Search NASA⌕ Search

SEARCH · Search NASA

Results for “High Performance Computing, ARM”

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 73 records · Page 4

Real-time fuzzy inference based robot path planning

This project addresses the problem of adaptive trajectory generation for a robot arm. Conventional trajectory generation involves computing a path in real time to minimize a performance measure such as expended energy. This method can be computationally intensive, and it may yield poor results if the trajectory is weakly constrained. Typically some implicit constraints are known, but cannot be encoded analytically. The alternative approach used here is to formulate domain-specific knowledge, including implicit and ill-defined constraints, in terms of fuzzy rules. These rules utilize linguistic terms to relate input variables to output variables. Since the fuzzy rulebase is determined off-line, only high-level, computationally light processing is required in real time. Potential applications for adaptive trajectory generation include missile guidance and various sophisticated robot control tasks, such as automotive assembly, high speed electrical parts insertion, stepper alignment, and motion control for high speed parcel transfer systems.

Pacini, Peter J.↗

Wide-ranging predictions of new stable compounds powered by recommendation engines

The computational search for new stable inorganic compounds is faster than ever, thanks to high-throughput density functional theory (DFT). However, stable compound searches remain highly expensive because of the enormous search space and the cost of DFT calculations. To aid these searches, recommendation engines have been developed. We conduct a systematic comparison of the performance of previously developed recommendation engines, specifically ones based on elemental substitution, data mining, and neural network prediction of formation enthalpy. After identifying ways to improve the recommendation engines, we find the neural network to be superior at recommending stable Heusler compounds. Armed with improved recommendation engines, we identify tens of thousands of compounds that are stable at zero temperature and pressure, now available in the Open Quantum Materials Database. We summarize this diverse pool of compounds, including the elusive mixed anion compounds, and two of their many applications: thermoelectricity and solar thermochemical fuel production.

Science & Technology - Other Topics↗

SequenceL: Automated Parallel Algorithms Derived from CSP-NT Computational Laws

With the introduction of new parallel architectures like the cell and multicore chips from IBM, Intel, AMD, and ARM, as well as the petascale processing available for highend computing, a larger number of programmers will need to write parallel codes. Adding the parallel control structure to the sequence, selection, and iterative control constructs increases the complexity of code development, which often results in increased development costs and decreased reliability. SequenceL is a high-level programming language that is, a programming language that is closer to a human s way of thinking than to a machine s. Historically, high-level languages have resulted in decreased development costs and increased reliability, at the expense of performance. In recent applications at JSC and in industry, SequenceL has demonstrated the usual advantages of high-level programming in terms of low cost and high reliability. SequenceL programs, however, have run at speeds typically comparable with, and in many cases faster than, their counterparts written in C and C++ when run on single-core processors. Moreover, SequenceL is able to generate parallel executables automatically for multicore hardware, gaining parallel speedups without any extra effort from the programmer beyond what is required to write the sequen tial/singlecore code. A SequenceL-to-C++ translator has been developed that automatically renders readable multithreaded C++ from a combination of a SequenceL program and sample data input. The SequenceL language is based on two fundamental computational laws, Consume-Simplify- Produce (CSP) and Normalize-Trans - pose (NT), which enable it to automate the creation of parallel algorithms from high-level code that has no annotations of parallelism whatsoever. In our anecdotal experience, SequenceL development has been in every case less costly than development of the same algorithm in sequential (that is, single-core, single process) C or C++, and an order of magnitude less costly than development of comparable parallel code. Moreover, SequenceL not only automatically parallelizes the code, but since it is based on CSP-NT, it is provably race free, thus eliminating the largest quality challenge the parallelized software developer faces.

