Search NASA⌕ Search

SEARCH · Search NASA

Results for “parallel systems”

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 667 records · Page 37

PRIMA-X - Performance Retargeting of Instrumentation, Measurement, and Analysis Technologies for Exascale Computing

The PRIMA-X (Performance Retargeting of Instrumentation, Measurement, and Analysis Technologies for Exascale Computing) project is the successor of the DOE PRIMA (Performance Refactoring of Instrumentation, Measurement, and Analysis Technologies for Petascale Computing) project, which addressed the challenge of creating a core measurement infrastructure that would serve as a common platform for both integrating leading parallel performance systems (notably TAU and Scalasca) and developing next-generation scalable performance tools. The PRIMA-X project shifts the focus away from refactorization of robust performance tools towards a re-targeting of the parallel performance measurement and analysis architecture for extreme scales. The massive concurrency, asynchronous execution dynamics, hardware heterogeneity, and multi-objective prerequisites (performance, power, resilience) that identify exascale systems introduce fundamental constraints on the ability to carry forward existing performance methodologies. In particular, there must be a deemphasis of per-thread observation techniques to significantly reduce the otherwise unsustainable flood of redundant performance data. Instead, it will be necessary to assimilate multi-level resource observations into macroscopic performance views, from which resilient performance metrics can be attributed to the computational features of the application. This requires a scalable framework for node-level and system-wide monitoring and runtime analyses of dynamic performance information. Also, the interest in optimizing parallelism parameters with respect to performance and energy drives the integration of tool capabilities in the exascale environment further. Initially, PRIMA-X was a collaborative project between the University of Oregon (lead institution) and the German Research School for Simulation Sciences (GRS). Because Prof. Wolf, the PI at GRS, accepted a position as full professor at Technische Universitaet Darmstadt (TU Darmstadt) starting February 1st, 2015, the work of GRS was continued at TU Darmstadt. This report covers the work at TU Darmstadt after the transition. The first main accomplishment of TU Darmstadt is the development of different techniques to aggregate performance data on the level of threads. TU Darmstadt evaluated different schemes designed at GRS during the first phase of this project and integrated them into Score-P, a widely used performance measurement framework for HPC applications. The second main accomplishment is a substantial increase of Score-P’s scalability, achieved by improving its internal representation of the underlying system. Third, we extended our performance-modeling tool Extra-P to automatically create models with more than one input parameter (e.g., process count and input size), which was previously impossible. These models allow the performance behavior of an application to be extrapolated to larger machines. Specific applications of the new multi-parameter capability realized in this project include modeling the isoefficiency function of task-based applications and a novel co-design methodology. Further extensions of Extra-P comprise online modeling functionality, automatic refinement of the model search space, and segmented performance modeling. Further contributions include new locality metrics for both shared- and distributed-memory applications, a new way of measuring the impact of inter-application inference on the execution time of an application, and finally an automatic method that selects appropriate OpenMP constructs for the parallelization of sequential code and classifies the affected variables based on their sharing semantics.

97 MATHEMATICS AND COMPUTING↗

Supporting the Global Arrays PGAS Model Using MPI One-Sided Communication

The industry-standard Message Passing Interface (MPI) provides one-sided communication functionality and is available on virtually every parallel computing system. However, it is believed that MPI’s one-sided model is not rich enough to support higher-level global address space parallel programming models. We present the first successful application of MPI one-sided communication as a runtime system for a PGAS model, Global Arrays (GA). This work has an immediate impact on users of GA applications, such as NWChem, who often must wait several months to a year or more before GA becomes available on a new architecture. We explore challenges present in the application of MPI-2 to PGAS models and motivate new features in the upcoming MPI-3 standard. The performance of our system is evaluated on several popular high-performance computing architectures through communication benchmarking and application benchmarking using the NWChem computational chemistry suite.

