Search NASA⌕ Search

SEARCH · Search NASA

Results for “architecture optimization”

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 1,279 records · Page 71
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Integrating Safety, Security, and Nuclear Operations for Advanced Reactors

The traditional separation between safety, security, and operations teams has created significant barriers to achieving optimal outcomes. When security considerations are introduced late in the design process, they often conflict with already-established architectural, operational, or engineering parameters. Retrofitting security measures can lead to increased costs, schedule delays, and compromises in security effectiveness. For instance, the need to retrofit physical barriers or surveillance systems often results in trade-offs that could have been avoided with earlier input from security professionals. Delayed integration can also affect regulatory processes and result in licensing delays. Security reviews conducted at later stages frequently identify gaps that necessitate significant redesign efforts, impacting not only scope, schedule, and budget, but also adding risk and lowering stakeholder confidence in the project. This paper aims to address these challenges by identifying practical opportunities for integrating security considerations seamlessly with design and operations teams throughout the entire lifecycle of nuclear facilities—from conceptual design to commissioning and beyond. The research emphasizes the value of early and continuous collaboration among stakeholders to ensure that security measures are robust, operationally effective, and cost-efficient. By examining case studies, analyzing past incidents, and leveraging best practices from other high-security industries, this study highlights actionable strategies for bridging the gap between safety, security, and operations teams.

Zineddin, Dr. Z. [ORNL] (ORCID:0009000848740725)↗
NASA NTRS1996

Distributed Large Data-Object Environments: End-to-End Performance Analysis of High Speed Distributed Storage Systems in Wide Area ATM Networks

We have developed and deployed a distributed-parallel storage system (DPSS) in several high speed asynchronous transfer mode (ATM) wide area networks (WAN) testbeds to support several different types of data-intensive applications. Architecturally, the DPSS is a network striped disk array, but is fairly unique in that its implementation allows applications complete freedom to determine optimal data layout, replication and/or coding redundancy strategy, security policy, and dynamic reconfiguration. In conjunction with the DPSS, we have developed a 'top-to-bottom, end-to-end' performance monitoring and analysis methodology that has allowed us to characterize all aspects of the DPSS operating in high speed ATM networks. In particular, we have run a variety of performance monitoring experiments involving the DPSS in the MAGIC testbed, which is a large scale, high speed, ATM network and we describe our experience using the monitoring methodology to identify and correct problems that limit the performance of high speed distributed applications. Finally, the DPSS is part of an overall architecture for using high speed, WAN's for enabling the routine, location independent use of large data-objects. Since this is part of the motivation for a distributed storage system, we describe this architecture.

Johnston, William↗
DOE OSTI2022

A Method of Optimal Control for Class 8 Vehicle Platoons Over Hilly Terrain

This work develops and implements an NMPC control system to facilitate fuel-optimal platooning of Class 8 vehicles over challenging terrain. Prior research has shown that Cooperative Adaptive Cruise Control (CACC), which allows multiple Class 8 vehicles to follow in close succession, can save between 3 and 8% in overall fuel consumption on flat terrain. However, on more challenging terrain, e.g. rolling hills, platooning vehicles can experience diminished fuel savings, and, in some cases, an increase in fuel consumption relative to individual vehicle operation. This research explores the use of Nonlinear Model Predictive Control (NMPC) with predefined route grade profiles to allow platooning vehicles to generate an optimal velocity trajectory with respect to fuel consumption. In order to successfully implement the NMPC system, a model relating vehicle velocity to fuel consumption was generated and validated using experimental data. Additionally, the predefined route grade profiles were created by using the vehicle's GPS velocity over the desired terrain. The real-time NMPC system was then implemented on a two-truck platoon operating over challenging terrain, with a reference vehicle running individually. The results from NMPC platooning are compared against fuel results from a classical proportional-integral-derivative (PID) headway control method. Furthermore, this comparison yields the comparative fuel savings and energy efficiency benefit of NMPC system. In the final analysis, significant fuel savings of greater than 14 and 20% were seen for the lead and following vehicles relative to their respective traditional cruise control and platooning architectures.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2016

SU-F-T-256: 4D IMRT Planning Using An Early Prototype GPU-Enabled Eclipse Workstation