Cooke, Daniel↗

Investigation of Combustion Control in a Dump Combustor Using the Feedback Free Fluidic Oscillator

A feedback free fluidic oscillator was designed and integrated into a single element rocket combustor with the goal of suppressing longitudinal combustion instabilities. The fluidic oscillator uses internal fluid dynamics to create an unsteady outlet jet at a specific frequency. An array of nine fluidic oscillators was tested to mimic modulated secondary oxidizer injection into the combustor dump plane. The combustor has a coaxial injector that uses gaseous methane and decomposed hydrogen peroxide with an overall O/F ratio of 11.7. A sonic choke plate on an actuator arm allows for continuous adjustment of the oxidizer post acoustics enabling the study of a variety of instability magnitudes. The fluidic oscillator unsteady outlet jet performance is compared against equivalent steady jet injection and a baseline design with no secondary oxidizer injection. At the most unstable operating conditions, the unsteady outlet jet saw a 67% reduction in the instability pressure oscillation magnitude when compared to the steady jet and baseline data. Additionally, computational fluid dynamics analysis of the combustor gives insight into the flow field interaction of the fluidic oscillators. The results indicate that open loop high frequency propellant modulation for combustion control can be achieved through fluidic devices that require no moving parts or electrical power to operate.

Meier, Eric J.↗

A Physical Protection Systems Test Bed for International Counter-Trafficking System Development

Physical protection systems have a widespread impact on the nuclear industry in areas such as nuclear safeguards, arms control, and trafficking of illicit goods (e.g., nuclear materials) across international borders around the world. Many challenges must be overcome in design and deployment of foreign border security systems such as lack of infrastructure, extreme environmental conditions, limited knowledge of terrain, insider threats, and occasional cultural resistance. Successful security systems, whether it be a system designed to secure a single facility or a whole border security system, rely on the entire integrated system composed of multiple subsystems. This test bed is composed of many unique sensors and subsystems, including wireless unattended ground sensors, a buried fiber-optic acoustic sensor, a lossy coaxial distributed sensor, wireless links, pan-tilt-zoom cameras, mobile power generation systems, unmanned aerial vehicles, and fiber-optic-fence intrusion detection systems. A Common Operating Picture software architecture is utilized to integrate a number of these subsystems. We are currently performance testing each system for border security and perimeter security applications by examining metrics such as probability of sense and a qualitative understanding of the sensor s vulnerability of defeat. The testing process includes different soil conditions for buried sensors (e.g., dry, wet, and frozen) and an array of different tests including walking, running, stealth detection, and vehicle detection. Also, long term sustainability of systems is tested including performance differences due to seasonal variations (e.g. summer versus winter, while raining, in foggy conditions). The capabilities of the test bed are discussed. Performance testing results, both at the individual component level and integrated into a larger system for a specific deployment (in situ), help illustrate the usefulness and need for integrated testing facilities to carry out this mission. The test bed provides access to grassy fields, wooded areas, and a large waterway three distinct testing environments. The infrastructure supporting deployment of systems at the test bed includes grid power, renewable power systems, climate controlled enclosures, high bandwidth wireless links, and a fiber optic communications backbone. With over 10 acres of dedicated area and direct waterway access, the test bed is well suited for long term test and evaluation of physical protection and security systems targeting a wide range of applications.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Evaluation of automated decision making methodologies and development of an integrated robotic system simulation: Study results

The implementation of a generic computer simulation for manipulator systems (ROBSIM) is described. The program is written in FORTRAN, and allows the user to: (1) Interactively define a manipulator system consisting of multiple arms, load objects, targets, and an environment; (2) Request graphic display or replay of manipulator motion; (3) Investigate and simulate various control methods including manual force/torque and active compliance control; and (4) Perform kinematic analysis, requirements analysis, and response simulation of manipulamotion. Previous reports have described the algorithms and procedures for using ROBSIM. These reports are superseded and additional features which were added are described. They are: (1) The ability to define motion profiles and compute loads on a common base to which manipulator arms are attached; (2) Capability to accept data describing manipulator geometry from a Computer Aided Design data base using the Initial Graphics exchange Specification format; (3) A manipulator control algorithm derived from processing the TV image of known reference points on a target; and (4) A vocabulary of simple high level task commands which can be used to define task scenarios.

