Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “distributed memory parallel”

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 343 records · Page 19

On the memory attribution problem: A solution and case study using MPI

As parallel applications running on large–scale computing systems become increasingly memory constrained, the ability to attribute memory usage to the various components of the application is becoming increasingly important. We present the design and implementation of memnesia, a novel memory usage profiler for parallel and distributed message–passing applications. Our approach captures both application– and message–passing library–specific memory usage statistics from unmodified binaries dynamically linked to a message–passing communication library. Using microbenchmarks and proxy applications, we evaluated our profiler across three Message Passing Interface (MPI) implementations and two hardware platforms. Furthermore, the results show that our approach and the corresponding implementation can accurately quantify memory resource usage as a function of time, scale, communication workload, and software or hardware system architecture, clearly distinguishing between application and MPI library memory usage at a per–process level. With this new capability, we show that job size, communication workload, and hardware/software architecture influence peak runtime memory usage. In practice, this tool provides a potentially valuable source of information for application developers seeking to measure and optimize memory usage.

97 MATHEMATICS AND COMPUTING↗

Use of networked workstations for parallel nonlinear structural dynamic simulations of rotating bladed-disk assemblies

The principal objective of this research is to investigate, develop and demonstrate coarse-grained, parallel-processing strategies for nonlinear dynamic simulations for rotating bladed-disk assemblies. The parallel -processing strategies addressed include numerical algorithms for parallel nonlinear solutions and techniques to effect load balancing among processors. The parallel environment employed is a distributed-memory, coarse-grained one consisting of networked workstations. A parallel explicit time integration method has been implemented for transient nonlinear solutions of rotationg bladed-disk assemblies. Automatic domain partitioning techniques have been investigated for load balancing among processors. Advanced computing environments, data structures and interactive computer graphics all contribute to an integrated parallel finite element analysis system to facilitate more efficient and powerful dynamic simulations.

Hsieh, Shang-Hsien↗

Exploring MPI Communication Models for Graph Applications Using Graph Matching as a Case Study

Traditional implementations of parallel graph operations on distributed memory platforms are written using Message Passing Interface (MPI) point to point communication primitives such as Send-Recv (blocking and nonblocking). Apart from this classical model, the MPI community has over the years added other communication models; however, their suitability for handling the irregular traffic workloads typical of graph operations remain comparatively less explored. Our aim in this paper is to study these relatively underutilized communication models of MPI for graph applications. More specifically, we evaluate MPI’s one-sided programming, or Remote Memory Access (RMA), and nearest neighborhood collectives using a process graph topology. There are features in these newer models that are intended to better map to irregular communication patterns, as exemplified in graph algorithms. As a concrete application for our case study, we use distributed memory implementations of a weighted graph matching algorithm to investigate performances of MPI-3 RMA and neighborhood collective operations compared to nonblocking Send- Recv. A matching in a graph is a subset of edges such that no two matched edges are incident on the same vertex. A maximum weight matching is a matching of maximum weight computed as the sum of the weights of matched edges. Algorithms for optimal matching have quadratic complexity and are difficult to parallelize. More importantly, execution of graph matching is dominated by high volume of irregular memory accesses, making it an ideal candidate for studying the effects of various MPI communication models on graph applications at scale. Our neighborhood collectives and RMA implementations yields up to 6× speedup over traditional optimized nonblocking Send-Recv implementations, on thousands of cores of the NERSC Cori supercomputer. We believe the lessons learned from this case study can be adopted to benefit a wider range of graph application codes.

Ghosh, Sayan↗

Work stealing for GPU-accelerated parallel programs in a global address space framework

Task parallelism is an attractive approach to automatically load balance the computation in a parallel system and adapt to dynamism exhibited by parallel systems. Exploiting task parallelism through work stealing has been extensively studied in shared and distributed-memory contexts. In this paper, we study the design of a system that uses work stealing for dynamic load balancing of task-parallel programs executed on hybrid distributed-memory CPU-graphics processing unit (GPU) systems in a global-address space framework. We take into account the unique nature of the accelerator model employed by GPUs, the significant performance difference between GPU and CPU execution as a function of problem size, and the distinct CPU and GPU memory domains. We consider various alternatives in designing a distributed work stealing algorithm for CPU-GPU systems, while taking into account the impact of task distribution and data movement overheads. These strategies are evaluated using microbenchmarks that capture various execution configurations as well as the state-of-the-art CCSD(T) application module from the computational chemistry domain

97 MATHEMATICS AND COMPUTING↗

CG-Kit: Code Generation Toolkit for performant and maintainable variants of source code applied to Flash-X hydrodynamics simulations

