on QoS-Less HPC Storage Systems?

For a production high-performance computing (HPC) system, where storage devices are shared between multiple applications and managed in a best effort manner, I/O contention is often a major problem. In this paper, we propose a balanced messaging-based re-routing in conjunction with throttling at the middleware level. This work tackles two key challenges that have not been fully resolved in the past: whether I/O variability can be reduced on a QoS-less HPC storage system, and how to design a runtime scheduling system that can scale up to a large amount of cores. The proposed scheme uses a two-level messaging system to re-route I/O requests to a less congested storage location so that write performance is improved, while limiting the impact on read by throttling re-routing. An analytical model is derived to guide the setup of optimal throttling factor. We thoroughly analyze the virtual messaging layer overhead and explore whether the in-transit buffering is effective in managing I/O variability. Contrary to the intuition, in-transit buffer cannot completely solve the problem. It can reduce the absolute variability but not the relative variability. The proposed scheme is verified against a synthetic benchmark as well as being used by production applications.

Huang, Dan↗

RISC Processors and High Performance Computing

This tutorial will discuss the top five RISC microprocessors and the parallel systems in which they are used. It will provide a unique cross-machine comparison not available elsewhere. The effective performance of these processors will be compared by citing standard benchmarks in the context of real applications. The latest NAS Parallel Benchmarks, both absolute performance and performance per dollar, will be listed. The next generation of the NPB will be described. The tutorial will conclude with a discussion of future directions in the field. Technology Transfer Considerations: All of these computer systems are commercially available internationally. Information about these processors is available in the public domain, mostly from the vendors themselves. The NAS Parallel Benchmarks and their results have been previously approved numerous times for public release, beginning back in 1991.

Bailey, David H.↗

Comparison of Origin 2000 and Origin 3000 Using NAS Parallel Benchmarks

This report describes results of benchmark tests on the Origin 3000 system currently being installed at the NASA Ames National Advanced Supercomputing facility. This machine will ultimately contain 1024 R14K processors. The first part of the system, installed in November, 2000 and named mendel, is an Origin 3000 with 128 R12K processors. For comparison purposes, the tests were also run on lomax, an Origin 2000 with R12K processors. The BT, LU, and SP application benchmarks in the NAS Parallel Benchmark Suite and the kernel benchmark FT were chosen to determine system performance and measure the impact of changes on the machine as it evolves. Having been written to measure performance on Computational Fluid Dynamics applications, these benchmarks are assumed appropriate to represent the NAS workload. Since the NAS runs both message passing (MPI) and shared-memory, compiler directive type codes, both MPI and OpenMP versions of the benchmarks were used. The MPI versions used were the latest official release of the NAS Parallel Benchmarks, version 2.3. The OpenMP versiqns used were PBN3b2, a beta version that is in the process of being released. NPB 2.3 and PBN 3b2 are technically different benchmarks, and NPB results are not directly comparable to PBN results.

Turney, Raymond D.↗

Benchmarking highly entangled states on a 60-atom analogue quantum simulator

Abstract Quantum systems have entered a competitive regime in which classical computers must make approximations to represent highly entangled quantum states 1,2 . However, in this beyond-classically-exact regime, fidelity comparisons between quantum and classical systems have so far been limited to digital quantum devices 2–5 , and it remains unsolved how to estimate the actual entanglement content of experiments 6 . Here, we perform fidelity benchmarking and mixed-state entanglement estimation with a 60-atom analogue Rydberg quantum simulator, reaching a high-entanglement entropy regime in which exact classical simulation becomes impractical. Our benchmarking protocol involves extrapolation from comparisons against an approximate classical algorithm, introduced here, with varying entanglement limits. We then develop and demonstrate an estimator of the experimental mixed-state entanglement 6 , finding our experiment is competitive with state-of-the-art digital quantum devices performing random circuit evolution 2–5 . Finally, we compare the experimental fidelity against that achieved by various approximate classical algorithms, and find that only the algorithm we introduce is able to keep pace with the experiment on the classical hardware we use. Our results enable a new model for evaluating the ability of both analogue and digital quantum devices to generate entanglement in the beyond-classically-exact regime, and highlight the evolving divide between quantum and classical systems.

