Search NASA⌕ Search

SEARCH · Search NASA

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 1,009 records · Page 56

Cyber security using multi-threaded architecture data diode at the NBSR - 114

Ongoing upgrades for the control room of the National Bureau of Standards Reactor (NBSR) located at the National Institute of Standards and Technology (NIST) require the ability to collect sensor data from the secured reactor network and transfer to the outside network for trend analysis, while maintaining the security of the reactor network. To accomplish this, a data diode was created to provide a physical barrier that prevents any outside data from reaching the secured reactor network. The hardware of the data diode consists of two embedded computers, running Unix based operating systems, connected by three DB-9 serial cables. The serial cables have been modified so that only two wires, a ground and a transmission line, provide connection between the computers. The data diode relies on a multi-threaded architecture to collect and simultaneously transfer data over three serial connections. A software program, implemented in Java, has been written to request data from the digital recorders installed to monitor the NBSR process instrumentation and transfer that data across the serial connections. The data diode can collect over 1200 data points from multiple digital recorders each second. The collected data can then be stored in a relational database for later analysis. The source codes for the software are available open source on GitHub. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Data-driven analysis to understand GPU hardware resource usage of optimizations

With heterogeneous systems, the number of GPUs per chip increases to provide computational capabilities for solving science at a nanoscopic scale. However, low utilization for single GPUs defies the need to invest more money in expensive accelerators. Although related work develops optimizations to improve application performance, none studies how these optimizations impact hardware resource usage or average GPU utilization. Here, this paper takes a data-driven analysis approach in addressing this gap by (1) characterizing how hardware resource usage affects device utilization, execution time, or both, (2) presenting a multiobjective metric to identify important application-device interactions that can be optimized to improve device utilization and application performance jointly, (3) studying hardware resource usage behaviors of several optimizations for a benchmark application, and finally (4) identifying optimization opportunities for several scientific proxy applications based on their hardware resource usage behaviors. Furthermore, we demonstrate the applicability of our methodology by applying the identified optimizations to a proxy application, which improves the execution time, device utilization, and power consumption by up to 29.6%, 5.3% and 26.5% respectively.

Computer science↗

The potential of quantum annealing for rapid solution structure identification

Abstract The recent emergence of novel computational devices, such as quantum computers, coherent Ising machines, and digital annealers presents new opportunities for hardware-accelerated hybrid optimization algorithms. Unfortunately, demonstrations of unquestionable performance gains leveraging novel hardware platforms have faced significant obstacles. One key challenge is understanding the algorithmic properties that distinguish such devices from established optimization approaches. Through the careful design of contrived optimization tasks, this work provides new insights into the computation properties of quantum annealing and suggests that this model has the potential to quickly identify the structure of high-quality solutions. A meticulous comparison to a variety of algorithms spanning both complete and local search suggests that quantum annealing’s performance on the proposed optimization tasks is distinct. This result provides new insights into the time scales and types of optimization problems where quantum annealing has the potential to provide notable performance gains over established optimization algorithms and suggests the development of hybrid algorithms that combine the best features of quantum annealing and state-of-the-art classical approaches.

97 MATHEMATICS AND COMPUTING↗

A tool and a methodology to use macros for abstracting variations in code for different computational demands

Scientific software used on high-performance computing platforms is in a phase of transformation because of the combined increase in the heterogeneity and complexity of models and hardware platforms. Having separate implementations for different platforms can easily lead to combinatorial explosions; therefore, the computational science community has been looking for mechanisms to express code through abstractions that can be specialized for different platforms. Most existing approaches use template meta-programming in C++, and are, therefore language specific. Here, we have developed a tool that uses customized expansion of macros to mimic some of C++ behavior in other languages. It enables unification of any code variants that may be necessary to run efficiently on different target architectures and different computational environments through use of macros with multiple alternative definitions and ability to arbitrate on definition selection for expansion. Combined with two other tools, a custom runtime, and a user specified recipe translator, our custom macroprocessor becomes a part of an overall performance portability solution that does not depend on any specific programming language. We also use macros as code-shorthand that lets code snippets become building blocks that allow variations in control flow to explore performance options. We demonstrate use of macros in Flash-X, a multiphysics multicomponent code with many Fortran legacy components derived from an earlier community code FLASH.