CG-Kit is a new Code Generation tool-Kit that we have developed as a part of the solution for portability and maintainability for multiphysics computing applications. The development of CG-Kit is rooted in the urgent need created by the shifting landscape of high-performance computing platforms and the algorithmic complexities of a particular large-scale multiphysics application: Flash-X. To efficiently use computing resources on a heterogeneous node, an application must have a map of computation to resources and a mechanism to move the data and computation to the resources according to the map. Most existing performance portability solutions are focussed on abstracting the expression of computations so that a unified source code can be specialized to run on different resources. However, such an approach is insufficient for a code like Flash-X, which has a multitude of code components that can be assembled in various permutations and combinations to form different instances of applications. Similar challenges apply to any code that has composability, where a single specified way of apportioning work among devices may not be optimal. Additionally, use cases arise where the optimal control flow of computation may differ for different devices while the underlying numerics remain identical. This combination leads to unique challenges including handling an existing large code base in Fortran and/or C/C++, subdivision of code into a great variety of units supporting a wide range of physics and numerical methods, different parallelization techniques for distributed and shared memory systems and accelerator devices, and heterogeneity of computing platforms requiring coexisting variants of parallel algorithms. All of these challenges demand that scientific software developers apply existing knowledge about domain applications, algorithms, and computing platforms to determine custom abstractions and granularity for code generation. There is a critical lack of tools to tackle those problems. CG-Kit is designed to fill this gap by providing a user with the ability to express their desired control flow and computation-to-resource map in the form a pseudocode-like recipe. It consists of standalone tools that can be combined into highly specific and, we argue, highly effective portability and maintainability toolchains. Here we present the design of our new tools: parametrized source trees, control flow graphs, and recipes. The tools are implemented in Python. They are agnostic to the programming language of the source code targeted for code generation. In conclusion, we demonstrate the capabilities of the toolkit with two examples, first, multithreaded variants of the basic AXPY operation, and second, variants of parallel algorithms within a hydrodynamics solver, called Spark, from Flash-X that operates on block-structured adaptive meshes.

Algorithmic portability↗

Implementation of a Parallel Kalman Filter for Stratospheric Chemical Tracer Assimilation

A Kalman filter for the assimilation of long-lived atmospheric chemical constituents has been developed for two-dimensional transport models on isentropic surfaces over the globe. An important attribute of the Kalman filter is that it calculates error covariances of the constituent fields using the tracer dynamics. Consequently, the current Kalman-filter assimilation is a five-dimensional problem (coordinates of two points and time), and it can only be handled on computers with large memory and high floating point speed. In this paper, an implementation of the Kalman filter for distributed-memory, message-passing parallel computers is discussed. Two approaches were studied: an operator decomposition and a covariance decomposition. The latter was found to be more scalable than the former, and it possesses the property that the dynamical model does not need to be parallelized, which is of considerable practical advantage. This code is currently used to assimilate constituent data retrieved by limb sounders on the Upper Atmosphere Research Satellite. Tests of the code examined the variance transport and observability properties. Aspects of the parallel implementation, some timing results, and a brief discussion of the physical results will be presented.

Chang, Lang-Ping↗

A communication-avoiding, hybrid-parallel, rank-revealing orthogonalization method.

Orthogonalization consumes much of the run time of many iterative methods for solving sparse linear systems and eigenvalue problems. Commonly used algorithms, such as variants of Gram-Schmidt or Householder QR, have performance dominated by communication. Here, 'communication' includes both data movement between the CPU and memory, and messages between processors in parallel. Our Tall Skinny QR (TSQR) family of algorithms requires asymptotically fewer messages between processors and data movement between CPU and memory than typical orthogonalization methods, yet achieves the same accuracy as Householder QR factorization. Furthermore, in block orthogonalizations, TSQR is faster and more accurate than existing approaches for orthogonalizing the vectors within each block ('normalization'). TSQR's rank-revealing capability also makes it useful for detecting deflation in block iterative methods, for which existing approaches sacrifice performance, accuracy, or both. We have implemented a version of TSQR that exploits both distributed-memory and shared-memory parallelism, and supports real and complex arithmetic. Our implementation is optimized for the case of orthogonalizing a small number (5-20) of very long vectors. The shared-memory parallel component uses Intel's Threading Building Blocks, though its modular design supports other shared-memory programming models as well, including computation on the GPU. Our implementation achieves speedups of 2 times or more over competing orthogonalizations. It is available now in the development branch of the Trilinos software package, and will be included in the 10.8 release.

