Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Compiler 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 361 records · Page 20
All sourcesNASA NTRSDOE OSTI
DOE OSTI2019

Robust and High-Waste Loaded Glass Formulations for Hanford Low-Activity Waste - 19050

The Hanford Low-Activity Waste (LAW) vitrification facility will receive LAW batches with abruptly changing compositions that span relatively broad ranges. In particular, the concentration ratios of sodium-to-sulfate, -chloride, -chromate, -phosphate, -potassium, and -aluminate create challenges in glass formulation. Glass compositions that simultaneously satisfy several processability, product quality, and composition constraints with sufficient confidence must be formulated for each LAW batch in near-realtime to enable desired throughput. A method for developing glass compositions while maximizing the waste loading and the process robustness was developed. This method compiled the glass composition-property data collected over nearly two decades, primarily by Pacific Northwest National Laboratory, The Catholic University of America, and Savannah River National Laboratory, in support of both the Hanford Tank Waste Treatment and Immobilization Plant project and the U.S. Department of Energy Office of River Protection Enhanced Waste Glass project. These data were used to develop models that link the melter feed composition to the resulting glass properties. Mathematical constructs were developed to optimize glass compositions for each waste batch in real-time that will simultaneously satisfy processability, product quality, and composition constraints with sufficient statistical confidence. Property prediction and various process uncertainties were reflected in the formulation. The formulation approach directly lends itself to adjustment of glass formulation to achieve program goals. This presentation will summarize the formulation approach and supporting data. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
NASA NTRS1989

OPTICON: Pro-Matlab software for large order controlled structure design

A software package for large order controlled structure design is described and demonstrated. The primary program, called OPTICAN, uses both Pro-Matlab M-file routines and selected compiled FORTRAN routines linked into the Pro-Matlab structure. The program accepts structural model information in the form of state-space matrices and performs three basic design functions on the model: (1) open loop analyses; (2) closed loop reduced order controller synthesis; and (3) closed loop stability and performance assessment. The current controller synthesis methods which were implemented in this software are based on the Generalized Linear Quadratic Gaussian theory of Bernstein. In particular, a reduced order Optimal Projection synthesis algorithm based on a homotopy solution method was successfully applied to an experimental truss structure using a 58-state dynamic model. These results are presented and discussed. Current plans to expand the practical size of the design model to several hundred states and the intention to interface Pro-Matlab to a supercomputing environment are discussed.

Peterson, Lee D.↗
DOE OSTI2025

Genetic tools for engineering Zymomonas mobilis , Cereibacter sphaeroides and Novosphingobium aromaticivorans to improve production of bioenergy compounds

Limited genetic tools for non-model bacteria are one of the limiting factors for genetic studies. This review compiles genetic tools used for three non-model alpha-proteobacteria, such as Zymomonas mobilis, Cereibacter (Rhodobacter) sphaeroides, and Novosphingobium aromaticivorans, which hold significant potential to produce industrially essential bioenergy compounds due to their distinctive metabolic pathways and resilience in extreme environments. Each of these strains has a unique genetic profile that enables them to efficiently carry out key reactions relevant to producing bioenergy compounds, such as converting sugars into bioenergy compounds and breaking down lignotoxins. Genetic tools can further optimize these strains for enhanced bioenergy compound production. This review explores the metabolic advantages of these organisms. It highlights the available array of genetic toolkits that can be shared among them to unlock their full potential for sustainable biofuel production.

Biofuel↗
DOE OSTI2019

Roll-to-Roll Advanced Materials Manufacturing DOE Laboratory Collaboration - FY2018 Final Report