ARMCI↗

Status report on HFIR irradiation of optimized alumina forming alloys

Properties of FeCrAl alloys under neutron irradiation are of interest because of these materials’ potential application as accident-tolerant fuel cladding in nuclear systems. In parallel, alumina-forming austenitic (AFA) alloys are of interest for use as structural materials in advanced nuclear systems for their potential higher resistance to embrittlement and high-temperature steam oxidation resistance. An irradiation campaign for fiscal year 2024 has been developed under the Advanced Fuels Campaign to perform irradiation testing of various FeCrAl and AFA alloys in Oak Ridge National Laboratory’s High Flux Isotope Reactor (HFIR). The goals of this irradiation campaign are to (1) study the impact of minor alloying elements on the neutron-irradiated mechanical properties of FeCrAl alloys and (2) collect neutron-irradiated mechanical properties on AFA alloys for comparison with those of FeCrAl alloys. This campaign will include both tensile and fracture toughness specimens tested following HFIR irradiation at temperatures representative of normal operating conditions in light-water reactors. The pre-irradiation characterization to date, the irradiation plan for the FeCrAl and AFA specimens, and the subsequent post-irradiation experimental test plan are presented in this report, along with the status of HFIR builds and scheduled insertion dates.

36 MATERIALS SCIENCE↗

Design for Reliability (DfR) in Space Life Support

The engineering process of Design for Reliability (DfR) is well established in the automotive and aerospace industries. DfR should be useful in the future development of space life support systems. DfR is a sequence of tasks that develop system requirements and plan reliability analysis and testing. First and fundamentally, the reliability requirement is defined. Next the system reliability model is developed, often using a reliability block diagram. The overall system reliability requirement is allocated to the subsystems and an estimate of the attainable reliability is made. This expected reliability can be improved by simplifying the design by removing components or by replacing less reliable components. Improving reliability can require difficult compromises, such as reducing performance requirements, increasing budget, or extending testing. The actual system reliability can be determined only by testing, which should continue long enough to provide the required confidence in the measured value. New systems often have unexpected design errors that cause failures in early testing. The usual reliability improvement process of testing, finding the failure modes, and redesigning to remove them reduces the failure rate and is referred to as “reliability growth.” After redesign has been completed, the system should be further tested to determine the actual achieved reliability more accurately. If the final system failure rate is too high, redundant systems can be used to improve overall operational reliability. Adding redundancy simply to increase the one- or two-fault tolerance metric may sometimes reduce reliability. Reliability can be improved in three ways: redesigning the system to include more reliable subsystems and components, reliability growth testing and failure mode removal, and by using parallel redundant systems. DfR should combine these approaches to achieve the required reliability while managing performance, cost, and schedule.

Reliability↗

Design for Reliability (DfR) in Space Life Support

The engineering process of Design for Reliability (DfR) is well established in the automotive and aerospace industries. DfR should be useful in the future development of space life support systems. DfR is a sequence of tasks that develop system requirements and plan reliability analysis and testing. First and fundamentally, the reliability requirement is defined. Next the system reliability model is developed, often using a reliability block diagram. The overall system reliability requirement is allocated to the subsystems and an estimate of the attainable reliability is made. This expected reliability can be improved by simplifying the design by removing components or by replacing less reliable components. Improving reliability can require difficult compromises, such as reducing performance requirements, increasing budget, or extending testing. The actual system reliability can be determined only by testing, which should continue long enough to provide the required confidence in the measured value. New systems often have unexpected design errors that cause failures in early testing. The usual reliability improvement process of testing, finding the failure modes, and redesigning to remove them reduces the failure rate and is referred to as “reliability growth.” After redesign has been completed, the system should be further tested to determine the actual achieved reliability more accurately. If the final system failure rate is too high, redundant systems can be used to improve overall operational reliability. Adding redundancy simply to increase the one- or two-fault tolerance metric may sometimes reduce reliability. Reliability can be improved in three ways: redesigning the system to include more reliable subsystems and components, reliability growth testing and failure mode removal, and by using parallel redundant systems. DfR should combine these approaches to achieve the required reliability while managing performance, cost, and schedule.

