Search NASA⌕ Search

SEARCH · Search NASA

Results for “IMPLEMENTATION”

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 145 records · Page 8

Making resonance a common case: a high-performance implementation of collective I/O on parallel file systems

Collective I/O is a widely used technique to improve I/O performance in parallel computing. It can be implemented as a client-based or server-based scheme. The client-based implementation is more widely adopted in MPI-IO software such as ROMIO because of its independence from the storage system configuration and its greater portability. However, existing implementations of client-side collective I/O do not take into account the actual pattern offile striping over multiple I/O nodes in the storage system. This can cause a significant number of requests for non-sequential data at I/O nodes, substantially degrading I/O performance. Investigating the surprisingly high I/O throughput achieved when there is an accidental match between a particular request pattern and the data striping pattern on the I/O nodes, we reveal the resonance phenomenon as the cause. Exploiting readily available information on data striping from the metadata server in popular file systems such as PVFS2 and Lustre, we design a new collective I/O implementation technique, resonant I/O, that makes resonance a common case. Resonant I/O rearranges requests from multiple MPI processes to transform non-sequential data accesses on I/O nodes into sequential accesses, significantly improving I/O performance without compromising the independence ofa client-based implementation. We have implemented our design in ROMIO. Our experimental results show that the scheme can increase I/O throughput for some commonly used parallel I/O benchmarks such as mpi-io-test and ior-mpi-io over the existing implementation of ROMIO by up to 157%, with no scenario demonstrating significantly decreased performance.

42 ENGINEERING↗

Implementation of remove monitoring in facilities under safeguards with unattended systems

Remote monitoring is being applied by the International Atomic Energy Agency (IAEA) at nuclear facilities around the world. At the Monju Reactor in Japan we have designed, developed and implemented a remote monitoring approach that can serve as a model for applying remote monitoring to facilities that are already under full-scope safeguards using unattended instrumentation. Remote monitoring implementations have historically relied upon the use of specialized data collection hardware and system design features that integrate remote monitoring into the safeguards data collection system. The integration of remote monitoring and unattended data collection increases the complexity of safeguards data collection systems. This increase in complexity necessarily produces a corresponding reduction of system reliability compared to less-complex unattended monitoring systems. At the Monju facility we have implemented a remote monitoring system that is decoupled from the activity of safeguards data collection. In the completed system the function of remote data transfer is separated from the function of safeguards data collection. As such, a failure of the remote monitoring function cannot produce an associated loss of safeguards data, as is possible with integrated remote-monitoring implementations. Currently, all safeguards data from this facility is available to the IAEA on a 24/7 basis. This facility employs five radiation-based unattended systems, video surveillance and numerous optical seal systems. The implementation of remote monitoring at this facility, while increasing the complexity of the safeguards system, is designed to avoid any corresponding reduction in reliability of the safeguards data collection systems by having decoupled these functions. This design and implementation can serve as a model for implementation of remote monitoring at nuclear facilities that currently employ unattended safeguards systems.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

OpenSHMEM-UCX: Evaluation of UCX for Implementing OpenSHMEM Programming Model, In: OpenSHMEM 2016: OpenSHMEM and Related Technologies. Enhancing OpenSHMEM for Hybrid Environments

The OpenSHMEM reference implementation was developed towards the goal of developing an open source and high-performing OpenSHMEM implementation. To achieve portability and performance across various networks, the OpenSHMEM reference implementation uses GASNet and UCCS for network operations. Recently, new network layers have emerged with the promise of providing high-performance, scalability, and portability for HPC applications. In this paper, we implement the OpenSHMEM reference implementation to use the UCX framework for network operations. Then, we evaluate its performance and scalability on Cray XK systems to understand UCX’s suitability for developing the OpenSHMEM programming model. Further, we develop a benchmark called SHOMS for evaluating the OpenSHMEM implementation. Our experimental results show that OpenSHMEM-UCX outperforms the vendor supplied OpenSHMEM implementation in most cases on the Cray XK system by up to 40% with respect to message rate and up to 70% for the execution of application kernels.