High-value R2R processing is used to support a wide range of products in applications which span many industrial business sectors. The overall R2R process technology can be considered as “mature” as the process methodology and has been in use for decades. This continuous processing technique traditionally involves deposition of material(s) onto moving webs or carriers or other continuous R2R, belt-fed, or conveyor-based processes that enable successive steps to build a final version which serves to support the deposited materials. Current process technologies, which typify “roll to roll”, include tape casting, silk-screen printing, reel-to-reel vacuum deposition/coating and R2R lithography. Products supported by R2R manufacturing include micro-electronics, electro-chromic window films, PVs, fuel cells for energy conversion, battery electrodes for energy storage, and barrier materials. Due to innovation in materials and process equipment, high-quality yet very low-cost multi-layer technologies can be manufactured on a very cost-competitive basis. To move energy-related products from high-cost niche applications to the commercial sector, a means must be available to enable manufacture of these products in a cost-competitive manner that is affordable by the general consumer. Fortunately, products such as fuel cells, thin- and mid-film PVs, batteries, electrochromic and piezoelectric films, water separation membranes, and other energy saving technologies readily lend themselves to manufacture using R2R approaches.Within the DOE EERE AMO, it was recognized that establishment of a program supported at the DOE National Laboratories, along with their immense design of materials and equipment modelling capabilities enabled with use of high-performance computing, could take advantage of available R2R infrastructure to manufacture new technologies. In FY 2016, a R2R Consortium was established and provided with initial “seed” funding to take an approach that was envisioned to be supportable by advanced manufacturing R2R processes. This collaborative approach was designed to foster identification and development of materials and processes related to R2R for clean-energy product development. Using computational and experimental capabilities by acknowledged subject matter experts within the supported National Laboratory system, this collaborative project would leverage the capabilities and expertise at each of four laboratories to further the development of an enabling high-volume cost-competitive platform technology. The collaboration team that is comprised of ORNL, ANL, NREL and LBNL, coordinating with EPB and other selected industry partners, was formed in April 2016 to initially address enhancing battery electrode performance and R2R manufacturing challenges. The research efforts were to predict and measure changes and results in electrode morphology and performance based on process condition changes; to evaluate mixed, active, particle size deposition and drying for novel electrode materials; to model various process condition changes and the resulting morphology and electrode performance; and to develop and validate NDE techniques for in-line measurement of battery electrode material properties. These efforts carried through FY 2017 and completed at the end of FY 2018.The approach was to look at compositions of materials with different particle sizes to make electrode samples using a R2R manufacturing process. The shape, size, and morphology of the materials, the chemistry of the formulation, the nature of slurries, their coating rate, the rate of drying all play a role in determining the final coating architecture, quality, and performance. A commercial cathode material was selected to make a series of cathodes and anodes by single pass, dual pass and slot die methods. Analysis of all the compiled results for this battery electrode development were that the best performing cathodes included: dual-pass electrode with large particles near the foil, mixed small and large particles, and small particles only. Whereas, the best performing anodes were with a mix of small and large graphite particles. An additional core project was added in FY 2017 to conduct studies of fuel cell materials that can be produced using R2R processes. The goal of this project is to explore, understand and optimize material and process parameters to support increased throughput, increased quality, and reduced cost for high volume production of gas-diffusion electrodes (GDEs) for PEMFCs. Project work in FY 2018 were to use a R2R process to fabricate electrodes without ionomer overlayer that can produce the equivalent mass activity as spray-coated electrodes with an ionomer overlayer. Oxygen-limiting current measurements were utilized to optimize oxygen mass transport. Alcohol-rich solvents were investigated, and results were that the alcohol and water ratio can be tuned to control ionomer distribution. Water-rich solvents produce a more dispersed ink which results in better high-current density performance.

36 MATERIALS SCIENCE↗
NASA NTRS2003

Self-Directed Cooperative Planetary Rovers

The project is concerned with the development of decision-theoretic techniques to optimize the scientific return of planetary rovers. Planetary rovers are small unmanned vehicles equipped with cameras and a variety of sensors used for scientific experiments. They must operate under tight constraints over such resources as operation time, power, storage capacity, and communication bandwidth. Moreover, the limited computational resources of the rover limit the complexity of on-line planning and scheduling. We have developed a comprehensive solution to this problem that involves high-level tools to describe a mission; a compiler that maps a mission description and additional probabilistic models of the components of the rover into a Markov decision problem; and algorithms for solving the rover control problem that are sensitive to the limited computational resources and high-level of uncertainty in this domain.

