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 865 records · Page 48

Efficient data IO for a Parallel Global Cloud Resolving Model

Execution of a Global Cloud Resolving Model (GCRM) at target resolutions of 2-4 km will generate, at a minimum, 10s of Gigabytes of data per variable per snapshot. Writing this data to disk without creating a serious bottleneck in the execution of the GCRM code while also supporting efficient post-execution data analysis is a significant challenge. This paper discusses an Input/Output (IO) application programmer interface (API) for the GCRM that efficiently moves data from the model to disk while maintaining support for community standard formats, avoiding the creation of very large numbers of files, and supporting efficient analysis. Several aspects of the API will be discussed in detail. First, we discuss the output data layout which linearizes the data in a consistent way that is independent of the number of processors used to run the simulation and provides a convenient format for subsequent analyses of the data. Second, we discuss the flexible API interface that enables modelers to easily add variables to the output stream by specifying where in the GCRM code these variables are located and to flexibly configure the choice of outputs and distribution of data across files. The flexibility of the API is designed to allow model developers to add new data fields to the output as the model develops and new physics is added and also provides a mechanism for allowing users of the GCRM code itself to adjust the output frequency and the number of fields written depending on the needs of individual calculations. Third, we describe the mapping to the NetCDF data model with an emphasis on the grid description. Fourth, we describe our messaging algorithms and IO aggregation strategies that are used to achieve high bandwidth while simultaneously writing concurrently from many processors to shared files. We conclude with initial performance results.

99 GENERAL AND MISCELLANEOUS↗

Accurate, Fast and Scalable Kernel Ridge Regression on Parallel and Distributed Systems

Kernel Ridge Regression (KRR) is a fundamental method in machine learning. Given an n-by-d data matrix as input, a traditional implementation requires Θ(n2) memory to form an n-by-n kernel matrix and Θ(n3) flops to compute the final model. These time and storage costs prohibit KRR from scaling up to large datasets. For example, even on a relatively small dataset (a 520k-by-90 input requiring 357 MB), KRR requires 2 TB memory just to store the kernel matrix. Additionally, the reason is that n usually is much larger than d for real-world applications. On the other hand, weak scaling becomes a problem: if we keep d and n/p fixed as p grows (p is # machines), the memory needed grows as Θ(p) per processor and the flops as Θ(p2) per processor. In the perfect weak scaling situation, both the memory needed and the flops grow as Θ(1) per processor (i.e. memory and flops are constant). The traditional Distributed KRR implementation (DKRR) only achieved 0.32% weak scaling efficiency from 96 to 1536 processors. In this work, we propose two new methods to address these problems: the Balanced KRR (BKRR) and K-means KRR (KKRR). These methods consider alternative ways to partition the input dataset into p different parts, generating p different models, and then selecting the best model among them. Compared to a conventional implementation, KKRR2 (optimized version of KKRR) improves the weak scaling efficiency from 0.32% to 38% and achieves a 591x speedup for getting the same accuracy by using the same data and the same hardware (1536 processors). BKRR2 (optimized version of BKRR) achieves a higher accuracy than the current fastest method using less training time for a variety of datasets. For the applications requiring only approximate solutions, BKRR2 improves the weak scaling efficiency to 92% and achieves 3505x speedup (theoretical speedup: 4096x).

97 MATHEMATICS AND COMPUTING↗

Web-based, GPU-accelerated, Monte Carlo simulation and visualization of indirect radiation imaging detector performance

Purpose: Monte Carlo simulations play a vital role in the understanding of the fundamental limitations, design, and optimization of existing and emerging medical imaging systems. Efforts in this area have resulted in the development of a wide variety of open-source software packages. One such package, hybridMANTIS, uses a novel hybrid concept to model indirect scintillator detectors by balancing the computational load using dual CPU and graphics processing unit (GPU) processors, obtaining computational efficiency with reasonable accuracy. In this work, the authors describe two open-source visualization interfaces, webMANTIS and visualMANTIS to facilitate the setup of computational experiments via hybridMANTIS. Methods: The visualization tools visualMANTIS and webMANTIS enable the user to control simulation properties through a user interface. In the case of webMANTIS, control via a web browser allows access through mobile devices such as smartphones or tablets. webMANTIS acts as a server back-end and communicates with an NVIDIA GPU computing cluster that can support multiuser environments where users can execute different experiments in parallel. Results: The output consists of point response and pulse-height spectrum, and optical transport statistics generated by hybridMANTIS. The users can download the output images and statistics through a zip file for future reference. In addition, webMANTIS provides a visualization window that displays a few selected optical photon path as they get transported through the detector columns and allows the user to trace the history of the optical photons. Conclusions: The visualization tools visualMANTIS and webMANTIS provide features such as on the fly generation of pulse-height spectra and response functions for microcolumnar x-ray imagers while allowing users to save simulation parameters and results from prior experiments. The graphical interfaces simplify the simulation setup and allow the user to go directly from specifying input parameters to receiving visual feedback for the model predictions.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Robust and efficient overset grid assembly for partitioned unstructured meshes

