Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Distributed System and Computing”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

DGaaS: GPU as a Service on Distributed Computing System

In the rapidly evolving landscape of scientific computing, Graphics Processing Units (GPUs) have become indispensable for their unparalleled ability to handle parallel tasks in complex calculations, simulations, and data analysis. Their utility is further magnified in machine learning and AI applications, where they significantly accelerate model training and predictive analytics. Within this context, the Triton Inference Server emerges as a pivotal open-source tool, specializing in AI inferencing and optimizing GPU utilization across various platforms and frameworks. This paper presents an in-depth study on distributed High Throughput Computing (HTC), specifically focusing on the HTCondor framework and its resource provisioning tools, GlideinWMS and HEPCloud. These systems enable large-scale scientific experiments like CMS and DUNE to efficiently access and utilize vast computational resources. The paper explores the core architectural components of GlideinWMS, including jobs, user pools, and worker nodes, and discusses their integration with GPUs and the Triton server. The primary aim of this research is to develop a solution that optimizes GPU utilization by leveraging Glideins and containers. This approach allows computational jobs, particularly those involving AI models, to use GPUs only when essential, thereby facilitating efficient sharing of limited GPU resources. To validate this architecture, the study conducted three key tests involving custom scripts, container-based servers, and Triton server deployments. However, the study faces challenges, notably in locating the Triton server and ensuring secure remote access. To address these issues, future work will focus on developing a proxy mechanism and enhancing security protocols. In conclusion, this study offers a comprehensive roadmap for effective and efficient GPU utilization in distributed High Throughput Computing. It aims to contribute significantly to the scientific community by solving pressing problems and implementing robust solutions in collaboration with the GlideinWMS and HEPCloud teams. The research sets the stage for a more efficient, scalable, and cost-effective paradigm in scientific computing.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1987

Distributed computer system enhances productivity for SRB joint optimization

Initial calculations of a redesign of the solid rocket booster joint that failed during the shuttle tragedy showed that the design had a weight penalty associated with it. Optimization techniques were to be applied to determine if there was any way to reduce the weight while keeping the joint opening closed and limiting the stresses. To allow engineers to examine as many alternatives as possible, a system was developed consisting of existing software that coupled structural analysis with optimization which would execute on a network of computer workstations. To increase turnaround, this system took advantage of the parallelism offered by the finite difference technique of computing gradients to allow several workstations to contribute to the solution of the problem simultaneously. The resulting system reduced the amount of time to complete one optimization cycle from two hours to one-half hour with a potential of reducing it to 15 minutes. The current distributed system, which contains numerous extensions, requires one hour turnaround per optimization cycle. This would take four hours for the sequential system.

Rogers, James L., Jr.↗
NASA NTRS1988

A strategy for reducing turnaround time in design optimization using a distributed computer system

There is a need to explore methods for reducing lengthly computer turnaround or clock time associated with engineering design problems. Different strategies can be employed to reduce this turnaround time. One strategy is to run validated analysis software on a network of existing smaller computers so that portions of the computation can be done in parallel. This paper focuses on the implementation of this method using two types of problems. The first type is a traditional structural design optimization problem, which is characterized by a simple data flow and a complicated analysis. The second type of problem uses an existing computer program designed to study multilevel optimization techniques. This problem is characterized by complicated data flow and a simple analysis. The paper shows that distributed computing can be a viable means for reducing computational turnaround time for engineering design problems that lend themselves to decomposition. Parallel computing can be accomplished with a minimal cost in terms of hardware and software.

Young, Katherine C.↗
DOE OSTI2024

RuralAI in Tomato Farming: Integrated Sensor System, Distributed Computing, and Hierarchical Federated Learning for Crop Health Monitoring

Precision horticulture is evolving due to scalable sensor deployment and machine learning (ML) integration. These advancements boost the operational efficiency of individual farms, balancing the benefits of analytics with autonomy requirements. However, given concerns that affect wide geographic regions (e.g., climate change), there is a need to apply models that span farms. Federated learning (FL) has emerged as a potential solution. FL enables decentralized ML across different farms without sharing private data. Traditional FL assumes simple two-tier network topologies and, thus, falls short of operating on more complex networks found in real-world agricultural scenarios. Networks vary across crops and farms and encompass various sensor data modes, extending across jurisdictions. New hierarchical FL (HFL) approaches are needed for more efficient and context-sensitive model sharing, accommodating regulations across multiple jurisdictions. Here, we present the RuralAI architecture deployment for tomato crop monitoring, featuring sensor field units for soil, crop, and weather data collection. HFL with personalization is used to offer localized and adaptive insights. Model management, aggregation, and transfers are facilitated via a flexible approach, enabling seamless communication between local devices, edge nodes, and the cloud.