Zilberstein, Shlomo↗
NASA NTRS1991

Branch strategies - Modeling and optimization

The authors provide a common platform for modeling different schemes for reducing the branch-delay penalty in pipelined processors as well as evaluating the associated increased instruction bandwidth. Their objective is twofold: to develop a model for different approaches to the branch problem and to help select an optimal strategy after taking into account additional i-traffic generated by branch strategies. The model presented provides a flexible tool for comparing different branch strategies in terms of the reduction it offers in average branch delay and also in terms of the associated cost of wasted instruction fetches. This additional criterion turns out to be a valuable consideration in choosing between two strategies that perform almost equally. More importantly, it provides a better insight into the expected overall system performance. Simple compiler-support-based low-implementation-cost strategies can be very effective under certain conditions. An active branch prediction scheme based on loop buffers can be as competitive as a branch-target-buffer based strategy.

Dubey, Pradeep K.↗
DOE OSTI2025

A Synthesis Methodology for Intelligent Memory Interfaces in Accelerator Systems

Domain-specific systems improve the performance of a specific set of applications compared to general-purpose processing systems by deploying custom hardware accelerators. These hardware accelerators are generated using high-level synthesis (HLS) tools. The HLS tools enable a comprehensive design space exploration to optimize the compute performance of the generated accelerators. However, they often ignore the challenges of implementing the accelerators in a system-on-chip, particularly how the accelerators access memory. Our work introduces a buffering system design that improves accelerators' memory accesses by intelligently employing burst transactions to prefetch useful data from external memory to on-chip local buffers. Our design is dynamic, parametric, and transparent to the accelerators generated by HLS tools. We derive the buffering system parameters using appropriate compiler-based analysis passes and memory channel latency constraints. The proposed buffering system design results in, on average, 8.8x performance improvements while lowering memory channel utilization on average by 53.2% for a set of PolyBench kernels.

Limaye, Ankur M. (ORCID:0000000194062584)↗
DOE OSTI2023

Usability and Optimization Improvements in MOOSE

The Multiphysics Object-Oriented Simulation Environment (MOOSE) framework is a foundational capability used by the Nuclear Energy Advanced Modeling and Simulation (NEAMS) program to create over 15 different simulation tools for advanced nuclear reactors. Due to MOOSE’s broad use, improvements to the framework in support of modeling and simulation goals are critical to the program. Such improvements can take many forms, including optimization, improved user experience, streamlined application programming interfaces (APIs), parallelism, and new capabilities. The work described in this report was conducted in direct support of the simulation tools and has already been deployed. The capabilities were implemented in the same order as they are covered in this report: multiple nonlinear systems in the same input file, implementation of generic field transfers and other transfer system enhancements, support for stateful material property redistribution for adaptivity and distributed meshes, and dynamic linking and loading of individually compiled applications. These four additions are fundamental capabilities that will be leveraged by many NEAMS applications.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Mapping Spiking Neural Networks to Heterogeneous Crossbar Architectures using Integer Linear Programming

Advances in novel hardware devices and architectures allow Spiking Neural Network (SNN) evaluation using ultra-low power, mixed-signal, memristor crossbar arrays. As individual network sizes quickly scale beyond the dimensional capabilities of single crossbars, networks must be mapped onto multiple crossbars. Crossbar sizes within modern Memristor Crossbar Architectures (MCAs) are determined predominately not by device technology but by network topology; more, smaller crossbars consume less area thanks to the high structural sparsity found in larger, brain-inspired SNNs. Motivated by continuing increases in SNN sparsity due to improvements in training methods, we propose utilizing heterogeneous crossbar sizes to further reduce area consumption. This approach was previously unachievable as prior compiler studies only explored solutions targeting homogeneous MCAs. Our work improves on the state-of-the-art by providing Integer Linear Programming (ILP) formulations supporting arbitrarily heterogeneous architectures. By modeling axonal interactions between neurons, our methods produce better mappings while removing inhibitive a priori knowledge requirements. We first show a 16.7-27.6% reduction in area consumption for square-crossbar homogeneous architectures. Then, we demonstrate 66.9-72.7% further reduction when using a reasonable configuration of heterogeneous crossbar dimensions. Next, we present a new optimization formulation capable of minimizing the number of inter-crossbar routes. When applied to solutions already near-optimal in area, an 11.9-26.4% routing reduction is observed without impacting area consumption. Finally, we present a profile-guided optimization capable of minimizing the number of runtime spikes between crossbars. Compared to the best-area-then-route optimized solutions, we observe a further 0.5-14.8% inter-crossbar spike reduction while requiring 1–3 orders of magnitude less solver time.