This paper presents a method to perform efficient and automated Overset Grid Assembly (OGA) on a system of overlapping unstructured meshes in a parallel computing environment where all meshes are partitioned into multiple mesh-blocks and processed on multiple cores. The main task of the overset grid assembler is to identify, in parallel, among all points in the overlapping mesh system, at which points the flow solution should be computed (field points), interpolated (receptor points), or ignored (hole points). Point containment search or donor search, an algorithm to efficiently determine the cell that contains a given point, is the core procedure necessary for accomplishing this task. Donor search is particularly challenging for partitioned unstructured meshes because of the complex irregular boundaries that are often created during partitioning. Another challenge arises because of the large variation in the type of mesh-block overlap and the resulting large load imbalance on multiple processors. Desirable traits for the grid assembly method are efficiency (requiring only a small fraction of the solver time), robustness (correct identification of all point types), and full automation (no user input required other than the mesh system). Additionally, the method should be scalable, which is an important challenge due to the inherent load imbalance. This paper describes a fully-automated grid assembly method, which can use two different donor search algorithms. One is based on the use of auxiliary grids and Exact Inverse Maps (EIM), and the other is based on the use of Alternating Digital Trees (ADT). The EIM method is demonstrated to be more efficient than the ADT method, while retaining robustness. An adaptive load re-balance algorithm is also designed and implemented, which considerably improves the scalability of the method.

97 MATHEMATICS AND COMPUTING↗

PRISMA: PARALLEL REFINEMENT AND INTEGRATION SYSTEM FOR MULTI-AZIMUTHAL ANALYSIS

The Parallel Refinement and Integration System for Multi-azimuthal Analysis (PRISMA, version 1.1.0) is a Python application for processing X-ray diffraction (XRD) image data. PRISMA wraps GSAS-II to perform azimuthally-binned peak refinement, computes per-frame strain and d-spacing from those fits, and provides three PyQt5 graphical interfaces: (1) a Recipe Builder for selecting GSAS-II control (.imctrl) files, optional mask (.immask) files or threshold-ased masking, reference and experiment image sets, peaks, zimuthal range and bin size, and an optional ceria-based auto-calibration; (2) a Batch Processor that uses Dask on local workstations and pure MPI (mpi4py.futures.MPICommExecutor) on HPC to distribute GSAS-II refinement across cores or compute nodes and write results to a 4-dimensional (peaks x frames x azimuths x measurements) Zarr dataset; and (3) a Data Analyzer that renders heatmaps of fit parameters, strain, frame-to-frame deltas, and percent-change-vs-reference, and exports user-defined subsections to CSV or Excel. The peak-refinement algorithm is deterministic. Benchmark on ALCF Crux: a 20,000-image set, single-peak fit in frame mode with 44 azimuthal bins on 128 nodes x 128 workers, 48 seconds total wall time.

Lorenzo Martin, Maria De La Cinta [Argonne Nationa↗

Exploiting Geometric Partitioning in Task Mapping for Parallel Computes

We present a new method for mapping applications' MPI tasks to cores of a parallel computer such that applications' communication time is reduced. We address the case of sparse node allocation, where the nodes assigned to a job are not necessarily located in a contiguous block nor within close proximity to each other in the network, although our methods generalize to contiguous allocations as well. The goal is to assign tasks to cores so that interdependent tasks are performed by "nearby' cores, thus lowering the distance messages must travel, the amount of congestion in the network, and the overall cost of communication. Our new method applies a geometric partitioning algorithm to both the tasks and the processors, and assigns task parts to the corresponding processor parts. We also present a number of algorithmic optimizations that exploit specific features of the network or application. We show that, for the structured finite difference mini-application MiniGhost, our mapping methods reduced communication time up to 75% relative to MiniGhost's default mapping on 128K cores of a Cray XK7 with sparse allocation. For the atmospheric modeling code E3SM/HOMME, our methods reduced communication time up to 31% on 32K cores of an IBM BlueGene/Q with contiguous allocation.