Computer Science↗

Taking stock of national climate policies to evaluate implementation of the Paris Agreement

Many countries have implemented national climate policies to accomplish pledged Nationally Determined Contributions and to contribute to the temperature objectives of the Paris Agreement on climate change. In 2023, the global stocktake will assess the combined effort of countries. Here, based on a public policy database and a multi-model scenario analysis, we show that implementation of current policies leaves a median emission gap of 22.4 to 28.2 GtCO 2 eq by 2030 with the optimal pathways to implement the well below 2 °C and 1.5 °C Paris goals. If Nationally Determined Contributions would be fully implemented, this gap would be reduced by a third. Interestingly, the countries evaluated were found to not achieve their pledged contributions with implemented policies (implementation gap), or to have an ambition gap with optimal pathways towards well below 2 °C. This shows that all countries would need to accelerate the implementation of policies for renewable technologies, while efficiency improvements are especially important in emerging countries and fossilfuel- dependent countries.

54 ENVIRONMENTAL SCIENCES↗

Optimizing blocking and nonblocking reduction operations for multicore systems: Hierarchical design and implementation

Many scientific simulations, using the Message Passing Interface (MPI) programming model, are sensitive to the performance and scalability of reduction collective operations such as MPI_Allreduce and MPI_Reduce. These operations are the most widely used abstractions to perform mathematical operations over all processes that are part of the simulation. In this work, we propose a hierarchical design to implement the reduction operations on multicore systems. This design aims to improve the efficiency of reductions by 1) tailoring the algorithms and customizing the implementations for various communication mechanisms in the system 2) providing the ability to configure the depth of hierarchy to match the system architecture, and 3) providing the ability to independently progress each of this hierarchy. Using this design, we implement MPI_Allreduce and MPI_Reduce operations (and its nonblocking variants MPI_Iallreduce and MPI_Ireduce) for all message sizes, and evaluate on multiple architectures including InfiniBand and Cray XT5. We leverage and enhance our existing infrastructure, Cheetah, which is a framework for implementing hierarchical collective operations to implement these reductions. The experimental results show that the Cheetah reduction operations outperform the production-grade MPI implementations such as Open MPI default, Cray MPI, and MVAPICH2, demonstrating its efficiency, flexibility and portability. On Infini-Band systems, with a microbenchmark, a 512-process Cheetah nonblocking Allreduce and Reduce achieves a speedup of 23x and 10x, respectively, compared to the default Open MPI reductions. The blocking variants of the reduction operations also show similar performance benefits. A 512-process nonblocking Cheetah Allreduce achieves a speedup of 3x, compared to the default MVAPICH2 Allreduce implementation. On a Cray XT5 system, a 6144-process Cheetah Allreduce outperforms the Cray MPI by 145%. The evaluation with an application kernel, Conjugate Gradient solver, shows that the Cheetah reductions speeds up total time to solution by 195%, demonstrating the potential benefits for scientific simulations.

Venkata, Manjunath Gorentla↗

Implementation of ISO 15118-202 messages within Everest EV Charging Open Source Framework [SWR-25-56]

This software implements the messages defined in the ISO 15118-202 standard within the Everest EV Charging open source framework. The protocol and messages defined in the ISO 15118-202 standard enable the exchange of additional information which is not available for exchange within the currently deployed EV/EVSE communications protocols. This information includes co-identification parameters, error message exchange and more. This fork of the everest-core repository adds a prototype of the Extensible Supply Equipment Communication Controller (SECC) Discovery Protocol (ESDP) implemented based on a draft of the ISO 15118-202 standard. This is achieved through additions and modifications to the EvseV2G module. The implementation provides a demonstration of the ESDP messages, encoding and decoding but does not include a full integration within the Everest framework. Much of the information being sent over ESDP in this implementation is set statically for the sake of demonstrating the protocol itself. This fork of the ext-switchev-iso15118 repository adds a prototype of the Extensible Supply Equipment Communication Controller (SECC) Discovery Protocol (ESDP) implemented based on a draft of the ISO 15118-202 standard. The implementation provides a demonstration of the ESDP messages, encoding and decoding but does not include a full integration within the Everest framework. Much of the information being sent over ESDP in this implementation is set statically for the sake of demonstrating the protocol itself. This fork adds the ESDP features for only the EVCC controller because that is the only portion that is utilized in the everest Software-in-the-Loop.