Pohl, Devin [ORNL] (ORCID:0009000040149027)↗
DOE OSTI2024

Cross-Feature Transfer Learning for Efficient Tensor Program Generation

Tuning tensor program generation involves navigating a vast search space to find optimal program transformations and measurements for a program on the target hardware. The complexity of this process is further amplified by the exponential combinations of transformations, especially in heterogeneous environments. This research addresses these challenges by introducing a novel approach that learns the joint neural network and hardware features space, facilitating knowledge transfer to new, unseen target hardware. A comprehensive analysis is conducted on the existing state-of-the-art dataset, TenSet, including a thorough examination of test split strategies and the proposal of methodologies for dataset pruning. Leveraging an attention-inspired technique, we tailor the tuning of tensor programs to embed both neural network and hardware-specific features. Notably, our approach substantially reduces the dataset size by up to 53% compared to the baseline without compromising Pairwise Comparison Accuracy (PCA). Furthermore, our proposed methodology demonstrates competitive or improved mean inference times with only 25–40% of the baseline tuning time across various networks and target hardware. The attention-based tuner can effectively utilize schedules learned from previous hardware program measurements to optimize tensor program tuning on previously unseen hardware, achieving a top-5 accuracy exceeding 90%. This research introduces a significant advancement in autotuning tensor program generation, addressing the complexities associated with heterogeneous environments and showcasing promising results regarding efficiency and accuracy.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Extending JuTrack’s capabilities to the FRIB accelerator to enhance online modeling

JuTrack is a Julia-based accelerator modeling and tracking package that utilizes compiler-level automatic differentiation (AD) to enable fast and accurate derivative calculations. While JuTrack provides a solid foundation for beam dynamics simulations, its capabilities must be extended to support the Facility for Rare Isotopes (FRIB) linac. This includes modeling heavy-ion linac accelerator components such as the liquid-lithium charge stripper, which facilitates efficient acceleration by remove electrons from heavy isotopes, and incorporating multi-charge state acceleration tracking, which allows for charge-dependent beam dynamics. These extensions address challenges such as the beam matching and optimization of multi charge state through various accelerating structures and beam-material interaction modeling while maintaining the auto differentiation capability. This work focuses on adapting JuTrack to incorporate these elements, enhancing its online modeling abilities. We present modifications to JuTrack’s framework and demonstrate their performance in FRIB simulations.

Accelerator Physics↗
NASA NTRS2020

Characterization of International Space Station Crew Members' Workload Contributing to Fatigue, Sleep Disruption and Circadian De-synchronization

The focus of this paper is to characterize how the International Space Station (ISS) crewmembers’ workload may be contributing to sleep loss, circadian misalignment and fatigue. Both sleep quantity and subjective sleep quality are reduced in ISS crewmembers (Barger, Flynn-Evans, Kubey, Walsh, Ronda, Wang, Wright, & Czeisler, 2014). Evidence indicates that the use of hypnotic drugs does not appear to promote extended sleep duration. Because sleep is often driven by psychosocial as well as somatic attributes, traditional therapies may only partially moderate the problem for some individuals. Accordingly, searching for additional abatement tactics is a sensible plan. Scientific studies have shown that sleep can be disrupted from work-related stressors. On the ISS, to optimize their time, the crewmembers follow prescribed, ambitious and rigorous schedules with shared deadlines. Here it will be argued that these human capital leveraging techniques may be undermining the astronaut’s sleep, which could negatively impact performance. Along with half of the Earth-bound working population (Paoli & Merllié, 2001), ISS crewmembers may not be adequately recovering from their workload. This paper begins with a characterization of the working conditions of ISS crewmembers, describes the development of rigorous schedules and portrays a typical workday. Terrestrially-based research is compiled to describe how full and partial sleep deprivation affect physical and cognitive performance and how ISS work characteristics may disrupt sleep and subsequent performance. The literature points toward potential solutions to astronaut fatigue that is related to their workload. Finally, throughout the text, evidence is provided from semi-structured interviews, biographies and textual databases to support the argument that astronaut workload is contributing to their sleep loss and fatigue and that research, development and mitigation strategies should focus on enhancing the restorative process.

