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 577 records · Page 32

Performance evaluation of OpenFOAM on many-core architectures

In this article application of Open Source Field Operation and Manipulation (OpenFOAM) C++ libraries for solving engineering problems on many-core architectures is presented. Objective of this article is to present scalability of OpenFOAM on parallel platforms solving real engineering problems of fluid dynamics. Scalability test of OpenFOAM is performed using various hardware and different implementation of standard PCG and PBiCG Krylov iterative methods. Speed up of various implementations of linear solvers using GPU and MIC accelerators are presented in this paper. Numerical experiments of 3D lid-driven cavity flow for several cases with various number of cells are presented.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Conceptual design of a replacement 2.1 K cold box for the Spallation Neutron Source Central Helium Liquefier

Abstract After more than 20 years of operation, the cold compressor technology in use at the Spallation Neutron Source (SNS) is obsolete, and replacement parts and service are no longer available. SNS has partnered with Jefferson Lab to design and construct a replacement sub-atmospheric cold box outfitted with modern cold compressor technology. The general design follows from Jefferson Lab’s experience on other recent sub-atmospheric cold box projects. Design decisions are backed by thorough engineering analysis to ensure technical requirements are met in a cost-effective manner. Conceptual design of the replacement cold box has been completed, and will be summarized in this paper. It features five cold compressors with an operating flow range of 80-140 g/s, and includes piping and valving to support cold compressor maintenance without interrupting flow circulation to the load. The approach to thermal shielding, insulation, and integration of the upgraded cold compressor hardware into the existing SNS control system will also be addressed.

Mastracci, B [Thomas Jefferson National Accelerato↗

Accelerated Architectures Create Programming Opportunities

In the early 2000s, industry switched to multicore microprocessors to address semiconductors' speed and power limits. However, the change was unsuccessful, leading to dire claims that “Moore's law is ending.” In conclusion, this column suggests that while the approach was sound, it needed a deeper architectural transformation. Industry has since discovered a suitable architecture, but work remains on software to support it.

97 MATHEMATICS AND COMPUTING↗

The Memory Scaling of Reverse-Mode Differentiation in Particle Accelerator Simulations with Space Charge

The recent development of differentiable simulation codes for particle accelerators has enabled gradient-based workflows that promise finer control and more realistic modeling of accelerator facilities. However, when using reverse-mode automatic differentiation, the memory usage continuously increases during the simulation, and can potentially exceed the available hardware memory - especially when costly space charge computation is included. To study the memory requirements for differentiable simulations, we have implemented space charge in Cheetah, a PyTorch-based beam tracking code that supports reverse-mode differentiation. We find that the memory usage for reverse-mode differentiation grows linearly with the number of macroparticles and cells, and that it is proportional to the number of space charge kicks involved in the simulation. This general scaling can be used to evaluate whether a given differentiable simulation is feasible given hardware memory constraints.

Dhamrait, Arjun↗

Optimization of the muon stopping target for the MU2E collaboration [Thesis]

The Mu2e Experiment utilizes state of the art accelerators, superconducting magnets, detectors, electronics, and other equipment to maximize the sensitivity to such a rare process. Many of the components of the Mu2e hardware are critical to the overall physics capability of the experiment. The muon stopping target, where muons are stopped and may interact via this very rare process, is one such component where any improvements beyond the base design can have a significant impact on the experiment. This thesis explores possible modifications to the geometry of the muon stopping target. The goal is to determine if any modifications can improve the sensitivity of observing the muon conversion process.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Closing plenary summary of working group 4 instrumentation and controls for ERL2011