97 MATHEMATICS AND COMPUTING↗

Solution to PDEs using radial basis function finite-differences (RBF-FD) on multiple GPUs

This paper presents parallelization strategies for the radial basis function-finite difference (RBF-FD) method. As a generalized finite differencing scheme, the RBF-FD method functions without the need for underlying meshes to structure nodes. It offers high-order accuracy approximation and scales as O(N) per time step, with N being with the total number of nodes. To our knowledge, this is the first implementation of the RBF-FD method to leverage GPU accelerators for the solution of PDEs. Additionally, this implementation is the first to span both multiple CPUs and multiple GPUs. OpenCL kernels target the GPUs and inter-processor communication and synchronization is managed by the Message Passing Interface (MPI). We verify our implementation of the RBF-FD method with two hyperbolic PDEs on the sphere, and demonstrate up to 9x speedup on a commodity GPU with unoptimized kernel implementations. On a high performance cluster, the method achieves up to 7x speedup for the maximum problem size of 27,556 nodes.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Parallel Hybrid Metaheuristics with Distributed Intensification and Diversification for Large-scale Optimization in Big Data Statistical Analysis

Important insights into many problems that are traditionally analyzed via statistical models can be obtained by re-formulating and evaluating within a large-scale optimization framework. The theoretical underpinnings of the statistical model often shift the goal of the solution space traversal from a traditional search for a single optimal solution to a traversal with the purpose of yielding a set of high quality, independent solutions. We examine statistical frameworks with astronomical solution spaces where the independence requirement constitutes a significant additional challenge for standard optimization methodologies. We design a hybrid metaheuristic with specialized intensification and diversification protocols in the base search algorithm. We extend our algorithm to the high-performance-computing realm using the Stampede2 supercomputer. We experimentally demonstrate the effectiveness of our algorithm to utilize multiple processors to collaboratively hill climb, broadcast messages to one another regarding landscape characteristics, diversify across the solution landscape, and request aid in climbing particularly difficult peaks.

Cho, Wendy K. Tam↗

An Approach to Enhance pnetCDF Performance in Environmental Modeling Applications

I/O has been considered as a bottleneck in parallel applications. The software package, pnetCDF which works with parallel file systems, was developed to address this issue and provide parallel I/O capability. This study examines the performance of a novel approach which performs data aggregation along either row or column dimension of the spatial domain, and then applies the pnetCDF parallel I/O paradigm. The test was done with three different domain sizes which represents small, moderately large and large data domains, using a small scale Community Multi-scale Air Quality model (CMAQ) mocked up code. The examination includes comparing I/O performance with traditional serial I/O technique, straight application of pnetCDF, and the data aggregation along row and column dimension before applying pnetCDF. After the comparison, “optimal” I/O configurations for this new novel approach were quantified. Data aggregation along the row dimension (pnetCDFcr) works better than along the column dimension (pnetCDFcc) although it may perform slightly worse than straight the pnetCDF method with a small number of processors. When the number of processors becomes larger, pnetCDFcr out performs pnetCDF significantly. If the number of processors keeps increasing, pnetCDF reaches a point that the performance is even worse than the serial I/O technique. This new approach has also been tested on a real application where it performs two times better than the straight pnetCDF paradigm.

I/O↗

Hybrid memory module bridge network and buffers

Systems, apparatuses, and methods for implementing a hybrid memory module bridge network and buffers are disclosed. A system includes one or more host processors and multiple memory modules. Each memory module includes a relatively low pin count, high-bandwidth serial link to one or more other memory modules to perform inter-memory data transfers without consuming host-memory bandwidth. In one embodiment, a first memory module acts as a cache and a second memory module acts as the main memory for the system. The traffic between the host and the first memory module utilizes a first interface, and the cache traffic between the first and second memory modules utilizes a second interface. Cache line fill and writeback transfers between the first and second memory modules occur in parallel with timing-critical cache demand accesses from the host, in a latency-tolerant and buffered manner, without interfering with the cache demand accesses.

97 MATHEMATICS AND COMPUTING↗

Evaluating the networking characteristics of the Cray XC-40 Intel Knights Landing-based Cori supercomputer at NERSC

There are many potential issues associated with deploying the Intel Xeon Phi™ (code named Knights Landing [KNL]) manycore processor in a large-scale supercomputer. One in particular is the ability to fully utilize the high-speed communications network, given that the serial performance of a Xeon Phi TM core is a fraction of a Xeon®core. In this paper, we take a look at the trade-offs associated with allocating enough cores to fully utilize the Aries high-speed network versus cores dedicated to computation, e.g., the trade-off between MPI and OpenMP. In addition, we evaluate new features of Cray MPI in support of KNL, such as internode optimizations. We also evaluate one-sided programming models such as Unified Parallel C. We quantify the impact of the above trade-offs and features using a suite of National Energy Research Scientific Computing Center applications.