Heterogenous computing↗

Thermo-chemical Fluid Flow Simulation in Hot-Dip Galvanizing: The Evaluation of Dross Build-Up Formation

This paper presents a new computational framework to investigate the driving force for the formation of intermetallic dross particles in the zinc bath and dross build-up on the bath hardware. This is a major problem in continuous hot-dip galvanizing lines. The Computational Fluid Dynamics (CFD) model calculates the turbulent thermo-chemical flow conditions within the liquid melt. A detailed modeling of the steel strip–liquid interface enhances this approach, by means of a conjugated heat transfer calculation and a spatially resolved, temperature- and concentration-dependent iron dissolution and aluminum uptake. The heart of the computational framework is a thermodynamic model, which assesses the driving force for the formation or dissolution of dross particles in the bath and dross build-up on stationary and rotating equipment. The simulation results are validated with temperature and species depth profile measurements. The applicability of the CFD model is shown by investigating the locally resolved aluminum uptake and iron dissolution at the steel-strip surface, and the multi-physics conditions in the region near the roll. The novel approach of evaluating the thermodynamic driving force enables the assessment of the formation of dross build-up at the roll surface.

36 MATERIALS SCIENCE↗

SU-C-206-03: Metal Artifact Reduction in X-Ray Computed Tomography Based On Local Anatomical Similarity

Purpose: Metal implants such as orthopedic hardware and dental fillings cause severe bright and dark streaking in reconstructed CT images. These artifacts decrease image contrast and degrade HU accuracy, leading to inaccuracies in target delineation and dose calculation. Additionally, such artifacts negatively impact patient set-up in image guided radiation therapy (IGRT). In this work, we propose a novel method for metal artifact reduction which utilizes the anatomical similarity between neighboring CT slices. Methods: Neighboring CT slices show similar anatomy. Based on this anatomical similarity, the proposed method replaces corrupted CT pixels with pixels from adjacent, artifact-free slices. A gamma map, which is the weighted summation of relative HU error and distance error, is calculated for each pixel in the artifact-corrupted CT image. The minimum value in each pixel’s gamma map is used to identify a pixel from the adjacent CT slice to replace the corresponding artifact-corrupted pixel. This replacement only occurs if the minimum value in a particular pixel’s gamma map is larger than a threshold. The proposed method was evaluated with clinical images. Results: Highly attenuating dental fillings and hip implants cause severe streaking artifacts on CT images. The proposed method eliminates the dark and bright streaking and improves the implant delineation and visibility. In particular, the image non-uniformity in the central region of interest was reduced from 1.88 and 1.01 to 0.28 and 0.35, respectively. Further, the mean CT HU error was reduced from 328 HU and 460 HU to 60 HU and 36 HU, respectively. Conclusions: The proposed metal artifact reduction method replaces corrupted image pixels with pixels from neighboring slices that are free of metal artifacts. This method proved capable of suppressing streaking artifacts, improving HU accuracy and image detectability.

60 APPLIED LIFE SCIENCES↗

RAJA Performance Suite

The RAJA Performance Suite is designed to evaluate performance of the RAJA performance portability library on a wide variety of important high performance computing (HPC) algorithmic lulmels. These kernels assess compiler optimizations and various parallel programming model backends accessible through RAJA, such as OpenMP, CUDA, etc. The Initial version of the suite contains 25 computational kernels, each of which appears in 6 variants: Baseline SequcntiaJ, RAJA SequentiaJ, Baseline OpenMP, RAJA OpenMP, Baseline CUDA, RAJA CUDA. All variants of each kernel perform essentially the same mathematical operations and the loop body code for each kernel is identical across all variants. There are a few kernels, such as those that contain reduction operations, that require CUDA-specific coding for their CUDA variants. ActuaJ computer instructions executed and how they run in parallel differs depending on the parallel programming model backend used and which optimizations are perfonned by the compiler used to build the Perfonnance Suite executable. The Suite will be used primarily by RAJA developers to perform regular assessments of RAJA performance across a range of hardware platforms and compilers as RAJA features are being developed. It will also be used by LLNL hardware and software vendor panners for new defining requirements for future computing platform procurements and acceptance testing. In particular, the RAJA Performance Suite will be used for compiler acceptance testing of the upcoming CORAUSierra machine {initial LLNL delivery expected in late-2017/early 2018) and the CORAL-2 procurement. The Suite will aJso be used to generate concise source code reproducers of compiler and runtime issues we uncover so that we may provide them to relevant vendors to be fixed.

