Results for “execution” — Page 4

NASA NTRS2020

Using a Model of Scheduler Runtime to Improve the Effectiveness of Scheduling Embedded in Execution

Scheduling often interacts with execution. When the scheduler is developing a schedule, real time (execution) proceeds. Usually a scheduler cannot modify portions of the schedule expected to start execution prior to the scheduler's expected completion. In deployed systems, often little effort is spent on predicting scheduler runtime and instead an extremely conservative, simple model is used, resulting in loss of performance as less of the schedule can be updated. We develop predictive model(s) of scheduler runtime and use these models to improve scheduler and execution performance. We present several models of scheduler runtime based on a scheduler being deployed onboard NASA's next Mars rover, the M2020 rover Perseverance. The models consider algorithmic complexity, characteristics of the input plan, and prior runtime data. First, we show how these still relatively unsophisticated models can more accurately predict scheduler runtime compared to the static conservative baseline being used for the actual M2020 onboard scheduler. Second, we show how the more accurate scheduler runtime models' tighter (shorter) runtime predictions enable better scheduler performance as measured by makespan and percentage of activities executed. Finally, we discuss a number of future steps to further advance this line of work.

Chi, Wayne↗

NASA NTRSDate not supplied

A Discussion of Time Management Concepts and Time Constraint Equations for Multi-Rate Federation Executions

The High Level Architecture (HLA) is a simulation interoperability standard developed by the Simulation Interoperability Standards Organization (SISO) and published as the international standard IEEE 1516-2010 by the Institute for Electrical and Electronics Engineers (IEEE). HLA is a widely used standard for the development and execution of collaborative distributed simulations. HLA provides a number of Management Services to simulation developers: Federation, Declaration, Object, Ownership, Data Distribution, and Time. Of those services, Time Management Services is probably one of the least understood and least used. However, Time Management Services are critical to technical simulations like those created for space systems using the Space Reference Federation Object Model (SpaceFOM). Time Management can be used to insure data coherence and execution repeatability in distributed simulations. When combined with real time execution policies, Time Management is being used to support real time execution of mixed software and hardware in the loop integration, verification, and validation simulations for active space systems development. This paper starts by providing an overview of the HLA Time Management Services. This provides the background to discuss the challenges associated with Time Management and its use, starting with simple common rate frame scheduled simulations, then simple multi-rate simulations, and ending with complex mixed rate simulations. The authors then formulate the significant time constraint relationships between identified frame scheduling parameters. The intent of the paper is to provide a concise discussion of how to use Time Management in both simple cases and in more complex mixed frame rate federation executions.

Simulation Interoperability↗

NASA NTRSDate not supplied

A Discussion of Time Management Concepts and Time Constraint Equations for Multi-Rate Federation Executions

The High Level Architecture (HLA) is a simulation interoperability standard developed by the Simulation Interoperability Standards Organization (SISO) and published as the international standard IEEE 1516-2010 by the Institute for Electrical and Electronics Engineers (IEEE). HLA is a widely used standard for the development and execution of collaborative distributed simulations. HLA provides a number of Management Services to simulation developers: Federation, Declaration, Object, Ownership, Data Distribution, and Time. Of those services, Time Management Services is probably one of the least understood and least used. However, Time Management Services are critical to technical simulations like those created for space systems using the Space Reference Federation Object Model (SpaceFOM). Time Management can be used to insure data coherence and execution repeatability in distributed simulations. When combined with real time execution policies, Time Management is being used to support real time execution of mixed software and hardware in the loop integration, verification, and validation simulations for active space systems development. This paper starts by providing an overview of the HLA Time Management Services. This provides the background to discuss the challenges associated with Time Management and its use, starting with simple common rate frame scheduled simulations, then simple multi-rate simulations, and ending with complex mixed rate simulations. The authors then formulate the significant time constraint relationships between identified frame scheduling parameters. The intent of the paper is to provide a concise discussion of how to use Time Management in both simple cases and in more complex mixed frame rate federation executions.