Purpose: True 4D IMRT planning, based on simultaneous spatiotemporal optimization has been shown to significantly improve plan quality in lung radiotherapy. However, the high computational complexity associated with such planning represents a significant barrier to widespread clinical deployment. We introduce an early prototype GPU-enabled Eclipse workstation for inverse planning. To our knowledge, this is the first GPUintegrated Eclipse system demonstrating the potential for clinical translation of GPU computing on a major commercially-available TPS. Methods: The prototype system comprised of four NVIDIA Tesla K80 GPUs, with a maximum processing capability of 8.5 Tflops per K80 card. The system architecture consisted of three key modules: (i) a GPU-based inverse planning module using a highly-parallelizable, swarm intelligence-based global optimization algorithm, (ii) a GPU-based open-source b-spline deformable image registration module, Elastix, and (iii) a CUDA-based data management module. For evaluation, aperture fluence weights in an IMRT plan were optimized over 9 beams,166 apertures and 10 respiratory phases (14940 variables) for a lung cancer case (GTV = 95 cc, right lower lobe, 15 mm cranio-caudal motion). Sensitivity of the planning time and memory expense to parameter variations was quantified. Results: GPU-based inverse planning was significantly accelerated compared to its CPU counterpart (36 vs 488 min, for 10 phases, 10 search agents and 10 iterations). The optimized IMRT plan significantly improved OAR sparing compared to the original internal target volume (ITV)-based clinical plan, while maintaining prescribed tumor coverage. The dose-sparing improvements were: Esophagus Dmax 50%, Heart Dmax 42% and Spinal cord Dmax 25%. Conclusion: Our early prototype system demonstrates that through massive parallelization, computationally intense tasks such as 4D treatment planning can be accomplished in clinically feasible timeframes. With further optimization, such systems are expected to enable the eventual clinical translation of higher-dimensional and complex treatment planning strategies to significantly improve plan quality. This work was partially supported through research funding from National Institutes of Health (R01CA169102) and Varian Medical Systems, Palo Alto, CA, USA.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2022

Bimetallic NiCo boride nanoparticles confined in a MXene network enable efficient ambient ammonia electrosynthesis

Ambient electrocatalytic nitrogen fixation is an emerging technology for green ammonia synthesis, but the absence of optimized, stable and performant catalysts can render its practical application challenging. Herein, bimetallic NiCo boride nanoparticles confined in MXene are shown to accomplish high-performance nitrogen reduction electrolysis. Taking advantage of the synergistic effect in specific compositions with unique electronic d and p orbits and typical architecture of rich nanosized particles embedded in the interconnected conductive network, the synthesized MXene@NiCoB composite demonstrates extensive improvements in nitrogen molecule chemisorption, active area exposure and charge transport. As a result, optimal NH 3 yield rate of 38.7 μg h -1 mgcat. -1 and Faradaic efficiency of 6.92% are acquired in 0.1 M Na 2 SO 4 electrolyte. Moreover, the great catalytic performance can be almost entirely maintained in the cases of repeatedly-cycled and long-term electrolysis. Theoretical investigations reveal that the nitrogen reduction reaction on MXene@NiCoB catalyst proceeds according to the distal pathway, with a distinctly-reduced energy barrier relative to the Co 2 B counterpart. In conclusion, this work may inspire a new route towards the rational catalyst design for the nitrogen reduction reaction.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS2011

Multidisciplinary Modeling Software for Analysis, Design, and Optimization of HRRLS Vehicles