Working group 4 was charged with presentations and discussions on instrumentation and controls with regards to Energy Recovery Linacs (ERL). There were 4 sessions spanning 3.5 hours in which 7 talks were delivered, the first being an invited plenary presentation. The time allotted for each talk was limited to 20-25 minutes in order to allow 5-10 minutes for discussion. Most of the talks were held in joint session with working group 5 (Unwanted Beam Loss). This format was effective for the purpose of this workshop. A final series of discussion sessions were also held with working group 5. Summary of the working group 4 activities, presented in the closing plenary session. We had a plenary presentation on operational performance, experience, and future plans at the existing ERL injector prototype at Cornell. This included instrumentation data, controls system configurations, as well as description of future needs. This was followed by four talks from KEK and RIKEN/SPring-8 that described electron beam instrumentation already in use or under development that can be applied to ERL facilities. The final talks described the ERLs under construction at KEK and BNL. The format of having joint sessions with working group 5 was beneficial as there were a significant number of common topics and concerns with regards to the causes of beam loss, instrumentation hardware, and techniques used to measure and analyze beam loss.

43 PARTICLE ACCELERATORS↗

ATCA/muTCA for Physics

ATCA/{mu}TCA platforms are attractive because of the modern serial link architecture, high availability features and many packaging options. Less-demanding availability applications can be met economically by scaling back speed and redundancy. The ATCA specification was originally targeted for the Telecom industry but has gained recently a much wider user audience. The purpose of this paper is to report on present hardware and software R and D efforts where ATCA and {mu}TCA are planned, already being used or in development using selected examples for accelerator and detectors in the Physics community. It will present also the status of a proposal for physics extensions to ATCA/{mu}TCA specifications to promote inter-operability of laboratory and industry designs for physics.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Accelerating the Gauss-Seidel Power Flow Solver on a High Performance Reconfigurable Computer

The computationally intensive power flow problem determines the voltage magnitude and phase angle at each bus in a power system for hundreds of thousands of buses under balanced three-phase steady-state conditions. We report an FPGA acceleration of the Gauss-Seidel based power flow solver employed in the transmission module of the GridLAB-D power distribution simulator and analysis tool. The prototype hardware is implemented on an SGI Altix-RASC system equipped with a Xilinx Virtex II 6000 FPGA. Due to capacity limitations of the FPGA, only the bus voltage calculations of the power network are implemented on hardware while the branch current calculations are implemented in software. For a 200,000 bus system, the bus voltage calculation on the FPGA achieves a 48x speed-up with PQ buses and a 62 times for PV over an equivalent sequential software implementation. The average overall speed up of the FPGA-CPU implementation with 100 iterations of the Gauss-Seidel power solver is 2.6x over a software implementation, with the branch calculations on the CPU accounting for 85% of the total execution time. The FPGA-CPU implementation also shows linear scaling with increase in the size of the input power network.

24 POWER TRANSMISSION AND DISTRIBUTION↗

A data acquisition system for longitudinal beam properties in a rapid cycling synchrotron

A longitudinal beam properties, data acquisition system has been commissioned to operate in the Fermilab booster ring. This system captures real time information including beam synchronous phase, bunch length, and coupled bunch instability amplitudes as the beam is accelerated from 400 MeV to 8 GeV in 33 ms. The system uses an off-the-shelf Tektronix oscilloscope running Labview software and a synchronous pulse generator. This paper describes the hardware configuration and the software configuration used to optimize the data processing rate. The Fermilab Booster is currently pushed to its intensity limit due to the high demand from different experiments for protons. This will continue into the era of the intensity frontier. While intensity is the most critical parameter, emittance must be controlled as well. Longitudinal emittance is an important parameter for optimizing the slip stacking process in the Main Injector. Longitudinal instabilities can spoil the emittance, so it is important to monitor bunch lengths and bunch phase oscillations in the Booster. The Booster presents a special challenge when it comes to measuring beam properties. The acceleration ramp is short (33ms), and the RF frequency varies from 38-52.8 MHz. Standard instrumentation like spectrum analyzers and network analyzers cannot effectively measure beam properties, because they cannot track the changing frequencies. Early instrumentation involved a series of tracking oscillators, mixers, and diode detectors that would require vigilant calibration. There was a demand for a more robust means of gathering beam parameters.

