Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “COMPUTER ARCHITECTURE”

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 1,765 records · Page 98

SU-E-T-180: Fano Cavity Test of Proton Transport in Monte Carlo Codes Running On GPU and Xeon Phi

Purpose: In proton dose calculation, clinically compatible speeds are now achieved with Monte Carlo codes (MC) that combine 1) adequate simplifications in the physics of transport and 2) the use of hardware architectures enabling massive parallel computing (like GPUs). However, the uncertainties related to the transport algorithms used in these codes must be kept minimal. Such algorithms can be checked with the so-called “Fano cavity test”. We implemented the test in two codes that run on specific hardware: gPMC on an nVidia GPU and MCsquare on an Intel Xeon Phi (60 cores). Methods: gPMC and MCsquare are designed for transporting protons in CT geometries. Both codes use the method of fictitious interaction to sample the step-length for each transport step. The considered geometry is a water cavity (2×2×0.2 cm{sup 3}, 0.001 g/cm{sup 3}) in a 10×10×50 cm{sup 3} water phantom (1 g/cm{sup 3}). CPE in the cavity is established by generating protons over the phantom volume with a uniform momentum (energy E) and a uniform intensity per unit mass I. Assuming no nuclear reactions and no generation of other secondaries, the computed cavity dose should equal IE, according to Fano's theorem. Both codes were tested for initial proton energies of 50, 100, and 200 MeV. Results: For all energies, gPMC and MCsquare are within 0.3 and 0.2 % of the theoretical value IE, respectively (0.1% standard deviation). Single-precision computations (instead of double) increased the error by about 0.1% in MCsquare. Conclusion: Despite the simplifications in the physics of transport, both gPMC and MCsquare successfully pass the Fano test. This ensures optimal accuracy of the codes for clinical applications within the uncertainties on the underlying physical models. It also opens the path to other applications of these codes, like the simulation of ion chamber response.

60 APPLIED LIFE SCIENCES↗

Superconducting disordered neural networks for neuromorphic processing with fluxons

In superconductors, magnetic fields are quantized into discrete fluxons (flux quanta Φ 0 ), made of microscopic circulating supercurrents. We introduce a multiterminal synapse network comprising a disordered array of superconducting loops with Josephson junctions. The loops can trap fluxons defining memory, while the junctions allow their movement between loops. Dynamics of fluxons through such a disordered system through a complex reconfigurable energy landscape represents brain-like spiking information flow. In this work, we experimentally demonstrate a three-loop network using YBa 2 Cu 3 O 7 –δ -based superconducting loops and Josephson junctions, which exhibit stable memory configurations of trapped flux in loops that determine the rate of flow of fluxons through synaptic connections. The memory states are, in turn, affected by the applied input signals but can also be externally configured electrically through control current/feedback terminals. These results establish a previously unexplored, biologically similar architectural approach to neuromorphic computing that is scalable while dissipating energy of atto Joules/spike.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

TrioSim: A Lightweight Simulator for Large-Scale DNN Workloads on Multi-GPU Systems

Deep Neural Networks (DNNs) have become increasingly capable of performing tasks ranging from image recognition to content generation. The training and inference of DNNs heavily rely on GPUs, as GPUs' massively parallel architecture delivers extremely high computing capability. With the growing complexity of DNNs and the size of training datasets, training DNNs with a large number of GPUs is becoming a prevalent strategy. Researchers have been exploring how to design software and hardware systems for GPU farms to achieve the best utilization, efficiency, and DNN accuracy during training or inference. However, when designing and deploying such systems, designers usually rely on testing on physical hardware platforms equipped with many GPUs, incurring high costs that are almost prohibitive for system designers to test different configurations and designs, even for highly resourceful companies. While an alternative solution is to test on GPU simulators, they are often too slow for these l