fatigue↗
NASA NTRS2004

The Role of Ontologies in Schema-based Program Synthesis

Program synthesis is the process of automatically deriving executable code from (non-executable) high-level specifications. It is more flexible and powerful than conventional code generation techniques that simply translate algorithmic specifications into lower-level code or only create code skeletons from structural specifications (such as UML class diagrams). Key to building a successful synthesis system is specializing to an appropriate application domain. The AUTOBAYES and AUTOFILTER systems, under development at NASA Ames, operate in the two domains of data analysis and state estimation, respectively. The central concept of both systems is the schema, a representation of reusable computational knowledge. This can take various forms, including high-level algorithm templates, code optimizations, datatype refinements, or architectural information. A schema also contains applicability conditions that are used to determine when it can be applied safely. These conditions can refer to the initial specification, to intermediate results, or to elements of the partially-instantiated code. Schema-based synthesis uses AI technology to recursively apply schemas to gradually refine a specification into executable code. This process proceeds in two main phases. A front-end gradually transforms the problem specification into a program represented in an abstract intermediate code. A backend then compiles this further down into a concrete target programming language of choice. A core engine applies schemas on the initial problem specification, then uses the output of those schemas as the input for other schemas, until the full implementation is generated. Since there might be different schemas that implement different solutions to the same problem this process can generate an entire solution tree. AUTOBAYES and AUTOFILTER have reached the level of maturity where they enable users to solve interesting application problems, e.g., the analysis of Hubble Space Telescope images. They are large (in total around 100kLoC Prolog), knowledge intensive systems that employ complex symbolic reasoning to generate a wide range of non-trivial programs for complex application do- mains. Their schemas can have complex interactions, which make it hard to change them in isolation or even understand what an existing schema actually does. Adding more capabilities by increasing the number of schemas will only worsen this situation, ultimately leading to the entropy death of the synthesis system. The root came of this problem is that the domain knowledge is scattered throughout the entire system and only represented implicitly in the schema implementations. In our current work, we are addressing this problem by making explicit the knowledge from Merent parts of the synthesis system. Here; we discuss how Gruber's definition of an ontology as an explicit specification of a conceptualization matches our efforts in identifying and explicating the domain-specific concepts. We outline the dual role ontologies play in schema-based synthesis and argue that they address different audiences and serve different purposes. Their first role is descriptive: they serve as explicit documentation, and help to understand the internal structure of the system. Their second role is prescriptive: they provide the formal basis against which the other parts of the system (e.g., schemas) can be checked. Their final role is referential: ontologies also provide semantically meaningful "hooks" which allow schemas and tools to access the internal state of the program derivation process (e.g., fragments of the generated code) in domain-specific rather than language-specific terms, and thus to modify it in a controlled fashion. For discussion purposes we use AUTOLINEAR, a small synthesis system we are currently experimenting with, which can generate code for solving a system of linear equations, Az = b.

Bures, Tomas↗
DOE OSTI2023

Numerical Circuit Synthesis and Compilation for Multi-State Preparation

Near-term quantum computers have significant error rates and short coherence times, so compilation of circuits to be as short as possible is essential. Two types of compilation problems are typically considered: circuits to prepare a given state from a fixed input state, called 'state preparation'; and circuits to implement a given unitary operation, for example by 'unitary synthesis'. In this paper we solve a more general problem: the transformation of a set of m states to another set of m states, which we call 'multi-state preparation'. State preparation and unitary synthesis are special cases; for state preparation, m=1, while for unitary synthesis, m is the dimension of the full Hilbert space. We generate and optimize circuits for multi-state preparation numerically. In cases where a top-down approach based on matrix decompositions is also possible, our method finds circuits with substantially (up to 40 %) fewer two-qubit gates. We discuss possible applications, including efficient preparation of macroscopic superposition ('cat') states and synthesis of quantum channels.