Reliability↗

PRIMA-X Final Report

The PRIMA-X (Performance Retargeting of Instrumentation, Measurement, and Analysis Technologies for Exascale Computing) project is the successor of the DOE PRIMA (Performance Refactoring of Instrumentation, Measurement, and Analysis Technologies for Petascale Computing) project, which addressed the challenge of creating a core measurement infrastructure that would serve as a common platform for both integrating leading parallel performance systems (notably TAU and Scalasca) and developing next-generation scalable performance tools. The PRIMA-X project shifts the focus away from refactorization of robust performance tools towards a re-targeting of the parallel performance measurement and analysis architecture for extreme scales. The massive concurrency, asynchronous execution dynamics, hardware heterogeneity, and multi-objective prerequisites (performance, power, resilience) that identify exascale systems introduce fundamental constraints on the ability to carry forward existing performance methodologies. In particular, there must be a deemphasis of per-thread observation techniques to significantly reduce the otherwise unsustainable flood of redundant performance data. Instead, it will be necessary to assimilate multi-level resource observations into macroscopic performance views, from which resilient performance metrics can be attributed to the computational features of the application. This requires a scalable framework for node-level and system-wide monitoring and runtime analyses of dynamic performance information. Also, the interest in optimizing parallelism parameters with respect to performance and energy drives the integration of tool capabilities in the exascale environment further. Initially, PRIMA-X was a collaborative project between the University of Oregon (lead institution) and the German Research School for Simulation Sciences (GRS). Because Prof. Wolf, the PI at GRS, accepted a position as full professor at Technische Universität Darmstadt (TU Darmstadt) starting February 1st, 2015, the project ended at GRS on January 31st, 2015. This report reflects the work accomplished at GRS until then. The work of GRS is expected to be continued at TU Darmstadt. The first main accomplishment of GRS is the design of different thread-level aggregation techniques. We created a prototype capable of aggregating the thread-level information in performance profiles using these techniques. The next step will be the integration of the most promising techniques into the Score-P measurement system and their evaluation. The second main accomplishment is a substantial increase of Score-P’s scalability, achieved by improving the design of the system-tree representation in Score-P’s profile format. We developed a new representation and a distributed algorithm to create the scalable system tree representation. Finally, we developed a lightweight approach to MPI wait-state profiling. Former algorithms either needed piggy-backing, which can cause significant runtime overhead, or tracing, which comes with its own set of scaling challenges. Our approach works with local data only and, thus, is scalable and has very little overhead.

97 MATHEMATICS AND COMPUTING↗

Unobtrusive Software and System Health Management with R2U2 on a Parallel MIMD Coprocessor

Dynamic monitoring of software and system health of a complex cyber-physical system requires observers that continuously monitor variables of the embedded software in order to detect anomalies and reason about root causes. There exists a variety of techniques for code instrumentation, but instrumentation might change runtime behavior and could require costly software re-certification. In this paper, we present R2U2E, a novel realization of our real-time, Realizable, Responsive, and Unobtrusive Unit (R2U2). The R2U2E observers are executed in parallel on a dedicated 16-core EPIPHANY co-processor, thereby avoiding additional computational overhead to the system under observation. A DMA-based shared memory access architecture allows R2U2E to operate without any code instrumentation or program interference.

Schumann, Johann↗

Self-consistent nonlinear kinetic simulations of the anomalous Doppler instability of suprathermal electrons in plasmas