Watt, Ed [National Renewable Energy Laboratory (NR↗

COVID-19 prevention at institutions of higher education, United States, 2020–2021: implementation of nonpharmaceutical interventions

Background, In early 2020, following the start of the coronavirus disease 2019 (COVID-19) pandemic, institutions of higher education (IHEs) across the United States rapidly pivoted to online learning to reduce the risk of on-campus virus transmission. We explored IHEs’ use of this and other nonpharmaceutical interventions (NPIs) during the subsequent pandemic-affected academic year 2020–2021. Methods, From December 2020 to June 2021, we collected publicly available data from official webpages of 847 IHEs, including all public (n = 547) and a stratified random sample of private four-year institutions (n = 300). Abstracted data included NPIs deployed during the academic year such as changes to the calendar, learning environment, housing, common areas, and dining; COVID-19 testing; and facemask protocols. We performed weighted analysis to assess congruence with the October 29, 2020, US Centers for Disease Control and Prevention (CDC) guidance for IHEs. For IHEs offering ≥50% of courses in person, we used weighted multivariable linear regression to explore the association between IHE characteristics and the summated number of implemented NPIs. Results, Overall, 20% of IHEs implemented all CDC-recommended NPIs. The most frequently utilized NPI was learning environment changes (91%), practiced as one or more of the following modalities: distance or hybrid learning opportunities (98%), 6-ft spacing (60%), and reduced class sizes (51%). Additionally, 88% of IHEs specified facemask protocols, 78% physically changed common areas, and 67% offered COVID-19 testing. Among the 33% of IHEs offering ≥50% of courses in person, having < 1000 students was associated with having implemented fewer NPIs than IHEs with ≥ 1000 students. Conclusions, Only 1 in 5 IHEs implemented all CDC recommendations, while a majority implemented a subset, most commonly changes to the classroom, facemask protocols, and COVID-19 testing. IHE enrollment size and location were associated with degree of NPI implementation. Additional research is needed to assess adherence to NPI implementation in IHE settings.

59 BASIC BIOLOGICAL SCIENCES↗

OpenSHMEM Implementation of IOR Benchmark

The benchmarking effort within the Computational Research & Development Programs at the Oak Ridge National Laboratory (ORNL) seeks to design and enable High Performance Computing (HPC) benchmarks and test suites. The work described in this report is a part of the effort focusing on the comparison and analysis of OpenSHMEM implementations using the Interleave Or Random (IOR) software for benchmarking parallel file system using POSIX, MPIIO, or HDF5 interfaces. We describe the effort to emulate the MPIIO parallel collective capabilities in the IOR benchmark using OpenSHMEM communication. One development effort was in emulating the MPI derived datatype used in the read/write operations and in setting the file view. Another effort was in implementing an internal cache in OpenSHMEM distributed shared memory to facilitate global collective I/O operations. Experiments comparing collective I/O in MPIIO implementations with the OpenSHMEM implementations were performed on the SGI Turing Cluster and the Cray XK7 Titan supercomputer at the Oak Ridge Leadership Computing Facility (OLCF). The preliminary results suggest that on the Cray XK7 Titan, the MPIIO implementations obtained higher write performance and the OpenSHMEM version obtained slightly higher read performance. On the SGI Turing Cluster, the MPIIO implementations obtained slightly higher performance over the OpenSHMEM implementations on large files.

97 MATHEMATICS AND COMPUTING↗

Toward fidelity between specification and implementation

This paper describes the methods used to specify and implement a complex communications protocol that provides reliable delivery of data in multicast-capable, packet-switching telecommunication networks. The protocol, called the Reliable Multicasting Protocol (RMP), was developed incrementally by two complementary teams using a combination of formal and informal techniques in an attempt to ensure the correctness of the protocol implementation. The first team, called the Design team, initially specified protocol requirements using a variant of SCR requirements tables and implemented a prototype solution. The second team, called the V&V team, developed a state model based on the requirements tables and derived test cases from these tables to exercise the implementation. In a series of iterative steps, the Design team added new functionality to the implementation while the V&V team kept the state model in fidelity with the implementation through testing. Test cases derived from state transition paths in the formal model formed the dialogue between teams during development and served as the vehicles for keeping the model and implementation in fidelity with each other. This paper describes our experiences in developing our process model, details of our approach, and some example problems found during the development of RMP.

