Search NASA⌕ Search

SEARCH · Search NASA

Results for “hardware accelerators”

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 559 records · Page 31

PLATFORM for Product Launch

Pecan Street Inc. (PSI) and its partners set out in 2017 to validate the PLATFORM for Product Launch, a new model for improving the effectiveness of investments in clean energy technologies and accelerating market entry of disruptive technologies. In partnership with a newly formed Innovation Advisory Council, PSI recruited fourteen companies with new hardware-based technologies that enable or create clean energy opportunities. Pecan Street carried out product evaluations and conducted market research with stakeholders and target customers to develop recommendations on product optimization opportunities for all companies, and created third party performance evaluation reports that include environmental metrics, such as water and energy savings potential, to assist in creating investment confidence and to unlock additional sources of funding, such as impact investments. Pecan Street set-up the product testing environment, performed small-batch field testing, and provided a verified third-party performance report on the product of twelve companies. PSI Street and its partners leveraged the performance evaluations and insights from the newly formed PRI toolkit to raise over $1.5M across five companies, and garner interest for private sector adoption of the PLATFORM for Product Launch.

24 POWER TRANSMISSION AND DISTRIBUTION↗

An Evaluation of Molecular Dynamics Performance on the Hybrid Cray XK6 Supercomputer

For many years, the drive towards computational physics studies that match the size and time-scales of experiment has been fueled by increases in processor and interconnect performance that could be exploited with relatively little modification to existing codes. Engineering and electrical power constraints have disrupted this trend, requiring more drastic changes to both hardware and software solutions. Here, we present details of the Cray XK6 architecture that achieves increased performance with the use of GPU accelerators. We review software development efforts in the LAMMPS molecular dynamics package that have been implemented in order to utilize hybrid high performance computers. We present benchmark results for solid-state, biological, and mesoscopic systems and discuss some challenges for utilizing hybrid systems. We present some early work in improving application performance on the XK6 and performance results for the simulation of liquid copper nanostructures with the embedded atom method.

43 PARTICLE ACCELERATORS↗

On the Marriage of Asynchronous Many Task Runtimes and Big Data: A Glance

The rise of the accelerator-based architectures and reconfigurable computing have showcased the weakness of software stack toolchains that still maintain a static view of the hardware instead of relying on a symbiotic relationship between static (e.g., compilers) and dynamic tools (e.g., runtimes). In the past decades, this need has given rise to adaptive runtimes with increasingly finer computational tasks. These finer tasks help to take advantage of the hardware by switching out when a long latency operation is encountered (because of the deeper memory hierarchies and new memory technologies that might target streaming instead of random access), thus trading off idle time for unrelated work. Examples of these finer task runtimes are Asynchronous Many Task (AMT) runtimes, in which highly efficient computational graphs run on a variety of hardware. Due to its inherent latency tolerant characteristics, Latency-sensitive applications, such as Graph Analytics and Big Data can effectively use these runtimes. This paper aims to present an example of how the careful design of an AMT can exploit the hardware substrate when faced with high latency applications such as the ones given in the Big Data domain. Moreover, with its introspection and adaptive capabilities, we aim to show the power of these runtimes when facing the changing requirements of the application workloads. We use the Performance Open Community Runtime (P-OCR) as our vehicle to demonstrate the concepts presented here.

adaptive runtime, big data analysis↗

Accelerating DNA analysis applications on GPU clusters

DNA analysis is an emerging application of high performance bioinformatic. Modern sequencing machinery are able to provide, in few hours, large input streams of data which needs to be matched against exponentially growing databases known fragments. The ability to recognize these patterns effectively and fastly may allow extending the scale and the reach of the investigations performed by biology scientists. Aho-Corasick is an exact, multiple pattern matching algorithm often at the base of this application. High performance systems are a promising platform to accelerate this algorithm, which is computationally intensive but also inherently parallel. Nowadays, high performance systems also include heterogeneous processing elements, such as Graphic Processing Units (GPUs), to further accelerate parallel algorithms. Unfortunately, the Aho-Corasick algorithm exhibits large performance variabilities, depending on the size of the input streams, on the number of patterns to search and on the number of matches, and poses significant challenges on current high performance software and hardware implementations. An adequate mapping of the algorithm on the target architecture, coping with the limit of the underlining hardware, is required to reach the desired high throughputs. Load balancing also plays a crucial role when considering the limited bandwidth among the nodes of these systems. In this paper we present an efficient implementation of the Aho-Corasick algorithm for high performance clusters accelerated with GPUs. We discuss how we partitioned and adapted the algorithm to fit the Tesla C1060 GPU and then present a MPI based implementation for a heterogeneous high performance cluster. We compare this implementation to MPI and MPI with pthreads based implementations for a homogeneous cluster of x86 processors, discussing the stability vs. the performance and the scaling of the solutions, taking into consideration aspects such as the bandwidth among the different nodes.

