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 505 records · Page 28

Summer Internship Report: ARA2 Benchmarking

Over the past decade, the RISC-V Instruction Set Architecture (ISA) has emerged as a significant player in both academic and industrial processor design due to its open-source nature, modular extension system, and versatility across domains ranging from microcontrollers to high-performance computing (HPC). One of its most important recent advancements is the RISC-V Vector Extension (RVV), which enables explicit data-level parallelism through vector registers and vectorized instructions. Unlike traditional SIMD (Single Instruction, Multiple Data) architectures that fix vector lengths at design time, RVV uses the concept of VLEN (vector register length) as a hardware-independent parameter and allows software to adapt dynamically to the available vector width. This flexible approach ensures portability across implementations while enabling scalable performance. The ARA2 core is a parameterizable RISC-V vector processor developed at the Integrated Systems Lab at ETH Zürich and the University of Bologna. Designed as a tightly-coupled accelerator to a scalar RISC-V core, ARA2 implements the RVV 1.0 specification and offers tunable architectural parameters such as the number of vector lanes, VLEN, and cache sizes.

97 MATHEMATICS AND COMPUTING↗

Tools for Simulation and Benchmark Generation at Exascale

The path to exascale high-performance computing (HPC) poses several challenges related to power, performance, resilience, productivity, programmability, data movement, and data management. Investigating the performance of parallel applications at scale on future architectures and the performance impact of different architecture choices is an important component of HPC hardware/software co-design. Simulations using models of future HPC systems and communication traces from applications running on existing HPC systems can offer an insight into the performance of future architectures. This work targets technology developed for scalable application tracing of communication events and memory profiles, but can be extended to other areas, such as I/O, control flow, and data flow. It further focuses on extreme-scale simulation of millions of Message Passing Interface (MPI) ranks using a lightweight parallel discrete event simulation (PDES) toolkit for performance evaluation. Instead of simply replaying a trace within a simulation, the approach is to generate a benchmark from it and to run this benchmark within a simulation using models to reflect the performance characteristics of future-generation HPC systems. This provides a number of benefits, such as eliminating the data intensive trace replay and enabling simulations at different scales. The presented work utilizes the ScalaTrace tool to generate scalable trace files, the ScalaBenchGen tool to generate the benchmark, and the xSim tool to run the benchmark within a simulation.

Lagadapati, Mahesh↗

Neutronic-Thermal Hydraulic Benchmark using the SKINATH Point Kinetics Model

The SKINATH point kinetics program, whose name comes from: A Computer Program for Solving the Reactor Point Kinetics Equations with Simple Thermal Hydraulic-Feedback, had its origins at ORNL. The authors were interested in investigating low-level criticality events such as might occur in a waste repository of 55 gallon drums. We assume a relatively realistic thermal feedback for fissionable material in a container (called a reactor here), either critical or subcritical, with the potential to undergo a further excursion. The system is a homogeneous fissile fluid (mostly water), increasing in temperature as it absorbs all heat from the excursion. An ideal gas eternally cools the reactor at constant temperature T{sub c}. The SKINATH numerical concept in 1984 was to use an off-the-shelf Livermore ODE solver LSODE to solve the kinetic equations, much as one does today with MATLAB{sup TM}. Here, we develop a novel solver that uses the simplest of numerical methods including convergence acceleration. This work represents the initiation of a Multiphysics benchmark effort at INL. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Chasing the limits of the one electron approximation

Rapid progress in the development of computational methods for quantum chemistry is not properly balanced by the development of basis sets. Even in the case of few-electron systems it is hard to find basis set which are able to reproduce the ECG benchmarks with the mhartree accuracy. In this paper we show early work on improvements of the basis sets for small atomic and molecular systems. As a starting point the ground state of lithium atom and the lowest states of lithium dimer will be investigated. The exploratory optimization of the exponents of primitive gaussians will be based on even tempered scheme combined with CISD method.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Taming Wild Horses: The Need for Virtual Time-based Scheduling of VMs in Network Simulations

