检索结果-内蒙古大学图书馆

massively parallel algorithm and Implementation of RI-MP2 Energy Calculation for Peta-Scale Many-Core Supercomputers

引用

JOURNAL OF COMPUTATIONAL CHEMISTRY 2016年第30期37卷 2623-2633页

作者： Katouda, Michio Naruse, Akira Hirano, Yukihiko Nakajima, Takahito RIKEN Adv Inst Computat Sci Computat Mol Sci Res Team Chuo Ku 7-1-26 Minatojima Minami Machi Kobe Hyogo 6500047 Japan NVIDIA Corp Minato Ku 2-11-7 Akasaka Tokyo 1070052 Japan

A new parallel algorithm and its implementation for the RIMP2 energy calculation utilizing peta-flop-class many-core supercomputers are presented. Some improvements from the previous algorithm (J. Chem. Theory Comput. 2013, 9, 5373) have been performed: (1) a dual-level hierarchical parallelization scheme that enables the use of more than 10,000 Message Passing Interface (MPI) processes and (2) a new data communication scheme that reduces network communication overhead. A multi-node and multi-GPU implementation of the present algorithm is presented for calculations on a central processing unit (CPU)/graphics processing unit (GPU) hybrid supercomputer. Benchmark results of the new algorithm and its implementation using the K computer (CPU clustering system) and TSUBAME 2.5 (CPU/GPU hybrid system) demonstrate high efficiency. The peak performance of 3.1 PFLOPS is attained using 80,199 nodes of the K computer. The peak performance of the multi-node and multi-GPU implementation is 514 TFLOPS using 1349 nodes and 4047 GPUs of TSUBAME 2.5. (C) 2016 Wiley Periodicals, Inc.

关键词： massively parallel algorithm GPGPU electron correlation theory second-order Moller-Plesset perturbation theory K computer TSUBAME 2.5 NTChem

来源：评论

学校读者我要写书评

暂无评论

Application of parallel Hybrid algorithm in massively parallel GPGPU-The Improved Effective and Efficient Method for Calculating Coulombic Interactions in Simulations of Many Ions with SIMION

引用

JOURNAL OF THE AMERICAN SOCIETY FOR MASS SPECTROMETRY 2012年第9期23卷 1609-1615页

作者： Saito, Kenichiro Koizumi, Eiko Koizumi, Hideya Arkansas State Univ Dept Chem & Phys Jonesboro AR 72467 USA

In our previous study, we introduced a new hybrid approach to effectively approximate the total force on each ion during a trajectory calculation in mass spectrometry device simulations, and the algorithm worked successfully with SIMION. We took one step further and applied the method in massively parallel general-purpose computing with GPU (GPGPU) to test its performance in simulations with thousands to over a million ions. We took extra care to minimize the barrier synchronization and data transfer between the host (CPU) and the device (GPU) memory, and took full advantage of the latency hiding. parallel codes were written in CUDA C++ and implemented to SIMION via the user-defined Lua program. In this study, we tested the parallel hybrid algorithm with a couple of basic models and analyzed the performance by comparing it to that of the original, fully-explicit method written in serial code. The Coulomb explosion simulation with 128,000 ions was completed in 309 s, over 700 times faster than the 63 h taken by the original explicit method in which we evaluated two-body Coulomb interactions explicitly on one ion with each of all the other ions. The simulation of 1,024,000 ions was completed in 2650 s. In another example, we applied the hybrid method on a simulation of ions in a simple quadrupole ion storage model with 100,000 ions, and it only took less than 10 d. Based on our estimate, the same simulation is expected to take 5-7 y by the explicit method in serial code.