Science & Technology - Other Topics↗

Covariance Applications in Criticality Safety, Light Water Reactor Analysis, and Spent Fuel Characterization

A new covariance data library based on ENDF/B-VII.1 was recently processed for the SCALE nuclear analysis code system. The multigroup covariance data are discussed here, along with testing and application results for critical benchmark experiments. The cross section covariance library, along with covariances for fission product yields and decay data, is used to compute uncertainties in the decay heat produced by a burned reactor fuel assembly.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Numerically exact configuration interaction at quadrillion-determinant scale

The combinatorial growth of configuration interaction (CI) has long limited this formally exact quantum chemistry method to only the smallest molecules. Here, we report a numerically exact CI calculation exceeding one quadrillion (10 15 ) determinants, made possible by a lossless categorical compression strategy within the small-tensor-product distributed active space (STP-DAS) framework. This approach overcomes the traditional memory bottlenecks of CI by a numerically exact compression of the wavefunction representation and reformulating the most computationally demanding matrix–vector operations. Using this method, we performed a fully relativistic CI calculation of the ground state of HBrTe with over 10 15 complex-valued determinants in just 34.5 h on 1000 computing nodes—the largest CI calculation ever reported. We further achieved fast computation for systems with hundreds of billions of determinants on only a few compute nodes. Extensive benchmarks confirm that the method retains full numerical exactness while cutting memory and computational cost by orders of magnitude. Compared to previous state-of-the-art CI calculations, this work achieves a 1000 times increase in CI space, a 10 6 -fold increase in floating-point operations performed, and a 10 6 -fold improvement in computational speed.

Computational chemistry↗

Application Experiences on a GPU-Accelerated Arm-based HPC Testbed

This paper assesses and reports the experience of ten teams working to port, validate, and benchmark several High Performance Computing applications on a novel GPU-accelerated Arm testbed system. The testbed consists of eight NVIDIA Arm HPC Developer Kit systems, each one equipped with a server-class Arm CPU from Ampere Computing and two data center GPUs from NVIDIA Corp. The systems are connected together using InfiniBand interconnect. The selected applications and mini-apps are written using several programming languages and use multiple accelerator-based programming models for GPUs such as CUDA, OpenACC, and OpenMP offloading. Working on application porting requires a robust and easy-to-access programming environment, including a variety of compilers and optimized scientific libraries. The goal of this work is to evaluate platform readiness and assess the effort required from developers to deploy well-established scientific workloads on current and future generation Arm-based GPU-accelerated HPC systems. The reported case studies demonstrate that the current level of maturity and diversity of software and tools is already adequate for large-scale production deployments.

Elwasif, Wael↗

PETSc/TAO developments for GPU-based early exascale systems

The Portable Extensible Toolkit for Scientific Computation (PETSc) library provides scalable solvers for nonlinear time-dependent differential and algebraic equations and for numerical optimization via the Toolkit for Advanced Optimization (TAO). PETSc is used in dozens of scientific fields and is an important building block for many simulation codes. During the U.S. Department of Energy’s Exascale Computing Project, the PETSc team has made substantial efforts to enable efficient utilization of the massive fine-grain parallelism present within exascale compute nodes and to enable performance portability across exascale architectures. We recap some of the challenges that designers of numerical libraries face in such an endeavor, and then discuss the many developments we have made, which include the addition of new GPU backends, features supporting efficient on-device matrix assembly, better support for asynchronicity and GPU kernel concurrency, and new communication infrastructure. In conclusion, we evaluate the performance of these developments on some pre-exascale systems as well as the early exascale systems Frontier and Aurora, using compute kernel, communication layer, solver, and mini-application benchmark studies, and then close with a few observations drawn from our experiences on the tension between portable performance and other goals of numerical libraries.

Exascale Computing Project (ECP)↗

Real Time Simulation of Power Grid Disruptions

DOE-OE and DOE-SC workshops (Reference 1-3) identified the key power grid problem that requires insight addressable by the next generation of exascale computing is coupling of real-time data streams (1-2 TB per hour) as the streams are ingested to dynamic models. These models would then identify predicted disruptions in time (2-4 seconds) to trigger the smart grid s self healing functions. This project attempted to establish the feasibility of this approach and defined the scientific issues, and demonstrated example solutions to important smart grid simulation problems. These objectives were accomplished by 1) using the existing frequency recorders on the national grid to establish a representative and scalable real-time data stream; 2) invoking ORNL signature identification algorithms; 3) modeling dynamically a representative region of the Eastern interconnect using an institutional cluster, measuring the scalability and computational benchmarks for a national capability; and 4) constructing a prototype simulation for the system s concept of smart grid deployment. The delivered ORNL enduring capability included: 1) data processing and simulation metrics to design a national capability justifying exascale applications; 2) Software and intellectual property built around the example solutions; 3) demonstrated dynamic models to design few second self-healing.