Li, Ying [William & Mary, Williamsburg, VA, USA] (↗

AMReX: a framework for block-structured adaptive mesh refinement

AMReX is a C++ software framework that supports the development of block-structured adaptive mesh refinement (AMR) algorithms for solving systems of partial differential equations (PDEs) with complex boundary conditions on current and emerging architectures. AMR reduces the computational cost and memory footprint compared to a uniform mesh while preserving the local descriptions of different physical processes in complex multiphysics algorithms. Current AMReX-based application codes span a number of areas, including atmospheric modeling, astrophysics, combustion, cosmology, fluctuating hydrodynamics, multiphase flows, and particle accelerators. In particular, the AMReX-Astro GitHub repository holds a number of astrophysical modeling tools based on AMReX. The origins of AMReX trace back to the BoxLib software framework. AMReX supports a number of different time-stepping strategies and spatial discretizations. Solution strategies supported by AMReX range from level-by-level approaches (with or without subcycling in time) with multilevel synchronization to full-hierarchy approaches, and any combination thereof. User-defined kernels that operate on patches of data can be written in C++ or Fortran; there is also a Fortran-interface functionality which wraps the core C++ data structures and operations in Fortran wrappers so that an application code based on AMReX can be written entirely in Fortran.

97 MATHEMATICS AND COMPUTING↗

Solid oxide electrochemical reactor science.

Solid-oxide electrochemical cells are an exciting new technology. Development of solid-oxide cells (SOCs) has advanced considerable in recent years and continues to progress rapidly. This thesis studies several aspects of SOCs and contributes useful information to their continued development. This LDRD involved a collaboration between Sandia and the Colorado School of Mines (CSM) ins solid-oxide electrochemical reactors targeted at solid oxide electrolyzer cells (SOEC), which are the reverse of solid-oxide fuel cells (SOFC). SOECs complement Sandia's efforts in thermochemical production of alternative fuels. An SOEC technology would co-electrolyze carbon dioxide (CO{sub 2}) with steam at temperatures around 800 C to form synthesis gas (H{sub 2} and CO), which forms the building blocks for a petrochemical substitutes that can be used to power vehicles or in distributed energy platforms. The effort described here concentrates on research concerning catalytic chemistry, charge-transfer chemistry, and optimal cell-architecture. technical scope included computational modeling, materials development, and experimental evaluation. The project engaged the Colorado Fuel Cell Center at CSM through the support of a graduate student (Connor Moyer) at CSM and his advisors (Profs. Robert Kee and Neal Sullivan) in collaboration with Sandia.

02 PETROLEUM↗

Reactor Subsystem Simulation for Nuclear Hybrid Energy Systems

Nuclear Hybrid Energy Systems (NHES) could be a key part of the solution to achieving energy security, may provide reliable power availability even with increasing renewable energy penetration into the power grid, and may allow repurposing excess electricity in times of low demand. Incorporating a fission-based power source in a multi-output system (electricity and process heat) can offer significant advantages over carbon-based production sources, such as coal or natural gas, including reduction in atmospheric carbon emissions. In an integrated multi-output system, thermal energy from the nuclear reactor subsystem can be diverted to industrial applications in times of low electricity demand. High temperature, high quality heat from advanced reactor designs might be used for hydrogen production or synthetic fuel production (coal-to-liquid or natural gas-to-liquid processes). Low temperature heat from advanced reactor designs or the current and future fleet of light water reactors (LWRs) might be applied to desalination processes or be stored for later use in low temperature ammonia or hydrocarbon-based thermal cycles. The NHES research team is currently developing a dynamic simulation of an integrated hybrid energy system. A detailed simulation of proposed NHES architectures will allow initial computational demonstration of a tightly coupled NHES to identify key reactor subsystem requirements, identify candidate reactor technologies for a hybrid system, and identify key challenges to operation of the coupled system. This work will provide a baseline for later coupling of design-specific reactor models through industry collaboration. The modeling capability addressed in this report focuses on the reactor subsystem simulation. Many computational tools and methods are available for modeling a nuclear reactor, power conversion systems and associated process applications. One method is to develop a single program capable of modeling the entire system. Another is to combine two or more existing computer programs, each modeling a portion of the system for which it is validated, where the programs exchange information to compute the solution. The former method requires a lengthy development and verification and validation process. The latter method leverages industry standard software to reduce development and funding requirements. Preliminary system models have been developed by Idaho National Laboratory researchers and are currently being enhanced to assess integrated system performance given multiple sources (e.g., nuclear + wind) and multiple applications (i.e., electricity + process heat). Initial efforts to integrate a Fortran-based simulation of a small modular reactor (SMR) with the balance of plant model have been completed in FY12. This initial effort takes advantage of an existing SMR model developed at North Carolina State University to provide initial integrated system simulation for a relatively low cost. The SMR subsystem simulation details are discussed in this report.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Fully-Coupled Thermo-Electrical Modeling and Simulation of Transition Metal Oxide Memristors