关键词： Simulation Coulomb interaction massively parallel algorithm

来源：评论

学校读者我要写书评

暂无评论

MPI/OpenMP Hybrid parallel algorithm for Resolution of Identity Second-Order Moller-Plesset Perturbation Calculation of Analytical Energy Gradient for massively parallel Multicore Supercomputers

引用

JOURNAL OF COMPUTATIONAL CHEMISTRY 2017年第8期38卷 489-507页

作者： Katouda, Michio Nakajima, Takahito RIKEN Adv Inst Computat Sci Computat Mol Sci Res Team Chuo Ku 7-1-26 Minatojima Minami Machi Kobe Hyogo 6500047 Japan

A massively parallel algorithm of the analytical energy gradient calculations based the resolution of identity Moller-Plesset perturbation (RI-MP2) method from the restricted Hartree-Fock reference is presented for geometry optimization calculations and one-electron property calculations of large molecules. This algorithm is designed for massively parallel computation on multicore supercomputers applying the Message Passing Interface (MPI) and Open Multi-Processing (OpenMP) hybrid parallel programming model. In this algorithm, the two-dimensional hierarchical MP2 parallelization scheme is applied using a huge number of MPI processes (more than 1000 MPI processes) for acceleration of the computationally demanding O(N-5) step such as calculations of occupied-occupied and virtual-virtual blocks of MP2 one-particle density matrix and MP2 two-particle density matrices. The new parallel algorithm performance is assessed using test calculations of several large molecules such as buckycatcher C-60@C60H28 (144 atoms, 1820 atomic orbitals (AOs) for def2-SVP basis set, and 3888 AOs for def2-TZVP), nanographene dimer (C96H24)(2) (240 atoms, 2928 AOs for def2-SVP, and 6432 AOs for cc-pVTZ), and trp-cage protein 1L2Y (304 atoms and 2906 AOs for def2-SVP) using up to 32,768 nodes and 262,144 central processing unit (CPU) cores of the K computer. The results of geometry optimization calculations of trp-cage protein 1L2Y at the RI-MP2/def2-SVP level using the 3072 nodes and 24,576 cores of the K computer are presented and discussed to assess the efficiency of the proposed algorithm. (C) 2017 Wiley Periodicals, Inc.

关键词： RI-MP2 analytical energy gradient massively parallel algorithm geometry optimization NTChem K computer

来源：评论

学校读者我要写书评

暂无评论

Optimal surrogate boundary selection and scalability studies for the shifted boundary method on octree meshes

引用

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING 2024年 419卷

作者： Yang, Cheng-Hau Saurabh, Kumar Scovazzi, Guglielmo Canuto, Claudio Krishnamurthy, Adarsh Ganapathysubramanian, Baskar Iowa State Univ Dept Mech Engn Ames IA 50011 USA Duke Univ Dept Civil & Environm Engn Durham NC 27708 USA Politecn Torino Dipartimento Sci Matemat Corso Duca del Abruzzi 24 I-10129 Turin Italy

The accurate and efficient simulation of Partial Differential Equations (PDEs) in and around arbitrarily defined geometries is critical for many application domains. Immersed boundary methods (IBMs) alleviate the usually laborious and time-consuming process of creating bodyfitted meshes around complex geometry models (described by CAD or other representations, e.g., STL, point clouds), especially when high levels of mesh adaptivity are required. In this work, we advance the field of IBM in the context of the recently developed Shifted Boundary Method (SBM). In the SBM, the location where boundary conditions are enforced is shifted from the actual boundary of the immersed object to a nearby surrogate boundary, and boundary conditions are corrected utilizing Taylor expansions. This approach allows choosing surrogate boundaries that conform to a Cartesian mesh without losing accuracy or stability. Our contributions in this work are as follows: (a) we show that the SBM numerical error can be greatly reduced by an optimal choice of the surrogate boundary, (b) we mathematically prove the optimal convergence of the SBM for this optimal choice of the surrogate boundary, (c) we deploy the SBM on massively parallel octree meshes, including algorithmic advances to handle incomplete octrees, and (d) we showcase the applicability of these approaches with a wide variety of simulations involving complex shapes, sharp corners, and different topologies. Specific emphasis is given to Poisson's equation and the linear elasticity equations.