99 GENERAL AND MISCELLANEOUS↗

Parallel computing for probabilistic fatigue analysis

This paper presents the results of Phase I research to investigate the most effective parallel processing software strategies and hardware configurations for probabilistic structural analysis. We investigate the efficiency of both shared and distributed-memory architectures via a probabilistic fatigue life analysis problem. We also present a parallel programming approach, the virtual shared-memory paradigm, that is applicable across both types of hardware. Using this approach, problems can be solved on a variety of parallel configurations, including networks of single or multiprocessor workstations. We conclude that it is possible to effectively parallelize probabilistic fatigue analysis codes; however, special strategies will be needed to achieve large-scale parallelism to keep large number of processors busy and to treat problems with the large memory requirements encountered in practice. We also conclude that distributed-memory architecture is preferable to shared-memory for achieving large scale parallelism; however, in the future, the currently emerging hybrid-memory architectures will likely be optimal.

Sues, Robert H.↗

pFlogger: The Parallel Fortran Logging Utility

In the context of high performance computing (HPC), software investments in support of text-based diagnostics, which monitor a running application, are typically limited compared to those for other types of IO. Examples of such diagnostics include reiteration of configuration parameters, progress indicators, simple metrics (e.g., mass conservation, convergence of solvers, etc.), and timers. To some degree, this difference in priority is justifiable as other forms of output are the primary products of a scientific model and, due to their large data volume, much more likely to be a significant performance concern. In contrast, text-based diagnostic content is generally not shared beyond the individual or group running an application and is most often used to troubleshoot when something goes wrong. We suggest that a more systematic approach enabled by a logging facility (or 'logger)' similar to those routinely used by many communities would provide significant value to complex scientific applications. In the context of high-performance computing, an appropriate logger would provide specialized support for distributed and shared-memory parallelism and have low performance overhead. In this paper, we present our prototype implementation of pFlogger - a parallel Fortran-based logging framework, and assess its suitability for use in a complex scientific application.

Clune, Tom↗

Position Paper - pFLogger: The Parallel Fortran Logging framework for HPC Applications

In the context of high performance computing (HPC), software investments in support of text-based diagnostics, which monitor a running application, are typically limited compared to those for other types of IO. Examples of such diagnostics include reiteration of configuration parameters, progress indicators, simple metrics (e.g., mass conservation, convergence of solvers, etc.), and timers. To some degree, this difference in priority is justifiable as other forms of output are the primary products of a scientific model and, due to their large data volume, much more likely to be a significant performance concern. In contrast, text-based diagnostic content is generally not shared beyond the individual or group running an application and is most often used to troubleshoot when something goes wrong. We suggest that a more systematic approach enabled by a logging facility (or logger) similar to those routinely used by many communities would provide significant value to complex scientific applications. In the context of high-performance computing, an appropriate logger would provide specialized support for distributed and shared-memory parallelism and have low performance overhead. In this paper, we present our prototype implementation of pFlogger a parallel Fortran-based logging framework, and assess its suitability for use in a complex scientific application.

Fortran↗

POSITION PAPER - pFLogger: The Parallel Fortran Logging Framework for HPC Applications

In the context of high performance computing (HPC), software investments in support of text-based diagnostics, which monitor a running application, are typically limited compared to those for other types of IO. Examples of such diagnostics include reiteration of configuration parameters, progress indicators, simple metrics (e.g., mass conservation, convergence of solvers, etc.), and timers. To some degree, this difference in priority is justifiable as other forms of output are the primary products of a scientific model and, due to their large data volume, much more likely to be a significant performance concern. In contrast, text-based diagnostic content is generally not shared beyond the individual or group running an application and is most often used to troubleshoot when something goes wrong. We suggest that a more systematic approach enabled by a logging facility (or 'logger') similar to those routinely used by many communities would provide significant value to complex scientific applications. In the context of high-performance computing, an appropriate logger would provide specialized support for distributed and shared-memory parallelism and have low performance overhead. In this paper, we present our prototype implementation of pFlogger - a parallel Fortran-based logging framework, and assess its suitability for use in a complex scientific application.

Clune, Thomas L.↗

SSCA1-K1

SSCA1-K1 is a parallel implementation of kernel 1 of the SSCA1 benchmark suite released by the DARPA HPCS program. This kernel is able to run in parallel on a distributed shared memory system at extreme scales using OpenSHMEM.