Hornung, RichardD.↗

Benchmarking a Tunable Quantum Neural Network on Trapped-Ion and Superconducting Hardware

We implement a quantum generalization of a neural network on trapped-ion and IBM superconducting quantum computers to classify MNIST images, a common benchmark in computer vision. The network feedforward involves qubit rotations whose angles depend on the results of measurements in the previous layer. The network is trained via simulation, but inference is performed experimentally on quantum hardware. The classical-to-quantum correspondence is controlled by an interpolation parameter, $a$, which is zero in the classical limit. Increasing $a$ introduces quantum uncertainty into the measurements, which is shown to improve network performance at moderate values of the interpolation parameter. We then focus on particular images that fail to be classified by a classical neural network but are detected correctly in the quantum network. For such borderline cases, we observe strong deviations from the simulated behavior. We attribute this to physical noise, which causes the output to fluctuate between nearby minima of the classification energy landscape. Such strong sensitivity to physical noise is absent for clear images. We further benchmark physical noise by inserting additional single-qubit and two-qubit gate pairs into the neural network circuits. Our work provides a springboard toward more complex quantum neural networks on current devices: while the approach is rooted in standard classical machine learning, scaling up such networks may prove classically non-simulable and could offer a route to near-term quantum advantage.

FOS: Physical sciences↗

Assessment of cardiac single-photon emission computed tomography performance using a scanning linear observer

Purpose: Single-photon emission computed tomography (SPECT) is widely used to detect myocardial ischemia and myocardial infarction. It is important to assess and compare different SPECT system designs in order to achieve the highest detectability of cardiac defects. Methods: Whitaker et al.'s study ['Estimating random signal parameters from noisy images with nuisance parameters: linear and scanning-linear methods,' Opt. Express 16(11), 8150-8173 (2008)] on the scanning linear observer (SLO) shows that the SLO can be used to estimate the location and size of signals. One major advantage of the SLO is that it can be used with projection data rather than with reconstruction data. Thus, this observer model assesses the overall hardware performance independent of any reconstruction algorithm. In addition, the computation time of image quality studies is significantly reduced. In this study, three systems based on the design of the GE cadmium zinc telluride-based dedicated cardiac SPECT camera Discovery 530c were assessed. This design, which is officially named the Alcyone Technology: Discovery NM 530c, was commercialized in August, 2009. The three systems, GE27, GE19, and GE13, contain 27, 19, and 13 detectors, respectively. Clinically, a human heart can be virtually segmented into three coronary artery territories: the left-anterior descending artery, left-circumflex artery, and right coronary artery. One of the most important functions of a cardiac SPECT system is to produce images from which a radiologist can accurately predict in which territory the defect exists [http://www.asnc.org/media/PDFs/PPReporting081511.pdf, Guideline from American Society of Nuclear Cardiology]. A good estimation of the extent of the defect from the projection images is also very helpful for determining the seriousness of the myocardial ischemia. In this study, both the location and extent of defects were estimated by the SLO, and the system performance was assessed by localization receiver operating characteristic (LROC) [P. Khurd and G. Gindi, 'Decision strategies maximizing the area under the LROC curve,' Proc. SPIE 5749, 150-161 (2005)] or estimation receiver operating characteristic (EROC) [E. Clarkson, 'Estimation receiver operating characteristic curve and ideal observers for combined detection/estimation tasks,' J. Opt. Soc. Am. A 24, B91-B98 (2007)] curves. Results: The area under the LROC/EROC curve (AULC/AUEC) and the true positive fraction (TPF) at a specific false positive fraction (FPF) can be treated as the figures of merit. For radii estimation with a 1 mm tolerance, the AUEC values of the GE27, GE19, and GE13 systems are 0.8545, 0.8488, and 0.8329, and the TPF at FPF = 5% are 77.1%, 76.46%, and 73.55%, respectively. The assessment of all three systems revealed that the GE19 system yields estimated information and cardiac defect detectability very close to those of the GE27 system while using eight fewer detectors. Thus, 30% of the expensive detector units can be removed with confidence. Conclusions: As the results show, a combination of the SLO and LROC/EROC curves can determine the configuration that yields the most relevant estimation/detection information. Thus, this is a useful method for assessing cardiac SPECT systems.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Enabling Co-Design of Multi-Layer Exascale Storage Architectures

