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 757 records · Page 42

SHARP Assembly-Scale Multiphysics Demonstration Simulations

The NEAMS Reactor Product Line effort aims to develop an integrated multiphysics simulation capability for the design and analysis of future generations of nuclear power plants. The Reactor Product Line code suite’s multi-resolution hierarchy is being designed to ultimately span the full range of length and time scales present in relevant reactor design and safety analyses, as well as scale from desktop to petaflop computing platforms. In this report, we describe our efforts to integrate thermal/hydraulics, neutronics, and structural mechanics modeling codes to perform coupled analysis of a representative fast sodium-cooled reactor fuel assembly. Over the past five years, the Reactor Product Line effort has developed high-fidelity single-physics codes for neutron transport modeling, in the PROTEUS code, and Large Eddy Simulation-based thermal/fluid modeling in the Nek5000 code. Both these codes have been exercised on over 100,000 processors of the IBM Blue Gene/P. The Diablo code has been used to perform structural mechanics and thermo-mechanical modeling. MOAB, the Reactor Geometry Generator (RGG), and MeshKit have been developed to generate and manipulate mesh and mesh-based data, in both serial and parallel environments. These tools together form a strong basis on which to build a multi-physics modeling capability. The goal of developing such a tool is to perform multi-physics neutronics, thermal/fluid, and structural mechanics modeling of the components inside a reactor core. While the focus of this report is on modeling a fast sodium-cooled reactor, it is also the goal that this simulation tool be useful for most reactor types. Here we report on the integration of PROTEUS and Nek5000 into the NEAMS framework. Both codes have been modified to read and write data from and to the MOAB library, in both serial and parallel environments. We focused on broad support for as many original physics code options as possible, rather than focusing only on near-term needs. Both codes were demonstrated through this interface on a relatively simple, seven-pin hexagonal fuel assembly. To support coupled analysis, the new multi-physics driver library COUPE was developed; this library provides flexible support for both loose and tight coupling, and can interface flexibly with codes in multiple programming languages. To couple results between the separate meshes used in each physics, the driver, PROTEUS, and Nek5000 all interface with the MBCoupler solution transfer tool provided with MOAB. Together, these tools form the basis of a new, coupled neutronics and thermal/fluid modeling code, that works in both serial and parallel. In a related effort, a driver in the Diablo code was used to access Nek5000-computed results written to a MOAB database, as well as the temperature data used to drive structural mechanics computations.

Tautges, Timothy J.↗

FOX: A Fault Oblivious Extreme-Scale Execution Environment

The FOX project, funded under the ASCR X-stack I program, developed systems software and runtime libraries for a new approach to the data and work distribution for massively parallel, fault oblivious application execution. Our work was motivated by the premise that exascale computing systems will provide a thousand-fold increase in parallelism and a proportional increase in failure rate relative to today’s machines. To deliver the capability of exascale hardware, the systems software must provide the infrastructure to support existing applications while simultaneously enabling efficient execution of new programming models that naturally express dynamic, adaptive, irregular computation; coupled simulations; and massive data analysis in a highly unreliable hardware environment with billions of threads of execution. Our OS research has prototyped new methods to provide efficient resource sharing, synchronization, and protection in a many-core compute node. We have experimented with alternative task/dataflow programming models and shown scalability in some cases to hundreds of thousands of cores. Much of our software is in active development through open source projects. Concepts from FOX are being pursued in next generation exascale operating systems. Our OS work focused on adaptive, application tailored OS services optimized for multi → many core processors. We developed a new operating system NIX that supports role-based allocation of cores to processes which was released to open source. We contributed to the IBM FusedOS project, which promoted the concept of latency-optimized and throughput-optimized cores. We built a task queue library based on distributed, fault tolerant key-value store and identified scaling issues. A second fault tolerant task parallel library was developed, based on the Linda tuple space model, that used low level interconnect primitives for optimized communication. We designed fault tolerance mechanisms for task parallel computations employing work stealing for load balancing that scaled to the largest existing supercomputers. Finally, we implemented the Elastic Building Blocks runtime, a library to manage object-oriented distributed software components. To support the research, we won two INCITE awards for time on Intrepid (BG/P) and Mira (BG/Q). Much of our work has had impact in the OS and runtime community through the ASCR Exascale OS/R workshop and report, leading to the research agenda of the Exascale OS/R program. Our project was, however, also affected by attrition of multiple PIs. While the PIs continued to participate and offer guidance as time permitted, losing these key individuals was unfortunate both for the project and for the DOE HPC community.