Szasz, Aaron↗
NASA NTRS2021

Performance of JAXA’s SGLI standard ocean color products for oceanic to coastal waters: chlorophyll a concentration and light absorption coefficients of colored dissolved organic matter

We present the performance of JAXA’s SGLI standard algorithms for estimating chlorophyll a (chl a) concentration and the light absorption coefcients of colored dissolved organic matter (CDOM) using recently compiled high-quality data obtained from oceanic to coastal waters. Prior to the evaluation of the algorithms, we frst compare two forward models (Gordon et al. in J Geophys Res 93(D9):10909-10924, 1988: G88 and Park and Ruddick in Appl Opt 44(7):1236–1249, 2005: PR05) using a wide range of inherent optical properties (IOPs) to (1) examine if the water refectance is appropriately reproduced and (2) correct measured refectance in terms of its bidirectionality. Based on a good reproducibility of water refectance using the PR05, the optimized IOPs are further used for explaining errors in estimates of chl a concentration and CDOM absorption when using the SGLI, the GSM (Maritorena et al. in Appl Opt 41:2705–2714, 2002), and the QAA (Lee et al. in Appl Opt 41:5755, 2002) inversion algorithms. Results show that the mean error for estimating chl a concentration using the SGLI algorithm is 110% for our dataset. Although this error is lower than that of the GSM and the QAA algorithms, a signifcant underestimate at chl a higher than 2.0 mg m−3 is observed, which is further shown by independent match-up analyses. Another SGLI CDOM product includes the mean error of 50% and shows deviation at high CDOM range (>1.0 per m). A similar trend is observed for the GSM but not for the QAA when a global relationship of CDOM to colored detrital matter is applied. The sources of errors are discussed for potentially improving the retrievals

Second-generation GLobal Imager (SGLI)↗
DOE OSTI2020

Use of the Manuela 3D/Radiation Scanning Tool at Nuclear Facilities - 20437

Licensees, facility operators and decommissioning contractors have a need for comprehensive, accurate and precise radiological and topographical data to plan and execute safe and efficient Decontamination and Decommissioning (D and D) projects. Traditional approaches rely greatly upon labor and administratively intensive data collection methods that require considerable time and effort to glean the relevant data to plan and perform work in a radiological work area. Orano Decommissioning Services has developed and utilized at French nuclear facilities a lightweight portable scanning instrument called MANUELA (Mobile Apparatus for Nuclear Expertise Localization Assistance). Recently Orano conducted demonstrations at two United States nuclear facilities using MANUELA that may prove useful in areas of the fuel cycle including: - ALARA (As Low As Reasonably Achievable) planning during facility operations; - Scoping and site characterization during the D and D planning phase; - Remedial action support during active decommissioning work; - Radiation and modeling planning for plant modifications; - Support Final Status Survey and demonstration of 'end state' compliance for license termination. MANUELA is currently being evaluated for use during decommissioning of nuclear facilities and could aide in demonstrating compliance with end state criteria after decommissioning. Of particular interest are decommissioning projects planned for various sites across the United States. Most of these sites present unique challenges and opportunities to safely and efficiently decommission in a regulatory compliant manner. The two demonstration site's current conditions of relatively low radiation levels inside containment proved to be ideal platforms to deploy the MANUELA instrument for evaluation of the complex geometries typically found in a nuclear facility. The MANUELA instrument was able to precisely identify local hot spots of the reactor system's primary equipment and was able to simultaneously overlay the dose information onto the scanned 3D images. Using data like this, a licensee would be able to make informed technical and personnel decisions on methods to remediate, shield or properly dispose of the radioactive source term. MANUELA can be used throughout the decommissioning process to validate progress and continue to refine the work activities to optimize the efforts of the crew which reduces downtime waiting for survey results, whereas traditional survey methodology relies on a physical survey to be performed and the data transcribed onto survey maps that are only two dimensional. The traditional format tends to be inaccurate and difficult to interpret the precise location(s) of hot spots or generalized dose rates. The resultant scan also allows the user to know the exact extent of the survey versus transposing information onto a map with only a portion of the map area scanned. MANUELA also compiles all of the relevant survey data into a downloadable table format which includes the measurement identification number, time stamp, point space location on the XYZ plane, and the dose rate value. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
NASA NTRS1996