Growing demands for computing power in applications such as energy production, climate analysis, computational chemistry, and bioinformatics have propelled computing systems toward the exascale: systems with 10 18 floating-point operations per second. These systems, to be designed and constructed over the next decade, will create unprecedented challenges in component counts, power consumption, resource limitations, and system complexity. Data storage and access are an increasingly important and complex component in extreme-scale computing systems, and significant design work is needed to develop successful storage hardware and software architectures at exascale. Co-design of these systems will be necessary to find the best possible design points for exascale systems. The goal of this work has been to enable the exploration and co-design of exascale storage systems by providing a detailed, accurate, and highly parallel simulation of exascale storage and the surrounding environment. Specifically, this simulation has (1) portrayed realistic application checkpointing and analysis workloads, (2) captured the complexity, scale, and multilayer nature of exascale storage hardware and software, and (3) executed in a timeframe that enables “what if'” exploration of design concepts. We developed models of the major hardware and software components in an exascale storage system, as well as the application I/O workloads that drive them. We used our simulation system to investigate critical questions in reliability and concurrency at exascale, helping guide the design of future exascale hardware and software architectures. Additionally, we provided this system to interested vendors and researchers so that others can explore the design space. We validated the capabilities of our simulation environment by configuring the simulation to represent the Argonne Leadership Computing Facility Blue Gene/Q system and comparing simulation results for application I/O patterns to the results of executions of these I/O kernels on the actual system.

97 MATHEMATICS AND COMPUTING↗

A Survey Of Techniques for Managing and Leveraging Caches in GPUs

Initially introduced as special-purpose accelerators for graphics applications, graphics processing units (GPUs) have now emerged as general purpose computing platforms for a wide range of applications. To address the requirements of these applications, modern GPUs include sizable hardware-managed caches. However, several factors, such as unique architecture of GPU, rise of CPU–GPU heterogeneous computing, etc., demand effective management of caches to achieve high performance and energy efficiency. Recently, several techniques have been proposed for this purpose. In this paper, we survey several architectural and system-level techniques proposed for managing and leveraging GPU caches. We also discuss the importance and challenges of cache management in GPUs. The aim of this paper is to provide the readers insights into cache management techniques for GPUs and motivate them to propose even better techniques for leveraging the full potential of caches in the GPUs of tomorrow.

cache memory↗

Detecting and Blocking Network Attacks at Ultra High Speeds

Stateful, in-depth, in-line traffic analysis for intrusion detection and prevention has grown increasingly more difficult as the data rates of modern networks rise. One point in the design space for high-performance network analysis - pursued by a number of commercial products - is the use of sophisticated custom hardware. For very high-speed processing, such systems often cast the entire analysis process in ASICs. This project pursued a different architectural approach, which we term Shunting. Shunting marries a conceptually quite simple hardware device with an Intrusion Prevention System (IPS) running on commodity PC hardware. The overall design goal is was to keep the hardware both cheap and readily scalable to future higher speeds, yet also retain the unparalleled flexibility that running the main IPS analysis in a full general-computing environment provides. The Shunting architecture we developed uses a simple in-line hardware element that maintains several large state tables indexed by packet header fields, including IP/TCP flags, source and destination IP addresses, and connection tuples. The tables yield decision values the element makes on a packet-by-packet basis: forward the packet, drop it, or divert ('shunt') it through the IPS (the default). By manipulating table entries, the IPS can, on a fine-grained basis: (i) specify the traffic it wishes to examine, (ii) directly block malicious traffic, and (iii) 'cut through' traffic streams once it has had an opportunity to 'vet' them, or (iv) skip over large items within a stream before proceeding to further analyze it. For the Shunting architecture to yield benefits, it needs to operate in an environment for which the monitored network traffic has the property that - after proper vetting - much of it can be safely skipped. This property does not universally hold. For example, if a bank needs to examine all Web traffic involving its servers for regulatory compliance, then a monitor in front of one of the bank's server farms cannot safely omit a subset of the traffic from analysis. In this environment, Shunting cannot realize its main performance benefits, and the monitoring task likely calls for using custom hardware instead. However, in many other environments we find Shunting holds promise for delivering major performance gains. This arises due to the the widely documented 'heavy tail' nature of most forms of network traffic, which we might express as 'a few of the connections carry just about all the bytes.' The key additional insight is '... and very often for these few large connections, the very beginning of the connection contains nearly all the information of interest from a security analysis perspective.' We argue that this second claim holds because it is at the beginning of connections that authentication exchanges occur, data or file names and types are specified, request and reply status codes conveyed, and encryption is negotiated. Once these occur, we have seen most of the interesting facets of the dialog. Certainly the remainder of the connection might also yield some grist for analysis, but this is generally less likely, and thus if we want to lower analysis load at as small a loss as possible of information relevant to security analysis, we might best do so by skipping the bulk of large connections. In a different context, the 'Time Machine' work by Kornexl and colleagues likewise shows that in some environments we can realize major reductions in the volume of network traffic processed, by limiting the processing to the first 10-20 KB of each connection. As a concrete example, consider an IPS that monitors SSH traffic. When a new SSH connection arrives and the Shunt fails to find an entry for it in any of its tables (per-address, per-port, per-connection), it executes the default action of diverting the connection through the IPS. The IPS analyzes the beginning of the connection in this fashion. As long as it is satisified with the dialog, it reinjects the packets forwarded to it so that the connection can continue. If the connection successfully negotiates encryption, the IPS can no longer profitably analyze it, so it downloads a per-connection table entry to the Shunt specifying that the action for the connection in the future is 'forward.' For heavy-tailed connections, this means a very large majority of the connection's packets will now pass through the Shunt device without burdening the IPS with any further analysis load. On the other hand, if the IPS is dissatisfied with some element of the initial dialog, it downloads a 'drop' entry to terminate the connection. Note that by providing for reinjection, we can promote an intrusion detection system into an intrusion prevention system, one that does not merely detect attacks but can block them before they complete. Reinjection also allows the IPS to normalize traffic to remove ambiguities that attackers can leverage to evade the IPS.