The next generation of scalable network simulators employ virtual machines (VMs) to act as high-fidelity models of traffic producer/consumer nodes in simulated networks. However, network simulations could be inaccurate if VMs are not scheduled according to virtual time, especially when many VMs are hosted per simulator core in a multi-core simulator environment. Since VMs are by default free-running, on the outset, it is not clear if, and to what extent, their untamed execution affects the results in simulated scenarios. Here, we provide the first quantitative basis for establishing the need for generalized virtual time scheduling of VMs in network simulators, based on an actual prototyped implementations. To exercise breadth, our system is tested with multiple disparate applications: (a) a set of message passing parallel programs, (b) a computer worm propagation phenomenon, and (c) a mobile ad-hoc wireless network simulation. We define and use error metrics and benchmarks in scaled tests to empirically report the poor match of traditional, fairness-based VM scheduling to VM-based network simulation, and also clearly show the better performance of our simulation-specific scheduler, with up to 64 VMs hosted on a 12-core simulator node.

99 GENERAL AND MISCELLANEOUS↗

Benchmark Generation and Simulation at Extreme Scale

The path to extreme scale high-performance computing (HPC) poses several challenges related to power, performance, resilience, productivity, programmability, data movement, and data management. Investigating the performance of parallel applications at scale on future architectures and the performance impact of different architectural choices is an important component of HPC hardware/software co-design. Simulations using models of future HPC systems and communication traces from applications running on existing HPC systems can offer an insight into the performance of future architectures. This work targets technology developed for scalable application tracing of communication events. It focuses on extreme-scale simulation of HPC applications and their communication behavior via lightweight parallel discrete event simulation for performance estimation and evaluation. Instead of simply replaying a trace within a simulator, this work promotes the generation of a benchmark from traces. This benchmark is subsequently exposed to simulation using models to reflect the performance characteristics of future-generation HPC systems. This technique provides a number of benefits, such as eliminating the data intensive trace replay and enabling simulations at different scales. The presented work features novel software co-design aspects, combining the ScalaTrace tool to generate scalable trace files, the ScalaBenchGen tool to generate the benchmark, and the xSim tool to assess the benchmark characteristics within a simulator.

Lagadapati, Mahesh↗

Theoretical framework for new magnetic materials for quantum computing and information storage. Final report for the Award No. DE-SC0018910

The focus of this grant was on molecular magnetic materials for information storage and quantum computing. We have been developing robust, first-principle methods for computing relevant electronic and magnetic properties of molecular building blocks (SMMs) of novel magnetic materials and quantum computers. These tools enable theoretical modeling of SMMs’ behavior, facilitating the interpretation of experimental studies and aiding the design of novel magnetic materials. Our strategy is based on the spin-flip (SF) approach, which extends the hierarchy of black-box single-reference methods to strongly correlated systems. Specifically, we developed general scalable algorithms and computer codes for calculating molecular properties, with an emphasis on spin-related properties, such as zero-field splittings, hyperfine couplings, and g-tensors. While our primary focus was on SF wave functions and SF-TDDFT, the underlying theory and computer codes were formulated using reduced density matrices, such that these tools are applicable to a broader class of methods. To extend the scope of applicability of wave-function-based SF methods to larger systems, we developed reduced-scaling approaches for the equation-of-motion coupled-cluster (EOM-CC) methods and continue developing libtensor (our open-source general tensor contraction library for many-body methods). We carried out extensive benchmarks and also carried out several applications.

36 MATERIALS SCIENCE↗

A Sparse Distributed Gigascale Resolution Material Point Method

In this paper, we present a four-layer distributed simulation system and its adaptation to the Material Point Method (MPM). The system is built upon a performance portable C++ programming model targeting major High-Performance-Computing (HPC) platforms. A key ingredient of our system is a hierarchical block-tile-cell sparse grid data structure that is distributable to an arbitrary number of Message Passing Interface (MPI) ranks. We additionally propose strategies for efficient dynamic load balance optimization to maximize the efficiency of MPI tasks. Our simulation pipeline can easily switch among backend programming models, including OpenMP and CUDA, and can be effortlessly dispatched onto supercomputers and the cloud. Finally, we construct benchmark experiments and ablation studies on supercomputers and consumer workstations in a local network to evaluate the scalability and load balancing criteria. We demonstrate massively parallel, highly scalable, and gigascale resolution MPM simulations of up to 1.01 billion particles for less than 323.25 seconds per frame with 8 OpenSSH-connected workstations.