97 MATHEMATICS AND COMPUTING↗

A parallel geometric multigrid method for finite elements on octree meshes

In this article, we present a parallel geometric multigrid algorithm for solving variable-coefficient elliptic partial differential equations on the unit box (with Dirichlet or Neumann boundary conditions) using highly nonuniform, octree-based, conforming finite element discretizations. Our octrees are 2:1 balanced, that is, we allow no more than one octree-level difference between octants that share a face, edge, or vertex. We describe a parallel algorithm whose input is an arbitrary 2:1 balanced fine-grid octree and whose output is a set of coarser 2:1 balanced octrees that are used in the multigrid scheme. Also, we derive matrix-free schemes for the discretized finite element operators and the intergrid transfer operations. The overall scheme is second-order accurate for sufficiently smooth right-hand sides and material properties; its complexity for nearly uniform trees is {Omicron}(N/n{sub p} log N/n{sub p}) + {Omicron}(n{sub p} log n{sub p}), where N is the number of octree nodes and n{sub p} is the number of processors. Our implementation uses the Message Passing Interface standard. We present numerical experiments for the Laplace and Navier (linear elasticity) operators that demonstrate the scalability of our method. Our largest run was a highly nonuniform, 8-billion-unknown, elasticity calculation using 32,000 processors on the Teragrid system, 'Ranger,' at the Texas Advanced Computing Center. Our implementation is publically available in the Dendro library, which is built on top of the PETSc library from Argonne National Laboratory.

99 GENERAL AND MISCELLANEOUS↗

Evaluation of Low Power ARM Processors for Monte Carlo Particle Transport: MCNP6 on the ARM Cortex-A8 - Paper 83

In the push towards exascale computing, the limiting factors are power requirements and heat dissipation. Using current technology, the power required to drive an exascale supercomputer would near 400-MW. Clearly, future computing hardware will have to be more energy efficient in order to achieve exascale performance. Most of the current research in advanced computing architectures is in the use of standard CPUs with accelerators. However, these accelerators are not generally supported by the traditional scientific programming languages (C, C++, and Fortran) and the scientific software must be tailored specifically to take advantage of the accelerators. Large scale scientific software (hundreds-of-thousand to millions of lines of code) can not be easily ported to the computing platform du jour. The widespread use of low power ARM based processors in the mobile computing market offer a low power alternative to accelerators that are also supported by the traditional scientific programming languages and programming paradigms such as MPI and OpenMP. Computing architectures for scientific computing are often assessed using standard benchmarks such as LINPACK benchmark or using suites of mini-applications that are greatly simplified stand-ins for scientific software. Often the real applications that will deployed on the scientific supercomputers are not ported or tested until delivery of the machines. In order to evaluate the use of ARM processors for scientific computing the Monte Carlo particle transport code, MCNP version 6 was compiled on the ARM Cortex-A8 and a set of benchmark problems were used to assess performance in comparison to an Intel Xeon E5-2670 and the low power Intel Atom N270. MCNP is a continuous energy Monte Carlo particle transport code in development at Los Alamos National Laboratory since 1977. MCNP is used to transport neutrons, photon, electrons, and charged particles using continuous energy interaction data. It is commonly used in fields of nuclear power, nuclear medicine, radiation protection, and high-energy physics through-out the world. MCNP version 6 is approximately 450 thousand lines of code, written primary in Fortran90, with some C and C++. MCNP supports distributed multiprocessing using MPI and threading with OpenMP. The ARM Cortex-A8 executes MCNP6 using about twice as much power as the Intel Xeon E5-2670 and about the same amount of power as the Intel Atom N270. However, these results are encouraging for the use of low-power ARM chips in future supercomputers. The ARM Cortex-A8 is a 32-bit CPU and it's NEON general-purpose SIMD (single-instruction multiple data) engine does not support double-precision floating-point arithmetic. More recent ARM processors (ARM Cortex-A53 and Cortex-A57) support 64-bit addressing and have NEON co-processors that support double-precision floating-point arithmetic. ARM claims that the A50 series delivers a performance increase of 15 times the Cortex-A8 performance for similar power usage. (authors)

61 RADIATION PROTECTION AND DOSIMETRY↗

Scalable Work Stealing

Irregular and dynamic parallel applications pose significant challenges to achieving scalable performance on large-scale multicore clusters. These applications often require ongoing, dynamic load balancing in order to maintain efficiency. While effective at small scale, centralized load balancing schemes quickly become a bottleneck on large-scale clusters. Work stealing is a popular approach to distributed dynamic load balancing; however its performance on large-scale clusters is not well understood. Prior work on work stealing has largely focused on shared memory machines. In this work we investigate the design and scalability of work stealing on modern distributed memory systems. We demonstrate high efficiency and low overhead when scaling to 8,192 processors for three benchmark codes: a producer-consumer benchmark, the unbalanced tree search benchmark, and a multiresolution analysis kernel.

