检索结果-内蒙古大学图书馆

Porting the Princeton Ocean Model to GPUs 1

14th international conference on algorithms and architectures for parallel processing (ICA3PP)

作者： Xu, Shizhen Huang, Xiaomeng Zhang, Yan Hu, Yong Fu, Haohuan Yang, Guangwen Tsinghua Univ Minist Educ Key Lab Earth Syst Modeling Beijing 100084 Peoples R China

ISBN: (数字)9783319111971

ISBN: (纸本)9783319111971;9783319111964

While GPU is becoming a compelling acceleration solution for a series of scientific applications, most existing work on climate models only achieved limited speedup. It is due to partial porting of the huge code and the memory bound inherence of these models. In this work, we design and implement a customized GPU-based acceleration of the Princeton Ocean Model (gpuPOM). Based on Nvidia's state-of-the-art GPU architectures (K20X and K40m), we rewrite the original model from the Fortran into the CUDA-C completely. Several accelerating methods, including optimizing memory access in a single GPU, overlapping communication and boundary operations among multiple GPUs, are presented. the experimental results show that the gpuPOM on one K40m GPU achieves 6.9-fold to 17.8-fold speedup and 5.8-fold to 15.5-fold speedup on one K20X GPU comparing with different Intel CPUs. Further experiments on multiple GPUs indicate that the performance of the gpuPOM on a super-workstation containing 4 GPUs is equivalent to a powerful cluster consisting of 34 pure CPU nodes with over 400 CPU cores.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

A Platform for Stock Market Simulation with Distributed Agent-Based Modeling 1

引用

14th international conference on algorithms and architectures for parallel processing (ICA3PP)

作者： Wang, Chunyu Yu, Ce Wu, Hutong Chen, Xiang Li, Yuelei Zhang, Xiaotao Tianjin Univ Sch Comp Sci & Technol Tianjin 300072 Peoples R China Tianjin Univ Sch Econ & Management Tianjin Peoples R China

ISBN: (数字)9783319111940

ISBN: (纸本)9783319111940;9783319111933

Agent-based modeling (ABM) has been widely used in stock market simulation. However, traditional simulations of stock markets with ABM on single computers are limited by the computing capability as breakthroughs in financial research need much larger amount of agents. this paper introduces a platform for stock market simulation with ABM focusing on large scale parallel agents in a distributed computing environment such as Cluster and MPP. With the customized trade strategies inside the agents, the runtime system of the platform can distribute the massive amount of agents to multiple computing nodes automatically during the execution of the simulation. And agents exchange information with each other and the market through a uniform communication system. With this platform financial researchers can design their own financial model without caring about the complexity of parallelization and related problems. the sample simulation on the platform is verified to be compatible with the data from Euronext-NYSE and the platform shows fair scalability and performance under different parallelism configurations.

关键词： stock market simulation agent-based modeling parallel distributed environment

来源：评论

学校读者我要写书评

暂无评论

Applying OpenMP-based parallel Implementations of NSGA-II and SPEA2 to Study Phylogenetic Relationships 16

Applying OpenMP-based Parallel Implementations of NSGA-II an...

引用

16th IEEE international conference on Cluster Computing (CLUSTER)

作者： Santander-Jimenez, Sergio Vega-Rodriguez, Miguel A. Univ Extremadura Dept Technol Comp & Commun Caceres Spain

ISBN: (纸本)9781479955480

throughout the years, biological processing demands have been addressed by relying on the design of algorithmic approaches for parallel architectures. By taking advantage of multicore processor systems, we can deal with the main sources of complexity which explain the NP-hard nature of multiple problems in computational biology. In this work, we address the inference of phylogenetic topologies by using two multiobjective metaheuristics: Fast Non-Dominated Sorting Genetic Algorithm and Strength Pareto Evolutionary Algorithm 2. the additional complexity introduced by the multiobjective formulation of the problem motivates that parallel designs of these algorithms must be undertaken. For this purpose, OpenMP-based implementations of these two metaheuristics are applied. To evaluate the performance of these approaches, a comparative study has been conducted by performing experimentation on four nucleotide data sets. Our experiments suggest the relevance of these parallel algorithmic designs, improving the phylogenetic results reported by other multiobjective tools in reduced execution times.

