Search NASA⌕ Search

SEARCH · Search NASA

Results for “Parallel processors”

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 505 records · Page 28

IMEX Runge-Kutta Parareal for Non-diffusive Equations

Parareal is a widely studied parallel-in-time method that can achieve meaningful speedup on certain problems. However, it is well known that the method typically performs poorly on non-diffusive equations. This paper analyzes linear stability and convergence for IMEX Runge-Kutta Parareal methods on non-diffusive equations. By combining standard linear stability analysis with a simple convergence analysis, we find that certain Parareal configurations can achieve parallel speedup on non-diffusive equations. These stable configurations all posses low iteration counts, large block sizes, and a large number of processors. Numerical examples using the nonlinear Schrodinger equation demonstrate the analytical conclusions.

97 MATHEMATICS AND COMPUTING↗

Roofline scaling trajectories: A method for parallel application and architectural performance analysis

The end of Dennard scaling signaled a shift in HPC supercomputer architectures from systems built from single-core processor architectures to systems built from multicore and eventually manycore architectures. This transition substantially complicated performance optimization and analysis as new programming models were created, new scaling methodologies deployed, and on-chip contention became a bottleneck to performance. Existing distributed memory performance models like logP and logGP were unable to capture this contention. The Roofline model was created to address this contention and its interplay with locality. However, to date, the Roofline model has focused on full-node concurrency. In this paper, we extend the Roofline model to capture the effects of concurrency on data locality and on-chip contention. We demonstrate the value of this new technique by evaluating the NAS parallel benchmarks on both multicore and manycore architectures under both strong-And weak-scaling regimes. In order to quantify the interplay between programming model and locality, we evaluate scaling under both the OpenMP and flat MPI programming models.

Ibrahim, K↗

Simulation of unsteady blood flows in a patient-specific compliant pulmonary artery with a highly parallel monolithically coupled fluid-structure interaction algorithm

Computational fluid dynamics (CFD) is increasingly used to study blood flows in patient-specific arteries for understanding certain cardiovascular diseases. The techniques work quite well for relatively simple problems, but need improvements when the problems become harder in the case when (1) the geometry becomes complex (from a few branches to a full pulmonary artery), (2) the model becomes more complex (from fluid-only calculation to coupled fluid-structure interaction calculation), (3) both the fluid and wall models become highly nonlinear, and (4) the computer on which we run the simulation is a supercomputer with tens of thousands of processor cores. To push the limit of CFD in all four fronts, in this paper, we develop and study a highly parallel algorithm for solving a monolithically coupled fluid-structure system for the modeling of the interaction of the blood flow and the arterial wall. As a case study, we consider a patient-specific, full size pulmonary artery obtained from CT (Computed Tomography) images, with an artificially added layer of wall with a fixed thickness. The fluid is modeled with a system of incompressible Navier-Stokes equations and the wall is modeled by a geometrically nonlinear elasticity equation. As far as we know this is the first time the unsteady blood flow in a full pulmonary artery is simulated without assuming a rigid wall. We report the proposed numerical algorithm and software scale well beyond 10,000 processor cores on a supercomputer for solving the fluid-structure interaction problem discretized with a stabilized finite element method in space and an implicit scheme in time involving hundreds of millions of unknowns.