The concept for Highly Reliable Reusable Launch Systems (HRRLS) under the NASA Hypersonics project is a two-stage-to-orbit, horizontal-take-off / horizontal-landing, (HTHL) architecture with an air-breathing first stage. The first stage vehicle is a slender body with an air-breathing propulsion system that is highly integrated with the airframe. The light weight slender body will deflect significantly during flight. This global deflection affects the flow over the vehicle and into the engine and thus the loads and moments on the vehicle. High-fidelity multi-disciplinary analyses that accounts for these fluid-structures-thermal interactions are required to accurately predict the vehicle loads and resultant response. These predictions of vehicle response to multi physics loads, calculated with fluid-structural-thermal interaction, are required in order to optimize the vehicle design over its full operating range. This contract with ResearchSouth addresses one of the primary objectives of the Vehicle Technology Integration (VTI) discipline: the development of high-fidelity multi-disciplinary analysis and optimization methods and tools for HRRLS vehicles. The primary goal of this effort is the development of an integrated software system that can be used for full-vehicle optimization. This goal was accomplished by: 1) integrating the master code, FEMAP, into the multidiscipline software network to direct the coupling to assure accurate fluid-structure-thermal interaction solutions; 2) loosely-coupling the Euler flow solver FEFLO to the available and proven aeroelasticity and large deformation (FEAP) code; 3) providing a coupled Euler-boundary layer capability for rapid viscous flow simulation; 4) developing and implementing improved Euler/RANS algorithms into the FEFLO CFD code to provide accurate shock capturing, skin friction, and heat-transfer predictions for HRRLS vehicles in hypersonic flow, 5) performing a Reynolds-averaged Navier-Stokes computation on an HRRLS configuration; 6) integrating the RANS solver with the FEAP code for coupled fluid-structure-thermal capability; and 7) integrating the existing NASA SRGULL propulsion flow path prediction software with the FEFLO software for quasi-3D propulsion flow path predictions, 8) improving and integrating into the network, an existing adjoint-based design optimization code.

Spradley, Lawrence W.↗
DOE OSTI2026

Optimal invariant sets for atomistic machine learning

The representation of atomic configurations for machine learning models has led to numerous sets of descriptors. However, many descriptor sets are incomplete and/or functionally dependent. Incomplete sets cannot faithfully represent atomic environments. Yet complete constructions often suffer from a high degree of functional dependence, where some descriptors are functions of others. These redundant descriptors do not improve discrimination between atomic environments. We employ pattern recognition techniques to remove dependent descriptors to produce the smallest possible set that satisfies completeness. We apply this in two ways: First, we refine an existing description, the atomic cluster expansion. Second, we augment an incomplete construction, yielding a new message-passing neural network architecture that can recognize up to 5-body patterns. This architecture shows strong accuracy on state-of-the-art benchmarks while retaining low computational cost. Our results demonstrate the utility of this strategy to optimize descriptor sets across a range of descriptors and application datasets.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

ECP libraries and tools: An overview

The Exascale Computing Project (ECP) Software Technology and Co-Design teams addressed the growing complexities in high-performance computing (HPC) by developing scalable software libraries and tools that leverage exascale system capabilities. As we enter the exascale era, the need for reusable, optimized software solutions that can handle the unique challenges posed by these systems becomes increasingly important. The primary challenges the ECP teams faced were to create software libraries and tools that are performant on exascale architectures and portable and usable across diverse hardware platforms. Efforts addressed issues related to concurrent execution, memory management, and the integration of heterogeneous computing resources, such as GPUs from multiple vendors. The ECP’s strategy involved a structured development process encompassing the creation, optimization, and deployment of software in collaboration with industry, academia, and national laboratories. The project was organized into several technical areas: co-design of domain-specific suites with target applications, programming models and runtimes, development tools, mathematical libraries, data and visualization tools, and software ecosystem and delivery mechanisms. ECP has successfully developed a large portfolio of software libraries and tools that demonstrate significant improvements in performance and scalability on exascale systems. These products have been integrated into the Department of Energy’s computing facilities, supporting various scientific applications and ensuring robust performance across different hardware setups. ECP advancements in software development for exascale computing highlight the importance of a collaborative and adaptive approach to handling next-generation HPC systems complexities. The lessons learned emphasize the need for continuous engagement with end-users and vendors, and the importance of maintaining a balance between innovation and practical implementation. Future efforts will focus on ensuring scalability, keeping pace with rapid hardware advancements, and further enhancing the interoperability and usability of the software ecosystem. In conclusion, subsequent articles in this special issue provide in-depth discussions and case studies into specific library and tool efforts.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Improving Lithium Metal Composite Anodes with Seeding and Pillaring Effects of Silicon Nanoparticles

Metallic lithium (Li) anodes are crucial for the development of high specific energy batteries yet plagued by their poor cycling efficiency. Electrode architecture engineering is vital for maintaining a stable anode volume and suppress Li corrosion during cycling. In this paper, a reduced graphene oxide “host” framework for Li metal anodes is further optimized by embedding silicon (Si) nanoparticles between the graphene layers. They serve as Li nucleation seeds to promote Li deposition within the framework even without pre-stored Li. Meanwhile, the LixSi alloy particles serve as supporting “pillars” between the graphene layers, enabling a minimized thickness shrinkage after full stripping of metallic Li. Combined with a Li compatible electrolyte, 99.4% Coulombic efficiency over ~600 cycles is achieved, and stable cycling of a Li||NMC532 full cell for ~380 cycles with negligible capacity decay is realized.