Haley, D. C.↗

Computer experiments on the structure and dynamics of spiral galaxies

The evolution of an initially balanced rotating disk of stars with an initial velocity dispersion given by Toomre's local criterion was investigated by means of a computer model for isolated disks of stars. It was found that the disk is unstable against very large scale modes. A stable axisymmetric disk with a velocity dispersion much larger than that given by Toomre's criterion was generated. The final mass distribution for the disk gives a high density central core and a disk population of stars that is closely approximated by an exponential variation. Various methods and rates of cooling the hot axisymmetric disks were investigated. It was found that the cooling resulted in the development of two-arm spiral structures which persisted as long as cooling continued. An experiment was performed to induce spiral structure in a galaxy by means of the close passage of a companion galaxy. Parameters similar to those expected for M51 and its companion were used. It was found that because of the high velocity dispersion of the disturbed disk galaxy, only a weak two-arm spiral structure appeared. The evolution of a uniformly rotating disk galaxy which is a stationary solution of the collisionless Boltzmann equation was investigated for various values of the initial rms velocity dispersion. It was found that the disk becomes stable at a value of the velocity dispersion predicted by theory.

Hohl, F.↗

THE SUN WAS NOT BORN IN M67

Using the most recent proper-motion determination of the old, solar-metallicity, Galactic open cluster M67 in orbital computations in a non-axisymmetric model of the Milky Way, including a bar and three-dimensional spiral arms, we explore the possibility that the Sun once belonged to this cluster. We have performed Monte Carlo numerical simulations to generate the present-day orbital conditions of the Sun and M67, and all the parameters in the Galactic model. We compute 3.5 Multiplication-Sign 10{sup 5} pairs of orbits Sun-M67 looking for close encounters in the past with a minimum distance approach within the tidal radius of M67. In these encounters we find that the relative velocity between the Sun and M67 is larger than 20 km s{sup -1}. If the Sun had been ejected from M67 with this high velocity by means of a three-body encounter, this interaction would have either destroyed an initial circumstellar disk around the Sun or dispersed its already formed planets. We also find a very low probability, much lower than 10{sup -7}, that the Sun was ejected from M67 by an encounter of this cluster with a giant molecular cloud. This study also excludes the possibility that the Sun and M67 were born in the same molecular cloud. Our dynamical results convincingly demonstrate that M67 could not have been the birth cluster of our solar system.

79 ASTRONOMY AND ASTROPHYSICS↗

Macro-physical Properties of Shallow Cumulus from Integrated ARM Observations (Final Report)