97 MATHEMATICS AND COMPUTING↗

Scalable I/O Systems via Node-Local Storage: Approaching 1 TB/sec File I/O

In the race to PetaFLOP-speed supercomputing systems, the increase in computational capability has been accompanied by corresponding increases in CPU count, total RAM, and storage capacity. However, a proportional increase in storage bandwidth has lagged behind. In order to improve system reliability and to reduce maintenance effort for modern large-scale systems, system designers have opted to remove node-local storage from the compute nodes. Today's multi-TeraFLOP supercomputers are typically attached to parallel file systems that provide only tens of GBs/s of I/O bandwidth. As a result, such machines have access to much less than 1GB/s of I/O bandwidth per TeraFLOP of compute power, which is below the generally accepted limit required for a well-balanced system. In a many ways, the current I/O bottleneck limits the capabilities of modern supercomputers, specifically in terms of limiting their working sets and restricting fault tolerance techniques, which become critical on systems consisting of tens of thousands of components. This paper resolves the dilemma between high performance and high reliability by presenting an alternative system design which makes use of node-local storage to improve aggregate system I/O bandwidth. In this work, we focus on the checkpointing use-case and present an experimental evaluation of the Scalable Checkpoint/Restart (SCR) library, a new adaptive checkpointing library that uses node-local storage to significantly improve the checkpointing performance of large-scale supercomputers. Experiments show that SCR achieves unprecedented write speeds, reaching a measured 700GB/s of aggregate bandwidth on 8,752 processors and an estimated 1TB/s for a similarly structured machine of 12,500 processors. This corresponds to a speedup of over 70x compared to the bandwidth provided by the 10GB/s parallel file system the cluster uses. Further, SCR can adapt to an environment in which there is wide variation in performance or capacity among the individual node-local storage elements.

99 GENERAL AND MISCELLANEOUS↗

The Kokkos Ecosystem [Brief]

In 2016/2017, the field of High-Performance Computing (HPC) entered a new era driven by fundamental physics challenges to produce ever more energy and cost-efficient processors. Since the convergence on the Message-Passing Interface (MPI) standard in the mid-1990s, application developers enjoyed a seemingly static view of the underlying machine — that of a distributed collection of homogeneous nodes executing in collaboration. However, after almost two decades of dominance, the sole use of MPI to derive parallelism acted as a limiter to improved future performance. While MPI is widely expected to continue to function as the basic mechanism for communication between compute nodes for the immediate future, additional parallelism is required on the computing node itself if high performance and efficiency goals are to be realized. When reviewing the architectures of the top HPC systems today, the change in paradigm is clear: the compute nodes of the leading machines in the world are either powered by many-core chips with a few dozen cores each, or use heterogeneous designs, where traditional CPUs marshal work to massively parallel compute accelerators which has as many as 200,000 processing threads in flight simultaneously. Complicating matters further for application developers, each processor vendor has its own preferred way of writing code for their architecture.The Kokkos EcoSystem was released by Sandia in 2017 to address this new era in HPC system design by providing a vendor independent performance portable programming system for scientific, engineering, and mathematical software applications written in the C++ programming language. Using Kokkos, application developers can be more productive because they will not have to create and maintain separate versions of their software for each architecture, nor will they have to be experts in each architecture's peculiar requirements. Instead, they will have a single method of programming for the diverse set of modern HPC architectures. While Kokkos started in 2011 as a programming model only, it soon became clear that complex applications needed more. It is also critical to have a portable mathematical functions and developers need tools to debug their applications, gain insight into the performance characteristics of their codes and tune algorithm performance parameters through automated processes. The Kokkos EcoSystem addresses those needs through its three main components: the Kokkos Core programming model, the Kokkos Kernels math library, and the Kokkos Tools project.

97 MATHEMATICS AND COMPUTING↗

Explicit spatial scattering for load balancing in conservatively synchronized parallel discrete-event simulations