99 GENERAL AND MISCELLANEOUS↗

Software Development for a CompactRIO-Based Wire Scanner Control and Data Acquisition SYstem

The Beam Diagnostics and Instrumentation Team at the Los Alamos Neutron Science Center is developing a wire scanner data acquisition and control system with a National Instrument's compactRIO at its core. For this application, the compactRIO controller not only requires programming the FPGA and RT computer internal to the compactRIO, but also requires programming a client computer and a touch panel display. This article will summarize the hardware interfaces and describe the software design approach utilized for programming and interfacing the four systems together in order to fulfill the design requirements and promote reliable interoperability.

42 ENGINEERING↗

AI-Powered Knowledge Graphs for Neuromorphic and Energy-Efficient Computing

The surge in scientific literature obscures breakthroughs and hinders the discovery of new research paths. We propose an artificial intelligence (AI) powered framework using large language models (LLMs) and knowledge graphs (KGs) to automate parts of scientific discovery, focusing on energy-efficient AI circuits. Our hybrid approach combines LLMs, structured data, and ontology-based reasoning to construct a comprehensive knowledge graph that integrates insights across computational neuroscience, spiking neuron models, learning rules, architectural motifs, and neuromorphic device technologies. This multi-domain representation enables the generation of hypotheses that connect biological function with implementable, energy-efficient hardware architectures. Using KG embeddings and graph neural networks, the framework generates hypotheses for novel circuits, validates them through optimization on exascale HPC systems, and with tools like SuperNeuro and Fugu, the most promising designs will be prototyped in hardware. This open-source system aims to accelerate discoveries and bridging neuroscience with hardware innovation, drive collaboration, and unlock new opportunities in low-power AI computing.

Gautam, Ashish [ORNL]↗

Exascale Operating Systems and Runtime Software Report

Here U.S. Department of Energy (DOE) workshops and reports have identified four key exascale challenges: dramatically improving power efficiency; improving resilience in the presence of increasing faults; enabling efficient data movement across deepening memory hierarchies and new storage technologies; and managing dramatically increased parallelism, especially at the node level. Software solutions that address these challenges must also improve programmability, expanding the community of computational scientists who can use leadership-class platforms. To address these challenges, DOE must develop new techniques, novel designs, and advanced software architectures for next-generation exascale software infrastructure. In this report, we discuss challenges and approaches to exascale operating system and runtime (OS/R) software. The Exascale Operating Systems and Runtime (OS/R) Software Technical Council canvassed hardware architects, application programmers, parallel tool developers, DOE high-performance computing (HPC) facilities, and the vendors that sell and support integrated platforms. After considering the collective requirements of these constituents and examining the future research challenges and current software gaps, the council recommends that DOE invest in targeted advanced computer science research and in specific coordinating activities to enable the effective and successful development of anticipated exascale systems.