43 PARTICLE ACCELERATORS↗

Designing a Magnetic Measurement Data Acquisition and Control System With Reuse in Mind: A Rotating Coil System Example

Accelerator magnet test facilities frequently need to measure different magnets on differently equipped test stands and with different instrumentation. Designing a modular and highly reusable system that combines flexibility built-in at the architectural level as well as on the component level addresses this need. Specification of the backbone of the system, with the interfaces and dataflow for software components and core hardware modules, serves as a basis for building such a system. The design process and implementation of an extensible magnetic measurement data acquisition and control system are described, including techniques for maximizing the reuse of software. The discussion is supported by showing the application of this methodology to constructing two dissimilar systems for rotating coil measurements, both based on the same architecture and sharing core hardware modules and many software components. The first system is for production testing 10 m long cryo-assemblies containing two MQXFA quadrupole magnets for the high-luminosity upgrade of the Large Hadron Collider and the second for testing IQC conventional quadrupole magnets in support of the accelerator system at Fermilab.

43 PARTICLE ACCELERATORS↗

Development of a Laser-Electron-Interaction Region for Compact High Repetition-Rate Mono-Energetic Laser Based Gamma Sources

Inverse-Compton scattering (ICS) is a well-established technique capable of producing monochromatic radiation over a large range of the electromagnetic spectrum. Most recently, ICS has attracted attention, owing to its compactness and possible coupling with novel acceleration methods to yield compact X- and 𝛄-ray sources. Under this award, we carried out a systematic optimization of the ICS and demonstrate via numerical simulation that combining ICS with a conventional superconducting linac could produce Watt-level average-power 𝛄 rays with high spectral brightness. The study is performed with idealized laser and electron-beam distributions and confirmed with the realistic distributions simulated from start-to-end numerical modeling of the electron accelerator. The studies led to the design and engineering design of an ICS interaction point for the FAST facility along with some beam measurement. Due to the cancellation of the program in Year 3 long with delay in the commissioning of the FAST facility, we were not able to demonstrate the generation of 𝛄 rays, we, however, procured some of the hardware, installed some of the required infrastructures and plan to eventually generate 𝛄 ray pending future interest on the topics and availability of funding.

43 PARTICLE ACCELERATORS↗

OpenACC unified programming environment for GPU and FPGA multi-hybrid acceleration

Attached accelerators have been frequently used in recent High Per- formance Computing (HPC) systems because of their high performance/power ratio. In particular, the Graphics Processing Unit (GPU) is the most popu- lar accelerator owing to its high peak FLOPS performance and high memory bandwidth supported by HBM2, etc. However, the performance of GPU depends highly on a large degree of SIMD parallelism and has difficulty sustaining a high performance on programs with frequent branch operations or a partially low degree of parallelism.By contrast, a Field Programmable Gate Array (FPGA) has received attention as a different type of accelerator than GPU as a fully reconfigurable processor fitting the target applications. The high performance of FPGA is mainly provided by a pipelined operation and optimized circuit suitable for any operation even with frequent conditional branches. We have been focusing on the flexibility of FPGA to compensate for the weakness of GPU. We believe that the coupling of GPU with FPGA can result in one of the most powerful accelerating platforms available.However, the program coding of GPU and FPGA coupling can be quite difficult for application users. Traditionally, CUDA by NVIDIA has been the most popular programming language with the largest share of GPUs used in HPC, whereas a hardware description language such as Verilog HDL has been used in FPGA programming. OpenCL coding has recently become available even on high-end FPGAs. Moreover, several recent studies have also enabled the OpenACC coding for use in FPGA. In this study, we provide a unified programming system based on OpenACC for a platform equipped with both GPU and FPGA aiming at the next-generation accelerated supercomputer framework. Our programming environment is called Multi-Hybrid OpenACC Translator (MHOAT), and in this paper, we describe the basic concept and prototype system of MHOAT based on an evaluation on the amount of coding required and the performance of a hybrid multi-device accelerated system.