Transition metal oxide (TMO) memristors have recently attracted special attention from the semiconductor industry and academia. Memristors are one of the strongest candidates to replace flash memory, and possibly DRAM and SRAM in the near future. Moreover, memristors have a high potential to enable beyond-CMOS technology advances in novel architectures for high performance computing (HPC). The utility of memristors has been demonstrated in reprogrammable logic (cross-bar switches), brain-inspired computing and in non-CMOS complementary logic. Indeed, the potential use of memristors as logic devices is especially important considering the inevitable end of CMOS technology scaling that is anticipated by 2025. In order to aid the on-going Sandia memristor fabrication effort with a memristor design tool and establish a clear physical picture of resistance switching in TMO memristors, we have created and validated with experimental data a simulation tool we name the Memristor Charge Transport (MCT) Simulator.

97 MATHEMATICS AND COMPUTING↗

Virtual Integrated Battery Environment (VIBE): Version 1.2 Release Documentation

As part of the CAEBAT (Computer Aided Engineering for Batteries) activities, ORNL developed a flexible, robust, and computationally scalable open-architecture framework that integrates multi-physics and multi-scale battery models. The physics phenomena of interest include charge and thermal transport, electrochemical reactions, and mechanical stresses. They operate and interact across the porous 3D structure of the electrodes (cathodes an d anodes), the solid or liquid electrolyte system and the other battery components. The underlying lower-length processes are accounted for through closure equations and sub-models that are based on resolved quantities.

25 ENERGY STORAGE↗

Early Performance Results on 4th Gen Intel(R) Xeon (R) Scalable Processors with DDR and Intel(R) Xeon(R) processors, codenamed Sapphire Rapids with HBM

The Crossroads supercomputer was designed to simulate some of the most complex physical devices in the world. These simulations routinely require 1/2 petabyte or more of system memory running on thousands of compute nodes for months at a time on the most powerful supercomputers. Improvements in time to solutions for these workloads can have major impact on our mission capabilities. In this paper we present early results of representative application workloads on 4th Gen Intel Xeon and Intel Xeon Processors codenamed Sapphire Rapids with HBM. These results demonstrate an extremely promising 8.57x improvement (node to node) over our prior generation Intel Broadwell (BDW) based HPC systems. No code modifications were required to achieve this speedup, providing a compelling path forward toward major reductions in time to solution and the complexity of physical systems that can be simulated in the future.

97 MATHEMATICS AND COMPUTING↗

How is statistical thinking useful for evaluating foundation models?

Good’s statement appears to be rather prescient – while humanity has marched on through to the 21st century, modern artificial intelligence (AI), driven by a menagerie of immense deep-neural-network architectures aided with parallel computation, seems positioned to change life as we know it. It would be an understatement to say that the world has been captivated by AI. Recent engineering feats, such as autonomous vehicles and generative AI, have gripped the public sphere, and AI is poised to disrupt a host of industries – including software, pharmaceuticals, healthcare, manufacturing, entertainment, and a slew of others; indeed, one is hard pressed to find any industry that does not claim to bear an impact from the so-called AI revolution.