99 GENERAL AND MISCELLANEOUS↗

Notified access in coarray-based hydrodynamics applications on many-core architectures: Design and performance

With the increasing availability of the Remote Direct Memory Access (RDMA) support in computer networks, the so called Partitioned Global Address Space (PGAS) model has evolved in the last few years. Although there are several cases where a PGAS approach can easily solve difficult message passing situations, like in particle tracking and adaptive mesh refinement applications, the producer-consumer pattern, usually adopted in task-based parallelism, can only be implemented inefficiently because of the separation between data transfer and synchronization (which is usually unified in message passing programming models). Here, in this paper, we provide two contributions: (1) we propose an extension for the Fortran language that provides the concept of Notified Access by associating regular coarray variables with event variables. (2) We demonstrate that the MPI extension proposed by foMPI for Notified Access can be used effectively to implement the same concept in a PGAS run-time library like OpenCoarrays. Moreover, for a hydrodynamics mini-application, we found that Fortran 2018 events perform always better than Fortran 2008 sync statements on many-core processors. We finally show how the proposed Notified Access can improve the performance even more.

97 MATHEMATICS AND COMPUTING↗

Scaling To A Million Cores And Beyond: Using Light-Weight Simulation to Understand The Challenges Ahead On The Road To Exascale

As supercomputers scale to 1,000 PFlop/s over the next decade, investigating the performance of parallel applications at scale on future architectures and the performance impact of different architecture choices for high-performance computing (HPC) hardware/software co-design is crucial. This paper summarizes recent efforts in designing and implementing a novel HPC hardware/software co-design toolkit. The presented Extreme-scale Simulator (xSim) permits running an HPC application in a controlled environment with millions of concurrent execution threads while observing its performance in a simulated extreme-scale HPC system using architectural models and virtual timing. This paper demonstrates the capabilities and usefulness of the xSim performance investigation toolkit, such as its scalability to 2^27 simulated Message Passing Interface (MPI) ranks on 960 real processor cores, the capability to evaluate the performance of different MPI collective communication algorithms, and the ability to evaluate the performance of a basic Monte Carlo application with different architectural parameters.

Engelmann, Christian↗

Exploring the Performance Potential of Chapel in Scientific Computations

Languages are being designed that simplify the tasks of creating, extending, and maintaining scientific application specifically for use on parallel computing architectures. Widespread adoption of any language by the high performance computing (HPC) community is strongly dependent upon achieved performance of applications. A common presumption is that performance is adversely affected as the level of abstraction increases. In this paper we report on our investigations into the potential of one such language, Chapel, to deliver performance while adhering to its code development and maintenance goals. In particular, we explore how the unconstrained memory model presented by Chapel may be exploited by the compiler and runtime system in order to efficiently execute computations common to numerous scientific application programs. Experiments, executed on a Cray X1E, AMD dual-core, and Intel quad- core processor based systems, reveal that with the appropriate architecture and runtime support, the Chapel model can achieve performance equal to the best Fortran/MPI, Co-Array Fortran, and OpenMP implementations, while substantially easing the burden on the application code developer.

Barrett, Richard F↗

A Self Consistent Multiprocessor Space Charge Algorithm that is Almost Embarrassingly Parallel

We present a space charge code that is self consistent, massively parallelizeable, and requires very little communication between computer nodes; making the calculation almost embarrassingly parallel. This method is implemented in the code COSY Infinity where the differential algebras used in this code are important to the algorithm's proper functioning. The method works by calculating the self consistent space charge distribution using the statistical moments of the test particles, and converting them into polynomial series coefficients. These coefficients are combined with differential algebraic integrals to form the potential, and electric fields. The result is a map which contains the effects of space charge. This method allows for massive parallelization since its statistics based solver doesn't require any binning of particles, and only requires a vector containing the partial sums of the statistical moments for the different nodes to be passed. All other calculations are done independently. The resulting maps can be used to analyze the system using normal form analysis, as well as advance particles in numbers and at speeds that were previously impossible.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