Simulation Interoperability↗

NASA NTRS2013

Supporting Real-Time Operations and Execution through Timeline and Scheduling Aids

Since 2003, the NASA Ames Research Center has been actively involved in researching and advancing the state-of-the-art of planning and scheduling tools for NASA mission operations. Our planning toolkit SPIFe (Scheduling and Planning Interface for Exploration) has supported a variety of missions and field tests, scheduling activities for Mars rovers as well as crew on-board International Space Station and NASA earth analogs. The scheduled plan is the integration of all the activities for the day/s. In turn, the agents (rovers, landers, spaceships, crew) execute from this schedule while the mission support team members (e.g., flight controllers) follow the schedule during execution. Over the last couple of years, our team has begun to research and validate methods that will better support users during realtime operations and execution of scheduled activities. Our team utilizes human-computer interaction principles to research user needs, identify workflow processes, prototype software aids, and user test these. This paper discusses three specific prototypes developed and user tested to support real-time operations: Score Mobile, Playbook, and Mobile Assistant for Task Execution (MATE).

scheduling↗

NASA NTRS2014

Exact and Approximate Probabilistic Symbolic Execution

Probabilistic software analysis seeks to quantify the likelihood of reaching a target event under uncertain environments. Recent approaches compute probabilities of execution paths using symbolic execution, but do not support nondeterminism. Nondeterminism arises naturally when no suitable probabilistic model can capture a program behavior, e.g., for multithreading or distributed systems. In this work, we propose a technique, based on symbolic execution, to synthesize schedulers that resolve nondeterminism to maximize the probability of reaching a target event. To scale to large systems, we also introduce approximate algorithms to search for good schedulers, speeding up established random sampling and reinforcement learning results through the quantification of path probabilities based on symbolic execution. We implemented the techniques in Symbolic PathFinder and evaluated them on nondeterministic Java programs. We show that our algorithms significantly improve upon a state-of- the-art statistical model checking algorithm, originally developed for Markov Decision Processes.

Symbolic Execution↗

DOE OSTI2025

Advanced Fuels Campaign Execution Plan

The Advanced Fuels Campaign (AFC) Execution Plan details the strategy, mission, scope, and goals—both near-term and long-term—along with the structure and organization of nuclear fuels and materials research, development, and demonstration (RD&D) activities within the Fuel Cycle Technologies (FCT) program. The FCT program, tasked by the U.S. Department of Energy (DOE), employs a science-based approach to advance fuel technologies. This approach integrates theory, experiments, and multi-scale modeling and simulation (M&S) to develop a predictive understanding of fuel fabrication processes and fuel/cladding performance under irradiation, moving beyond traditional empirical methods. The long-term goals of the AFC are guided by the AFC Strategic Plan and align with the DOE Office of Nuclear Energy (NE) Roadmap [1], which outlines a multi-decade vision for demonstrating and qualifying advanced fuel forms to support diverse fuel cycle options. Near-term goals focus on enhancing accident tolerant fuels (ATF) for Light Water Reactors (LWR), a significant challenge that demands balancing immediate objectives with ongoing progress toward advanced reactor missions. Accelerating the traditional fuel qualification process to meet ATF objectives is another critical challenge. A detailed set of 5-year goals, summarized below, has been developed in line with the overarching science-based fuel development approach: • Advanced LWR Fuel Technologies: By 2027, support the development of advanced LWR fuel technologies with improved performance and enhanced accident tolerance. This includes high burnup (HBu), low enriched uranium (LEU)+, coated cladding, and doped fuel, aimed at complementing industry-led significant LWR uprates and plant refurbishments. • Tristructural Isotropic (TRISO) Fuel: Achieve qualification by 2028 and develop improved designs for emerging markets. • Metal Fuel: Achieve qualification by 2028 and develop improved designs for emerging markets. • Molten Salt Fuel: By 2027, deploy a robust program that enables fuel salt qualification technologies needed to support fuel salt research and development (R&D), focusing on emergent needs to derisk fuel salt production and utilization in advanced reactors. • Long-Term ATF: Develop fuel technologies that enable significant power uprates (~50%) in refurbished or new LWRs while optimizing fissile material utilization and waste disposal. The 5-year milestones in the AFC Execution Plan are contingent on an assumed budget. This Execution Plan will be updated annually to reflect actual funding profiles as budget guidance becomes available, ensuring milestones are adjusted accordingly. In summary, the AFC Execution Plan presents a comprehensive strategy to advance nuclear fuel technologies through a science-based approach, addressing both near-term and long-term goals while adapting to funding realities.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