60 APPLIED LIFE SCIENCES↗
NASA NTRS1991

Distributed-Computer System Optimizes SRB Joints

Initial calculations of redesign of joint on solid rocket booster (SRB) that failed during Space Shuttle tragedy showed redesign increased weight. Optimization techniques applied to determine whether weight could be reduced while keeping joint closed and limiting stresses. Analysis system developed by use of existing software coupling structural analysis with optimization computations. Software designed executable on network of computer workstations. Took advantage of parallelism offered by finite-difference technique of computing gradients to enable several workstations to contribute simultaneously to solution of problem. Key features, effective use of redundancies in hardware and flexible software, enabling optimization to proceed with minimal delay and decreased overall time to completion.

Rogers, James L., Jr.↗
NASA NTRS1992

Survivable algorithms and redundancy management in NASA's distributed computing systems

The design of survivable algorithms requires a solid foundation for executing them. While hardware techniques for fault-tolerant computing are relatively well understood, fault-tolerant operating systems, as well as fault-tolerant applications (survivable algorithms), are, by contrast, little understood, and much more work in this field is required. We outline some of our work that contributes to the foundation of ultrareliable operating systems and fault-tolerant algorithm design. We introduce our consensus-based framework for fault-tolerant system design. This is followed by a description of a hierarchical partitioning method for efficient consensus. A scheduler for redundancy management is introduced, and application-specific fault tolerance is described. We give an overview of our hybrid algorithm technique, which is an alternative to the formal approach given.

Malek, Miroslaw↗
NASA NTRS2000

Automation of the CFD Process on Distributed Computing Systems

A script system was developed to automate and streamline portions of the CFD process. The system was designed to facilitate the use of CFD flow solvers on supercomputer and workstation platforms within a parametric design event. Integrating solver pre- and postprocessing phases, the fully automated ADTT script system marshalled the required input data, submitted the jobs to available computational resources, and processed the resulting output data. A number of codes were incorporated into the script system, which itself was part of a larger integrated design environment software package. The IDE and scripts were used in a design event involving a wind tunnel test. This experience highlighted the need for efficient data and resource management in all parts of the CFD process. To facilitate the use of CFD methods to perform parametric design studies, the script system was developed using UNIX shell and Perl languages. The goal of the work was to minimize the user interaction required to generate the data necessary to fill a parametric design space. The scripts wrote out the required input files for the user-specified flow solver, transferred all necessary input files to the computational resource, submitted and tracked the jobs using the resource queuing structure, and retrieved and post-processed the resulting dataset. For computational resources that did not run queueing software, the script system established its own simple first-in-first-out queueing structure to manage the workload. A variety of flow solvers were incorporated in the script system, including INS2D, PMARC, TIGER and GASP. Adapting the script system to a new flow solver was made easier through the use of object-oriented programming methods. The script system was incorporated into an ADTT integrated design environment and evaluated as part of a wind tunnel experiment. The system successfully generated the data required to fill the desired parametric design space. This stressed the computational resources required to compute and store the information. The scripts were continually modified to improve the utilization of the computational resources and reduce the likelihood of data loss due to failures. An ad-hoc file server was created to manage the large amount of data being generated as part of the design event. Files were stored and retrieved as needed to create new jobs and analyze the results. Additional information is contained in the original.

Tejnil, Ed↗
NASA NTRS1985

One approach for evaluating the Distributed Computing Design System (DCDS)

The Distributed Computer Design System (DCDS) provides an integrated environment to support the life cycle of developing real-time distributed computing systems. The primary focus of DCDS is to significantly increase system reliability and software development productivity, and to minimize schedule and cost risk. DCDS consists of integrated methodologies, languages, and tools to support the life cycle of developing distributed software and systems. Smooth and well-defined transistions from phase to phase, language to language, and tool to tool provide a unique and unified environment. An approach to evaluating DCDS highlights its benefits.