Fair-weather shallow cumuli (ShCu) play an important role in many climate-related processes. Irregular geometry of ShCu and their strong temporal and spatial variability make it challenging to observe ShCu holistically and to represent them correctly in climate models. To improve ShCu parameterizations, information on both vertically and horizontally resolved cloud properties is required. Commonly, the vertically resolved cloud properties are provided by zenith pointing lidar-radar observations with a very narrow field of view (FOV). Thus, these “pencil-beam” properties may not be representative of a larger surrounding area. Limited number of areal-averaged cloud properties, such as fractional sky cover (FSC), are offered typically by wide-FOV observations. The main goal of our project was to integrate advantages of the narrow-FOV (vertical structure of clouds) and wide-FOV (spatial arrangement of clouds) observations for an improved characterization of single-layer ShCu observed at the Atmospheric Radiation Measurement (ARM) Southern Great Plains (SGP) site for an 18-yr period (2000-2017). There are four major accomplishments of our project, First, an updated operational cloud classification for days with ShCu has been suggested and evaluated through a detailed comparison with the manually curated records. Our classification extends successfully the latest ARM cloud type Value Added Product (VAP) based on the Active Remote Sensing of Clouds (ARSCL) cloud product by incorporating both cloud fraction (CF) provided by narrow-FOV ceilometer data and FSC from wide-FOV images offered by a Total Sky Imager (TSI). Moreover, our classification allows one to identify impact of instrumentation changes at the SGP site, namely the transition to KAZRARSCL with the updated cloud radar, on the identification of periods with single-layer ShCu. Second, a new approach that resolves cloud area distributions for a given region (up to 4x4 km 2 ) has been suggested and cloud equivalent diameters (CEDs) have been estimated for the first time. These estimations have been performed over a wide range of cloud sizes (about 0.01–3.5 km) with high temporal resolution (30s) using wide-FOV TSI images and cloud base height (CBH) provided by complementary narrow-FOV lidar measurements. Our simple and computationally inexpensive approach offers a previously unavailable dataset for process studies in the convective boundary layer and evaluation of ShCu parameterizations in cloud-resolving models. Third, a long-term integrated record of ShCu macrophysical properties has been developed. The developed record represents the longest available compilation of events with ShCu and includes (i) a novel visualization of the spatial variability in cloud cover both along- and across-wind directions, (ii) updated estimates of narrow-FOV CF and wide-FOV FSC, (iii) updated narrow-FOV CBH, and (iv) complementary data, such as wind speed and direction from the 915-MHz Radar Wind Profiler (RWP) data. The developed record has been used successfully to assess conventional observational estimates of cloud cover and their sensitivity to the following two factors: (i) instrument-dependent cloud detection and data merging criteria and (ii) FOV configuration. Fourth, co-variability of the ShCu macrophysical properties and environmental parameters has been analyzed for a 3-yr period (2016-2018). Our initial analysis includes diurnal changes of FSCs obtained for clouds with small, moderate and large CEDs and several environmental parameters, such as lifted condensation level (LCL) and mixed layer height (zi). Preliminary results of our analysis suggest that the horizontal extent of ShCu is controlled substantially by the sign and magnitude of difference between these two parameters (zi-LCL): the CED tends to grow with increase of this difference (zi exceeds LCL). We have initiated relationships between the ShCu and key atmospheric parameters that control both the development and evolution of ShCu using our new data product, which combines effectively the advantages of narrow-FOV data offered by zenith pointing cloud radars and lidars and wide-FOV TSI images. While the latest instrumentation at the ARM sites may address these challenging relationships in the future, we believe that the historical ARM data at the SGP site has not yet been fully utilized. Overall, our data product can be used by researchers working on a wide range of climate-related projects. These projects may include (i) a comprehensive evaluation of outputs from the Large-Eddy Simulation (LES) and single-column models for their future improvement, (ii) the representativeness of “short-period” results obtained from the previous model and observational studies and (iii) the planning of future field campaigns with focus on improved understanding of the diurnal cycle of cumulus convection.