59 BASIC BIOLOGICAL SCIENCES↗

Low-Level Radio Frequency System Development for the National Synchrotron Light Source II

The National Synchrotron Light Source-II (NSLS-II) is a new ultra-bright 3GeV 3rd generation synchrotron radiation light source. The performance goals require operation with a beam current of 500mA and a bunch current of at least 0.5mA. The position and timing specifications of the ultra-bright photon beam imposes a set of stringent requirements on the performance of radio frequency (RF) control. In addition, commissioning and staged installation of damping wigglers and insertion devices requires the flexibility of handling varying beam conditions. To meet these requirements, a digital implementation of the LLRF is chosen, and digital serial links are planned for the system integration. The first prototype of the controller front-end hardware has been built, and is currently being tested.

43 PARTICLE ACCELERATORS↗

Benchmarking Non-Hardware Balance-of-System (Soft) Costs for U.S. Photovoltaic Systems Using a Bottom-Up Approach and Installer Survey

This report presents results from the first U.S. Department of Energy (DOE) sponsored, bottom-up data-collection and analysis of non-hardware balance-of-system costs—often referred to as “business process” or “soft” costs—for residential and commercial photovoltaic (PV) systems. Annual expenditure and labor-hour-productivity data are analyzed to benchmark 2010 soft costs related to the DOE priority areas of (1) customer acquisition; (2) permitting, inspection, and interconnection; (3) installation labor; and (4) installer labor for arranging third-party financing. Annual expenditure and labor-hour data were collected from 87 PV installers. After eliminating outliers, the survey sample consists of 75 installers, representing approximately 13% of all residential PV installations and 4% of all commercial installations added in 2010. Including assumed permitting fees, in 2010 the average soft costs benchmarked in this analysis total $1.50/W for residential systems (ranging from $0.66/W to $1.66/W between the 20th and 80th percentiles). For commercial systems, the median 2010 benchmarked soft costs (including assumed permitting fees) are $0.99/W for systems smaller than 250 kW (ranging from $0.51/W to $1.45/W between the 20th and 80th percentiles) and $0.25/W for systems larger than 250 kW (ranging from $0.17/W to $0.78/W between the 20th and 80th percentiles). Additional soft costs not benchmarked in the present analysis (e.g., installer profit, overhead, financing, and contracting) are significant and would add to these figures. The survey results provide a benchmark for measuring—and helping to accelerate—progress over the next decade toward achieving the DOE SunShot Initiative’s soft-cost-reduction targets. We conclude that the selected non-hardware business processes add considerable cost to U.S. PV systems, constituting 23% of residential PV system price, 17% of small commercial system price, and 5% of large commercial system price (in 2010). These processes present significant opportunities for further cost reductions and labor-productivity gains.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

A Modular Accelerator Robotics Framework for AD Robotics

Accelerator tunnels, such as the ones at Fermilab, remain highly radioactive after beam shutoff due to induced radiation from the beam. This residual radiation creates a hazardous environment for manual inspection and repair of beamline components. To minimize worker radiation dose and reduce beam downtime, the AD Robotics Initiative previously built a fleet of low-cost custom mobile robots. However, the custom Python sockets server-client architecture lacked standardization, causing development delays and complicating the integration of new sensors and actuators. Here, we developed a modular system using ROS2 and Docker to standardize the teleoperation and control interfaces. This system was validated by implementing a teleoperation controller with real-time, low-latency, and high-definition video feedback. The aim of this framework is for a new feature or even a robot to be integrated into the system simply by documenting the hardware configuration. Current integration of LiDAR, Odometry, and Depth Cameras provides the foundation for Simultaneous Localization and Mapping (SLAM) tasks. Finally, future work involves integration into the accelerator control system and the attachment of a 6 degree-of-freedom robotic arm for telemanipulation.