关键词： Immersed boundary method Incomplete octree Optimal surrogate boundary massively parallel algorithm

来源：评论

学校读者我要写书评

暂无评论

Fast density-based clustering through dataset partition using graphics processing units

引用

INFORMATION SCIENCES 2015年 308卷 94-112页

作者： Loh, Woong-Kee Yu, Hwanjo Gachon Univ Dept Software Songnam South Korea POSTECH Dept Comp Sci & Engn Pohang Si Gyeongsangbuk D South Korea

Graphics processing units (GPUs) have been utilized to improve the processing speed of many conventional data mining algorithms. DBSCAN, a popular clustering algorithm that has been often used in practice, was extended to execute on a GPU. However, existing GPU-based DBSCAN extensions still have impediments in that the distances from all objects need to be repeatedly computed to find the neighbor objects and the objects and intermediate clustering results are stored in costly off-chip memory of the GPU. This paper proposes CudaSCAN, a novel algorithm that improves the efficiency of DBSCAN by making better use of the GPU. CudaSCAN consists of three phases: (1) partitioning the entire dataset into sub-regions of size of an integer multiple of the on-chip shared memory size in the GPU;(2) local clustering within sub-regions in parallel;and (3) merging the local clustering results. CudaSCAN allows an overlap between sub-regions to ensure independent, parallel local clustering in each sub-region, which in turn enables for objects and/or intermediate results to be stored in on-chip shared memory that has an access cost a few hundred times cheaper than that of off-chip global memory. The independence also enables for merging to be parallelized. This paper proves the correctness of CudaSCAN, and according to our extensive experiments, CudaSCAN outperforms CUDA-DClust, a previous GPU-based DBSCAN extension, by up to 163.6 times. (C) 2014 Elsevier Inc. All rights reserved.

关键词： Density-based clustering Graphics processing unit massively parallel algorithm Dataset partition On-chip shared memory

来源：评论

学校读者我要写书评

暂无评论

The Quadratic Assignment Problem: Metaheuristic Optimization Using HC12 algorithm 19

The Quadratic Assignment Problem: Metaheuristic Optimization...

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Matousek, Radomil Dobrovsky, Ladislav Kudela, Jakub Brno Univ Technol Inst Automat & Comp Sci Brno Czech Republic

ISBN: (纸本)9781450367486

The Quadratic Assignment Problem (QAP) is a classical NP hard combinatorial optimization problem. In the paper will be presented suitable metaheuristic algorithm HC12. The algorithm is population based and uses a massive parallel search of the binary space which represents the solution space of the QAP. The presented implementation of the metaheuristic HC12 utilizes the latest GPU CUDA platform. The results are presented on standard test problems from the QAP library.*

关键词： Quadratic assignment problem massively parallel algorithm

来源：评论

学校读者我要写书评

暂无评论

An Optimal MPC algorithm for Subunit-Monge Matrix Multiplication, with Applications to LIS 24

An Optimal MPC Algorithm for Subunit-Monge Matrix Multiplica...

引用

36th ACM Symposium on parallelism in algorithms and Architectures (SPAA)

作者： Koo, Jaehyun MIT 77 Massachusetts Ave Cambridge MA 02139 USA

ISBN: (纸本)9798400704161

We present an O(1)-round fully-scalable deterministic massively parallel algorithm for computing the min-plus matrix multiplication of unit-Monge matrices. We use this to derive a O(log n)-round fully-scalable massively parallel algorithm for solving the exact longest increasing subsequence (LIS) problem. For a fully-scalable MPC regime, this result substantially improves the previously known algorithm of O(log(4) n)-round complexity, and matches the best algorithm for computing the (1 + epsilon)-approximation of LIS.

关键词： longest increasing subsequence longest common subsequences subunit-Monge matrix multiplication massively parallel algorithm

来源：评论

学校读者我要写书评

暂无评论

parallel algorithm for Dynamic Community Detection 29

Parallel Algorithm for Dynamic Community Detection

引用

8th International Symposium on Computer Architecture and High Performance Computing (SBAC-PADW)

作者： Resende, Hugo Fazenda, Alvaro Luiz Quiles, Marcos Goncalves Fed Inst Educ Sci & Technol South Minas Gerais Pouso Alegre MG Brazil Univ Fed Sao Paulo Sao Paulo SP Brazil