97 MATHEMATICS AND COMPUTING↗

Neutronics Calculation of Fast Reactor Using Modern Computing Systems

The possibility of using the LUCKY-A three-dimensional multiprocessor transport code as a neutronics module for the COREMELT integrated non-stationary code for performing safety analysis, which is used for fast sodium reactor safety validation, is discussed. In this application, more stringent requirements are imposed on the computing speed of the LUCKY-A code. To test LUCKY-A possibilities, a typical computational problem is examined in a formulation characteristic for the proposed use of the code. The possibilities of the code for parallelized calculations are shown, and a comparison is made with calculations performed with the MMKKENO and TRIGEX codes. The efficacy of a parallel computational process is investigated as a function of the number of computing kernels used.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Gyrokinetic particle-in-cell optimization on emerging multi- and manycore platforms

The next decade of high-performance computing (HPC) systems will see a rapid evolution and divergence of multi- and manycore architectures as power and cooling constraints limit increases in microprocessor clock speeds. Understanding efficient optimization methodologies on diverse multicore designs in the context of demanding numerical methods is one of the greatest challenges faced today by the HPC community. In this paper, we examine the efficient multicore optimization of GTC, a petascale gyrokinetic toroidal fusion code for studying plasma microturbulence in tokamak devices. For GTC’s key computational components (charge deposition and particle push), we explore efficient parallelization strategies across a broad range of emerging multicore designs, including the recently-released Intel Nehalem-EX, the AMD Opteron Istanbul, and the highly multithreaded Sun UltraSparc T2+. We also present the first study on tuning gyrokinetic particle-in-cell (PIC) algorithms for graphics processors, using the NVIDIA C2050 (Fermi). Our work discusses several novel optimization approaches for gyrokinetic PIC, including mixed-precision computation, particle binning and decomposition strategies, grid replication, SIMDized atomic floating-point operations, and effective GPU texture memory utilization. Overall, we achieve significant performance improvements of 1.3–4.7× on these complex PIC kernels, despite the inherent challenges of data dependency and locality. Finally, our work also points to several architectural and programming features that could significantly enhance PIC performance and productivity on next-generation architectures.

97 MATHEMATICS AND COMPUTING↗

Neural network methods for radiation detectors and imaging

Recent advances in image data proccesing through deep learning allow for new optimization and performance-enhancement schemes for radiation detectors and imaging hardware. This enables radiation experiments, which includes photon sciences in synchrotron and X-ray free electron lasers as a subclass, through data-endowed artificial intelligence. We give an overview of data generation at photon sources, deep learning-based methods for image processing tasks, and hardware solutions for deep learning acceleration. Most existing deep learning approaches are trained offline, typically using large amounts of computational resources. However, once trained, DNNs can achieve fast inference speeds and can be deployed to edge devices. A new trend is edge computing with less energy consumption (hundreds of watts or less) and real-time analysis potential. While popularly used for edge computing, electronic-based hardware accelerators ranging from general purpose processors such as central processing units (CPUs) to application-specific integrated circuits (ASICs) are constantly reaching performance limits in latency, energy consumption, and other physical constraints. These limits give rise to next-generation analog neuromorhpic hardware platforms, such as optical neural networks (ONNs), for high parallel, low latency, and low energy computing to boost deep learning acceleration (LA-UR-23-32395).

edge computing↗

Parallel and Streaming Generation of Ghost Data for Structured Grids

Parallel simulations decompose large domains into many blocks. A fundamental requirement for subsequent parallel analysis and visualization is the presence of ghost data that supplements each block with a layer of adjacent data elements from neighboring blocks. The standard approach for generating ghost data requires all blocks to be in memory at once. This becomes impractical when there are fewer processors - and thus less aggregate memory - available for analysis than for simulation. We describe an algorithm for generating ghost data for structured grids that uses many fewer processors than previously possible. Our algorithm stores as little as one block per processor in memory and can run on as few processors as are available (possibly just one). The key idea is to slightly change the size of the original blocks by declaring parts of them to be ghost data, and by later padding adjacent blocks with this data.