Tsunashima, Ryuta↗

Parallel beamlet dose calculation via beamlet contexts in a distributed multi‐GPU framework

Purpose Dose calculation is one of the most computationally intensive, yet essential tasks in the treatment planning process. With the recent interest in automatic beam orientation and arc trajectory optimization techniques, there is a great need for more efficient model‐based dose calculation algorithms that can accommodate hundreds to thousands of beam candidates at once. Foundational work has shown the translation of dose calculation algorithms to graphical processing units ( GPU s), lending to remarkable gains in processing efficiency. But these methods provide parallelization of dose for only a single beamlet, serializing the calculation of multiple beamlets and under‐utilizing the potential of modern GPU s. In this paper, the authors propose a framework enabling parallel computation of many beamlet doses using a novel beamlet context transformation and further embed this approach in a scalable network of multi‐ GPU computational nodes. Methods The proposed context‐based transformation separates beamlet‐local density and TERMA into distinct beamlet contexts that independently provide sufficient data for beamlet dose calculation. Beamlet contexts are arranged in a composite context array with dosimetric isolation, and the context array is subjected to a GPU collapsed‐cone convolution superposition procedure, producing the set of beamlet‐specific dose distributions in a single pass. Dose from each context is converted to a sparse representation for efficient storage and retrieval during treatment plan optimization. The context radius is a new parameter permitting flexibility between the speed and fidelity of the dose calculation process. A distributed manager‐worker architecture is constructed around the context‐based GPU dose calculation approach supporting an arbitrary number of worker nodes and resident GPU s. Phantom experiments were executed to verify the accuracy of the context‐based approach compared to Monte Carlo and a reference CPU ‐ CCCS implementation for single beamlets and broad beams composed by addition of beamlets. Dose for representative 4 π beam sets was calculated in lung and prostate cases to compare its efficiency with that of an existing beamlet‐sequential GPU ‐ CCCS implementation. Code profiling was also performed to evaluate the scalability of the framework across many networked GPU s. Results The dosimetric accuracy of the context‐based method displays <1.35% and 2.35% average error from the existing serialized CPU ‐ CCCS algorithm and Monte Carlo simulation for beamlet‐specific PDD s in water and slab phantoms, respectively. The context‐based method demonstrates substantial speedup of up to two orders of magnitude over the beamlet‐sequential GPU ‐ CCCS method in the tested configurations. The context‐based framework demonstrates near linear scaling in the number of distributed compute nodes and GPU s employed, indicating that it is flexible enough to meet the performance requirements of most users by simply increasing the hardware utilization. Conclusions The context‐based approach demonstrates a new expectation of performance for beamlet‐based dose calculation methods. This approach has been successful in accelerating the dose calculation process for very large‐scale treatment planning problems ‐ such as automatic 4 π IMRT beam orientation and VMAT arc trajectory selection, with hundreds of thousands of beamlets ‐ in clinically feasible timeframes. The flexibility of this framework makes it as a strong candidate for use in a variety of other very large‐scale treatment planning tasks and clinical workflows.

Neph, Ryan↗

FitCache: A Transparent Drop-In Framework for Multi-Tier Caching to Accelerate Distributed Deep Learning Workloads

Training in Deep learning (DL) remains highly compute- and data-intensive, with I/O becoming a critical bottleneck as models and datasets scale. Recent studies report that data loading can dominate training time, especially on large-scale HPC systems with shared parallel file systems (PFS). Existing caching approaches either rely on single-tier designs or require intrusive modifications to training pipelines, limiting their portability and effectiveness. In this work, we present FitCache, a transparent drop-in framework for multi-tier caching to accelerate distributed DL training by coordinating fast local memory (e.g., DRAM, Persistent Memory (PMem)) and NVMe as hierarchical caches atop PFS. Our design adapts to hardware diversity, i.e., if NVMe is missing, memory transparently acts as a caching tier, ensuring stable performance. FitCache transparently intercepts I/O requests and issues concurrent fetches across all tiers, returning data from the fastest responder without centralized metadata or static redirection paths. FitCache adapts to dynamic workloads and heterogeneous clusters while maintaining POSIX compatibility. Experiments on Frontier (2048 GPUs) and smaller research clusters show that FitCache reduces training time by up to 40% and per-batch I/O latency by up to 71.6% compared to Lustre Orion PFS, offering a drop-in solution for scalable DL training.