关键词： Multiobjective optimization evolutionary computation parallel computing phylogeny reconstruction

来源：评论

学校读者我要写书评

暂无评论

Efficient Non-uniform Channelization for SDR Using Frequency Domain Filtering 5

Efficient Non-uniform Channelization for SDR Using Frequency...

引用

5th IEEE international conference on Software Engineering and Service Science (ICSESS)

作者： Jiang, Tian-li Gong, Ke-xian Peng, Hua Wu, Di Informat Engn Univ Inst Informat Syst Engn Zhengzhou Peoples R China

ISBN: (纸本)9781479932795

An arbitrary sampling rate conversion algorithm based on frequency domain filtering (FDF-ASRC) is proposed. the number of Fourier coefficients in FDF-ASRC is irrelevant to the symbol rate of interested signal. Applying the resampling algorithm to non-uniform channelization, a few modules of Fourier transform (FT) and inverse Fourier transform (IFT) can guarantee infinite channels in channelization. Meanwhile, the sampling rate of output signal can be adjusted to an integer multiple of symbol rate, which can be passed to demodulator directly. By comparison with seven architectures of non-uniform channelizers, the computational complexity of the proposed channelizers is equal to the best.

关键词： SD Non-uniform channelization Multi-rate signal processing Arbitrary sampling rate conversion Frequency domain filtering

来源：评论

学校读者我要写书评

暂无评论

Data-driven techniques to overcome workload disparity 4

Data-driven techniques to overcome workload disparity

引用

4th Workshop on Irregular Applications: architectures and algorithms, IA3 2014

作者： Connors, Dan Saleh, Skyler Joshi, Tejas Bueter, Ryan Department of Electrical Engineering University of Colorado Denver DenverCO80217-3364 United States

ISBN: (纸本)9781479970568

General-purpose computing on graphics processing unit (GPGPU) architectures rely on data locality and regular computation to leverage parallel resources to achieve performance benefits over multi-core systems. Current GPUs often cannot effectively accommodate irregular algorithms and non-uniform memory accesses. Irregular execution corrupts the efficiency of the rigid GPU groups of threads that lead to idle execution execution and workload disparity in the GPU architecture. While hardware aspects of branch divergence, local memory bank conflicts, and non-coalesced memory accesses cause workload disparity, the greater issue is the lost of execution potential from other GPU workgroups. this paper sets out to characterize the workload disparity and toexplore data-driven models for executing irregular computations on GPU architectures. © 2014 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

parallel online spatial and temporal aggregations on multi-core CPUs and many-core GPUs

引用

INFORMATION SYSTEMS 2014年第Aug.期44卷 134-154页

作者： Zhang, Jianting You, Simin Gruenwald, Le CUNY Dept Comp Sci New York NY 10031 USA CUNY Grad Ctr Dept Comp Sci New York NY 10016 USA Univ Oklahoma Sch Comp Sci Norman OK 73071 USA