99 GENERAL AND MISCELLANEOUS↗

Virtual Cable Impedance based Load Sharing in a Microgrid for Parallel Connected Grid Forming Converters

This paper presents a novel approach to power sharing between direct connected grid-forming converters, utilizing virtual cable impedance and droop-based outer loop control. To enhance stability, resistive droop is implemented, while virtual cable impedance with non-zero resistive and inductive components ensures improved power sharing. The inner loop controller employs a Lyapunov energy function to achieve superior dynamic performance. The proposed control architecture is validated through comprehensive modeling and real-time processor-in-the-loop simulations, demonstrating its robustness and efficiency under various operating conditions. The results highlight the potential of this control strategy to improve the reliability and efficiency of renewable energy systems. Additionally, a comparative analysis with traditional methods underscores the advantages of the proposed approach in terms of stability and performance. The proposed control architecture offers a scalable and flexible solution for grid-forming converters, enabling seamless integration of renewable energy sources. Its robustness and adaptability make it an attractive solution for real-world applications. Furthermore, the approach can be extended to other power electronic systems, enhancing overall system performance and efficiency. By providing a reliable and efficient control strategy, this paper contributes to the advancement of renewable energy systems and their adoption in the energy sector. The proposed control strategy has far-reaching implications for the widespread adoption of renewable energy sources, enabling a more sustainable and efficient energy future. The overall system is modeled in MATLAB/Simulink and PLECS software domain.

grid forming converters (GFM)↗

NWChem: Quantum Chemistry Simulations at Scale

Methods based on quantum mechanics equations have been developed since the 1930's with the purpose of accurately studying the electronic structure of molecules. However, it is only during the last two decades that intense development of new computational algorithms has opened the possibility of performing accurate simulations of challenging molecular processes with high-order many-body methods. A wealth of evidence indicates that the proper inclusion of instantaneous interactions between electrons (or the so-called electron correlation effects) is indispensable for the accurate characterization of chemical reactivity, molecular properties, and interactions of light with matter. The availability of reliable methods for benchmarking of medium-size molecular systems provides also a unique chance to propagate high-level accuracy across spatial scales through the multiscale methodologies. Some of these methods have potential to utilize computational resources in an effi*cient way since they are characterized by high numerical complexity and appropriate level of data granularity, which can be effi*ciently distributed over multi-processor architectures. The broad spectrum of coupled cluster (CC) methods falls into this class of methodologies. Several recent CC implementations clearly demonstrated the scalability of CC formalisms on architectures composed of hundreds thousand computational cores. In this context NWChem provides a collection of Tensor Contraction Engine (TCE) generated parallel implementations of various coupled cluster methods capable of taking advantage of many thousand of cores on leadership class parallel architectures.

chemistry↗

Contention Modeling for Multithreaded Distributed Shared Memory Machines: The Cray XMT

Distributed Shared Memory (DSM) machines are a wide class of multi-processor computing systems where a large virtually-shared address space is mapped on a network of physically distributed memories. High memory latency and network contention are two of the main factors that limit performance scaling of such architectures. Modern high-performance computing DSM systems have evolved toward exploitation of massive hardware multi-threading and fine-grained memory hashing to tolerate irregular latencies, avoid network hot-spots and enable high scaling. In order to model the performance of such large-scale machines, parallel simulation has been proved to be a promising approach to achieve good accuracy in reasonable times. One of the most critical factors in solving the simulation speed-accuracy trade-off is network modeling. The Cray XMT is a massively multi-threaded supercomputing architecture that belongs to the DSM class, since it implements a globally-shared address space abstraction on top of a physically distributed memory substrate. In this paper, we discuss the development of a contention-aware network model intended to be integrated in a full-system XMT simulator. We start by measuring the effects of network contention in a 128-processor XMT machine and then investigate the trade-off that exists between simulation accuracy and speed, by comparing three network models which operate at different levels of accuracy. The comparison and model validation is performed by executing a string-matching algorithm on the full-system simulator and on the XMT, using three datasets that generate noticeably different contention patterns.