Callahan, John R.↗

Implementation of Adaptive Digital Controllers on Programmable Logic Devices

Much has been made of the capabilities of FPGA's (Field Programmable Gate Arrays) in the hardware implementation of fast digital signal processing (DSP) functions. Such capability also makes and FPGA a suitable platform for the digital implementation of closed loop controllers. There are myriad advantages to utilizing an FPGA for discrete-time control functions which include the capability for reconfiguration when SRAM- based FPGA's are employed, fast parallel implementation of multiple control loops and implementations that can meet space level radiation tolerance in a compact form-factor. Other researchers have presented the notion that a second order digital filter with proportional-integral-derivative (PID) control functionality can be implemented in an FPGA. At Marshall Space Flight Center, the Control Electronics Group has been studying adaptive discrete-time control of motor driven actuator systems using digital signal processor (DSF) devices. Our goal is to create a fully digital, flight ready controller design that utilizes an FPGA for implementation of signal conditioning for control feedback signals, generation of commands to the controlled system, and hardware insertion of adaptive control algorithm approaches. While small form factor, commercial DSP devices are now available with event capture, data conversion, pulse width modulated outputs and communication peripherals, these devices are not currently available in designs and packages which meet space level radiation requirements. Meeting our goals requires alternative compact implementation of such functionality to withstand the harsh environment encountered on spacecraft. Radiation tolerant FPGA's are a feasible option for reaching these goals.

Gwaltney, David A.↗

Interplanetary Overlay Network Bundle Protocol Implementation

The Interplanetary Overlay Network (ION) system's BP package, an implementation of the Delay-Tolerant Networking (DTN) Bundle Protocol (BP) and supporting services, has been specifically designed to be suitable for use on deep-space robotic vehicles. Although the ION BP implementation is unique in its use of zero-copy objects for high performance, and in its use of resource-sensitive rate control, it is fully interoperable with other implementations of the BP specification (Internet RFC 5050). The ION BP implementation is built using the same software infrastructure that underlies the implementation of the CCSDS (Consultative Committee for Space Data Systems) File Delivery Protocol (CFDP) built into the flight software of Deep Impact. It is designed to minimize resource consumption, while maximizing operational robustness. For example, no dynamic allocation of system memory is required. Like all the other ION packages, ION's BP implementation is designed to port readily between Linux and Solaris (for easy development and for ground system operations) and VxWorks (for flight systems operations). The exact same source code is exercised in both environments. Initially included in the ION BP implementations are the following: libraries of functions used in constructing bundle forwarders and convergence-layer (CL) input and output adapters; a simple prototype bundle forwarder and associated CL adapters designed to run over an IPbased local area network; administrative tools for managing a simple DTN infrastructure built from these components; a background daemon process that silently destroys bundles whose time-to-live intervals have expired; a library of functions exposed to applications, enabling them to issue and receive data encapsulated in DTN bundles; and some simple applications that can be used for system checkout and benchmarking.

Burleigh, Scott C.↗

Implementation of J-A Methodology Elastic-Plastic Crack Instability Analysis Capability into the WARP-3D Code