Suprathermal tails in the distributions of electron velocities parallel to the magnetic field are found in many areas of plasma physics, from magnetic confinement fusion to solar system plasmas. Parallel electron kinetic energy can be transferred into plasma waves and perpendicular gyration energy of particles through the anomalous Doppler instability (ADI), provided that energetic electrons with parallel velocities v{sub ||}≥(ω+Ω{sub ce})/k{sub ||} are present; here Ω{sub ce} denotes electron cyclotron frequency, ω the wave angular frequency, and k{sub ||} the component of wavenumber parallel to the magnetic field. This phenomenon is widely observed in tokamak plasmas. Here, we present the first fully self-consistent relativistic particle-in-cell simulations of the ADI, spanning the linear and nonlinear regimes of the ADI. We test the robustness of the analytical theory in the linear regime and follow the ADI through to the steady state. By directly evaluating the parallel and perpendicular dynamical contributions to j·E in the simulations, we follow the energy transfer between the excited waves and the bulk and tail electron populations for the first time. We find that the ratio Ω{sub ce}/(ω{sub pe}+Ω{sub ce}) of energy transfer between parallel and perpendicular, obtained from linear analysis, does not apply when damping is fully included, when we find it to be ω{sub pe}/(ω{sub pe}+Ω{sub ce}); here ω{sub pe} denotes the electron plasma frequency. We also find that the ADI can arise beyond the previously expected range of plasma parameters, in particular when Ω{sub ce}>ω{sub pe}. The simulations also exhibit a spectral feature which may correspond to the observations of suprathermal narrowband emission at ω{sub pe} detected from low density tokamak plasmas.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Operationally Efficient Propulsion System Study (OEPSS) Data Book: Integrated Booster Propulsion Module (BPM) Engine Start Dynamics - Volume 8

A fluid-dynamic, digital-transient computer model of an integrated, parallel propulsion system was developed for the CDC mainframe and the SUN workstation computers. Since all STME component designs were used for the integrated system, computer subroutines were written characterizing the performance and geometry of all the components used in the system, including the manifolds. Three transient analysis reports were completed. The first report evaluated the feasibility of integrated engine systems in regards to the start and cutoff transient behavior. The second report evaluated turbopump out and combined thrust chamber/turbopump out conditions. The third report presented sensitivity study results in staggered gas generator spin start and in pump performance characteristics.

Kemp, Victoria R.↗

A robust hierarchical solver for ill-conditioned systems with applications to ice sheet modeling

A hierarchical solver is proposed for solving sparse ill-conditioned linear systems in parallel. The solver is based on a modification of the LoRaSp method, but employs a deferred-compression technique, which provably reduces the approximation error and significantly improves efficiency. Moreover, the deferred-compression technique introduces minimal overhead and does not affect parallelism. As a result, the new solver achieves linear computational complexity under mild assumptions and excellent parallel scalability. To demonstrate the performance of the new solver, we focus on applying it to solve sparse linear systems arising from ice sheet modeling. The strong anisotropic phenomena associated with the thin structure of ice sheets creates serious challenges for existing solvers. To address the anisotropy, we additionally developed a customized partitioning scheme for the solver, which captures the strong-coupling direction accurately. In general, the partitioning can be computed algebraically with existing software packages, and thus the new solver is generalizable for solving other sparse linear systems. Our results show that ice sheet problems of about 300 million degrees of freedom have been solved in just a few minutes using a thousand processors.

97 MATHEMATICS AND COMPUTING↗

Improving Block-level Efficiency with scsi-mq

Current generation solid-state storage devices are exposing a new bottlenecks in the SCSI and block layers of the Linux kernel, where IO throughput is limited by lock contention, inefficient interrupt handling, and poor memory locality. To address these limitations, the Linux kernel block layer underwent a major rewrite with the blk-mq project to move from a single request queue to a multi-queue model. The Linux SCSI subsystem rework to make use of this new model, known as scsi-mq, has been merged into the Linux kernel and work is underway for dm-multipath support in the upcoming Linux 4.0 kernel. These pieces were necessary to make use of the multi-queue block layer in a Lustre parallel filesystem with high availability requirements. We undertook adding support of the 3.18 kernel to Lustre with scsi-mq and dm-multipath patches to evaluate the potential of these efficiency improvements. In this paper we evaluate the block-level performance of scsi-mq with backing storage hardware representative of a HPC-targerted Lustre filesystem. Our findings show that SCSI write request latency is reduced by as much as 13.6%. Additionally, when profiling the CPU usage of our prototype Lustre filesystem, we found that CPU idle time increased by a factor of 7 with Linux 3.18 and blk-mq as compared to a standard 2.6.32 Linux kernel. Our findings demonstrate increased efficiency of the multi-queue block layer even with disk-based caching storage arrays used in existing parallel filesystems.