Wang, Hansen↗
DOE OSTI2016

A Study of Complex Deep Learning Networks on High Performance, Neuromorphic, and Quantum Computers

Current Deep Learning models use highly optimized convolutional neural networks (CNN) trained on large graphical processing units (GPU)-based computers with a fairly simple layered network topology, i.e., highly connected layers, without intra-layer connections. Complex topologies have been proposed, but are intractable to train on current systems. Building the topologies of the deep learning network requires hand tuning, and implementing the network in hardware is expensive in both cost and power.In this paper, we evaluate deep learning models using three different computing architectures to address these problems: quantum computing to train complex topologies, high performance computing (HPC) to automatically determine network topology, and neuromorphic computing for a low-power hardware implementation. Due to input size limitations of current quantum computers we use the MNIST dataset for our evaluation.The results show the possibility of using the three architectures in tandem to explore complex deep learning networks that are untrainable using a von Neumann architecture. We show that a quantum computer can find high quality values of intra-layer connections and weights, while yielding a tractable time result as the complexity of the network increases; a high performance computer can find optimal layer-based topologies; and a neuromorphic computer can represent the complex topology and weights derived from the other architectures in low power memristive hardware.This represents a new capability that is not feasible with current von Neumann architecture. It potentially enables the ability to solve very complicated problems unsolvable with current computing technologies.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2016

Enhanced Engine Performance During Emergency Operation Using a Model-Based Engine Control Architecture

This paper discusses the design and application of model-based engine control (MBEC) for use during emergency operation of the aircraft. The MBEC methodology is applied to the Commercial Modular Aero-Propulsion System Simulation 40k (CMAPSS40k) and features an optimal tuner Kalman Filter (OTKF) to estimate unmeasured engine parameters, which can then be used for control. During an emergency scenario, normally-conservative engine operating limits may be relaxed to increase the performance of the engine and overall survivability of the aircraft; this comes at the cost of additional risk of an engine failure. The MBEC architecture offers the advantage of estimating key engine parameters that are not directly measureable. Estimating the unknown parameters allows for tighter control over these parameters, and on the level of risk the engine will operate at. This will allow the engine to achieve better performance than possible when operating to more conservative limits on a related, measurable parameter.

engine control↗
DOE OSTI2016

A Study of Complex Deep Learning Networks on High Performance, Neuromorphic, and Quantum Computers

Current Deep Learning models use highly optimized convolutional neural networks (CNN) trained on large graphical processing units (GPU)-based computers with a fairly simple layered network topology, i.e., highly connected layers, without intra-layer connections. Complex topologies have been proposed, but are intractable to train on current systems. Building the topologies of the deep learning network requires hand tuning, and implementing the network in hardware is expensive in both cost and power. In this paper, we evaluate deep learning models using three different computing architectures to address these problems: quantum computing to train complex topologies, high performance computing (HPC) to automatically determine network topology, and neuromorphic computing for a low-power hardware implementation. Due to input size limitations of current quantum computers we use the MNIST dataset for our evaluation. The results show the possibility of using the three architectures in tandem to explore complex deep learning networks that are untrainable using a von Neumann architecture. We show that a quantum computer can find high quality values of intra-layer connections and weights, while yielding a tractable time result as the complexity of the network increases; a high performance computer can find optimal layer-based topologies; and a neuromorphic computer can represent the complex topology and weights derived from the other architectures in low power memristive hardware. This represents a new capability that is not feasible with current von Neumann architecture. It potentially enables the ability to solve very complicated problems unsolvable with current computing technologies.