99 GENERAL AND MISCELLANEOUS↗

Parallel adaptation of general three-dimensional hybrid meshes

A new parallel dynamic mesh adaptation and load balancing algorithm for general hybrid grids has been developed. The meshes considered in this work are composed of four kinds of elements; tetrahedra, prisms, hexahedra and pyramids, which poses a challenge to parallel mesh adaptation. Additional complexity imposed by the presence of multiple types of elements affects especially data migration, updates of local data structures and interpartition data structures. Efficient partition of hybrid meshes has been accomplished by transforming them to suitable graphs and using serial graph partitioning algorithms. Communication among processors is based on the faces of the interpartition boundary and the termination detection algorithm of Dijkstra is employed to ensure proper flagging of edges for refinement. An inexpensive dynamic load balancing strategy is introduced to redistribute work load among processors after adaptation. In particular, only the initial coarse mesh, with proper weighting, is balanced which yields savings in computation time and relatively simple implementation of mesh quality preservation rules, while facilitating coarsening of refined elements. Special algorithms are employed for (i) data migration and dynamic updates of the local data structures, (ii) determination of the resulting interpartition boundary and (iii) identification of the communication pattern of processors. Several representative applications are included to evaluate the method.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Local search to improve coordinate-based task mapping

We present a local search strategy to improve the coordinate-based mapping of a parallel job’s tasks to the MPI ranks of its parallel allocation in order to reduce network congestion and the job’s communication time. The goal is to reduce the number of network hops between communicating pairs of ranks. Our target is applications with a nearest-neighbor stencil communication pattern running on mesh systems with non-contiguous processor allocation, such as Cray XE and XK Systems. Utilizing the miniGhost mini-app, which models the shock physics application CTH, we demonstrate that our strategy reduces application running time while also reducing the runtime variability. Furthermore, we further show that mapping quality can vary based on the selected allocation algorithm, even between allocation algorithms of similar apparent quality.

97 MATHEMATICS AND COMPUTING↗

Parallel implementation of three-dimensional molecular dynamic simulation for laser-cluster interaction

The objective of this article is to report the parallel implementation of the 3D molecular dynamic simulation code for laser-cluster interactions. The benchmarking of the code has been done by comparing the simulation results with some of the experiments reported in the literature. Scaling laws for the computational time is established by varying the number of processor cores and number of macroparticles used. The capabilities of the code are highlighted by implementing various diagnostic tools. To study the dynamics of the laser-cluster interactions, the executable version of the code is available from the author.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

pGraph: Efficient Parallel Construction of Large-Scale Protein Sequence Homology Graphs

Detecting sequence homology between protein sequences is a fundamental problem in computational molecular biology, with a pervasive application in nearly all analyses that aim to structurally and functionally characterize protein molecules. While detecting the homology between two protein sequences is relatively inexpensive, detecting pairwise homology for a large number of protein sequences can become computationally prohibitive for modern inputs, often requiring millions of CPU hours. Yet, there is currently no robust support to parallelize this kernel. In this paper, we identify the key characteristics that make this problemparticularly hard to parallelize, and then propose a new parallel algorithm that is suited for detecting homology on large data sets using distributed memory parallel computers. Our method, called pGraph, is a novel hybrid between the hierarchical multiple-master/worker model and producer-consumer model, and is designed to break the irregularities imposed by alignment computation and work generation. Experimental results show that pGraph achieves linear scaling on a 2,048 processor distributed memory cluster for a wide range of inputs ranging from as small as 20,000 sequences to 2,560,000 sequences. In addition to demonstrating strong scaling, we present an extensive report on the performance of the various system components and related parametric studies.