Rayyan Khan, M. [Fermilab; Rensselaer Poly.; Unlis↗

Modular Accelerator Robotics Framework Implementation For Accelerator Inspection

Accelerator tunnels, such as the ones at Fermilab, remain highly radioactive after beam shutoff due to induced radiation from the beam. This residual radiation creates a hazardous environment for manual inspection and repair of beamline components. To minimize worker radiation dose and reduce beam downtime, the AD Robotics Initiative previously built a fleet of low-cost custom mobile robots. However, the custom Python sockets server-client architecture lacked standardization, causing development delays and complicating the integration of new sensors and actuators. Here, we developed a modular system using ROS2 and Docker to standardize the teleoperation and control interfaces. This system was validated by implementing a teleoperation controller with real-time, low-latency, and high-definition video feedback. The aim of this framework is for a new feature or even a robot to be integrated into the system simply by documenting the hardware configuration. Current integration of LiDAR, Odometry, and Depth Cameras provides the foundation for Simultaneous Localization and Mapping (SLAM) tasks. Finally, future work involves integration into the accelerator control system and the attachment of a 6 degree-of-freedom robotic arm for telemanipulation.

Rayyan Khana, M. [Unlisted, US, IL] (ORCID:0009000↗

Considerations on the Use of Custom Accelerators for Big Data Analytics

Accelerators, including Graphic Processing Units (GPUs) for gen- eral purpose computation, many-core designs with wide vector units (e.g., Intel Phi), have become a common component of many high performance clusters. The appearance of more stable and reliable tools tools that can automatically convert code written in high-level specifications with annotations (such as C or C++) to hardware de- scription languages (High-Level Synthesis - HLS), is also setting the stage for a broader use of reconfigurable devices (e.g., Field Pro- grammable Gate Arrays - FPGAs) in high performance system for the implementation of custom accelerators, helped by the fact that new processors include advanced cache-coherent interconnects for these components. In this chapter, we briefly survey the status of the use of accelerators in high performance systems targeted at big data analytics applications. We argue that, although the progress in the use of accelerators for this class of applications has been sig- nificant, differently from scientific simulations there still are gaps to close. This is particularly true for the ”irregular” behaviors exhibited by no-SQL, graph databases. We focus our attention on the limits of HLS tools for data analytics and graph methods, and discuss a new architectural template that better fits the requirement of this class of applications. We validate the new architectural templates by mod- ifying the Graph Engine for Multithreaded System (GEMS) frame- work to support accelerators generated with such a methodology, and testing with queries coming from the Lehigh University Benchmark (LUBM). The architectural template enables better supporting the task and memory level parallelism present in graph methods by sup- porting a new control model and a enhanced memory interface. We show that out solution allows generating parallel accelerators, pro- viding speed ups with respect to conventional HLS flows. We finally draw conclusions and present a perspective on the use of reconfig- urable devices and Design Automation tools for data analytics.

Data Analytics↗

Electron Cooling With Space-Charge Dominated Proton Beams at IOTA

We describe a new electron cooler being developed for 2.5 MeV protons at the Integrable Optics Test Accelerator (IOTA), which is a highly re-configurable storage ring at Fermilab. This system would enable the study of magnetized electron cooling in the presence of intense space-charge with transverse tune shifts approaching -0.5 as well as highly non-linear focusing optics in the IOTA ring. We present an overview of the design, simulations and hardware to be used for this project.