Potok, Thomas E↗
DOE OSTI2014

SU-D-18A-02: Towards Real-Time On-Board Volumetric Image Reconstruction for Intrafraction Target Verification in Radiation Therapy

Purpose: To expedite on-board volumetric image reconstruction from limited-angle kV—MV projections for intrafraction verification. Methods: A limited-angle intrafraction verification (LIVE) system has recently been developed for real-time volumetric verification of moving targets, using limited-angle kV—MV projections. Currently, it is challenged by the intensive computational load of the prior-knowledge-based reconstruction method. To accelerate LIVE, we restructure the software pipeline to make it adaptable to model and algorithm parameter changes, while enabling efficient utilization of rapidly advancing, modern computer architectures. In particular, an innovative two-level parallelization scheme has been designed: At the macroscopic level, data and operations are adaptively partitioned, taking into account algorithmic parameters and the processing capacity or constraints of underlying hardware. The control and data flows of the pipeline are scheduled in such a way as to maximize operation concurrency and minimize total processing time. At the microscopic level, the partitioned functions act as independent modules, operating on data partitions in parallel. Each module is pre-parallelized and optimized for multi-core processors (CPUs) and graphics processing units (GPUs). Results: We present results from a parallel prototype, where most of the controls and module parallelization are carried out via Matlab and its Parallel Computing Toolbox. The reconstruction is 5 times faster on a data-set of twice the size, compared to recently reported results, without compromising on algorithmic optimization control. Conclusion: The prototype implementation and its results have served to assess the efficacy of our system concept. While a production implementation will yield much higher processing rates by approaching full-capacity utilization of CPUs and GPUs, some mutual constraints between algorithmic flow and architecture specifics remain. Based on a careful analysis of the prototype performance, it will be feasible to resolve such issues through appropriate algorithmic modifications or special-purpose hardware, thus enabling target verification in seconds with the LIVE system. This work was partially supported by a research grant from Varian Medical Systems.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

Quantum annealing for combinatorial optimization: a benchmarking study

Quantum annealing (QA) has the potential to significantly improve solution quality and reduce time complexity in solving combinatorial optimization problems compared to classical optimization methods. However, due to the limited number of qubits and their connectivity, the QA hardware did not show such an advantage over classical methods in past benchmarking studies. Recent advancements in QA with more than 5000 qubits, enhanced qubit connectivity, and the hybrid architecture promise to realize the quantum advantage. Here, we use a quantum annealer with state-of-the-art techniques and benchmark its performance against classical solvers. To compare their performance, we solve over 50 optimization problem instances represented by large and dense Hamiltonian matrices using quantum and classical solvers. The results demonstrate that a state-of-the-art quantum solver has higher accuracy (~0.013%) and a significantly faster problem-solving time (~6561×) than the best classical solver. Our results highlight the advantages of leveraging QA over classical counterparts, particularly in hybrid configurations, for achieving high accuracy and substantially reduced problem solving time in large-scale real-world optimization problems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2016

OpenACC to FPGA: A Framework for Directive-based High-Performance Reconfigurable Computing

This paper presents a directive-based, high-level programming framework for high-performance reconfigurable computing. It takes a standard, portable OpenACC C program as input and generates a hardware configuration file for execution on FPGAs. We implemented this prototype system using our open-source OpenARC compiler; it performs source-to-source translation and optimization of the input OpenACC program into an OpenCL code, which is further compiled into a FPGA program by the backend Altera Offline OpenCL compiler. Internally, the design of OpenARC uses a high- level intermediate representation that separates concerns of program representation from underlying architectures, which facilitates portability of OpenARC. In fact, this design allowed us to create the OpenACC-to-FPGA translation framework with minimal extensions to our existing system. In addition, we show that our proposed FPGA-specific compiler optimizations and novel OpenACC pragma extensions assist the compiler in generating more efficient FPGA hardware configuration files. Our empirical evaluation on an Altera Stratix V FPGA with eight OpenACC benchmarks demonstrate the benefits of our strategy. To demonstrate the portability of OpenARC, we show results for the same benchmarks executing on other heterogeneous platforms, including NVIDIA GPUs, AMD GPUs, and Intel Xeon Phis. This initial evidence helps support the goal of using a directive-based, high-level programming strategy for performance portability across heterogeneous HPC architectures.