97 MATHEMATICS AND COMPUTING↗

Rasterization with Data-Parallel Primitives

Parallel rasterization can suffer from race conditions during fragment generation, which is traditionally addressed by using specialized hardware accessible via vendor graphics APIs. Unfortunately, graphics APIs are increasingly problematic on high-performance computers, either because they are not provided or because of concerns about dependencies with in situ visualization. In response, we present a hardware-agnostic rasterization algorithm that handles race conditions using only data-parallel primitives (DPPs), enabling efficient rendering on HPC systems without graphics API dependencies and aligning with recent efforts to deliver visualization software with DPPs. Our evaluation consists of three phases: (1) evaluating portability across different CPU and GPU architectures, (2) evaluating competitiveness with a community standard, and (3) evaluating performance across varying workloads and available parallelism. The supporting experiments run on both AMD and NVIDIA GPUs, considering data sets as large as 460 million triangles and 160 million pixels. While performance generally falls short of graphics API baselines, it achieves interactive frame rates on most workloads. As a result, we conclude our approach is a viable solution for rasterization on high-performance computers since our approach is portably performant across different architectures without the need for specialized vendor support.

Buckley, Makani [University of Oregon] (ORCID:0009↗

CFD simulations of electric motor end ring cooling for improved thermal management

Proper thermal management of an electric motor for vehicle applications extends its operating range. One cooling approach is to impinge Automatic Transmission Fluid (ATF) onto the rotor end ring. Increased ATF coverage correlates to enhanced heat transfer. Computational Fluid Dynamics (CFD) analytical tools provide a mechanism to assess motor thermal management prior to hardware fabrication. The complexity of the fluid flow (e.g., jet atomization, interface tracking, wall impingement) and heat transfer makes these simulations challenging. Computational costs are high when solving these flows on high-speed rotating meshes. Typically, a Volume-of Fluid (VOF) technique (i.e., two-fluid system) is used to resolve ATF dynamics within this rotating framework. Suitable numerical resolution of the relevant physics for thin films under strong inertial forces at high rotor speeds is computationally expensive, further increasing the run times. In this work, a numerical study of rotor-ring cooling by ATF is presented using a patent automated Cartesian cut-cell based method coupled with Automatic Mesh Refinement (AMR). This approach automatically creates the Cartesian mesh on-the-fly and can effectively handle complex rotating geometries by adaptively refining the mesh based on local gradients in the flow field which results in better resolution of the air-ATF interface. A Single non-inertial Reference Frame (SRF) approach is used to account for the rotating geometry and to further improve the overall computational efficiency. Quasi-steady state conditions are targeted in the analysis of the results. Important physics such as ATF jet structure, velocity detail near the air-jet interface, ATF coverage/accumulation on the ring surface, and cooling capacity are presented for a low-resolution Reynolds averaged Navier-Stokes (RANS), high-resolution RANS, and high-resolution Large-Eddy Simulation (LES) models. Computations are scaled over hundreds of cores on a supercomputer to maximize turnaround time. Each numerical approach is shown to capture the general trajectory of the oil jet prior to surface impingement. The high-resolution LES simulation, however, is superior in capturing small scale details and heat transfer between the free jet and surrounding air.

42 ENGINEERING↗

SU-F-BRD-13: Quantum Annealing Applied to IMRT Beamlet Intensity Optimization

Purpose: We report on the first application of quantum annealing (QA) to the process of beamlet intensity optimization for IMRT. QA is a new technology, which employs novel hardware and software techniques to address various discrete optimization problems in many fields. Methods: We apply the D-Wave Inc. proprietary hardware, which natively exploits quantum mechanical effects for improved optimization. The new QA algorithm, running on this hardware, is most similar to simulated annealing, but relies on natural processes to directly minimize the free energy of a system. A simple quantum system is slowly evolved into a classical system, representing the objective function. To apply QA to IMRT-type optimization, two prostate cases were considered. A reduced number of beamlets were employed, due to the current QA hardware limitation of ∼500 binary variables. The beamlet dose matrices were computed using CERR, and an objective function was defined based on typical clinical constraints, including dose-volume objectives. The objective function was discretized, and the QA method was compared to two standard optimization Methods: simulated annealing and Tabu search, run on a conventional computing cluster. Results: Based on several runs, the average final objective function value achieved by the QA was 16.9 for the first patient, compared with 10.0 for Tabu and 6.7 for the SA. For the second patient, the values were 70.7 for the QA, 120.0 for Tabu, and 22.9 for the SA. The QA algorithm required 27–38% of the time required by the other two methods. Conclusion: In terms of objective function value, the QA performance was similar to Tabu but less effective than the SA. However, its speed was 3–4 times faster than the other two methods. This initial experiment suggests that QA-based heuristics may offer significant speedup over conventional clinical optimization methods, as quantum annealing hardware scales to larger sizes.

07 ISOTOPE AND RADIATION SOURCES↗