Baker, Matthew↗

Medial axis and local thickness computation using the Fast Sweeping Method

This report describes an efficient and robust voxel-based methodology for computing the medial axis, local thickness, and distance-to-skeleton of arbitrary three-dimensional geometries. It is assumed that the object can be represented by an exact or approximate signed distance function on a discrete grid. The gradient of such function is used to formulate a hyperbolic partial differential equation (PDE) that models the collapse of the position vector in space. By exploiting the causality property of the PDE, the Fast Sweeping Method is able to obtain the solution in a finite number of sweeps independent of the mesh resolution. The intersection of characteristic lines leads to the formation of shocks and a discrete bisector function is used to identify the medial axis. The same PDE approach is used to compute the local thickness inside the object and obtain the distance-to-skeleton field. Multiple examples are given in two and three dimensions along with a resolution study. The methodology has optimal complexity and yields subsecond computational times for geometries with over a million zones on a single core. The methodology is also capable of parallelization across shared and distributed memory architectures.

97 MATHEMATICS AND COMPUTING↗

Programming model for distributed intelligent systems

A programming model and architecture which was developed for the design and implementation of complex, heterogeneous measurement and control systems is described. The Multigraph Architecture integrates artificial intelligence techniques with conventional software technologies, offers a unified framework for distributed and shared memory based parallel computational models and supports multiple programming paradigms. The system can be implemented on different hardware architectures and can be adapted to strongly different applications.

Sztipanovits, J.↗

Flexible language constructs for large parallel programs

The goal of the research described is to develop flexible language constructs for writing large data parallel numerical programs for distributed memory (MIMD) multiprocessors. Previously, several models have been developed to support synchronization and communication. Models for global synchronization include SIMD (Single Instruction Multiple Data), SPMD (Single Program Multiple Data), and sequential programs annotated with data distribution statements. The two primary models for communication include implicit communication based on shared memory and explicit communication based on messages. None of these models by themselves seem sufficient to permit the natural and efficient expression of the variety of algorithms that occur in large scientific computations. An overview of a new language that combines many of these programming models in a clean manner is given. This is done in a modular fashion such that different models can be combined to support large programs. Within a module, the selection of a model depends on the algorithm and its efficiency requirements. An overview of the language and discussion of some of the critical implementation details is given.

Rosing, Matthew↗

Aligning parallel arrays to reduce communication

Axis and stride alignment is an important optimization in compiling data-parallel programs for distributed-memory machines. We previously developed an optimal algorithm for aligning array expressions. Here, we examine alignment for more general program graphs. We show that optimal alignment is NP-complete in this setting, so we study heuristic methods. This paper makes two contributions. First, we show how local graph transformations can reduce the size of the problem significantly without changing the best solution. This allows more complex and effective heuristics to be used. Second, we give a heuristic that can explore the space of possible solutions in a number of ways. We show that some of these strategies can give better solutions than a simple greedy approach proposed earlier. Our algorithms have been implemented; we present experimental results showing their effect on the performance of some example programs running on the CM-5.

Sheffler, Thomas J.↗

Sparse Linear Algebra Toolkit for Computational Aerodynamics

Finding solutions to sparse linear systems of equations is an essential step in Computational Engineering applications of interest to NASA. Linear systems of equations are composed and solved in almost every computational engineering application. The characteristics of linear systems vary greatly from one application to another. Accordingly, there are a wide variety of methods for the solution of linear systems of equations. The operations and methods prepared by the authors are focused on linear systems of interest to NASA, primarily those associated with Computational Fluid Dynamics (CFD), Aeroelasticity, and Aeroacoustics. The Sparse Linear Algebra Toolkit (SLAT) is a coordinated collection of software featuring operations, methods, and data structures that are useful when solving sparse linear systems of equations on modern computer architectures. The implemented operations and methods are designed and tuned for parallelism in shared memory, in distributed memory, and across the hybrid combination of distributed-shared memory. The toolkit includes novel methods and implementations for modern architectures and facilitates development of new approaches for meeting NASA’s evolving computational engineering challenges using evolving computer architectures that are not available in vendor libraries. In this paper, significant features and interfaces within SLAT are presented and verified for simulations performed with NASA’s CFD solver, FUN3D. The runtime and scaling performance of the Generalized Minimum Residual (GMRES) method implemented in SLAT is analyzed for the linear subproblems within the solution of turbulent Navier-Stokes equations employed in the simulation of high-lift configurations. Prior to this work, the SPARSKIT GMRES implementation was the only Krylov subspace method available within FUN3D. A strong scaling study shows the SLAT GMRES implementation facilitates accurate Reynolds-averaged Navier-Stokes CFD solutions between 15% and 56% faster than the SPARSKIT GMRES implementation.

Stephen L Wood↗

SSCA1-K1

SSCA1-K1 is a parallel implementation of kernel 1 of the SSCA1 benchmark suite released by the DARPA HPCS program. This kernel is able to run in parallel on a distributed shared memory system at extreme scales using OpenSHMEM.

Baker, Matthew↗