ISBN: (纸本)9781538648193

Many real systems can be naturally modeled by complex networks. A complex network represents an abstraction of the system regarding its components and their respective interactions. Thus, by scrutinizing the network, interesting properties of the system can be revealed. Among them, the presence of communities, which consists of groups of densely connected nodes, is a significant one. For instance, a community might reveal patterns, such as the functional units of the system, or even groups correlated people in social networks. Albeit important, the community detection process is not a simple computational task, in special when the network is dynamic. Thus, several researchers have addressed this problem providing distinct methods, especially to deal with static networks. Recently, a new algorithm was introduced to solve this problem. The approach consists of modeling the network as a set of particles inspired by a N-body problem. Besides delivering similar results to state-of-the-art community detection algorithm, the proposed model is dynamic in nature;thus, it can be straightforwardly applied to time-varying complex networks. However, the Particle Model still has a major drawback. Its computational cost is quadratic per cycle, which restricts its application to mid-scale networks. To overcome this limitation, here, we present a novel parallel algorithm using many-core high-performance resources. Through the implementation of a new data structure, named distance matrix, was allowed a massive parallelization of the particle's interactions. Simulation results show that our parallel approach, running both traditional CPUs and hardware accelerators based on multicore CPUs and GPUs, can speed up the method permitting its application to large-scale networks.

关键词： community detection massively parallel algorithm high-performance computing on hardware accelerators

来源：评论

学校读者我要写书评

暂无评论

Scaling Graph Traversal to 281 Trillion Edges with 40 Million Cores 22

Scaling Graph Traversal to 281 Trillion Edges with 40 Millio...

引用

27th ACM SIGPLAN Symposium on Principles and Practice of parallel Programming (PPoPP)

作者： Cao, Huanqi Wang, Yuanwei Wang, Haojie Lin, Heng Ma, Zixuan Yin, Wanwang Chen, Wenguang Tsinghua Univ Dept Comp Sci & Technol Beijing Peoples R China Tsinghua Univ BNRist Beijing Peoples R China Peking Univ Sch Comp Sci Beijing Peoples R China Natl Supercomp Ctr Wuxi Wuxi Jiangsu Peoples R China

ISBN: (纸本)9781450392044

Graph processing, especially high-performance graph traversal, plays a more and more important role in data analytics. The successor of Sunway TaihuLight, NEW SUNWAY, is equipped with nearly 10 PB memory and over 40 million cores, which brings the opportunity to process hundreds of trillions of edges graphs. However, the graph with an unprecedented scale also brings severe performance challenges, including load imbalance, poor locality, and irregular access of graph traversal workload. To address the scalability problem, we propose a novel 3-level degree-aware 1.5D graph partitioning, which benefits from both delegated 1D and 2D partitioning. By delegating extremely heavy vertices globally and other heavy vertices on columns and rows in the processes mesh, we break the scalability wall of previous partitioning methods. Together with sub-iteration direction optimization, core group -aware core subgraph segmenting, and a new on-chip sorting mechanism using RMA, we achieve 180,792 GTEPS on a graph with 281 trillion edges, using 103,912 processors with over 40 million cores, achieving 1.75x performance and 8x capacity compared to the previous state of the art and conforming to the Graph 500 BFS benchmark[14].

关键词： massively parallel algorithm breadth-first search heterogeneous architecture

来源：评论

学校读者我要写书评

暂无评论

The large scale parallelization of a conformational 3D Protein structure prediction application 98

The large scale parallelization of a conformational 3D Prote...

引用

Proceedings of the 1998 ACM/IEEE conference on Supercomputing

作者： Philip LoCascio Kaizhi Yue Peter Cummings Ken Dill Center for Computational Sciences Oak Ridge TN University of California-San Francisco San Francisco CA University of Tennessee Knoxville TN and Oak Ridge National Laboratory Oak Ridge TN

ISBN: (纸本)9780897919845

We present here the design strategy and performance analysis of a large scale scientific application, for the prediction of 3D Protein structures. The unique challenges which will be investigated are the primary objectives of a reduction in wall clock run time through the parallelization process, and the production of an application capable of running and scaling to a massively parallel configuration (currently 1024 nodes of the Intel Paragon) reliably for many non-contiguous days of supercomputer time. Enough flexibility to be reconfigured for a number of different parallel architectures including the CRAY T3E and IBM SP2 was included through the use of MPI as the parallel software *** application, GEOCORE, predicts small ensembles of native-like peptide conformations from amino acid sequences. GEOCORE uses a very simple energy function and an extensive conformational search process. The serial program has been tested on around 20 small peptides and is shown to be capable of discriminating native from non-native structures.

关键词： massively parallel algorithm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：