Lee, Seyong↗
DOE OSTI2016

Developing Materials Processing to Performance Modeling Capabilities and the Need for Exascale Computing Architectures (and Beyond)

Additive Manufacturing techniques are presenting the Department of Energy and the NNSA Laboratories with new opportunities to consider novel component production and repair processes, and to manufacture materials with tailored response and optimized performance characteristics. Additive Manufacturing technologies already are being applied to primary NNSA mission areas, including Nuclear Weapons. These mission areas are adapting to these new manufacturing methods, because of potential advantages, such as smaller manufacturing footprints, reduced needs for specialized tooling, an ability to embed sensing, novel part repair options, an ability to accommodate complex geometries, and lighter weight materials. To realize the full potential of Additive Manufacturing as a game-changing technology for the NNSA’s national security missions; however, significant progress must be made in several key technical areas. In addition to advances in engineering design, process optimization and automation, and accelerated feedstock design and manufacture, significant progress must be made in modeling and simulation. First and foremost, a more mature understanding of the process-structure-property-performance relationships must be developed. Because Additive Manufacturing processes change the nature of a material’s structure below the engineering scale, new models are required to predict materials response across the spectrum of relevant length scales, from the atomistic to the continuum. New diagnostics will be required to characterize materials response across these scales. And not just models, but advanced algorithms, next-generation codes, and advanced computer architectures will be required to complement the associated modeling activities. Based on preliminary work in each of these areas, a strong argument for the need for Exascale computing architectures can be made, if a legitimate predictive capability is to be developed.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Architectural Approaches for Integrating ADMS and DERMS: Challenges, Comparisons, and Real-World Use Cases

The electrical distribution landscape is rapidly transforming due to the proliferation of distributed energy resources (DERs) such as solar panels, wind turbines, battery storage systems, combined heat and power units, and electric vehicles, introducing variability and uncontrollability that traditional grid operators are ill-equipped to manage. This transformation is further accelerated by advancements in Information and Communication Technology infrastructure that connects control centers with end devices, demanding automation and a deeper understanding of new technologies by utility personnel. Advanced grid control techniques using system-level optimization, Artificial Intelligence, and Machine Learning at the enterprise level and distributed level are evolving to address these issues. There is also an opportunity to utilize the enormous data created by these new DER technologies in the grid. Advanced Distribution Management Systems (ADMS) and Distributed Energy Resource Management Systems (DERMS) are critical in addressing these challenges by automating grid operations and enhancing reliability. Given the relatively recent development of ADMS and DERMS, and the still relatively low level of ADMS and DERMS deployment in the industry, there is a notable deficiency in the comprehensive understanding of the challenges and benefits associated with these new technologies, especially with their complementary natures and integration architectures. This paper aims to bridge the knowledge gap in ADMS and DERMS integration, presenting three distinct integration architectures currently available, and discussing the challenges and benefits of each architecture to guide utilities, industry professionals, and researchers in optimizing grid management and decision-making processes for a resilient and efficient energy future.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2016

Algorithmic Improvements for Portable Event-Based Monte Carlo Transport Using the Nvidia Thrust Library

High performance computing environments are progressively moving towards many-core computing architectures. The Los Alamos National Laboratory Trinity machine, available in late 2016, will use both Intel Xeon Haswell processors and Intel Xeon Phi Knights Landing many integrated core (MIC) coprocessors. The Lawrence Livermore National Laboratory Sierra machine, available in 2018, will use an IBM PowerPC architecture along with Nvidia graphics processing units (GPUs). Applications that must work in this supercomputing environment must continue to adapt in order to take advantage of the diverse hardware architectures that are coming. A significant consideration is not only the performance of the application on a given platform but also the portability of the application to other platforms. The algorithmic improvements presented in this paper build upon recently-reported work on event-based Monte Carlo transport in the ALPSMC code that models particle transport in one-dimensional binary stochastic media. That paper discussed the lack of available vectorization in the traditional history-based algorithm used for Monte Carlo transport and presented a data parallel event-based algorithm implemented using the Nvidia Thrust library for portability. The performance of the data parallel event-based algorithm implemented using Thrust was compared to a native CUDA implementation. The conclusions from that work were that the Thrust library abstraction technique caused too significant a loss in performance but that the event-based method was a viable option that should be further investigated. In this paper, we describe algorithmic improvements to the data parallel event-based algorithm previously presented. We made further algorithmic optimizations to the event-based CUDA implementation, most notably: data structure changes, a new conditional particle removal scheme in the event-based process, and the use of multiple GPUs. In addition to improvements to the algorithm, we re-implemented the Thrust version from the now further optimized CUDA version, giving a greater chance for success at a performant abstraction. Finally, we revisited our previous assumptions about the inability of the history-based method to achieve performance on vector style architectures such as the MICs and GPUs, with surprising and promising results. (authors)

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