Characterization of the near crack-tip stress/strain fields is the foundation of fracture mechanics. The description of the near tip stress field and the prediction of when fracture occurs is well established for brittle materials that exhibit linear elastic behavior. However, in ductile materials or conditions that violate linear elastic assumptions (Aluminum alloys, Al 2024-T3, Al 2024- T351 etc.), the elastic-plastic crack-tip stress fields are characterized by the Hutchison-Rice-Rosengren (HRR) field. The J-integral is commonly used to characterize amplitude of the HRR field under elastic-plastic conditions. The J-integral has been demonstrated for crack-tip fields that are under high constraint conditions (i.e., small-scale plasticity where the J-dominance is maintained). However, as the external load increases, yielding changes from small- to largescale plasticity and usually a loss of constraint (i.e., reduction in the triaxial stress field along the crack front). The loss of constraint leads to the deviation of the crack-tip stress fields from that given by the HRR field. Hence, the J-dominance will be gradually lost and additional parameter(s) are required to quantify the crack-tip stress fields and predict fracture behavior. The assessment objectives were to: 1) implement a two-parameter (i.e., J-A) fracture criterion into an elastic-plastic three-dimensional (3D) finite element analysis (FEA), 2) validate the implementation by comparison with the A parameter from literature data, 3) conduct material characterization tests to quantify the material behavior and provide fracture data for validation of the J-A fracture criteria, and (4) perform evaluations to establish if the J-A criteria can be used to predict fracture in a ductile metallic material (e.g., aluminum alloys). The A parameter in these criteria is the second parameter in a three-term elastic-plastic asymptotic expansion of the neartip stress behavior. A series of extensive FEAs were performed using WARP3D software package to obtain solutions for the A parameter for different specimen configurations. The methodology needed for the estimation of the A parameter in the asymptotic expansion was developed and implemented using Matlab®. A user material (UMAT) routine was used to model the material stress-strain response using a Ramberg-Osgood power law with a hardening exponent (n) and a material coefficient (alpha). This UMAT routine was successfully implemented in WARP3D software and validated through comparison with the experimental data. Three configurations were extracted from published results: 1) center cracked plate (CCP), 2) single edge-cracked plate (SECP), and 3) double edge-cracked plate (DECP). These configurations and four other configurations (three-hole tension (THT)), three-point bend (3PTB), three-hole compact tension (3PCT), and compact tension (CT)) were analyzed to verify the methodology that was developed and implemented into WARP3D. Solutions of the A parameter were obtained for remote tension loading conditions that started with small-scale yielding and continued into the large-scale plasticity regime. The results indicate that the methodology developed can be used to calculate the elastic-plastic J-A parameters for test specimens with a range of crack geometries, material strain hardening behaviors, and loading conditions. The J-A parameters were implemented as fracture criteria and used to predict the test results. For comparison, other fracture criteria were used to predict the same test results. Major findings include: The A constraint parameter A varies with specimen type and applied load thus accurate determination is crucial in predicting the failure load, and the A parameter is asymptotic as the failure load is approached, making an accurate determination difficult (i.e., small differences in the A parameter can cause large variations in failure load) for materials exhibiting elastic-plastic behavior. The failure predictions from J-A methodology were more accurate than the traditionally used KC and J methods, and have comparable scatter to that observed when using the crack-tip opening angle (CTOA) method. However, the J-A methodology requires considerable effort (expertise level and labor) to implement and to evaluate the A parameter for different specimen types and materials, or to apply this methodology to part-through crack (e.g., 3D problems) structural applications.

Hamm, Kenneth R., Jr.↗

Implementation of Human Systems Integration Technical and Management Process for the Lunar Gateway Program

NASA recognizes Human Systems Integration (HSI) as part of the overall systems engineering and acquisition strategy for space systems. The Lunar Gateway Program is implementing HSI technical and management process across the lifecycle of the mission, as required by NPR 7123.1C NASA Systems Engineering Processes and Requirements, and led by the Gateway HSI team as required by NPR 8705.2C Human-Rating Requirements for Space Systems, now HEOMD-003 Crewed Deep Space Systems Human Rating Certification Requirements and Standards for NASA Missions. NASA has been using HSI principles for many years and has applied them to many of its previous human spaceflight Programs. As NASA returns to the Moon in a more sustainable manner, the Gateway Program is maturing the application of HSI by implementing it more visibly as part of Artemis, with guidance from the NASA/SP-20210010952 NASA HSI Handbook. This paper discusses how HSI is being implemented in the Gateway Program, challenges faced with its implementation during the development phase, and strategies/approaches used to overcome those. The paper also covers HSI implementation for flight systems, vehicle processing, and interfaces across the six identified NASA HSI Domains: human factors engineering, operations, safety, training, maintainability and supportability, habitability and environment. The goal is to provide an overview of the implementation process of HSI in the Gateway Program as an example for other Programs/Projects/Missionsthat are looking to implement HSI.