With the increasing availability of locating and navigation technologies on portable wireless devices, huge amounts of location data are being captured at ever growing rates. Spatial and temporal aggregations in an Online Analytical processing (OLAP) setting for the large-scale ubiquitous urban sensing data play an important role in understanding urban dynamics and facilitating decision making. Unfortunately, existing spatial, temporal and spatiotemporal OLAP techniques are mostly based on traditional computing frameworks, i.e., disk-resident systems on uniprocessors based on serial algorithms, which makes them incapable of handling large-scale data on parallel hardware architectures that have already been equipped with commodity computers. In this study, we report our designs, implementations and experiments on developing a data management platform and a set of parallel techniques to support high-performance online spatial and temporal aggregations on multi-core CPUs and many-core Graphics processing Units (CPUs). Our experiment results show that we are able to spatially associate nearly 170 million taxi pickup location points with their nearest street segments among 147,011 candidates in about 5-25 s on both an Nvidia Quadro 6000 GPU device and dual Intel Xeon E5405 quad-core CPUs when their Vector processing Units (VPUs) are utilized for computing intensive tasks. After spatially associating points with road segments, spatial, temporal and spatiotemporal aggregations are reduced to relational aggregations and can be processed in the order of a fraction of a second on both CPUs and multi-core CPUs. In addition to demonstrating the feasibility of building a high-performance OLAP system for processing large-scale taxi trip data for real-time, interactive data explorations, our work also opens the paths to achieving even higher OLAP query efficiency for large-scale applications through integrating domain-specific data management platforms, novel parallel data structu

关键词： OLAP parallel design GPU Multi-core CPU Spatiotemporal aggregation Spatial indexing Spatial join Large-scale data

来源：评论

学校读者我要写书评

暂无评论

High energy electromagnetic particle transportation on the GPU

High energy electromagnetic particle transportation on the G...

引用

20th international conference on Computing in High Energy and Nuclear Physics (CHEP)

作者： Canal, P. Elvira, D. Jun, S. Y. Kowalkowski, J. Paterno, M. Apostolakis, J. Fermilab Natl Accelerator Lab MS234POB 500 Batavia IL 60510 USA CERN PH Dept CH-1211 Geneva Switzerland

We present massively parallel high energy electromagnetic particle transportation through a finely segmented detector on a Graphics processing Unit (GPU). Simulating events of energetic particle decay in a general-purpose high energy physics (HEP) detector requires intensive computing resources, due to the complexity of the geometry as well as physics processes applied to particles copiously produced by primary collisions and secondary interactions. the recent advent of hardware architectures of many-core or accelerated processors provides the variety of concurrent programming models applicable not only for the high performance parallel computing, but also for the conventional computing intensive application such as the HEP detector simulation. the components of our prototype are a transportation process under a non-uniform magnetic field, geometry navigation with a set of solid shapes and materials, electromagnetic physics processes for electrons and photons, and an interface to a framework that dispatches bundles of tracks in a highly vectorized manner optimizing for spatial locality and throughput. Core algorithms and methods are excerpted from the Geant4 toolkit, and are modified and optimized for the GPU application. Program kernels written in C/C++ are designed to be compatible with CUDA and OpenCL and with the aim to be generic enough for easy porting to future programming models and hardware architectures. To improve throughput by overlapping data transfers with kernel execution, multiple CUDA streams are used. Issues with floating point accuracy, random numbers generation, data structure, kernel divergences and register spills are also considered. Performance evaluation for the relative speedup compared to the corresponding sequential execution on CPU is presented as well.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Analysis and Realization of Relaxed Consistency Memory Model for Multi-core CPU or GPU 5th

Analysis and Realization of Relaxed Consistency Memory Model...

引用

5th international conference on Confluence - the Next Generation Information Technology Summit (Confluence)

作者： Mohanty, Ramanarayan Behera, Dipti Prakash Routray, Aurobinda Indian Inst Technol Adv Technol Dev Ctr Kharagpur 721302 W Bengal India Indian Inst Technol Dept Reliabil Engg Kharagpur 721302 W Bengal India Indian Inst Technol Dept Elect Engn Kharagpur 721302 W Bengal India

ISBN: (纸本)9781479942367

parallel and distributed systems that support the shared memory paradigm are becoming widely accepted in many areas of computing. the memory consistency model of a shared-memory multiprocessor system influences both the performance and the programmability of the system. Under optimal condition it is found that multithreading contributes to more than 50 percent of performance improvement, while the improvement from Relaxed Consistency Memory (RCM) models varies between 30-40 percent of total performance gain. the relaxed consistency memory model has been realized on a Graphics processing Unit (GPU) using Open Computing Language (OpenCL) as the programming language. this memory model has been applied on a case study of high order matrix multiplication and their performance has been analysed in terms of two metrics: GPU Computation Percentage (GCP) and GPU Load Balance (GLB). With sufficient parallelism and high PCIe data transfer bandwidth, the RCM model on GPU gives the better performance in comparison to a sequential model on CPU.