Chinthavali, Supriya↗

Benchmarking the PCMCI Causal Discovery Algorithm for Spatiotemporal Systems

Causal discovery algorithms construct hypothesized causal graphs that depict causal dependencies among variables in observational data. While powerful, the accuracy of these algorithms is highly sensitive to the underlying dynamics of the system in ways that have not been fully characterized in the literature. In this report, we benchmark the PCMCI causal discovery algorithm in its application to gridded spatiotemporal systems. Effectively computing grid-level causal graphs on large grids will enable analysis of the causal impacts of transient and mobile spatial phenomena in large systems, such as the Earth’s climate. We evaluate the performance of PCMCI with a set of structural causal models, using simulated spatial vector autoregressive processes in one- and two-dimensions. We develop computational and analytical tools for characterizing these processes and their associated causal graphs. Our findings suggest that direct application of PCMCI is not suitable for the analysis of dynamical spatiotemporal gridded systems, such as climatological data, without significant preprocessing and downscaling of the data. PCMCI requires unrealistic sample sizes to achieve acceptable performance on even modestly sized problems and suffers from a notable curse of dimensionality. This work suggests that, even under generous structural assumptions, significant additional algorithmic improvements are needed before causal discovery algorithms can be reliably applied to grid-level outputs of earth system models.

54 ENVIRONMENTAL SCIENCES↗

Final Report

The purpose of this project was to develop tools and techniques to improve the ability of computational scientists to investigate and correct problems (bugs) in their programs. Specifically, the University of Maryland component of this project focused on the problems associated with the finite number of bits available in a computer to represent numeric values. In large scale scientific computation, numbers are frequently added to and multiplied with each other billions of times. Thus even small errors due to the representation of numbers can accumulate into big errors. However, using too many bits to represent a number results in additional computation, memory, and energy costs. Thus it is critical to find the right size for numbers. This project focused on several aspects of this general problem. First, we developed a tool to look for cancelations, the catastrophic loss of precision in numbers due to the addition of two numbers whose actual values are close to each other, but whose representation in a computer is identical or nearly so. Second, we developed a suite of tools to allow programmers to identify exactly how much precision is required for each operation in their program. This tool allows programmers to both verify that enough precision is available, but more importantly find cases where extra precision could be eliminated to allow the program to use less memory, computer time, or energy. These tools use advanced binary modification techniques to allow the analysis of actual optimized code. The system, called Craft, has been applied to a number of benchmarks and real applications.

97 MATHEMATICS AND COMPUTING↗

Algorithms versus architectures for computational chemistry

The algorithms employed are computationally intensive and, as a result, increased performance (both algorithmic and architectural) is required to improve accuracy and to treat larger molecular systems. Several benchmark quantum chemistry codes are examined on a variety of architectures. While these codes are only a small portion of a typical quantum chemistry library, they illustrate many of the computationally intensive kernels and data manipulation requirements of some applications. Furthermore, understanding the performance of the existing algorithm on present and proposed supercomputers serves as a guide for future programs and algorithm development. The algorithms investigated are: (1) a sparse symmetric matrix vector product; (2) a four index integral transformation; and (3) the calculation of diatomic two electron Slater integrals. The vectorization strategies are examined for these algorithms for both the Cyber 205 and Cray XMP. In addition, multiprocessor implementations of the algorithms are looked at on the Cray XMP and on the MIT static data flow machine proposed by DENNIS.

Partridge, H.↗

MCNP5 Criticality Validation and Bias for Intermediate Enriched Uranium Systems

The purpose of this analysis is to validate the Monte Carlo N-Particle 5 (MCNP5) code Version 1.40 (LA-UR-03-1987, 2005) and its cross-section database for k-code calculations of intermediate enriched uranium systems on INTEL ® processor based PC's running any version of the WINDOWS operating system. Configurations with intermediate enriched uranium were modeled with the moderator range of 39≤HlFissile≤1438. See Table 2-1 for brief descriptions of selected cases and Table 3-1 for the range of applicability for this validation. A total of 167 input cases were evaluated including bare and reflected systems in a single body or arrays. The 167 cases were taken directly from the previous (Version 4C [Lan 2005]) validation database. Section 2.0 list data used to calculate k-effective (k eff ) for the 167 experimental criticality benchmark cases using the MCNP5 code v1.40 and its cross-section database. Appendix B lists the MCNP cross-section database entries validated for use in evaluating the intermediate enriched uranium systems for criticality safety. The dimensions and atom densities for the intermediate enriched uranium experiments were taken from NEA/NSC/DOC(95)03, September 2005, which will be referred to as the benchmark handbook throughout the report. For these input values, the experimental benchmark k eff is approximately 1.0. The MCNP validation computer runs ran to an accuracy of approximately ±0.001. For the cases where the reported benchmark k eff was not equal to 1.0000 the MCNP calculational results were normalized. The difference between the MCNP validation computer runs and the experimentally measured k eff is the MCNP5 v1.40 bias. The USLSTATS code (ORNL 1998) was utilized to perform the statistical analysis and generate an acceptable maximum k eff limit for calculations of the intermediate enriched uranium type systems.