Jackelynne Silva-Martinez↗

Implementing JEDI into NASA GMAO’s Real Time Production Suite

NASA’s Global Modeling and Assimilation Office (GMAO) has prepared their first production system involving the Joint Effort for Data assimilation Integration (JEDI) framework. In this system the central analysis, that drives the deterministic forecast, will be provided using JEDI. This talk outlines the phased approach to implementing JEDI into production that GMAO has designed, and how this approach will allow for a careful analysis of the system against the existing data assimilation framework (GSI). In the first phase of implementation the existing data assimilation system will perform certain actions that are still under development in JEDI. These include thinning the observations and producing satellite bias correction coefficients. JEDI is hooked up to the existing workflow so a single line switch can activate whether the existing or JEDI-based analysis is cycled. Outside of the monumental effort to construct JEDI that is ongoing at the Joint Center for Satellite Data Assimilation (JCSDA), GMAO have undertaken two areas of considerable effort. The talk will describe these efforts and highlight the main challenges that have been encountered. The first area of work is to implement the background error model from the existing data assimilation system into JEDI. The second is to validate the observing system in JEDI against the one in GSI, which has involved several new features being added to the observation operators in JEDI. While the longer-term plans involve trying to improve on the GSI in these two areas, GMAO is keen to have JEDI start from a trusted baseline. This is also key to implementing JEDI quickly so other priorities, such as increasing the number of model levels, can be easily worked on in parallel. GMAO is actively working on a framework to shepherd in the next generation coupled data assimilation system and model. As JEDI is implemented for the first time the plan is to ambitiously cycle through implementations, frequently bringing JEDI features to production. Details of these plans will be given in the talk and we will highlight key implementation and product milestones that we hope to achieve, as well as touch on the development environment that we will use to support frequent refreshing of the production system.

JEDI↗

Human Systems Integration (HSI) Framework and Training - Shifting the View of HSI for Better Implementation

The Implementation of Human Systems Integration (HSI) presents challenges within the acquisition community for two reasons. The first is that misconceptions of HSI still exist, with many Program Managers (PMs) and leadership uncertain of the value or where to begin. The second is due to an unbalanced approach to HSI in its own framework. These implementation challenges lead to barriers in the early prevention of mishaps. Understanding HSI practices and how they should be implemented in the Acquisition Product Life Cycle (PLC) has been a challenge across the government, leaving the value of HSI unknown and misunderstood with Program Managers. In the case for many acquisition programs, HSI is not implemented in early design, losing the perspective on human capabilities and limitations, creating impacts on human-centered design. Expectations in human performance are not clearly set and operations are baselined with no margin for changes in technology and processes that will affect system performance. The HSI framework addresses total system performance holistically using collaboration as the primary tool. The goal is to create a system with efficiencies while minimizing risk to the operators, maintainers, and support personnel, as well as any collateral personnel and systems. To accomplish this, HSI should be implemented as part of preemptive measures to minimize potential human error and mishaps during the operation phase. Investigative and assessment tools exist that consider events, issues, and other outside influences of a system that may not fall under the current construct of the HSI domains, leaving gaps in early HSI implementation and affecting the prevention of human errors and mishaps. This presentation will outline what NASA HSI is doing to support Early HSI implementation and Operational Performance shifts that affect human performance.

