Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “computer hardware”

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 1,027 records · Page 57

FPGA-Accelerated Machine Learning Inference as a Service for Particle Physics Computing

Large-scale particle physics experiments face challenging demands for high-throughput computing resources both now and in the future. New heterogeneous computing paradigms on dedicated hardware with increased parallelization, such as Field Programmable Gate Arrays (FPGAs), offer exciting solutions with large potential gains. The growing applications of machine learning algorithms in particle physics for simulation, reconstruction, and analysis are naturally deployed on such platforms. We demonstrate that the acceleration of machine learning inference as a web service represents a heterogeneous computing solution for particle physics experiments that potentially requires minimal modification to the current computing model. As examples, we retrain the ResNet-50 convolutional neural network to demonstrate state-of-the-art performance for top quark jet tagging at the LHC and apply a ResNet-50 model with transfer learning for neutrino event classification. Using Project Brainwave by Microsoft to accelerate the ResNet-50 image classification model, we achieve average inference times of 60 (10) ms with our experimental physics software framework using Brainwave as a cloud (edge or on-premises) service, representing an improvement by a factor of approximately 30 (175) in model inference latency over traditional CPU inference in current experimental hardware. A single FPGA service accessed by many CPUs achieves a throughput of 600–700 inferences per second using an image batch of one, comparable to large batch-size GPU throughput and significantly better than small batch-size GPU throughput. Deployed as an edge or cloud service for the particle physics computing model, coprocessor accelerators can have a higher duty cycle and are potentially much more cost-effective.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

FPGAs as a Service to Accelerate Machine Learning Inference [PowerPoint]

Large-scale particle physics experiments face challenging demands for high-throughput computing resources both now and in the future. New heterogeneous computing paradigms on dedicated hardware with increased parallelization, such as Field Programmable Gate Arrays (FPGAs), offer exciting solutions with large potential gains. The growing applications of machine learning algorithms in particle physics for simulation, reconstruction, and analysis are naturally deployed on such platforms. We demonstrate that the acceleration of machine learning inference as a web service represents a heterogeneous computing solution for particle physics experiments that requires minimal modification to the current computing model. As examples, we retrain the ResNet-50 convolutional neural network to demonstrate state-of-the-art performance for top quark jet tagging at the LHC, and apply a ResNet-50 model with transfer learning for neutrino event classification. Using Project Brainwave b y Microsoft to accelerate the ResNet-50 image classification model, we achieve average inference times of 60 (10) milliseconds with our experimental physics software framework using Brainwave as a cloud (edge or on-premises) service, representing an improvement by a factor of approximately 30 (175) in model inference latency over traditional CPU inference in current experimental hardware. A single FPGA service accessed by many CPUs achieves a throughput of 600--700 inferences per second using an image batch of one, comparable to large batch-size GPU throughput and significantly better than small batch-size GPU throughput. Deployed as an edge or cloud service for the particle physics computing model, coprocessor accelerators can have a higher duty cycle and are potentially much more cost-effective.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Containers on Switches: A Cluster School Experience

Network switches, such as those from Arista and Mellanox, often have underutilized computational resources in the form of built-in processors and memory. By leveraging these untapped resources, we can optimize functionality and efficiency of computational cluster networks. Our research focuses on deploying containers directly onto these switches to execute various auxiliary tasks ranging from metric logging to system-wide management via post-boot configuration. By doing so, we can significantly enchance the capabilities of the cluster without the need for additional dedicated hardware. Our research involved five distinct scenarios where switch utilization could have a profound impact on HPC Clusters: run cloud-init services via link-local connection; configuring a Telegraf container to export metrics; deploying a caching proxy; creating a reconfigurable IPv6 DHCP/DNS provider for VLAN; and implementing a client detection with Magellan discovery. These scenarios were containerized with podman and docker, and tested both physically on the switch virtually on a QEMU VM both running SONiC OS. Testing and findings indicate that network switches can indeed be used for these scenarios. They offer a wide range of possibilities beyond these applications. They run as expected as containers on the switches, and although there were some minor issues, work-arounds were implemented. Overall, this is a positive result that can be further explored with more scenarios.