Cluster Computing↗

Multiple Coarse Grid Multigrid Methods for Solving Elliptic Problems

In this paper we describe some classes of multigrid methods for solving large linear systems arising in the solution by finite difference methods of certain boundary value problems involving Poisson's equation on rectangular regions. If parallel computing systems are used, then with standard multigrid methods many of the processors will be idle when one is working at the coarsest grid levels. We describe the use of Multiple Coarse Grid MultiGrid (MCGMG) methods. Here one first constructs a periodic set of equations corresponding to the given system. One then constructs a set of coarse grids such that for each grid corresponding to the grid size h there are four grids corresponding to the grid size 2*h. Multigrid operations such as restriction of residuals and interpolation of corrections are done in parallel at each grid level. For suitable choices of the multigrid operators the MCGMG method is equivalent to the Parallel Superconvergent MultiGrid (PSMG) method of Frederickson and McBryan. The convergence properties of MCGMG methods can be accurately analyzed using spectral methods.

Xiao, Shengyou↗

Exploiting user activeness for data retention in HPC systems

HPC systems typically rely on the fixed-lifetime (FLT) data retention strategy, which only considers temporal locality of data accesses to parallel file systems. However, our extensive analysis based on the leadership-class HPC system traces suggests that the FLT approach often fails to capture the dynamics in users' behavior and leads to undesired data purge. In this study, we propose an activeness-based data retention (ActiveDR) solution, which advocates considering the data retention approach from a holistic activeness-based perspective. By evaluating the frequency and impact of users' activities, ActiveDR prioritizes the file purge process for inactive users and rewards active users with extended file lifetime on parallel storage. Our extensive evaluations based on the traces of the prior Titan supercomputer show that, when reaching the same purge target, ActiveDR achieves up to 37% file miss reduction as compared to the current FLT retention methodology.

Zhang, Wei↗

Scale-Dependent Fracture-Matrix Interactions And Their Impact on Radionuclide Transport - Final Report

Matrix diffusion and adsorption within a rock matrix are widely regarded as important mechanisms for retarding the transport of radionuclides and other solutes in fractured rock (e.g., Neretnieks, 1980; Tang et al., 1981; Maloszewski and Zuber, 1985; Novakowski and Lapcevic, 1994; Jardine et al., 1999; Zhou and Xie, 2003; Reimus et al., 2003a,b). When remediation options are being evaluated for old sources of contamination, where a large fraction of contaminants reside within the rock matrix, slow diffusion out of the matrix greatly increases the difficulty and timeframe of remediation. Estimating the rates of solute exchange between fractures and the adjacent rock matrix is a critical factor in quantifying immobilization and/or remobilization of DOE-relevant contaminants within the subsurface. In principle, the most rigorous approach to modeling solute transport with fracture-matrix interaction would be based on local-scale coupled advection-diffusion/dispersion equations for the rock matrix and in discrete fractures that comprise the fracture network (Discrete Fracture Network and Matrix approach, hereinafter referred to as DFNM approach), fully resolving aperture variability in fractures and matrix property heterogeneity. However, such approaches are computationally demanding, and thus, many predictive models rely upon simplified models. These models typically idealize fracture rock masses as a single fracture or system of parallel fractures interacting with slabs of porous matrix or as a mobile-immobile or multi-rate mass transfer system. These idealizations provide tractable approaches for interpreting tracer tests and predicting contaminant mobility, but rely upon a fitted effective matrix diffusivity or mass-transfer coefficients. However, because these fitted parameters are based upon simplified conceptual models, their effectiveness at predicting long-term transport processes remains uncertain. Evidence of scale dependence of effective matrix diffusion coefficients obtained from tracer tests highlights this point and suggests that the underlying mechanisms and relationship between rock and fracture properties are not fully understood in large complex fracture networks. In this project, we developed a high-resolution DFN model of solute transport in fracture networks to explore and quantify the mechanisms that control transport in complex fracture networks and how these may give rise to observed scale-dependent matrix diffusion coefficients. Results demonstrate that small scale heterogeneity in the flow field caused by local aperture variability within individual fractures can lead to long-tailed breakthrough curves indicative of matrix diffusion, even in the absence of interactions with the fracture matrix. Furthermore, the temporal and spatial scale dependence of these processes highlights the inability of short-term tracer tests to estimate transport parameters that will control long-term fate and transport of contaminants in fractured aquifers.