97 MATHEMATICS AND COMPUTING↗

Multiscale modelling of the phénix dissymmetric test benchmark

The Phenix sodium-cooled fast reactor contains two pools in which characteristic 3D effects like thermal stratification and jets play a significant role. One of the two active heat exchanger sets fails in the dissymmetric test, leading to changes in the thermal stratification and asymmetric conditions in the reactor. Therefore 3D modelling using Computational Fluid Dynamics codes (CFD) is required to model this transient in sufficient detail. However, several aspects of the reactor, like the core and the secondary side of the heat exchanger, can be modelled more efficiently by System Thermal-Hydraulics codes (STH). Therefore multiscale models are developed by coupling CFD and STH codes, exploiting the strengths of both codes in terms of modelling options and computational costs. The results provide insight in the local flow patterns and the temperature distribution during the dissymmetric transient. The results and modelling choices of the participants are compared in this paper and the main findings are discussed in the light of lessons learned from the blind phase of the benchmark and providing recommendations for future modelling of pool-type liquid metal-cooled reactors.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Performance Analysis and Projections for Petascale Applications on Cray XT Series Systems

The Petascale Cray XT5 system at the Oak Ridge National Laboratory (ORNL) Leadership Computing Facility (LCF) shares a number of system and software features with its predecessor, the Cray XT4 system including the quad-core AMD processor and a multi-core aware MPI library. We analyze performance of scalable scientific applications on the quad-core Cray XT4 system as part of the early system access using a combination of micro-benchmarks and Petascale ready applications. Particularly, we evaluate impact of key changes that occurred during the dual-core to quad-core processor upgrade on applications behavior and provide projections for the next-generation massively-parallel platforms with multicore processors, specifically for proposed Petascale Cray XT5 system. We compare and contrast the quad-core XT4 system features with the upcoming XT5 system and discuss strategies for improving scaling and performance for our target applications.

3LCF09TU↗

Mathematical efficiency calibration with uncertain source geometries using smart optimization

The In Situ Object Counting Software (ISOCS), a mathematical method developed by CANBERRA, is a well established technique for computing High Purity Germanium (HPGe) detector efficiencies for a wide variety of source shapes and sizes. In the ISOCS method, the user needs to input the geometry related parameters such as: the source dimensions, matrix composition and density, along with the source-to-detector distance. In many applications, the source dimensions, the matrix material and density may not be well known. Under such circumstances, the efficiencies may not be very accurate since the modeled source geometry may not be very representative of the measured geometry. CANBERRA developed an efficiency optimization software known as 'Advanced ISOCS' that varies the not well known parameters within user specified intervals and determines the optimal efficiency shape and magnitude based on available benchmarks in the measured spectra. The benchmarks could be results from isotopic codes such as MGAU, MGA, IGA, or FRAM, activities from multi-line nuclides, and multiple counts of the same item taken in different geometries (from the side, bottom, top etc). The efficiency optimization is carried out using either a random search based on standard probability distributions, or using numerical techniques that carry out a more directed (referred to as 'smart' in this paper) search. Measurements were carried out using representative source geometries and radionuclide distributions. The radionuclide activities were determined using the optimum efficiency and compared against the true activities. The 'Advanced ISOCS' method has many applications among which are: Safeguards, Decommissioning and Decontamination, Non-Destructive Assay systems and Nuclear reactor outages maintenance. (authors)

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

A hybrid framework of first principles molecular orbital calculations and a three-dimensional integral equation theory for molecular liquids: Multi-center molecular Ornstein–Zernike self-consistent field approach