97 MATHEMATICS AND COMPUTING↗

Tusas: A fully implicit parallel approach for coupled phase-field equations

In this study, we develop a fully-coupled, fully-implicit approach for phase-field modeling of solidification in metals and alloys. Predictive simulation of solidification in pure metals and metal alloys remains a significant challenge in the field of materials science, as microstructure formation during the solidification process plays a critical role in the properties and performance of the solid material. Our simulation approach consists of a finite element spatial discretization of the fully-coupled nonlinear system of partial differential equations at the microscale, which is treated implicitly in time with a preconditioned Jacobian-free Newton-Krylov method. The approach is algorithmically scalable as well as efficient due to an effective preconditioning strategy based on algebraic multigrid and block factorization. We implement this approach in the open-source Tusas framework, which is a general, flexible tool developed in C++ for solving coupled systems of nonlinear partial differential equations. The performance of our approach is analyzed in terms of algorithmic scalability and efficiency, while the computational performance of Tusas is presented in terms of parallel scalability and efficiency on emerging heterogeneous architectures. We demonstrate that modern algorithms, discretizations, and computational science, and heterogeneous hardware provide a robust route for predictive phase-field simulation of microstructure evolution during additive manufacturing.

97 MATHEMATICS AND COMPUTING↗

Comparing Computer Run Time of Building Simulation Programs

This paper presents an approach to comparing computer run time of building simulation programs. The computing run time of a simulation program depends on several key factors, including the calculation algorithm and modeling capabilities of the program, the run period, the simulation time step, the complexity of the energy models, the run control settings, and the software and hardware configurations of the computer that is used to make the simulation runs. To demonstrate the approach, simulation runs are performed for several representative DOE-2.1E and EnergyPlus energy models. The computer run time of these energy models are then compared and analyzed.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Hardware-Accelerated Ray Tracing of CAD-Based Geometry for Monte Carlo Radiation Transport

Monte Carlo radiation transport (MCRT) methods have been used to simulate radiation environments for many decades by tracking individual particles through a model to accumulate statistical information. MCRT geometry is historically formed using the constructive solid geometry (CSG). Recently, significant work has been performed to support simulations using computer-aided design (CAD)-based tessellated surfaces to support highly complex geometries. Ray tracing acceleration data structures from the rendering and visualization community are applied to accelerate particle tracking in CAD-based models. Despite these efforts, CSG representations provide the superior performance in surface intersection operations during particle flight. Concurrently, pseudo Monte Carlo methods have become prevalent in rendering applications to support more realistic models for scattering media, motivating innovations that are advantageous for MCRT simulations. Finally, the authors’ work extends these innovations by employing Intel’s Embree ray tracing kernel within a geometry toolkit for Monte Carlo to improve the simulation performance using CAD-based models by factors of 1.5 to 2.

42 ENGINEERING↗

Uncontrolled Learning: Codesign of Neuromorphic Hardware Topology for Neuromorphic Algorithms

Neuromorphic computing has the potential to revolutionize future technologies and our understanding of intelligence, yet it remains challenging to realize in practice. The learning-from-mistakes algorithm, inspired by the brain's simple learning rules of inhibition and pruning, is one of the few brain-like training methods. This algorithm is implemented in neuromorphic memristive hardware through a codesign process that evaluates essential hardware trade-offs. While the algorithm effectively trains small networks as binary classifiers and perceptrons, performance declines significantly with increasing network size unless the hardware is tailored to the algorithm. This work investigates the trade-offs between depth, controllability, and capacity—the number of learnable patterns—in neuromorphic hardware. This highlights the importance of topology and governing equations, providing theoretical tools to evaluate a device's computational capacity based on its measurements and circuit structure. The findings show that breaking neural network symmetry enhances both controllability and capacity. Additionally, by pruning the circuit, neuromorphic algorithms in all-memristive circuits can utilize stochastic resources to create local contrasts in network weights. Through combined experimental and simulation efforts, the parameters are identified that enable networks to exhibit emergent intelligence from simple rules, advancing the potential of neuromorphic computing.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Cloud Computing for the Grid: GridControl: A Software Platform to Support the Smart Grid