54 ENVIRONMENTAL SCIENCES↗

High Performance EVA Glove Collaboration: Glove Injury Data Mining Effort

Human hands play a significant role during Extravehicular Activity (EVA) missions and Neutral Buoyancy Lab (NBL) training events, as they are needed for translating and performing tasks in the weightless environment. Because of this high frequency usage, hand and arm related injuries are known to occur during EVA and EVA training in the NBL. The primary objectives of this investigation were to: 1) document all known EVA glove related injuries and circumstances of these incidents, 2) determine likely risk factors, and 3) recommend interventions where possible that could be implemented in the current and future glove designs. METHODS: The investigation focused on the discomforts and injuries of U.S. crewmembers who had worn the pressurized Extravehicular Mobility Unit (EMU) spacesuit and experienced 4000 Series or Phase VI glove related incidents during 1981 to 2010 for either EVA ground training or in-orbit flight. We conducted an observational retrospective case-control investigation using 1) a literature review of known injuries, 2) data mining of crew injury, glove sizing, and hand anthropometry databases, 3) descriptive statistical analyses, and finally 4) statistical risk correlation and predictor analyses to better understand injury prevalence and potential causation. Specific predictor statistical analyses included use of principal component analyses (PCA), multiple logistic regression, and survival analyses (Cox proportional hazards regression). Results of these analyses were computed risk variables in the forms of odds ratios (likelihood of an injury occurring given the magnitude of a risk variable) and hazard ratios (likelihood of time to injury occurrence). Due to the exploratory nature of this investigation, we selected predictor variables significant at p≤0.15. RESULTS: Through 2010, there have been a total of 330 NASA crewmembers, from which 96 crewmembers performed 322 EVAs during 1981-2010, resulting in 50 crewmembers being injured inflight and 44 injured during 11,704 ground EVA training events. Of the 196 glove related injury incidents, 106 related to EVA and 90 to EVA training. Over these 196 incidents, 277 total injuries (126 flight; 151 training) were reported and were then grouped into 23 types of injuries. Of EVA flight injuries, 65% were commonly reported to the hand (in general), metacarpophalangeal (MCP) joint, and finger (not including thumb) with fatigue, abrasion, and paresthesia being the most common injury types (44% of total flight injuries). Training injuries totaled to more than 70% being distributed to the fingernail, MCP joint, and finger crotch with 88% of the specific injuries listed as pain, erythema, and onycholysis. Of these training injuries, when reporting pain or erythema, the most common location was the index finger, but when reporting onycholysis, it was the middle finger. Predictor variables specific to increased risk of onycholysis included: female sex (OR=2.622), older age (OR=1.065), increased duration in hours of the flight or training event (OR=1.570), middle finger length differences in inches between the finger and the EVA glove (OR=7.709), and use of the Phase VI glove (OR=8.535). Differentiation between training and flight and injury reporting during 2002-2004 were significant control variables. For likelihood of time to first onycholysis injury, there was a 24% reduction in rate of reporting for each year increase in age. Also, more experienced crewmembers, based on number of EVA flight or training events completed, were less likely to report an onycholysis injury (3% less for every event). Longer duration events also found reporting rates to occur 2.37 times faster for every hour of length. Crewmembers with larger hand size reported onycholysis 23% faster than those with smaller hand size. Finally, for every 1/10th of an inch increase in difference between the middle finger length and the glove, the rate of reporting increased by 60%. DISCUSSION: One key finding was that the Series 4000 glove had a lower injury risk than the Phase VI, which provides a platform for further evaluation. General interventions that reduce hand overexertion and repetitive use exposure through tool development, procedural changes and shorter exposures may be one mitigation path, but due to the way the training event times were reported, we cannot provide a guideline for a specific event duration change. When the finger length was different from the glove length, the risk of injury increased indicating that the use of larger finger take-ups could be contributing to injury and therefore may not be recommended. Prior to this investigation, there was one previous investigation indicating hand anthropometry may be related to onycholysis. We found different hand anthropometry variables indicated by this investigation as compared to the prior, specifically differences in middle finger length compared to glove finger length, which point more towards a sizing issue than a specific anthropometry issue. Additionally, although this investigation has identified sizing as an issue, the force and environmental-related variables of the EVA glove that could also cause injury were not accounted for.

Reid, C. R.↗

Robonaut: A Robotic Astronaut Assistant

NASA's latest anthropomorphic robot, Robonaut, has reached a milestone in its capability. This highly dexterous robot, designed to assist astronauts in space, is now performing complex tasks at the Johnson Space Center that could previously only be carried out by humans. With 43 degrees of freedom, Robonaut is the first humanoid built for space and incorporates technology advances in dexterous hands, modular manipulators, lightweight materials, and telepresence control systems. Robonaut is human size, has a three degree of freedom (DOF) articulated waist, and two, seven DOF arms, giving it an impressive work space for interacting with its environment. Its two, five fingered hands allow manipulation of a wide range of tools. A pan/tilt head with multiple stereo camera systems provides data for both teleoperators and computer vision systems.