We re-examine the problem of load balancing in conservatively synchronized parallel, discrete-event simulations executed on high-performance computing clusters, focusing on simulations where computational and messaging load tend to be spatially clustered. Such domains are frequently characterized by the presence of geographic 'hot-spots' - regions that generate significantly more simulation events than others. Examples of such domains include simulation of urban regions, transportation networks and networks where interaction between entities is often constrained by physical proximity. Noting that in conservatively synchronized parallel simulations, the speed of execution of the simulation is determined by the slowest (i.e most heavily loaded) simulation process, we study different partitioning strategies in achieving equitable processor-load distribution in domains with spatially clustered load. In particular, we study the effectiveness of partitioning via spatial scattering to achieve optimal load balance. In this partitioning technique, nearby entities are explicitly assigned to different processors, thereby scattering the load across the cluster. This is motivated by two observations, namely, (i) since load is spatially clustered, spatial scattering should, intuitively, spread the load across the compute cluster, and (ii) in parallel simulations, equitable distribution of CPU load is a greater determinant of execution speed than message passing overhead. Through large-scale simulation experiments - both of abstracted and real simulation models - we observe that scatter partitioning, even with its greatly increased messaging overhead, significantly outperforms more conventional spatial partitioning techniques that seek to reduce messaging overhead. Further, even if hot-spots change over the course of the simulation, if the underlying feature of spatial clustering is retained, load continues to be balanced with spatial scattering leading us to the observation that spatial scattering can often obviate the need for dynamic load balancing.

97 MATHEMATICS AND COMPUTING↗

Transforming Power Grid Operations via High Performance Computing

Past power grid blackout events revealed the adequacy of grid operations in responding to adverse situations partially due to low computational efficiency in grid operation functions. High performance computing (HPC) provides a promising solution to this problem. HPC applications in power grid computation also become necessary to take advantage of parallel computing platforms as the computer industry is undergoing a significant change from the traditional single-processor environment to an era for multi-processor computing platforms. HPC applications to power grid operations are multi-fold. HPC can improve today’s grid operation functions like state estimation and contingency analysis and reduce the solution time from minutes to seconds, comparable to SCADA measurement cycles. HPC also enables the integration of dynamic analysis into real-time grid operations. Dynamic state estimation, look-ahead dynamic simulation and real-time dynamic contingency analysis can be implemented and would be three key dynamic functions in future control centers. HPC applications call for better decision support tools, which also need HPC support to handle large volume of data and large number of cases. Given the complexity of the grid and the sheer number of possible configurations, HPC is considered to be an indispensible element in the next generation control centers.

24 POWER TRANSMISSION AND DISTRIBUTION↗

A Domain Decomposition Approach for Large-Scale Simulations of Flow Processes in Hydrate-Bearing Geologic Media

Simulation of the system behavior of hydrate-bearing geologic media involves solving fully coupled mass- and heat-balance equations. In this study, we develop a domain decomposition approach for large-scale gas hydrate simulations with coarse-granularity parallel computation. This approach partitions a simulation domain into small subdomains. The full model domain, consisting of discrete subdomains, is still simulated simultaneously by using multiple processes/processors. Each processor is dedicated to following tasks of the partitioned subdomain: updating thermophysical properties, assembling mass- and energy-balance equations, solving linear equation systems, and performing various other local computations. The linearized equation systems are solved in parallel with a parallel linear solver, using an efficient interprocess communication scheme. This new domain decomposition approach has been implemented into the TOUGH+HYDRATE code and has demonstrated excellent speedup and good scalability. In this paper, we will demonstrate applications for the new approach in simulating field-scale models for gas production from gas-hydrate deposits.

58 GEOSCIENCES↗

Using Compiler Directives for Performance Portability in Scientific Computing: Kernels from Molecular Simulation

Achieving performance portability for high-performance computing (HPC) applications in scientific fields has become an increasingly important initiative due to large differences in emerging supercomputer architectures. Here we test some key kernels from molecular dynamics (MD) to determine whether the use of the OpenACC directive-based programming model when applied to these kernels can result in performance within an acceptable range for these types of programs in the HPC setting. We find that for easily parallelizable kernels, performance on the GPU remains within this range. On the CPU, OpenACC-parallelized pairwise distance kernels would not meet the performance standards required, when using AMD Opteron “Interlagos” processors, but with IBM Power 9 processors, performance remains within an acceptable range for small batch sizes. These kernels provide a test for achieving performance portability with compiler directives for problems with memory-intensive components as are often found in scientific applications.