GENI Project: Cornell University is creating a new software platform for grid operators called GridControl that will utilize cloud computing to more efficiently control the grid. In a cloud computing system, there are minimal hardware and software demands on users. The user can tap into a network of computers that is housed elsewhere (the cloud) and the network runs computer applications for the user. The user only needs interface software to access all of the cloud’s data resources, which can be as simple as a web browser. Cloud computing can reduce costs, facilitate innovation through sharing, empower users, and improve the overall reliability of a dispersed system. Cornell’s GridControl will focus on 4 elements: delivering the state of the grid to users quickly and reliably; building networked, scalable grid-control software; tailoring services to emerging smart grid uses; and simulating smart grid behavior under various conditions.

ARPA-E↗

Tools for 3D scientific visualization in computational aerodynamics at NASA Ames Research Center

Hardware, software, and techniques used by the Fluid Dynamics Division (NASA) for performing visualization of computational aerodynamics, which can be applied to the visualization of flow fields from computer simulations of fluid dynamics about the Space Shuttle, are discussed. Three visualization techniques applied, post-processing, tracking, and steering, are described, as well as the post-processing software packages used, PLOT3D, SURF (Surface Modeller), GAS (Graphical Animation System), and FAST (Flow Analysis software Toolkit). Using post-processing methods a flow simulation was executed on a supercomputer and, after the simulation was complete, the results were processed for viewing. It is shown that the high-resolution, high-performance three-dimensional workstation combined with specially developed display and animation software provides a good tool for analyzing flow field solutions obtained from supercomputers.

Bancroft, Gordon↗

A Case Study with the HACCmk Kernel in SYCL

The SYCL standard specifies a cross-platform abstraction layer that enables programming of heterogeneous computing systems using standard C++ [1]. In the Open Computing Language (OpenCL) programming model, host and device codes are written in different languages [2 ]. To improve development productivity and performance portability, the SYCL programming model combines host and device codes for an application in a type-safe way. In this report, we are interested in applying the SYCL programming model to a computationally intensive routine derived from the Hardware Accelerated Cosmology Code (HACC) framework for a study on performance portability on a heterogeneous computing device. We use Intel® OneAPI toolkit [3] to build the OpenCL and SYCL programs, and evaluate the performance of both implementations on Intel® integrated GPUs. We find that the SYCL implementation can achieve the same performance as the OpenCL implementation after we specify a target backend for the compiler to build the SYCL program in offline compilation. Without the specification of a target backend, the runtime will have to compile intermediate device codes for a target platform. Such runtime overhead may become significant compared to the execution of a kernel on a target device. As the kernel routine is compute-bound, we evaluate the impact of the number of compute units upon the kernel’s raw performance using two GPUs. When the hardware resource is not underutilized, we can obtain almost linear performance speedup from 48 compute units to 72 compute units in offline compilation, which indicates that the number of compute units on a GPU are important to improving the raw performance of a compute-bound kernel. The experimental results show that SYCL is a promising programming model for heterogeneous computing. The remainder of the report is organized as follows: In Section II, we describe the SYCL programming model, the steps to map an OpenCL program to a SYCL program, and the architecture of an integrated GPU. Section III introduces the kernel routine, and presents the OpenCL and SYCL implementations of the kernel. In Section IV, we evaluate the performance of the implementations on the GPUs. Section V concludes the report.