Hu, Guangxing [ORNL] (ORCID:0009000283203614)↗

Island model for parallel evolutionary optimization of spiking neuromorphic computing

Parallel genetic algorithms (PGAs) can be used to accelerate optimization by exploiting large-scale computational resources. In this work, we describe a PGA framework for evolving spiking neural networks (SNNs) for neuromorphic hardware implementation. The PGA framework is based on an islands model with migration. We show that using this framework, better SNNs for neuromorphic systems can be evolved faster.

Schuman, Catherine↗

Performance for GPU exceptions

Techniques for improving performance of accelerated processing devices (“APDs”) when exceptions occur are provided. In APDs, the very large number of parallel processing execution units, and the complexity of the hardware used to execute a large number of work-items in parallel, means that APDs typically stall when an exception occurs (unlike in central processing units (“CPUs”), which are able to execute speculatively and out-of-order). However, the techniques provided herein allow at least some execution to occur past exceptions. Execution past an exception generating instruction occurs by executing instructions that would not lead to a corruption while skipping those that would lead to a corruption. After the exception has been satisfied, execution occurs in a replay mode in which the potentially exception-generating instruction is executed and in which instructions that did not execute in the exception-wait mode are executed. A mask and counter are used to control execution in replay mode.

Gutierrez, Anthony T.↗

Surrogate Neural Architecture Codesign Package (SNAC-Pack)

Neural Architecture Search is a powerful approach for automating model design, but existing methods struggle to accurately optimize for real hardware performance, often relying on proxy metrics such as bit operations. We present Surrogate Neural Architecture Codesign Package (SNAC-Pack), an integrated framework that automates the discovery and optimization of neural networks focusing on FPGA deployment. SNAC-Pack combines Neural Architecture Codesign's multi-stage search capabilities with the Resource Utilization and Latency Estimator, enabling multi-objective optimization across accuracy, FPGA resource utilization, and latency without requiring time-intensive synthesis for each candidate model. We demonstrate SNAC-Pack on a high energy physics jet classification task, achieving 63.84% accuracy with resource estimation. When synthesized on a Xilinx Virtex UltraScale+ VU13P FPGA, the SNAC-Pack model matches baseline accuracy while maintaining comparable resource utilization to models optimized using traditional BOPs metrics. This work demonstrates the potential of hardware-aware neural architecture search for resource-constrained deployments and provides an open-source framework for automating the design of efficient FPGA-accelerated models.

Weitz, Jason [UC, San Diego] (ORCID:00090004631535↗

Electron Model Of A Dogbone RLA With Multi-Pass Arcs

The design of a dogbone Recirculated Linear Accelerator, RLA, with linear-field multi-pass arcs was earlier developed [1] for accelerating muons in a Neutrino Factory and a Muon Collider. It allows for efficient use of expensive RF while the multi-pass arc design based on linear combined-function magnets exhibits a number of advantages over separate-arc or pulsed-arc designs. Such an RLA may have applications going beyond muon acceleration. This paper describes a possible straightforward test of this concept by scaling a GeV scale muon design for electrons. Scaling muon momenta by the muon-to-electron mass ratio leads to a scheme, in which a 4.5 MeV electron beam is injected at the middle of a 3 MeV/pass linac with two double-pass return arcs and is accelerated to 18 MeV in 4.5 passes. All spatial dimensions including the orbit distortion are scaled by a factor of 7.5, which arises from scaling the 200 MHz muon RF to the frequency readily available at CEBAF: 1.5 GHz. The footprint of a complete RLA fits in an area of 25 by 7 m. The scheme utilizes only fixed magnetic fields including injection and extraction. The hardware requirements are not very demanding, making it straightforward to implement

43 PARTICLE ACCELERATORS↗