43 PARTICLE ACCELERATORS↗

Accelerating GNNs on GPU Sparse Tensor Cores through N:M Sparsity-Oriented Graph Reordering

Recent advancements in GPU hardware support have introduced the capability to leverage N:M sparse patterns for substantial performance gains. Graphs in Graph Neural Networks (GNNs) are typically sparse, but the sparsity is often irregular, not conforming to such sparse patterns. In this paper, we propose a novel graph reordering algorithm, the first of its kind, to reshape irregular graph data into the N:M structured sparse pattern at the tile level, allowing linear-algebra-based graph operations in GNNs to benefit from the N:M sparse hardware. The optimization is lossless, maintaining the accuracy of GNN. It can remove 98-100\% violations of the N:M sparse patterns at the vector level, and increase the proportion of conforming graphs in SuiteSparse collection from 5-9\% to 88.7-93.5\%. On A100 GPUs, the optimization accelerates Sparse Matrix Matrix (SpMM) by up to 43X (2.3X -- 7.5X on average) and speeds up the key graph operations in GNNs on real graphs by as much as 8.6X (3.5X on average).

artificial intelligence, graph neural networks↗

SU-E-T-423: Fast Photon Convolution Calculation with a 3D-Ideal Kernel On the GPU

Purpose: The calculation time is a trade-off for improving the accuracy of convolution dose calculation with fine calculation spacing of the KERMA kernel. We investigated to accelerate the convolution calculation using an ideal kernel on the Graphic Processing Units (GPU). Methods: The calculation was performed on the AMD graphics hardware of Dual FirePro D700 and our algorithm was implemented using the Aparapi that convert Java bytecode to OpenCL. The process of dose calculation was separated with the TERMA and KERMA steps. The dose deposited at the coordinate (x, y, z) was determined in the process. In the dose calculation running on the central processing unit (CPU) of Intel Xeon E5, the calculation loops were performed for all calculation points. On the GPU computation, all of the calculation processes for the points were sent to the GPU and the multi-thread computation was done. In this study, the dose calculation was performed in a water equivalent homogeneous phantom with 150{sup 3} voxels (2 mm calculation grid) and the calculation speed on the GPU to that on the CPU and the accuracy of PDD were compared. Results: The calculation time for the GPU and the CPU were 3.3 sec and 4.4 hour, respectively. The calculation speed for the GPU was 4800 times faster than that for the CPU. The PDD curve for the GPU was perfectly matched to that for the CPU. Conclusion: The convolution calculation with the ideal kernel on the GPU was clinically acceptable for time and may be more accurate in an inhomogeneous region. Intensity modulated arc therapy needs dose calculations for different gantry angles at many control points. Thus, it would be more practical that the kernel uses a coarse spacing technique if the calculation is faster while keeping the similar accuracy to a current treatment planning system.

60 APPLIED LIFE SCIENCES↗

Recovery Act: SeaMicro Volume Server Power Reduction Research Development

Cloud data centers are projected to be the fastest growing segment of the server market through 2015, according to IDC. Increasingly people and businesses rely on the Cloud to deliver digital content quickly and efficiently. Recovery Act funding from the Department of Energy has helped SeaMicro's technologies enhance the total cost of operation, performance and energy efficiency in large data center and Cloud environments. SeaMicro's innovative supercomputer fabric connects thousands of processor cores, memory, storage and input/output traffic. The company's fabric supports multiple processor instruction sets. Current systems featuring SeaMicro technology typically use one quarter the power and take one sixth the space of traditional servers with the same compute performance, yet deliver up to 12 times the bandwidth per core. Mozilla and eHarmony are two customers successfully using SeaMicro's technology. Numerous non-public customers have been successfully using the SeaMicro product in test and production facilities. As a result of the Recovery Act funding from the U.S. Department of Energy, more than 50 direct jobs were created at SeaMicro. To date, they primarily have been high-value, engineering jobs. Hardware, software and manufacturing engineering positions have been created, as well as sales and sales engineering. The positions have allowed SeaMicro to significantly accelerate engineering development and accelerate commercialization. As a result, commercialization and delivery to market are months ahead of initial schedule. Additional jobs were indirectly created through the development of the SeaMicro product. Through many years of research and hard work prior to receipt of public funding, SeaMicro was awarded 2 patents for its work. SeaMicro's product led the way for industry leaders to reconsider the market for low power servers and create new product lines. With valuable support of the U.S. Department of Energy and through SeaMicro's product, the market has been reshaped by the company's unique approach and ground breaking technology.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Electron Cooling Experiment for Proton Beams with Intense Space-Charge in IOTA

Electron cooling as a method of creating intense ion beams has a practical upper limit when it comes to the peak phase space density of ion beams which can be achieved in practice. We describe a new experiment to study electron cooling of 2.5 MeV protons at the intensity limit using the Integrable Optics Test Accelerator (IOTA), which is a storage ring dedicated to beam physics research at Fermilab. This system will enable the study of magnetized electron cooling of a proton beam with transverse incoherent tune shifts approaching -0.5 due to the presence of intense space-charge forces. We present an overview of the hardware design, simulations and specific experiments planned for this project.