97 MATHEMATICS AND COMPUTING↗

Proton Conducting Neuromorphic Materials and Devices

Neuromorphic computing and artificial intelligence hardware generally aims to emulate features found in biological neural circuit components and to enable the development of energy-efficient machines. In the biological brain, ionic currents and temporal concentration gradients control information flow and storage. It is therefore of interest to examine materials and devices for neuromorphic computing wherein ionic and electronic currents can propagate. Protons being mobile under an external electric field offers a compelling avenue for facilitating biological functionalities in artificial synapses and neurons. In this review, we first highlight the interesting biological analog of protons as neurotransmitters in various animals. We then discuss the experimental approaches and mechanisms of proton doping in various classes of inorganic and organic proton-conducting materials for the advancement of neuromorphic architectures. Since hydrogen is among the lightest of elements, characterization in a solid matrix requires advanced techniques. We review powerful synchrotron-based spectroscopic techniques for characterizing hydrogen doping in various materials as well as complementary scattering techniques to detect hydrogen. First-principles calculations are then discussed as they help provide an understanding of proton migration and electronic structure modification. Outstanding scientific challenges to further our understanding of proton doping and its use in emerging neuromorphic electronics are pointed out.

36 MATERIALS SCIENCE↗

A neurocomputer based on an analog-digital hybrid architecture

A novel analog-digital hybrid architecture based on the utilization of high density digital random access memories for the storage of the synaptic weights of a neural network, and high speed analog hardware to perform neural computation is described. An electronic neurocomputer based on such an architecture is ideally suited for investigating the dynamics, associative recall properties, and computational capabilities of neural networks and provides significant speed improvement in comparison to conventional software based neural network simulations. As a demonstration of the feasibility of the hybrid architectural concept, a prototype breadboard hybrid neurocomputer system with 32 neurons has been designed and fabricated with off-the-shelf hardware components. The performance of the breadboard system has been tested for variety of applications including associative memory and combinatorial problem solving such as Graph Coloring, and is discussed in this paper.

Moopenn, A.↗

Verification of the FtCayuga fault-tolerant microprocessor system. Volume 1: A case study in theorem prover-based verification

The design and formal verification of a hardware system for a task that is an important component of a fault tolerant computer architecture for flight control systems is presented. The hardware system implements an algorithm for obtaining interactive consistancy (byzantine agreement) among four microprocessors as a special instruction on the processors. The property verified insures that an execution of the special instruction by the processors correctly accomplishes interactive consistency, provided certain preconditions hold. An assumption is made that the processors execute synchronously. For verification, the authors used a computer aided design hardware design verification tool, Spectool, and the theorem prover, Clio. A major contribution of the work is the demonstration of a significant fault tolerant hardware design that is mechanically verified by a theorem prover.

Srivas, Mandayam↗

Hardware device binding and mutual authentication

Detection and deterrence of device tampering and subversion by substitution may be achieved by including a cryptographic unit within a computing device for binding multiple hardware devices and mutually authenticating the devices. The cryptographic unit includes a physically unclonable function ("PUF") circuit disposed in or on the hardware device, which generates a binding PUF value. The cryptographic unit uses the binding PUF value during an enrollment phase and subsequent authentication phases. During a subsequent authentication phase, the cryptographic unit uses the binding PUF values of the multiple hardware devices to generate a challenge to send to the other device, and to verify a challenge received from the other device to mutually authenticate the hardware devices.

97 MATHEMATICS AND COMPUTING↗

Advanced Simulation and Computing FY12-13 Implementation Plan, Volume 2, Revision 0.5