Anthony T Thomas↗

Optimizing Blocking and Nonblocking Reduction Operations for Multicore Systems: Hierarchical Design and Implementation

Many scientific simulations, using the Message Passing Interface (MPI) programming model, are sensitive to the performance and scalability of reduction collective operations such as MPI Allreduce and MPI Reduce. These operations are the most widely used abstractions to perform mathematical operations over all processes that are part of the simulation. In this work, we propose a hierarchical design to implement the reduction operations on multicore systems. This design aims to improve the efficiency of reductions by 1) tailoring the algorithms and customizing the implementations for various communication mechanisms in the system 2) providing the ability to configure the depth of hierarchy to match the system architecture, and 3) providing the ability to independently progress each of this hierarchy. Using this design, we implement MPI Allreduce and MPI Reduce operations (and its nonblocking variants MPI Iallreduce and MPI Ireduce) for all message sizes, and evaluate on multiple architectures including InfiniBand and Cray XT5. We leverage and enhance our existing infrastructure, Cheetah, which is a framework for implementing hierarchical collective operations to implement these reductions. The experimental results show that the Cheetah reduction operations outperform the production-grade MPI implementations such as Open MPI default, Cray MPI, and MVAPICH2, demonstrating its efficiency, flexibility and portability. On Infini- Band systems, with a microbenchmark, a 512-process Cheetah nonblocking Allreduce and Reduce achieves a speedup of 23x and 10x, respectively, compared to the default Open MPI reductions. The blocking variants of the reduction operations also show similar performance benefits. A 512-process nonblocking Cheetah Allreduce achieves a speedup of 3x, compared to the default MVAPICH2 Allreduce implementation. On a Cray XT5 system, a 6144-process Cheetah Allreduce outperforms the Cray MPI by 145%. The evaluation with an application kernel, Conjugate Gradient solver, shows that the Cheetah reductions speeds up total time to solution by 195%, demonstrating the potential benefits for scientific simulations.

Gorentla Venkata, Manjunath↗

OpenSHMEM-UCX : Evaluation of UCX for implementing OpenSHMEM Programming Model

The OpenSHMEM reference implementation was developed towards the goal of developing an open source and high-performing Open- SHMEM implementation. To achieve portability and performance across various networks, the OpenSHMEM reference implementation uses GAS- Net and UCCS for network operations. Recently, new network layers have emerged with the promise of providing high-performance, scalabil- ity, and portability for HPC applications. In this paper, we implement the OpenSHMEM reference implementation to use the UCX framework for network operations. Then, we evaluate its performance and scalabil- ity on Cray XK systems to understand UCX s suitability for developing the OpenSHMEM programming model. Further, we develop a bench- mark called SHOMS for evaluating the OpenSHMEM implementation. Our experimental results show that OpenSHMEM-UCX outperforms the vendor supplied OpenSHMEM implementation in most cases on the Cray XK system by up to 40% with respect to message rate and up to 70% for the execution of application kernels.

Baker, Matthew B↗

Assessment and Use of State-Specific Factors in the Implementation of Safeguards

The use of safeguards-relevant features and characteristics of a State in the implementation of safeguards has been a long-standing practice of the International Atomic Energy Agency (IAEA). These ‘State-specific factors’ can affect the development of State-level safeguards approaches and the planning, conduct and evaluation of safeguards activities. The IAEA has identified six State-specific factors for systematic consideration and use in the application of the State-level concept. These factors are: (i) the type of safeguards agreement in force for the State and the nature of the safeguards conclusion drawn by the IAEA; (ii) the nuclear fuel cycle and related technical capabilities of the State; (iii) the technical capabilities of the State or regional system of accounting for and control of nuclear material; (iv) the ability of the IAEA to implement certain safeguards measures in the State; (v) the nature and scope of cooperation between the State and the IAEA in the implementation of safeguards; and (vi) the IAEA’s experience in implementing safeguards in the State. State-specific factors are not to be used for rating or grading a State’s safeguards credentials but to identify issues that could affect the effectiveness or efficiency of safeguards implementation for the State. IAEA reports and presentations on the State-level concept have described these factors and have given examples of information that could be considered in assessing each factor. This paper expands upon the IAEA examples and makes recommendations as to how State-specific factors could be assessed by the IAEA and how these factors might affect safeguards implementation. Although quantitative metrics were considered for assessing the State-specific factors, it was determined that the general State characteristics comprising the factors cannot be meaningfully quantified; however, performance indicators can be developed for some elements comprising some factors. The paper thus discusses ‘considerations’ that the IAEA should assess with respect to the State-specific factors (iii), (v), and (vi) and how those considerations could affect safeguards implementation.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