43 PARTICLE ACCELERATORS↗

Control System Design for Automatic Cavity Tuning Machines

A series of four automatic tuning machines for 9-cell TESLA-type cavities are being developed and fabricated in a collaborative effort among DESY, FNAL, and KEK. These machines are intended to support high-throughput cavity fabrication for construction of large SRF-based accelerator projects. Two of these machines will be delivered to cavity vendors for the tuning of XFEL cavities. The control system for these machines must support a high level of automation adequate for industrial use by non-experts operators. This paper describes the control system hardware and software design for these machines.

43 PARTICLE ACCELERATORS↗

Progress in developing a superconducting accelerator for efficient eBeam and X-ray production

The PIP-II Accelerator is an 800 MeV superconducting Linac in the injection chain of the Fermilab accelerator complex. The LLRF systems for the 125 cavities which include a few normal conducting cavities in the warm front-end section, use a variety of LLRF hardware components and sub-systems that are part of the timing and synchronization system. This includes a master oscillator and phase averaging reference line, a beam pattern generator to enable beam transfer between non-harmonic RF systems and beam loading compensation systems synchronized to a start of beam trigger. The timing signals are based on a 650 MHz clock with manchester encoded event information and data provided over optical fiber. The timing and synchronization systems and their performance parameters will be described here.

43 PARTICLE ACCELERATORS↗

Architecture, implementation, and testing of a multiple-shell gas injection system for high current implosions on the Z accelerator

Tests are ongoing to conduct {approx}20 MA z-pinch implosions on the Z accelerator at Sandia National Laboratory using Ar, Kr, and D{sub 2} gas puffs as the imploding loads. The relatively high cost of operations on a machine of this scale imposes stringent requirements on the functionality, reliability, and safety of gas puff hardware. Here we describe the development of a prototype gas puff system including the multiple-shell nozzles, electromagnetic drivers for each nozzle's valve, a UV pre-ionizer, and an inductive isolator to isolate the {approx}2.4 MV machine voltage pulse present at the gas load from the necessary electrical and fluid connections made to the puff system from outside the Z vacuum chamber. This paper shows how the assembly couples to the overall Z system and presents data taken to validate the functionality of the overall system.

42 ENGINEERING↗

Optical neural engine for solving scientific partial differential equations

Abstract Solving partial differential equations (PDEs) is the cornerstone of scientific research and development. Data-driven machine learning (ML) approaches are emerging to accelerate time-consuming and computation-intensive numerical simulations of PDEs. Although optical systems offer high-throughput and energy-efficient ML hardware, their demonstration for solving PDEs is limited. Here, we present an optical neural engine (ONE) architecture combining diffractive optical neural networks for Fourier space processing and optical crossbar structures for real space processing to solve time-dependent and time-independent PDEs in diverse disciplines, including Darcy flow equation, the magnetostatic Poisson’s equation in demagnetization, the Navier-Stokes equation in incompressible fluid, Maxwell’s equations in nanophotonic metasurfaces, and coupled PDEs in a multiphysics system. We numerically and experimentally demonstrate the capability of the ONE architecture, which not only leverages the advantages of high-performance dual-space processing for outperforming traditional PDE solvers and being comparable with state-of-the-art ML models but also can be implemented using optical computing hardware with unique features of low-energy and highly parallel constant-time processing irrespective of model scales and real-time reconfigurability for tackling multiple tasks with the same architecture. The demonstrated architecture offers a versatile and powerful platform for large-scale scientific and engineering computations.

Tang, Yingheng (ORCID:0009000153622546)↗