The Stockpile Stewardship Program (SSP) is a single, highly integrated technical program for maintaining the surety and reliability of the U.S. nuclear stockpile. The SSP uses nuclear test data, computational modeling and simulation, and experimental facilities to advance understanding of nuclear weapons. It includes stockpile surveillance, experimental research, development and engineering (D&E) programs, and an appropriately scaled production capability to support stockpile requirements. This integrated national program requires the continued use of experimental facilities and programs, and the computational enhancements to support these programs. The Advanced Simulation and Computing Program (ASC) is a cornerstone of the SSP, providing simulation capabilities and computational resources that support annual stockpile assessment and certification, study advanced nuclear weapons design and manufacturing processes, analyze accident scenarios and weapons aging, and provide the tools to enable stockpile Life Extension Programs (LEPs) and the resolution of Significant Finding Investigations (SFIs). This requires a balanced resource, including technical staff, hardware, simulation software, and computer science solutions. In its first decade, the ASC strategy focused on demonstrating simulation capabilities of unprecedented scale in three spatial dimensions. In its second decade, ASC is now focused on increasing predictive capabilities in a three-dimensional (3D) simulation environment while maintaining support to the SSP. The program continues to improve its unique tools for solving progressively more difficult stockpile problems (sufficient resolution, dimensionality, and scientific details), quantify critical margins and uncertainties, and resolve increasingly difficult analyses needed for the SSP. Moreover, ASC’s business model is integrated and focused on requirements-driven products that address long-standing technical questions related to enhanced predictive capability in the simulation tools.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Advanced Simulation and Computing Fiscal Year 14 Implementation Plan, Rev. 0.5

The Stockpile Stewardship Program (SSP) is a single, highly integrated technical program for maintaining the surety and reliability of the U.S. nuclear stockpile. The SSP uses nuclear test data, computational modeling and simulation, and experimental facilities to advance understanding of nuclear weapons. It includes stockpile surveillance, experimental research, development and engineering programs, and an appropriately scaled production capability to support stockpile requirements. This integrated national program requires the continued use of experimental facilities and programs, and the computational enhancements to support these programs. The Advanced Simulation and Computing Program (ASC) is a cornerstone of the SSP, providing simulation capabilities and computational resources that support annual stockpile assessment and certification, study advanced nuclear weapons design and manufacturing processes, analyze accident scenarios and weapons aging, and provide the tools to enable stockpile Life Extension Programs (LEPs) and the resolution of Significant Finding Investigations (SFIs). This requires a balanced resource, including technical staff, hardware, simulation software, and computer science solutions. In its first decade, the ASC strategy focused on demonstrating simulation capabilities of unprecedented scale in three spatial dimensions. In its second decade, ASC is now focused on increasing predictive capabilities in a three-dimensional (3D) simulation environment while maintaining support to the SSP. The program continues to improve its unique tools for solving progressively more difficult stockpile problems (sufficient resolution, dimensionality, and scientific details), quantify critical margins and uncertainties, and resolve increasingly difficult analyses needed for the SSP. Moreover, ASC’s business model is integrated and focused on requirements-driven products that address long-standing technical questions related to enhanced predictive capability in the simulation tools.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Advanced Simulation & Computing FY15 Implementation Plan Volume 2, Rev. 0.5

The Stockpile Stewardship Program (SSP) is a single, highly integrated technical program for maintaining the surety and reliability of the U.S. nuclear stockpile. The SSP uses nuclear test data, computational modeling and simulation, and experimental facilities to advance understanding of nuclear weapons. It includes stockpile surveillance, experimental research, development and engineering programs, and an appropriately scaled production capability to support stockpile requirements. This integrated national program requires the continued use of experimental facilities and programs, and the computational enhancements to support these programs. The Advanced Simulation and Computing Program (ASC) is a cornerstone of the SSP, providing simulation capabilities and computational resources that support annual stockpile assessment and certification, study advanced nuclear weapons design and manufacturing processes, analyze accident scenarios and weapons aging, and provide the tools to enable stockpile Life Extension Programs (LEPs) and the resolution of Significant Finding Investigations (SFIs). This requires a balance of resource, including technical staff, hardware, simulation software, and computer science solutions. As the program approaches the end of its second decade, ASC is intently focused on increasing predictive capabilities in a three-dimensional (3D) simulation environment while maintaining support to the SSP. The program continues to improve its unique tools for solving progressively more difficult stockpile problems (sufficient resolution, dimensionality, and scientific details), quantify critical margins and uncertainties, and resolve increasingly difficult analyses needed for the SSP. Where possible, the program also enables the use of high-performance simulation and computing tools to address broader national security needs, such as foreign nuclear weapon assessments and counternuclear terrorism.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