Ellis, J. T.↗
NASA NTRS1991

Measuring the effects of heterogeneity on distributed systems

Distributed computer systems in daily use are becoming more and more heterogeneous. Currently, much of the design and analysis studies of such systems assume homogeneity. This assumption of homogeneity has been mainly driven by the resulting simplicity in modeling and analysis. A simulation study is presented which investigated the effects of heterogeneity on scheduling algorithms for hard real time distributed systems. In contrast to previous results which indicate that random scheduling may be as good as a more complex scheduler, this algorithm is shown to be consistently better than a random scheduler. This conclusion is more prevalent at high workloads as well as at high levels of heterogeneity.

El-Toweissy, Mohamed↗
NASA NTRS1994

Computer-aided operations engineering with integrated models of systems and operations

CONFIG 3 is a prototype software tool that supports integrated conceptual design evaluation from early in the product life cycle, by supporting isolated or integrated modeling, simulation, and analysis of the function, structure, behavior, failures and operation of system designs. Integration and reuse of models is supported in an object-oriented environment providing capabilities for graph analysis and discrete event simulation. Integration is supported among diverse modeling approaches (component view, configuration or flow path view, and procedure view) and diverse simulation and analysis approaches. Support is provided for integrated engineering in diverse design domains, including mechanical and electro-mechanical systems, distributed computer systems, and chemical processing and transport systems. CONFIG supports abstracted qualitative and symbolic modeling, for early conceptual design. System models are component structure models with operating modes, with embedded time-related behavior models. CONFIG supports failure modeling and modeling of state or configuration changes that result in dynamic changes in dependencies among components. Operations and procedure models are activity structure models that interact with system models. CONFIG is designed to support evaluation of system operability, diagnosability and fault tolerance, and analysis of the development of system effects of problems over time, including faults, failures, and procedural or environmental difficulties.

Malin, Jane T.↗
NASA NTRS1994

CONFIG: Integrated engineering of systems and their operation

This article discusses CONFIG 3, a prototype software tool that supports integrated conceptual design evaluation from early in the product life cycle, by supporting isolated or integrated modeling, simulation, and analysis of the function, structure, behavior, failures and operations of system designs. Integration and reuse of models is supported in an object-oriented environment providing capabilities for graph analysis and discrete event simulation. CONFIG supports integration among diverse modeling approaches (component view, configuration or flow path view, and procedure view) and diverse simulation and analysis approaches. CONFIG is designed to support integrated engineering in diverse design domains, including mechanical and electro-mechanical systems, distributed computer systems, and chemical processing and transport systems.

Malin, Jane T.↗
NASA NTRS1991

Dynamic resource allocation scheme for distributed heterogeneous computer systems

This invention relates to a resource allocation in computer systems, and more particularly, to a method and associated apparatus for shortening response time and improving efficiency of a heterogeneous distributed networked computer system by reallocating the jobs queued up for busy nodes to idle, or less-busy nodes. In accordance with the algorithm (SIDA for short), the load-sharing is initiated by the server device in a manner such that extra overhead in not imposed on the system during heavily-loaded conditions. The algorithm employed in the present invention uses a dual-mode, server-initiated approach. Jobs are transferred from heavily burdened nodes (i.e., over a high threshold limit) to low burdened nodes at the initiation of the receiving node when: (1) a job finishes at a node which is burdened below a pre-established threshold level, or (2) a node is idle for a period of time as established by a wakeup timer at the node. The invention uses a combination of the local queue length and the local service rate ratio at each node as the workload indicator.

Liu, Howard T.↗
NASA NTRS1996

Performance Evaluation of Communication Software Systems for Distributed Computing

In recent years there has been an increasing interest in object-oriented distributed computing since it is better quipped to deal with complex systems while providing extensibility, maintainability, and reusability. At the same time, several new high-speed network technologies have emerged for local and wide area networks. However, the performance of networking software is not improving as fast as the networking hardware and the workstation microprocessors. This paper gives an overview and evaluates the performance of the Common Object Request Broker Architecture (CORBA) standard in a distributed computing environment at NASA Ames Research Center. The environment consists of two testbeds of SGI workstations connected by four networks: Ethernet, FDDI, HiPPI, and ATM. The performance results for three communication software systems are presented, analyzed and compared. These systems are: BSD socket programming interface, IONA's Orbix, an implementation of the CORBA specification, and the PVM message passing library. The results show that high-level communication interfaces, such as CORBA and PVM, can achieve reasonable performance under certain conditions.

Fatoohi, Rod↗