42 ENGINEERING↗

Phase field benchmark problems for dendritic growth and linear elasticity

We present the second set of benchmark problems for phase field models that are being jointly developed by the Center for Hierarchical Materials Design (CHiMaD) and the National Institute of Standards and Technology (NIST) along with input from other members in the phase field community. As the integrated computational materials engineering (ICME) approach to materials design has gained traction, there is an increasing need for quantitative phase field results. New algorithms and numerical implementations increase computational capabilities, necessitating standard problems to evaluate their impact on simulated microstructure evolution as well as their computational performance. We propose one benchmark problem for solidifiication and dendritic growth in a single-component system, and one problem for linear elasticity via the shape evolution of an elastically constrained precipitate. We demonstrate the utility and sensitivity of the benchmark problems by comparing the results of 1) dendritic growth simulations performed with different time integrators and 2) elastically constrained precipitate simulations with different precipitate sizes, initial conditions, and elastic moduli. As a result, these numerical benchmark problems will provide a consistent basis for evaluating different algorithms, both existing and those to be developed in the future, for accuracy and computational efficiency when applied to simulate physics often incorporated in phase field models.

36 MATERIALS SCIENCE↗

A logical progression of steps for implementation and testing of the 7-equation, two-phase model into a computational framework

A seven-step progression is given for the implementation of the seven-equation model, employed in the new RELAP-7 thermal hydraulics system analysis code, within the MOOSE-compatible framework. The model is well-posed and treats both phases as compressible flow in a one-dimensional, variable cross-sectional area duct/pipe/component. Some appropriate tests are also outlined to benchmark the model/implementation for each step of the progression. (authors)

97 MATHEMATICS AND COMPUTING↗

Evaluating Cloud Computing in the Proposed NASA DESDynI Ground Data System

The proposed NASA Deformation, Ecosystem Structure and Dynamics of Ice (DESDynI) mission would be a first-of-breed endeavor that would fundamentally change the paradigm by which Earth Science data systems at NASA are built. DESDynI is evaluating a distributed architecture where expert science nodes around the country all engage in some form of mission processing and data archiving. This is compared to the traditional NASA Earth Science missions where the science processing is typically centralized. What's more, DESDynI is poised to profoundly increase the amount of data collection and processing well into the 5 terabyte/day and tens of thousands of job range, both of which comprise a tremendous challenge to DESDynI's proposed distributed data system architecture. In this paper, we report on a set of architectural trade studies and benchmarks meant to inform the DESDynI mission and the broader community of the impacts of these unprecedented requirements. In particular, we evaluate the benefits of cloud computing and its integration with our existing NASA ground data system software called Apache Object Oriented Data Technology (OODT). The preliminary conclusions of our study suggest that the use of the cloud and OODT together synergistically form an effective, efficient and extensible combination that could meet the challenges of NASA science missions requiring DESDynI-like data collection and processing volumes at reduced costs.

Benchmark↗

High-fidelity Multidisciplinary Sensitivity Analysis and Design Optimization for Rotorcraft Applications

A multidisciplinary sensitivity analysis of rotorcraft simulations involving tightly coupled high-fidelity computational fluid dynamics and comprehensive analysis solvers is presented and evaluated. A sensitivity-enabled fluid dynamics solver and a nonlinear flexible multibody dynamics solver are coupled to predict aerodynamic loads and structural responses of helicopter rotor blades. A discretely consistent adjoint-based sensitivity analysis available in the fluid dynamics solver provides sensitivities arising from unsteady turbulent flows and unstructured dynamic overset meshes, while a complex-variable approach is used to compute structural sensitivities with respect to aerodynamic loads. The multidisciplinary sensitivity analysis is conducted through integrating the sensitivity components from each discipline of the coupled system. Accuracy of the coupled system is validated by conducting simulations for a benchmark rotorcraft model and comparing solutions with established analyses and experimental data. Sensitivities of lift computed by the multidisciplinary sensitivity analysis are verified by comparison with the sensitivities obtained by complex-variable simulations. Finally the multidisciplinary sensitivity analysis is applied to a constrained gradient-based design optimization for a HART-II rotorcraft configuration.

Wang, Li↗

Benchmark neutrinoless double- β decay matrix elements in a light nucleus

We compute nuclear matrix elements of neutrinoless double-β decay mediated by light Majorana-neutrino exchange in the $\textit{A}$ = 6 system. The goal for this work is to benchmark two many-body approaches, the no-core shell model and the multireference in-medium similarity renormalization group (SRG). We use a SRG-evolved next-to-next-to-next-to-leading chiral order two-body potential for the nuclear interaction, and make the approximation that the isospin is conserved. We compare the results of the two approaches as a function of the cutoff on the many-body basis space. Although differences are seen in the predicted nuclear radii, the ground-state energies and neutrinoless double-β decay matrix elements produced by the two approaches show significant agreement. We discuss the implications for calculations in heavier nuclei.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