Sedova, Ada↗

Computing the ankle-brachial index with parallel computational fluid dynamics

The ankle-brachial index (ABI), a ratio of arterial blood pressure in the ankles and upper arms, is used to diagnose and monitor circulatory conditions such as coarctation of the aorta and peripheral artery disease. Computational simulations of the ABI can potentially determine the parameters that produce an ABI indicative of ischemia or other abnormalities in blood flow. However, 0- and 1-D computational methods are limited in describing a 3-D patient-derived geometry. Thus, we present a massively parallel framework for computational fluid dynamics (CFD) simulations in the full arterial system. Additionally, using the lattice Boltzmann method to solve the Navier–Stokes equations, we employ highly parallelized and scalable methods to generate the simulation domain and efficiently distribute the computational load among processors. For the first time, we compute an ABI with 3-D CFD. In this proof-of-concept study, we investigate the dependence of ABI on the presence of stenoses, or narrowed regions of the arteries, by directly modifying the arterial geometry. As a result, our framework enables the computation a hemodynamic factor characterizing flow at the scale of the full arterial system, in a manner that is extensible to patient-specific imaging data and holds potential for treatment planning.

59 BASIC BIOLOGICAL SCIENCES↗

Performance of a parallel algebraic multilevel preconditioner for stabilized finite element semiconductor device modeling

In this study results are presented for the large-scale parallel performance of an algebraic multilevel preconditioner for solution of the drift-diffusion model for semiconductor devices. The preconditioner is the key numerical procedure determining the robustness, efficiency and scalability of the fully-coupled Newton-Krylov based, nonlinear solution method that is employed for this system of equations. The coupled system is comprised of a source term dominated Poisson equation for the electric potential, and two convection-diffusion-reaction type equations for the electron and hole concentration. The governing PDEs are discretized in space by a stabilized finite element method. Solution of the discrete system is obtained through a fully-implicit time integrator, a fully-coupled Newton-based nonlinear solver, and a restarted GMRES Krylov linear system solver. The algebraic multilevel preconditioner is based on an aggressive coarsening graph partitioning of the nonzero block structure of the Jacobian matrix. Representative performance results are presented for various choices of multigrid V-cycles and W-cycles and parameter variations for smoothers based on incomplete factorizations. Parallel scalability results are presented for solution of up to 10{sup 8} unknowns on 4096 processors of a Cray XT3/4 and an IBM POWER eServer system.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Comparing the Performance of Julia on CPUs versus GPUs and Julia-MPI versus Fortran-MPI: a case study with MPAS-Ocean (Version 7.1)

Abstract. Some programming languages are easy to develop at the cost of slow execution, while others are fast at runtime but much more difficult to write. Julia is a programming language that aims to be the best of both worlds – a development and production language at the same time. To test Julia's utility in scientific high-performance computing (HPC), we built an unstructured-mesh shallow water model in Julia and compared it against an established Fortran-MPI ocean model, the Model for Prediction Across Scales–Ocean (MPAS-Ocean), as well as a Python shallow water code. Three versions of the Julia shallow water code were created: for single-core CPU, graphics processing unit (GPU), and Message Passing Interface (MPI) CPU clusters. Comparing identical simulations revealed that our first version of the Julia model was 13 times faster than Python using NumPy, where both used an unthreaded single-core CPU. Further Julia optimizations, including static typing and removing implicit memory allocations, provided an additional 10–20× speed-up of the single-core CPU Julia model. The GPU-accelerated Julia code was almost identical in terms of performance to the MPI parallelized code on 64 processes, an unexpected result for such different architectures. Parallelized Julia-MPI performance was identical to Fortran-MPI MPAS-Ocean for low processor counts and ranges from 2× faster to 2× slower for higher processor counts. Our experience is that Julia development is fast and convenient for prototyping but that Julia requires further investment and expertise to be competitive with compiled codes. We provide advice on Julia code optimization for HPC systems.