Environmental Molecular Sciences Laboratory↗

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

The growth in the computational capability of modern supercomputing systems has been accompanied by corresponding increases in CPU count, total RAM, and total storage capacity. Indeed, systems such as Blue-Gene/L [3], BlueGene/P, Ranger, and the Cray XT series have grown to more than 100k processors, with 100 TeraBytes of RAM and are attached to multi-PetaByte storage systems. However, as part of this design evolution, large supercomputers have lost node-local storage elements, such as disks. While this decision was motivated by important considerations like overall system reliability, it also resulted in these systems losing a key level in their memory hierarchy, with nothing to fill the gap between local RAM and the parallel file system. While today's large supercomputers are typically attached to fast parallel file systems, which provide tens of GBs/s of I/O bandwidth, the computational capacity has grown much faster than the storage bandwidth capacity. As such, these machines are now provided with 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 [8] [16]. The result is that today's limited I/O bandwidth is choking the capabilities of modern supercomputers, specifically in terms of limiting their working sets and making fault tolerance techniques, such as checkpointing, prohibitively expensive. This paper presents an alternative system design oriented on using node-local storage to improve aggregate system I/O bandwidth. We focus on the checkpointing use-case and present an experimental evaluation of SCR, a new checkpointing library that makes use of node-local storage to significantly improve the performance of checkpointing on large-scale supercomputers. Experiments show that SCR achieves unprecedented write speeds, reaching 700GB/s on 8,752 processors. Our results scale such that we expect a similarly structured system consisting of 12,500 processors to achieve aggregate I/O bandwidth of 1 TB/s.

99 GENERAL AND MISCELLANEOUS↗

Domain decomposition in the GPU-accelerated Shift Monte Carlo code

The GPU solver within the Shift continuous-energy Monte Carlo neutron transport code has been extended to provide domain decomposition in addition to domain replication to enable the solution of problems with memory requirements exceeding the capacity of a single GPU. The strategy follows the Multiple Set, Overlapping Domain (MSOD) approach that is used in Shift’s CPU solver and integrates into the event-based algorithm used for Shift’s GPU solver. Furthermore, the ability to assign processors to spatial domains non-uniformly has been maintained. In this work, two different approaches for communicating particle data between domains are considered, and multiple criteria for load balancing problems have been investigated. Numerical results are presented for both fresh and depleted small modular nuclear reactor (SMR) cores. A parallel efficiency of approximately 80% was achieved with up to 16 spatial domains measured relative to full domain replication. A scaling study on the Summit supercomputer demonstrates a weak scaling parallel efficiency of over 90% on over 24000 GPUs.

97 MATHEMATICS AND COMPUTING↗

Complex Version of High Performance Computing LINPACK Benchmark (HPL)

This paper describes our effort for enhancing the performance of the AORSA fusion energy simulation program through the use of High Performance Linpack (HPL) benchmark, commonly used in ranking the top 500 supercomputers. The algorithm used by HPL, enhanced by a set of tuning options, is more effective than that found in the ScaLAPACK library. However, HPL is configured as a benchmark, and only for real-valued coefficients. We therefore converted HPL for use within an application program that generates complex coefficient linear systems. The result is a significant increase in performance of the solver when simulating the highest resolution experiments thus far configured, achieving 87.5 TFLOPS on over 20,000 processors on the Cray XT4.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

OpenMP Parallelization and Optimization of Graph-Based Machine Learning Algorithms

In this paper, we investigate the OpenMP parallelization and optimization of two novel data classification algorithms. The new algorithms are based on graph and PDE solution techniques and provide significant accuracy and performance advantages over traditional data classification algorithms in serial mode. The methods leverage the Nystrom extension to calculate eigenvalue/eigenvectors of the graph Laplacian and this is a self-contained module that can be used in conjunction with other graph-Laplacian based methods such as spectral clustering. We use performance tools to collect the hotspots and memory access of the serial codes and use OpenMP as the parallelization language to parallelize the most time-consuming parts. Where possible, we also use library routines. We then optimize the OpenMP implementations and detail the performance on traditional supercomputer nodes (in our case a Cray XC30), and test the optimization steps on emerging testbed systems based on Intel’s Knights Corner and Landing processors. We show both performance improvement and strong scaling behavior. Finally, a large number of optimization techniques and analyses are necessary before the algorithm reaches almost ideal scaling.

97 MATHEMATICS AND COMPUTING↗

Peptide Hit Results Processor

The Peptide Hit Results Processor (PHRP) can be used to convert an X!Tandem results file (XML format), MSGF+ .tsv search result file, Sequest Synopsis/First Hits file, or Inspect search result into a series of tab-delimited text files summarizing the results. It will insert modification symbols into the peptide sequences for modified peptides. Parallel files are created containing sequence information, modification details, and protein information. The user can optionally provide a modification definition file that specifies the symbol to use for each modification mass.

Gibbons, Bryson↗