58 GEOSCIENCES↗

Cable Tester Box

Cables are very important electrical devices that carry power and signals across multiple instruments. Any fault in a cable can easily result in a catastrophic outcome. Therefore, verifying that all cables are built to spec is a very important part of Electrical Integration Procedures. Currently, there are two methods used in lab for verifying cable connectivity. (1) Using a Break-Out Box and an ohmmeter this method is time-consuming but effective for custom cables and (2) Commercial Automated Cable Tester Boxes this method is fast, but to test custom cables often requires pre-programmed configuration files, and cables used on spacecraft are often uniquely designed for specific purposes. The idea is to develop a semi-automatic continuity tester that reduces human effort in cable testing, speeds up the electrical integration process, and ensures system safety. The JPL-Cable Tester Box is developed to check every single possible electrical connection in a cable in parallel. This system indicates connectivity through LED (light emitting diode) circuits. Users can choose to test any pin/shell (test node) with a single push of a button, and any other nodes that are shorted to the test node, even if they are in the same connector, will light up with the test node. The JPL-Cable Tester Boxes offers the following advantages: 1. Easy to use: The architecture is simple enough that it only takes 5 minutes for anyone to learn how operate the Cable Tester Box. No pre-programming and calibration are required, since this box only checks continuity. 2. Fast: The cable tester box checks all the possible electrical connections in parallel at a push of a button. If a cable normally takes half an hour to test, using the Cable Tester Box will improve the speed to as little as 60 seconds to complete. 3. Versatile: Multiple cable tester boxes can be used together. As long as all the boxes share the same electrical potential, any number of connectors can be tested together.

Lee, Jason H.↗

Uncovering Access, Reuse, and Sharing Characteristics of I/O-Intensive Files on Large-Scale Production HPC Systems

Large-scale high-performance computing (HPC) applications running on supercomputers produce large amounts of data routinely and store it in files on multi-PB shared parallel storage systems. Unfortunately, storage community has a limited understanding of the access and reuse patterns of these files. This paper investigates the access and reuse patterns of I/O-intensive files on a production-scale supercomputer.

Patel, Tirthak↗

Parallel discrete-event simulation of FCFS stochastic queueing networks

Physical systems are inherently parallel. Intuition suggests that simulations of these systems may be amenable to parallel execution. The parallel execution of a discrete-event simulation requires careful synchronization of processes in order to ensure the execution's correctness; this synchronization can degrade performance. Largely negative results were recently reported in a study which used a well-known synchronization method on queueing network simulations. Discussed here is a synchronization method (appointments), which has proven itself to be effective on simulations of FCFS queueing networks. The key concept behind appointments is the provision of lookahead. Lookahead is a prediction on a processor's future behavior, based on an analysis of the processor's simulation state. It is shown how lookahead can be computed for FCFS queueing network simulations, give performance data that demonstrates the method's effectiveness under moderate to heavy loads, and discuss performance tradeoffs between the quality of lookahead, and the cost of computing lookahead.

Nicol, David M.↗

Algorithms and programming tools for image processing on the MPP, part 2

A number of algorithms were developed for image warping and pyramid image filtering. Techniques were investigated for the parallel processing of a large number of independent irregular shaped regions on the MPP. In addition some utilities for dealing with very long vectors and for sorting were developed. Documentation pages for the algorithms which are available for distribution are given. The performance of the MPP for a number of basic data manipulations was determined. From these results it is possible to predict the efficiency of the MPP for a number of algorithms and applications. The Parallel Pascal development system, which is a portable programming environment for the MPP, was improved and better documentation including a tutorial was written. This environment allows programs for the MPP to be developed on any conventional computer system; it consists of a set of system programs and a library of general purpose Parallel Pascal functions. The algorithms were tested on the MPP and a presentation on the development system was made to the MPP users group. The UNIX version of the Parallel Pascal System was distributed to a number of new sites.

Reeves, Anthony P.↗