54 ENVIRONMENTAL SCIENCES↗

Commnity Petascale Project for Accelerator Science And Simulation: Advancing Computational Science for Future Accelerators And Accelerator Technologies

The design and performance optimization of particle accelerators are essential for the success of the DOE scientific program in the next decade. Particle accelerators are very complex systems whose accurate description involves a large number of degrees of freedom and requires the inclusion of many physics processes. Building on the success of the SciDAC-1 Accelerator Science and Technology project, the SciDAC-2 Community Petascale Project for Accelerator Science and Simulation (ComPASS) is developing a comprehensive set of interoperable components for beam dynamics, electromagnetics, electron cooling, and laser/plasma acceleration modelling. ComPASS is providing accelerator scientists the tools required to enable the necessary accelerator simulation paradigm shift from high-fidelity single physics process modeling (covered under SciDAC1) to high-fidelity multiphysics modeling. Our computational frameworks have been used to model the behavior of a large number of accelerators and accelerator R&D experiments, assisting both their design and performance optimization. As parallel computational applications, the ComPASS codes have been shown to make effective use of thousands of processors.

43 PARTICLE ACCELERATORS↗

Community Petascale Project for Accelerator Science and Simulation: Advancing Computational Science for Future Accelerators and Accelerator Technologies

The design and performance optimization of particle accelerators are essential for the success of the DOE scientific program in the next decade. Particle accelerators are very complex systems whose accurate description involves a large number of degrees of freedom and requires the inclusion of many physics processes. Building on the success of the SciDAC-1 Accelerator Science and Technology project, the SciDAC-2 Community Petascale Project for Accelerator Science and Simulation (ComPASS) is developing a comprehensive set of interoperable components for beam dynamics, electromagnetics, electron cooling, and laser/plasma acceleration modelling. ComPASS is providing accelerator scientists the tools required to enable the necessary accelerator simulation paradigm shift from high-fidelity single physics process modeling (covered under SciDAC1) to high-fidelity multiphysics modeling. Our computational frameworks have been used to model the behavior of a large number of accelerators and accelerator R&D experiments, assisting both their design and performance optimization. As parallel computational applications, the ComPASS codes have been shown to make effective use of thousands of processors. ComPASS is in the first year of executing its plan to develop the next-generation HPC accelerator modeling tools. ComPASS aims to develop an integrated simulation environment that will utilize existing and new accelerator physics modules with petascale capabilities, by employing modern computing and solver technologies. The ComPASS vision is to deliver to accelerator scientists a virtual accelerator and virtual prototyping modeling environment, with the necessary multiphysics, multiscale capabilities. The plan for this development includes delivering accelerator modeling applications appropriate for each stage of the ComPASS software evolution. Such applications are already being used to address challenging problems in accelerator design and optimization. The ComPASS organization for software development and applications accounts for the natural domain areas (beam dynamics, electromagnetics, and advanced acceleration), and all areas depend on the enabling technologies activities, such as solvers and component technology, to deliver the desired performance and integrated simulation environment. The ComPASS applications focus on computationally challenging problems important for design or performance optimization to all major HEP, NP, and BES accelerator facilities. With the cost and complexity of particle accelerators rising, the use of computation to optimize their designs and find improved operating regimes becomes essential, potentially leading to significant cost savings with modest investment.

43 PARTICLE ACCELERATORS↗

Towards Flexible Exascale Stream Processing System Simulation

Stream processing is an important emerging computational model for performing complex operations on and across multi-source, high-volume, unpredictable dataflows. We present Flow, a platform for parallel and distributed stream processing system simulation that provides a flexible modeling environment for analyzing stream processing applications. The Flow stream processing system simulator is a high-performance, scalable simulator that automatically parallelizes chunks of the model space and incurs near-zero synchronization overhead for acyclic stream application graphs. We show promising parallel and distributed event rates exceeding 149 million events per second on a cluster with 512 processor cores.