Algorithms for Automatic Alignment of Arrays

Aggregate data objects (such as arrays) are distributed across the processor memories when compiling a data-parallel language for a distributed-memory machine. The mapping determines the amount of communication needed to bring operands of parallel operations into alignment with each other. A common approach is to break the mapping into two stages: an alignment that maps all the objects to an abstract template, followed by a distribution that maps the template to the processors. This paper describes algorithms for solving the various facets of the alignment problem: axis and stride alignment, static and mobile offset alignment, and replication labeling. We show that optimal axis and stride alignment is NP-complete for general program graphs, and give a heuristic method that can explore the space of possible solutions in a number of ways. We show that some of these strategies can give better solutions than a simple greedy approach proposed earlier. We also show how local graph contractions can reduce the size of the problem significantly without changing the best solution. This allows more complex and effective heuristics to be used. We show how to model the static offset alignment problem using linear programming, and we show that loop-dependent mobile offset alignment is sometimes necessary for optimum performance. We describe an algorithm with for determining mobile alignments for objects within do loops. We also identify situations in which replicated alignment is either required by the program itself or can be used to improve performance. We describe an algorithm based on network flow that replicates objects so as to minimize the total amount of broadcast communication in replication.

Chatterjee, Siddhartha↗
NASA NTRS2016

High-Performance Reaction Wheel Optimization for Fine-Pointing Space Platforms: Minimizing Induced Vibration Effects on Jitter Performance plus Lessons Learned from Hubble Space Telescope for Current and Future Spacecraft Applications

The Hubble Space Telescope (HST) applies large-diameter optics (2.5-m primary mirror) for diffraction-limited resolution spanning an extended wavelength range (approx. 100-2500 nm). Its Pointing Control System (PCS) Reaction Wheel Assemblies (RWAs), in the Support Systems Module (SSM), acquired an unprecedented set of high-sensitivity Induced Vibration (IV) data for 5 flight-certified RWAs: dwelling at set rotation rates. Focused on 4 key ratios, force and moment harmonic values (in 3 local principal directions) are extracted in the RWA operating range (0-3000 RPM). The IV test data, obtained under ambient lab conditions, are investigated in detail, evaluated, compiled, and curve-fitted; variational trends, core causes, and unforeseen anomalies are addressed. In aggregate, these values constitute a statistically-valid basis to quantify ground test-to-test variations and facilitate extrapolations to on-orbit conditions. Accumulated knowledge of bearing-rotor vibrational sources, corresponding harmonic contributions, and salient elements of IV key variability factors are discussed. An evolved methodology is presented for absolute assessments and relative comparisons of macro-level IV signal magnitude due to micro-level construction-assembly geometric details/imperfections stemming from both electrical drive and primary bearing design parameters. Based upon studies of same-size/similar-design momentum wheels' IV changes, upper estimates due to transitions from ground tests to orbital conditions are derived. Recommended HST RWA choices are discussed relative to system optimization/tradeoffs of Line-Of-Sight (LOS) vector-pointing focal-plane error driven by higher IV transmissibilities through low-damped structural dynamics that stimulate optical elements. Unique analytical disturbance results for orbital HST accelerations are described applicable to microgravity efforts. Conclusions, lessons learned, historical context/insights, and perspectives on future applications are given; these previously unpublished data and findings represents a valuable resource for fine-pointing spacecraft or space-based platforms using RWAs, Control Moment Gyros (CMGs), Momentum Wheels, or other ball-bearing-based rotational units.

Hasha, Martin D.↗