关键词： Graphics processing Unit GPU Computation Percentage GPU Load Balance OpenCL Relaxed Consistency Memory

来源：评论

学校读者我要写书评

暂无评论

Repairing Multiple Data Losses by parallel Max-min Trees Based on Regenerating Codes in Distributed Storage Systems

Repairing Multiple Data Losses by Parallel Max-min Trees Bas...

引用

14th international conference on algorithms and architectures for parallel processing (ICA3PP)

作者： You, Pengfei Peng, Yuxing Huang, Zhen Wang, Changjian Natl Univ Def Technol Coll Comp Changsha 410073 Hunan Peoples R China

ISBN: (纸本)9783319111940;9783319111933

Due to high storage efficiency, erasure codes are recently used to provide high data reliability in distributed storage systems. When multiple data loses in system, regeneration time for them demands to be as short as possible so as to keep data availbility and reliability. Common way is to repair them one by one, which prolongs the regeneration time. Tree-structured regeneration may reduce regeneration time when regenerating one single node failure by relaying the network traffic, and is also extended to regenerate multiple data losses. In this paper, based on regenerating codes which achieve minimal network traffic during the regeneration, we consider reducing regeneration time by using multiple max-min trees to parallel regenerate multiple data losses. And we proposed an algorithm: bandwidth-sharing max-min algorithm (BSM2RC) to construct multiple parallel max-min trees. It realizes efficient bandwidth utilization by maximizing the minimal bottleneck edge weight of multiple regeneration trees, thus improve regeneration efficiency. Our simulation experiment shows that multiple parallel max-min trees reduce total regeneration time for multiple data losses significantly, and thus enhance system reliability, compared with existing regeneration scheme.

关键词： Distributed storage System Data regeneration Regenerating codes Regeneration tree Max-min tree Maximum spanning tree

来源：评论

学校读者我要写书评

暂无评论

Efficient Execution of Erasure Codes on AMD APU Architecture

Efficient Execution of Erasure Codes on AMD APU Architecture

引用

10th international conference on parallel processing and Applied Mathematics (PPAM)

作者： Wyrzykowski, Roman Wozniak, Marcin Kuczynski, Lukasz Czestochowa Tech Univ Inst Comp & Informat Sci PL-42201 Czestochowa Poland

ISBN: (纸本)9783642552243

Erasure codes such as Reed-Solomon codes can improve the availability of distributed storage in comparison with replication systems. In previous studies we investigated implementation of these codes on multi/many-core architectures, such as Cell/B. E. and GPUs. In particular, it was shown that bandwidth of PCIe bus is a bottleneck for the implementation on GPUs. In this paper, we focus on investigation how to map systematically the Reed-Solomon erasure codes onto the AMD Accelerated processing Unit (APU), a new heterogeneous multi/many-core architecture. this architecture combines CPU and GPU in a single chip, eliminating costly transfers between them through the PCI bus. Moreover, APU processors combine some features of Cell/B. E. processors and many-core GPUs, allowing for both vectorization and SIMT processing simultaneously. Based on the previous works, the method for the systematic mapping of computation kernels of Reed-Solomon and Cauchy Reed-Solomon algorithms onto the AMD APU architecture is proposed. this method takes into account properties of the architecture on all the levels of its parallel processing hierarchy.

关键词： Erasure codes Reed-Solomon codes Multicore architectures GPU APU OpenCl

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：