99 GENERAL AND MISCELLANEOUS↗

Method and apparatus of parallel computing with simultaneously operating stream prefetching and list prefetching engines

A prefetch system improves a performance of a parallel computing system. The parallel computing system includes a plurality of computing nodes. A computing node includes at least one processor and at least one memory device. The prefetch system includes at least one stream prefetch engine and at least one list prefetch engine. The prefetch system operates those engines simultaneously. After the at least one processor issues a command, the prefetch system passes the command to a stream prefetch engine and a list prefetch engine. The prefetch system operates the stream prefetch engine and the list prefetch engine to prefetch data to be needed in subsequent clock cycles in the processor in response to the passed command.

97 MATHEMATICS AND COMPUTING↗

Streaming Matching and Edge Cover in Practice

Graph algorithms with polynomial space and time requirements often become infeasible for massive graphs with billions of edges or more. State-of-the-art approaches therefore employ approximate serial, parallel, and distributed algorithms to tackle these challenges. However, such approaches require storing the entire graph in memory and thus need access to costly computing resources such as clusters and supercomputers. In this paper, we present practical streaming approaches for solving massive graph problems using limited memory for two prototypical graph problems: maximum weighted matching and minimum weighted edge cover. For matching, we conduct a thorough computational study on two of the semi-streaming algorithms including a recent breakthrough result that achieves a $1/(2+\varepsilon)$-approximation of the weight while using $O( n \log W /\epsilon)$ memory (here $n$ is the number of vertices and $W$ is the maximum edge weight), designed by Paz and Schwartzman [SODA, 2017]. Empirically, we show that the semi-streaming algorithms produce matchings whose weight is close to the best $1/2$-approximate offline algorithm while requiring less time and an order-of-magnitude less memory. For minimum weighted edge cover, we develop three novel semi-streaming algorithms. Two of these algorithms require a single pass through the input graph, require $O(n \log n)$ memory, and provide a 2-approximation guarantee on the objective. We also leverage a relationship between approximate maximum weighted matching and approximate minimum weighted edge cover to develop a two-pass $3/2+\epsilon$-approximate algorithm with the memory requirement of Paz and Schwartzman's semi-streaming matching algorithm. These streaming approaches are compared against the state-of-the-art 3/2-approximate offline algorithm. The semi-streaming matching and the novel edge cover algorithms proposed in this paper can process graphs with several billions of edges in under 30 minutes using 6 GB of memory, which is at least an order of magnitude improvement from the offline (non-streaming) algorithms. For the largest graph, the best alternative offline parallel approximation algorithm (GPA+ROMA) could not finish in three hours even while employing hundreds of processors and 1 TB of memory. We also demonstrate an application of the semi-streaming algorithm by computing a matching using linearly bounded memory on item intersection graphs derived from three machine learning datasets, whereas the existing offline algorithms could not complete on one of these datasets since their memory requirements exceeded 1TB.

Ferdous, S M.↗

Commnity Petascale Project for Accelerator Science and Simulation: Advancing Computational Science for Future Accelerators and Accelerator Technologies

The design and performance optimization of particle accelerators is essential for the success of the DOE scientific program in the next decade. Particle accelerators are very complex systems whose accurate description involves a large number of degrees of freedom and requires the inclusion of many physics processes. Building on the success of the SciDAC1 Accelerator Science and Technology project, the SciDAC2 Community Petascale Project for Accelerator Science and Simulation (ComPASS) is developing a comprehensive set of interoperable components for beam dynamics, electromagnetics, electron cooling, and laser/plasma acceleration modeling. ComPASS is providing accelerator scientists the tools required to enable the necessary accelerator simulation paradigm shift from high-fidelity single physics process modeling (covered under SciDAC1) to high-fidelity multi-physics modeling. Our computational frameworks have been used to model the behavior of a large number of accelerators and accelerator R&D experiments, assisting both their design and performance optimization. As parallel computational applications, the ComPASS codes have been shown to make effective use of thousands of processors.

99 GENERAL AND MISCELLANEOUS↗