Ambrose, Robert O.↗

Simple Models of the Spatial Distribution of Cloud Radiative Properties for Remote Sensing Studies

This project aimed to assess the degree to which estimates of three-dimensional cloud structure can be inferred from a time series of profiles obtained at a point. The work was motivated by the desire to understand the extent to which high-frequency profiles of the atmosphere (e.g. ARM data streams) can be used to assess the magnitude of non-plane parallel transfer of radiation in thc atmosphere. We accomplished this by performing an observing system simulation using a large-eddy simulation and a Monte Carlo radiative transfer model. We define the 3D effect as the part of the radiative transfer that isn't captured by one-dimensional radiative transfer calculations. We assess the magnitude of the 3D effect in small cumulus clouds by using a fine-scale cloud model to simulate many hours of cloudiness over a continental site. We then use a Monte Carlo radiative transfer model to compute the broadband shortwave fluxes at the surface twice, once using the complete three-dimensional radiative transfer F(sup 3D), and once using the ICA F (sup ICA); the difference between them is the 3D effect given.

Source record↗

Active Flash: Performance-Energy Tradeoffs for Out-of-Core Processing on Non-Volatile Memory Devices

In this abstract, we study the performance and energy tradeoffs involved in migrating data analysis into the flash device, a process we refer to as Active Flash. The Active Flash paradigm is similar to 'active disks', which has received considerable attention. Active Flash allows us to move processing closer to data, thereby minimizing data movement costs and reducing power consumption. It enables true out-of-core computation. The conventional definition of out-of-core solvers refers to an approach to process data that is too large to fit in the main memory and, consequently, requires access to disk. However, in Active Flash, processing outside the host CPU literally frees the core and achieves real 'out-of-core' analysis. Moving analysis to data has long been desirable, not just at this level, but at all levels of the system hierarchy. However, this requires a detailed study on the tradeoffs involved in achieving analysis turnaround under an acceptable energy envelope. To this end, we first need to evaluate if there is enough computing power on the flash device to warrant such an exploration. Flash processors require decent computing power to run the internal logic pertaining to the Flash Translation Layer (FTL), which is responsible for operations such as address translation, garbage collection (GC) and wear-leveling. Modern SSDs are composed of multiple packages and several flash chips within a package. The packages are connected using multiple I/O channels to offer high I/O bandwidth. SSD computing power is also expected to be high enough to exploit such inherent internal parallelism within the drive to increase the bandwidth and to handle fast I/O requests. More recently, SSD devices are being equipped with powerful processing units and are even embedded with multicore CPUs (e.g. ARM Cortex-A9 embedded processor is advertised to reach 2GHz frequency and deliver 5000 DMIPS; OCZ RevoDrive X2 SSD has 4 SandForce controllers, each with 780MHz max frequency Tensilica core). Efforts that take advantage of the available computing cycles on the processors on SSDs to run auxiliary tasks other than actual I/O requests are beginning to emerge. Kim et al. investigate database scan operations in the context of processing on the SSDs, and propose dedicated hardware logic to speed up scans. Also, cluster architectures have been explored, which consist of low-power embedded CPUs coupled with small local flash to achieve fast, parallel access to data. Processor utilization on SSD is highly dependent on workloads and, therefore, they can be idle during periods with no I/O accesses. We propose to use the available processing capability on the SSD to run tasks that can be offloaded from the host. This paper makes the following contributions: (1) We have investigated Active Flash and its potential to optimize the total energy cost, including power consumption on the host and the flash device; (2) We have developed analytical models to analyze the performance-energy tradeoffs for Active Flash, by treating the SSD as a blackbox, this is particularly valuable due to the proprietary nature of the SSD internal hardware; and (3) We have enhanced a well-known SSD simulator (from MSR) to implement 'on-the-fly' data compression using Active Flash. Our results provide a window into striking a balance between energy consumption and application performance.