NASA NTRS1972

Technology assessment in the Executive Office of the President

The involvement of the President with technology, directly and indirectly, and the best way in which his responsibilities can be discharged are discussed. Technology assessment is considered essential at all levels of the Executive agencies, but the capacity of the agencies for assessment is limited and needs to be supplemented within the Executive Branch. Complete centralization of technological assessment is felt to be ineffective. The role of the Executive Office in initiating proposals for Presidential action and sustaining links with Congress are outlined, and the apparatus for technology assessment is described, emphasizing the Office of Science and Technology. A significant area of technology assessment for the Executive Office is the field of environmental quality, and the duties of the Environmental Quality Council are summarized. It is suggested that it may be more effective to set up a separate organization for the restoration and protection of the environment and to define the task in terms of what is to be protected rather than in terms of technology.

Kidd, C. V.↗

NASA NTRS1971

A simple executive for a fault-tolerant, real-time multiprocessor.

Description of a simple executive for operation with a fault-tolerant multiprocessor that is oriented toward application in an environment where the primary function is to provide real-time control. The primary executive function is to accept requests for jobs placed by other jobs or from peripheral equipment and then schedule their initiation in accordance with the request parameters. The executive is also brought into action when a processor fails, so that appropriate disposition may be made of the job that was running on the failed processor. Many architectural features intended to support this executive concept are included.

Filene, R. J.↗

NASA NTRS1977

Analysis of responses of cold pressor tests on pilots and executives

Statistical analyses were performed to study the relationship between cold pressor test responses and certain medical attributes of a group of 81 pilots and a group of 466 executives. The important results of this study were as follows: There was a significant relationship between a subject's cold pressor test response and his profession (that is, pilot or executive). The executives' diastolic cold pressor test responses were significantly related to their medical conditions, and their families' medical conditions. Significant relationships were observed between executives' diastolic and systolic cold pressor test responses and their history of tranquilizer and cardiac drug use.

Swaroop, R.↗

NASA NTRS1985

Designing a priority driven multi-frame rate flight executive

The Advanced Transport Operating System (ATOPS) project is a NASA operational research flight project which is concerned with upgrading the new generation of flight computers. In connection with this work, it becomes also necessary to reassess the adequacy of the flight executive and flight software. In the present discussion, attention is given to the ATOPS project upgrade, the operating flight system, the design criteria for the new flight executive, the implementation of the executive, a sample real-time execution, a real-time debug and test tool, and several experiences which could be useful to others considering a similar exercise.

Smith-Taylor, R.↗

NASA NTRS1984

Writing executable assertions to test flight software

An executable assertion is a logical statement about the variables or a block of code. If there is no error during execution, the assertion statement results in a true value. Executable assertions can be used for dynamic testing of software. They can be employed for validation during the design phase, and exception and error detection during the operation phase. The present investigation is concerned with the problem of writing executable assertions, taking into account the use of assertions for testing flight software. They can be employed for validation during the design phase, and for exception handling and error detection during the operation phase The digital flight control system and the flight control software are discussed. The considered system provides autopilot and flight director modes of operation for automatic and manual control of the aircraft during all phases of flight. Attention is given to techniques for writing and using assertions to test flight software, an experimental setup to test flight software, and language features to support efficient use of assertions.

Mahmood, A.↗

NASA NTRS1987

Computer architecture for efficient algorithmic executions in real-time systems: New technology for avionics systems and advanced space vehicles

Improvements and advances in the development of computer architecture now provide innovative technology for the recasting of traditional sequential solutions into high-performance, low-cost, parallel system to increase system performance. Research conducted in development of specialized computer architecture for the algorithmic execution of an avionics system, guidance and control problem in real time is described. A comprehensive treatment of both the hardware and software structures of a customized computer which performs real-time computation of guidance commands with updated estimates of target motion and time-to-go is presented. An optimal, real-time allocation algorithm was developed which maps the algorithmic tasks onto the processing elements. This allocation is based on the critical path analysis. The final stage is the design and development of the hardware structures suitable for the efficient execution of the allocated task graph. The processing element is designed for rapid execution of the allocated tasks. Fault tolerance is a key feature of the overall architecture. Parallel numerical integration techniques, tasks definitions, and allocation algorithms are discussed. The parallel implementation is analytically verified and the experimental results are presented. The design of the data-driven computer architecture, customized for the execution of the particular algorithm, is discussed.