In this study, we reported the development of a new quantum mechanics/molecular mechanics (QM/MM)-type framework to describe chemical processes in solution by combining standard molecular-orbital calculations with a three-dimensional formalism of integral equation theory for molecular liquids (multi-center molecular Ornstein–Zernike (MC-MOZ) method). The theoretical procedure is very similar to the 3D-reference interaction site model self-consistent field (RISM-SCF) approach. Since the MC-MOZ method is highly parallelized for computation, the present approach has the potential to be one of the most efficient procedures to treat chemical processes in solution. Benchmark tests to check the validity of this approach were performed for two solute (solute water and formaldehyde) systems and a simple S{sub N}2 reaction (Cl{sup −} + CH{sub 3}Cl → ClCH{sub 3} + Cl{sup −}) in aqueous solution. The results for solute molecular properties and solvation structures obtained by the present approach were in reasonable agreement with those obtained by other hybrid frameworks and experiments. In particular, the results of the proposed approach are in excellent agreements with those of 3D-RISM-SCF.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Comment on “Test of the Stark-effect theory using photoionization microscopy”

An article by Zhao et al. [Phys. Rev. A 86, 053413 (2012)] tests the local frame transformation (LFT) theory by comparing it with benchmark coupled-channel calculations. The system under consideration is an alkali-metal atom that is two-photon ionized in the presence of a static external electric field. Zhao et al. state that the differential cross sections computed in the LFT theory disagree with their supposedly more accurate coupled-channel calculations. They went on to diagnose the discrepancy and claimed that it originates in an inaccurate correspondence between the irregular functions in spherical and parabolic-cylindrical coordinates, a correspondence that lies at the heart of LFT theory. We have repeated the same tests and find that our calculations rule out the discrepancies that were claimed in Zhao et al. [Phys. Rev. A 86, 053413 (2012)] to exist between the LFT approximation and the exact calculations. Lastly, this Comment thus helps to clarify the accuracy of the Harmin-Fano theory and demonstrates that it is in fact remarkably accurate not only for the total photoionization cross section in the Stark effect, but also for the differential cross section in photoionization microscopy.

74 ATOMIC AND MOLECULAR PHYSICS↗

Compressed optimization of device architectures

Recent advances in nanotechnology have enabled researchers to control individual quantum mechanical objects with unprecedented accuracy, opening the door for both quantum and extreme- scale conventional computation applications. As these devices become more complex, designing for facility of control becomes a daunting and computationally infeasible task. Here, motivated by ideas from compressed sensing, we introduce a protocol for the Compressed Optimization of Device Architectures (CODA). It leads naturally to a metric for benchmarking and optimizing device designs, as well as an automatic device control protocol that reduces the operational complexity required to achieve a particular output. Because this protocol is both experimentally and computationally efficient, it is readily extensible to large systems. For this paper, we demonstrate both the bench- marking and device control protocol components of CODA through examples of realistic simulations of electrostatic quantum dot devices, which are currently being developed experimentally for quantum computation.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Dispatch Manager for NEML2 Constitutive Model Calculations Embedded in MOOSE

This report describes the extended capabilities of the NEML2 constitutive modeling library, including a flexible and efficient work dispatching system designed to leverage both CPU and GPU resources. This enhancement addresses one of the primary computational challenges in large-scale simulations: the ability to distribute and execute batches of material model evaluations across heterogeneous computing devices. The new dispatch system introduces a modular set of dispatcher and scheduler classes that coordinate the flow of data and execution between devices. The dispatcher is responsible for efficiently packaging work, managing device-specific memory operations, and synchronizing results. This modularity allows for extensibility, making it straightforward to integrate additional computing backends in the future. From an implementation standpoint, the dispatcher system interfaces seamlessly with NEML2's existing models. They handle device-aware tensor operations, optimize memory transfers, and support asynchronous execution when applicable. This design ensures that batches of material points can be evaluated concurrently, substantially improving throughput compared to previous single-device or serial implementations. These improvements not only enhance the raw performance of NEML2 but also improve its usability in multiscale and high-fidelity simulations, where the simultaneous evaluation of large material point batches is critical. Benchmarks included in the report demonstrate the system’s scalability, highlighting its effectiveness when leveraging modern GPU architectures.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

FY24 Progress Report on Viscosity and Thermal Conductivity Measurements of Nuclear Industry Relevant Chloride Salts: An Experimental and Computational Study