42 ENGINEERING↗

Optimal solutions for complex design problems: Using isoperformance software for human factors trade offs

A major application of isoperformance is as a trade-off methodology of the three major drivers of system design; equipment, training variables, and user characteristics. The flexibility of isoperformance allows each of these three components to be nearly any rational variation. For example, aptitude may be military Armed Forces Qualification Testing (AFQT) categories, cutoff scores within a selection procedure, or simply dichotomizing high and low scorers (pass/fail). Equipment may be new versus old, 'smart' versus dumb, high versus low resolution, etc. Training may be short versus long or varieties of media types (lecture versus CAI/CBI versus self-paced workbooks). In its final computerized form isoperformance lets the user set an operational level of performance (e.g., a jet pilot in a simulated emergency must take prescribed corrective action and clear the plane in several seconds, pilot astronauts will check out all shuttle flight systems within 30 minutes, or Mission Specialists must handle sucdessfully a required number of job elements). At this point the computer program guides the user through any requested trade-offs of the three components while maintaining the specified operational level of performance through isoperformance curves. A demonstration of the computer program is currently available.

Kennedy, Robert S.↗

RoboLab and virtual environments

A useful adjunct to the manned space station would be a self-contained free-flying laboratory (RoboLab). This laboratory would have a robot operated under telepresence from the space station or ground. Long duration experiments aboard RoboLab could be performed by astronauts or scientists using telepresence to operate equipment and perform experiments. Operating the lab by telepresence would eliminate the need for life support such as food, water and air. The robot would be capable of motion in three dimensions, have binocular vision TV cameras, and two arms with manipulators to simulate hands. The robot would move along a two-dimensional grid and have a rotating, telescoping periscope section for extension in the third dimension. The remote operator would wear a virtual reality type headset to allow the superposition of computer displays over the real-time video of the lab. The operators would wear exoskeleton type arms to facilitate the movement of objects and equipment operation. The combination of video displays, motion, and the exoskeleton arms would provide a high degree of telepresence, especially for novice users such as scientists doing short-term experiments. The RoboLab could be resupplied and samples removed on other space shuttle flights. A self-contained RoboLab module would be designed to fit within the cargo bay of the space shuttle. Different modules could be designed for specific applications, i.e., crystal-growing, medicine, life sciences, chemistry, etc. This paper describes a RoboLab simulation using virtual reality (VR). VR provides an ideal simulation of telepresence before the actual robot and laboratory modules are constructed. The easy simulation of different telepresence designs will produce a highly optimum design before construction rather than the more expensive and time consuming hardware changes afterwards.

Giarratano, Joseph C.↗

Automatic Generation of High-Performance Convolution Kernels on ARM CPUs for Deep Learning

In this work, we present FastConv, a template-based code auto-generation open source library that can automatically generate high-performance deep learning convolution kernels of arbitrary matrices/tensors shapes. FastConv is based on the Winograd algorithm, which is reportedly the highest performing algorithm for the time-consuming convolution layers of convolutional neural networks. ARM CPUs cover a wide range designs and specifications, from embedded devices to HPC-grade CPUs. The leads to the dilemma of how to consistently optimize Winograd-based convolution solvers for convolution layers of different shapes. FastConv addresses this problem by using templates to auto-generate multiple shapes of tuned kernels variants suitable for skinny tall matrices. As a performance portable library, FastConv transparently searches for the best combination of kernel shapes, cache tiles, scheduling of loop orders, packing strategies, access patterns, and online/offline computations. Auto-tuning is used to search the parameter configuration space for the best performance for a given target architecture and problem size. The experiments with layer-wise evaluation on the VGG--16 model confirms a 1.25x performance gains is got by tuning the Winograd library. Integrated comparison results shows 1.02x to 1.40x, 1.14x to 2.17x, and 1.22x and 2.48x speedup is achieved over NNPACK, Arm NN, and FeatherCNN on the Kunpeng 920 beside few cases. Furthermore, problem size performance portability experiments with various convolution shapes shows that FastConv achieves 1.2x to 1.7x speedup and 2x to 22x speedup over NNPACK and ARM NN inference engine using Winograd on Kunpeng 920 . CPU performance portability evaluation on the VGG--16 show an average speedup over NNPACK of 1.42x, 1.21x, 1.26x, 1.37x, 2.26x, and 11.02x is observed on Kunpeng 920, Snapdragon 835, 855, 888, Apple M1, and AWS Graviton2, respectively.