97 MATHEMATICS AND COMPUTING↗

Heterogeneous Computing

To leverage the increasing heterogeneity in modern computing resources, Geant4 incorporates advanced software tools and a task-based framework (G4Tasking) that enables efficient parallelism at event, sub-event, and track levels. Ongoing R&D efforts focus on integrating GPUs into high-energy physics (HEP) simulations, including optical photon simulation with Opticks/NVIDIA OptiX, offloading electromagnetic particle transport using G4HepEM/AdePT and Celeritas, and employing advanced surface-based geometry models such as VecGeom2.0 and ORANGE. As Geant4 continues evolving toward high-performance computing (HPC) and heterogeneous architectures, it remains a key tool for large-scale simulations in HEP and beyond.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

AMReX

AMReX is a software framework for the development and implementation of massively parallel algorithms using block-structured adaptive mesh refinement (AMR). Block-structured AMR provides the basis for the temporal and spatial discretization strategy for a large variety of applications of interest to the DOE. AMReX provides a unified infrastructure with the functionality needed for applications to be able to effectively and efficiently utilize machines from laptops to exascale accelerator-based architectures. AMR reduces the computational cost and memory footprint compared to a uniform mesh while preserving accurate descriptions of different physical processes in complex multi-physics algorithms. AMReX supports algorithms that solve systems of partial differential equations (PDEs) in simple or complex geometries, and those that use particles and/or particle-mesh operations to represent component physical processes.

Zhang, Weiqun↗

The staging system: Display and edit module

The Display and Edit (D and E) Module described is one of six major modules being developed for the STAGING (STructural Analysis through Generalized INteractive Graphics) System. Several remarks are included concerning the computer environment and the architecture of the data base. The utility of this module is emphasized.

Edwards, E.↗

Preliminary study for a Numerical Aerodynamic Simulation Facility

The state of the art of relevant technologies, of systems and processor architectures, and the measurable computational requirements of the two existing Navier-Stokes solution programs were assessed by Control Data Corporation to determine the best approach for designing a system for aerodynamic simulation. Standard parts and components were used to identify the support processing system, which is composed of commercially available equipment and software. Technological achievements in large scale integration technology and system organization of subcomponents borrowed from the STAR-100C project were used in the design of the Navier-Stokes solver.

Lincoln, N. R.↗

A vectorization of the Hess McDonnell Douglas potential flow program NUED for the STAR-100 computer

The computer program NUED for analyzing potential flow about arbitrary three dimensional lifting bodies using the panel method was modified to use vector operations and run on the STAR-100 computer. A high speed of computation and ability to approximate the body surface with a large number of panels are characteristics of NUEDV. The new program shows that vector operations can be readily implemented in programs of this type to increase the computational speed on the STAR-100 computer. The virtual memory architecture of the STAR-100 facilitates the use of large numbers of panels to approximate the body surface.

Boney, L. R.↗

Cost and performance characteristics of data system configurations for processing remotely sensed data

Some alternative approaches to constructing a large remote-sensing data system are explored. The cost and performance implications of using a collection of 'small' computers versus using one large computer are examined. Several architectures and associated costs for the large data system supporting a single data center are presented. Recurring cost factors (maintenance and operations) currently slightly favor the single large-machine architecture, but other factors may dictate the choice of one of the two multimachine architectures discussed.

Gregor, P. J.↗

Solar thermal heating and cooling. A bibliography with abstracts

This bibliographic series cites and abstracts the literature and technical papers on the heating and cooling of buildings with solar thermal energy. Over 650 citations are arranged in the following categories: space heating and cooling systems; space heating and cooling models; building energy conservation; architectural considerations, thermal load computations; thermal load measurements, domestic hot water, solar and atmospheric radiation, swimming pools; and economics.

Arenson, M.↗

SIFT - Multiprocessor architecture for Software Implemented Fault Tolerance flight control and avionics computers

A brief description of a SIFT (Software Implemented Fault Tolerance) Flight Control Computer with emphasis on implementation is presented. A multiprocessor system that relies on software-implemented fault detection and reconfiguration algorithms is described. A high level reliability and fault tolerance is achieved by the replication of computing tasks among processing units.

Forman, P.↗