Carroll, Chester C.↗

NASA NTRS1989

Monitoring The Execution Of A VAX Image

Computer program PROCSCAN developed to monitor profile of executable image during execution. Purpose to identify routines in which program is spending most of its time. PROSCAN very useful first step in optimization of program. PROSCAN samples program counter of executing image and compares its value to table of entry-point addresses to determine which subroutine is executing. Written in C (77 percent), Assembler (13 percent), and FORTRAN 77 (10 percent).

Scott, Peter J.↗

NASA NTRS1989

Performance impacts of look-ahead execution in the conversation scheme

The look-ahead execution approach, which allows participant processes that exist early to exit from a conversation before other participants finish their conversation activities, is presented here as a fundamental approach to reducing the synchronization overhead. Queuing network models are developed for systems operating under the basic conversation execution scheme and systems operating under the look-ahead execution scheme. Based on the models, various performance indicators such as the system throughput, the average number of processors idling inside a conversation due to the synchronization required, and the average time spent in conversation are evaluated numerically for different application environments. The results provide insights into the extent of benefits provided by the look-ahead execution approach.

Kim, K. H.↗

NASA NTRS1990

Technology for Space Station Evolution. Executive summary and overview

NASA's Office of Aeronautics and Space Technology (OAST) conducted a workshop on technology for space station evolution 16-19 Jan. 1990. The purpose of this workshop was to collect and clarify Space Station Freedom technology requirements for evolution and to describe technologies that can potentially fill those requirements. These proceedings are organized into an Executive Summary and Overview and five volumes containing the technology discipline presentations. The Executive Summary and Overview contains an executive summary for the workshop, the technology discipline summary packages, and the keynote address. The executive summary provides a synopsis of the events and results of the workshop and the technology discipline summary packages.

Source record↗

NASA NTRS1993

Application of compiler-assisted multiple instruction rollback recovery to speculative execution

Speculative execution is a method to increase instruction level parallelism which can be exploited by both super-scalar and VLIW architectures. The key to a successful general speculation strategy is a repair mechanism to handle mispredicted branches and accurate reporting of exceptions for speculated instructions. Multiple instruction rollback is a technique developed for recovery from transient processor failure. Many of the difficulties encountered during recovery from branch misprediction or from instruction re-execution due to exception in a speculative execution architecture are similar to those encountered during multiple instruction rollback. The applicability of a recently developed compiler-assisted multiple instruction rollback scheme to aid in speculative execution repair is investigated. Extensions to the compiler-assisted scheme to support branch and exception repair are presented along with performance measurements across ten application programs.

Alewine, N. J.↗

NASA NTRS1987

Design and evaluation of executable assertions for concurrent error detection

System level concurrent detection of errors due to hardware faults can be accomplished by introducing software redundancy in the form of executable assertions into a program to monitor the correct operation of the system during its execution. This paper attempts to formalize the use of executable assertions for the purpose of concurrent error detection, and discusses a transformation approach to the design of assertion statements. The second part deals with the effectiveness of the error detection technique. A fault simulation method for the evaluation of the reliability of the assertion statements is described. This scheme was used to study the effectiveness of a nontrivial program in providing protection against faults in the underlying system. The experimental results shows that the use of executable assertions provides an effective approach to achieve concurrent error detection.

Hua, Kien A.↗

NASA NTRS1993

Application of compiler-assisted multiple instruction rollback recovery to speculative execution

Speculative execution is a method to increase instruction level parallelism which can be exploited by both super-scalar and VLIW architectures. The key to a successful general speculation strategy is a repair mechanism to handle mispredicted branches and accurate reporting of exceptions for speculated instructions. Multiple instruction rollback is a technique developed for recovery from transient processor failure. Many of the difficulties encountered during recovery from branch misprediction or from instruction re-execution due to exception in a speculative execution architecture are similar to those encountered during multiple instruction rollback. The applicability of a recently developed compiler-assisted multiple instruction rollback scheme to aid in speculative execution repair is investigated. Extensions to the compiler-assisted scheme to support branch and exception repair are presented along with performance measurements across ten application programs.

Alewine, N. J.↗