97 MATHEMATICS AND COMPUTING↗

Imaging for dismantlement verification: information management and analysis algorithms

The level of detail discernible in imaging techniques has generally excluded them from consideration as verification tools in inspection regimes. An image will almost certainly contain highly sensitive information, and storing a comparison image will almost certainly violate a cardinal principle of information barriers: that no sensitive information be stored in the system. To overcome this problem, some features of the image might be reduced to a few parameters suitable for definition as an attribute. However, this process must be performed with care. Computing the perimeter, area, and intensity of an object, for example, might reveal sensitive information relating to shape, size, and material composition. This paper presents three analysis algorithms that reduce full image information to non-sensitive feature information. Ultimately, the algorithms are intended to provide only a yes/no response verifying the presence of features in the image. We evaluate the algorithms on both their technical performance in image analysis, and their application with and without an explicitly constructed information barrier. The underlying images can be highly detailed, since they are dynamically generated behind the information barrier. We consider the use of active (conventional) radiography alone and in tandem with passive (auto) radiography.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

WE-G-18A-01: JUNIOR INVESTIGATOR WINNER - Low-Dose C-Arm Cone-Beam CT with Model-Based Image Reconstruction for High-Quality Guidance of Neurosurgical Intervention

Purpose: To address the challenges of image quality, radiation dose, and reconstruction speed in intraoperative cone-beam CT (CBCT) for neurosurgery by combining model-based image reconstruction (MBIR) with accelerated algorithmic and computational methods. Methods: Preclinical studies involved a mobile C-arm for CBCT imaging of two anthropomorphic head phantoms that included simulated imaging targets (ventricles, soft-tissue structures/bleeds) and neurosurgical procedures (deep brain stimulation (DBS) electrode insertion) for assessment of image quality. The penalized likelihood (PL) framework was used for MBIR, incorporating a statistical model with image regularization via an edgepreserving penalty. To accelerate PL reconstruction, the ordered-subset, separable quadratic surrogates (OS-SQS) algorithm was modified to incorporate Nesterov's method and implemented on a multi-GPU system. A fair comparison of image quality between PL and conventional filtered backprojection (FBP) was performed by selecting reconstruction parameters that provided matched low-contrast spatial resolution. Results: CBCT images of the head phantoms demonstrated that PL reconstruction improved image quality (∼28% higher CNR) even at half the radiation dose (3.3 mGy) compared to FBP. A combination of Nesterov's method and fast projectors yielded a PL reconstruction run-time of 251 sec (cf., 5729 sec for OS-SQS, 13 sec for FBP). Insertion of a DBS electrode resulted in severe metal artifact streaks in FBP reconstructions, whereas PL was intrinsically robust against metal artifact. The combination of noise and artifact was reduced from 32.2 HU in FBP to 9.5 HU in PL, thereby providing better assessment of device placement and potential complications. Conclusion: The methods can be applied to intraoperative CBCT for guidance and verification of neurosurgical procedures (DBS electrode insertion, biopsy, tumor resection) and detection of complications (intracranial hemorrhage). Significant improvement in image quality, dose reduction, and reconstruction time of ∼4 min will enable practical deployment of low-dose C-arm CBCT within the operating room. AAPM Research Seed Funding (2013-2014); NIH Fellowship F32EB017571; Siemens Healthcare (XP Division)

60 APPLIED LIFE SCIENCES↗