As presented in this report, experimental and computational techniques were performed to assess the viscosity and thermal conductivity of key alkali and actinide chloride mixtures for molten salt reactor developers. These mixtures were pure LiCl, NaCl-KCl, LiCl-NaCl, LiCl-KCl, LiCl-NaCl-KCl, and NaCl-UCl 3 . Experimental measurements of viscosity were performed with a rolling ball viscometer, whereas experimental measurements of thermal conductivity were performed with a variable gap apparatus. Additional benchmarking work was performed using both property measurement systems to prepare for x-ray radiography in stainless-steel crucibles for viscosity and to ensure that calibration methods were accurate for thermal conductivity before assessing the NaCl-UCl 3 system. Validation data for the NaCl-UCl 3 in literature are minimal. Details on the calibration methods, salt measurement processes, and sources of error and uncertainty are discussed in detail for both property measurements. The computational methods described herein involved ab-initio molecular dynamics (AIMD) calculations using CP2K. The calculations were performed for the LiCl-KCl-NaCl and NaCl-UCl 3 systems. These calculations not only provided thermophysical property estimations for comparison to experimental data, but they also allowed for the determination of diffusion coefficients, coordination numbers, and radial distribution functions to provide insight into ion mobility and local coordination environments, which is linked to macroscopic property trends.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Virtualized Logical Qubits: A 2.5D Architecture for Error-Corrected Quantum Computing

Current, near-term quantum devices have shown great progress in the last several years culminating recently with a demonstration of quantum supremacy. In the medium-term, however, quantum machines will need to transition to greater reliability through error correction, likely through promising techniques like surface codes which are well suited for near-term devices with limited qubit connectivity. We discover quantum memory, particularly resonant cavities with transmon qubits arranged in a 2.5D architecture, can efficiently implement surface codes with substantial hardware savings and performance/fidelity gains. Specifically, we virtualize logical qubits by storing them in layers of qubit memories connected to each transmon. Surprisingly, distributing each logical qubit across many memories has a minimal impact on fault tolerance and results in substantially more efficient operations. Our design permits fast transversal application of CNOT operations between logical qubits sharing the same physical address (same set of cavities) which are 6x faster than standard lattice surgery CNOTs. We develop a novel embedding which saves approximately 10x in transmons with another 2x savings from an additional optimization for compactness. Although qubit virtualization pays a 10x penalty in serialization, advantages in the transversal CNOT and in area efficiency result in fault-tolerance and performance comparable to conventional 2D transmon-only architectures. Our simulations show our system can achieve fault tolerance comparable to conventional two-dimensional grids while saving substantial hardware. Furthermore, our architecture can produce magic states at 1.22x the baseline rate given a fixed number of transmon qubits. Here, this is a critical benchmark for future fault-tolerant quantum computers as magic states are essential and machines will spend the majority of their resources continuously producing them. This architecture substantially reduces the hardware requirements for fault-tolerant quantum computing and puts within reach a proof-of-concept experimental demonstration of around 10 logical qubits, requiring only 11 transmons and 9 attached cavities in total.

quantum computing↗

Investigating power capping toward energy-efficient scientific applications: Investigating Power Capping toward Energy-Efficient Scientific Applications

The emergence of power efficiency as a primary constraint in processor and system design poses new challenges concerning power and energy awareness for numerical libraries and scientific applications. Power consumption also plays a major role in the design of data centers, which may house petascale or exascale-level computing systems. At these extreme scales, understanding and improving the energy efficiency of numerical libraries and their related applications becomes a crucial part of the successful implementation and operation of the computing system. In this paper, we study and investigate the practice of controlling a compute system's power usage, and we explore how different power caps affect the performance of numerical algorithms with different computational intensities. Further, we determine the impact, in terms of performance and energy usage, that these caps have on a system running scientific applications. This analysis will enable us to characterize the types of algorithms that benefit most from these power management schemes. Our experiments are performed using a set of representative kernels and several popular scientific benchmarks. Lastly, we quantify a number of power and performance measurements and draw observations and conclusions that can be viewed as a roadmap to achieving energy efficiency in the design and execution of scientific algorithms.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