检索结果-内蒙古大学图书馆

Hyperfast parallel-Beam Backprojection

15th International Workshop on Room-Temperature Semiconductor X- and Gamma-Ray Detectors/ 2006 ieee Nuclear Science symposium

作者： Kachelriess, Marc Knaup, Michael Bockenbach, Olivier Univ Erlangen Nurnberg Inst Med Phys Henkestr 91 D-91052 Erlangen Germany Univ Erlangen Nurnberg D-91052 Erlangen Germany Mercury Comp Syst D-12163 Berlin Germany

ISBN: (纸本)9781424405619

Tomographic image reconstruction, such as the reconstruction of CT projection values, of tomosynthesis data, PET or SPECT events, is computational very demanding. the most time-consuming step is the backprojection which is often limited by the memory bandwidth. Recently, a novel general purpose architecture optimized for distributed computing became available: the Cell Broadband Engine (CBE). Its eight synergistic processing elements (SPEs) currently allow for a theoretical performance of 192 GFlops (3 GHz, 8 units, 4 floats per vector, 2 instructions, multiply and add, per clock). To maximize image reconstruction speed we modified our parallel-beam backprojection algorithm, that is highly optimized for standard PCs, and optimized the code for the Cell processor. Data mining techniques and double buffering of source data were extensively used to optimally utilize both the memory bandwidth and the available local store of each SPE. the pixel-driven backprojection code uses floating point arithmetic and either linear interpolation (LI) or nearest neighbor (NN) interpolation between neighboring detector channels. Performance was measured using simulated data with 512 parallel beam projections per half rotation and 1024 detector elements. the data were backprojected into an image of 512 by 512 pixels using our PC-based approach and the new Cell-based algorithm. Both the PC and the CBE were clocked at 3 GHz. Images obtained were found to be identical with both approaches. A throughput of 11 fps (LI) and 15 fps (NN) was measured on the PC whereas the CBE achieved 126 fps (LI) and 165 fps (NN). thereby, the Cell greatly outperforms today's top-notch backprojections based on graphical processing units (GPU). Using both CBEs of our dual Cell-based blade (Mercury Computer Systems) one can backproject 252 images per second with LI and and 330 images per second with NN.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

MegaProto/E: Power-aware high-performance cluster with commodity technology 20

MegaProto/E: Power-aware high-performance cluster with commo...

引用

20th ieee International parallel and distributed processing symposium, IPDPS 2006

作者： Boku, Taisuke Sato, Mitsuhisa Takahashi, Daisuke Nakashima, Hiroshi Nakamura, Hiroshi Matsuoka, Satoshi Hotta, Yoshihiko University of Tsukuba Japan Toyohashi University of Technology Japan University of Tokyo Japan Tokyo Institute of Technology Japan

ISBN: (纸本)1424400546

In our research project named "Mega-Scale Computing Based on Low-Power Technology and Workload Modeling", we have been developing a prototype cluster not based on ASIC or FPGA but instead only using commodity technology. Its packaging is extremely compact and dense, and its performance/power ratio is very high. Our previous prototype system named "MegaProto" demonstrated that one cluster unit, which consists of 16 commodity low-power processors, can be successfully implemented on just 1U height chassis and it is capable of up to 2.8 times higher performance/power ratio than ordinary high-performance dual-Xeon 1U server units. We have improved MegaProto by replacing the CPU and enhancing the I/O performance. the new cluster unit named "MegaProto/E" with 16 Transmeta Efficeon processors achieves 32 GFlops of peak performance, which is 2.2-fold greater than that of the original one. the cluster unit is equipped with an independent dual network of Gigabit Ethernet, including dual 24-port switches. the maximum power consumption of the cluster unit is 320 W, which is comparable with that of today's high-end PC servers for high performance clusters. Performance evaluation using NPB kernels and HPL shows that the performance of MegaProto/E exceeds that of a dual-Xeon server in all the benchmarks, and its performance ratio ranges from 1.3 to 3.7. these results reveal that our solution of implementing a number of ultra low-power processors in compact packaging is an excellent way to achieve extremely high performance in applications with a certain degree of parallelism. We are now building a multi-unit cluster with 128 CPUs (8 units) to prove that this advantage still holds with higher scalability. © 2006 ieee.

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

Large scale distributed simulation on the Grid

Large scale distributed simulation on the Grid

引用

6th ieee International symposium on Cluster Computing and the Grid, 2006. CCGRID 06

作者： theodoropoulos, Georgios Zhang, Yi Chen, Dan Minson, Rob Turner, Stephen J. Cai, Wentong Xie, Yong Logan, Brian University of Birmingham Edgbaston Birmingham B15 2TT United Kingdom School of Computer Engineering Nanyang Technological University Singapore 639798 Singapore Computing Laboratory Oxford University Oxford OX1 3QD United Kingdom School of Computer Science and Information Technology University of Nottingham Nottingham NG8 1BB United Kingdom

ISBN: (纸本)0769525857

the development of many complex simulation applications requires collaborative effort from researchers with different domain knowledge and expertise, possibly at different locations. these simulation systems often require huge computing resources and data sets, which may be geographically distributed. In order to support collaborative model development and to cater for the increasing complexity of such systems, it is necessary to harness distributed resources over the Internet. the emergence of Grid technologies provide exciting new opportunities for large scale distributed simulation, enabling collaboration and the use of distributed computing resources, while also facilitating access to geographically distributed data sets. this paper discusses the research challenges that must be addressed before these opportunities can he exploited and presents HLA_GRID_REPAST, a system for executing large scale distributed simulations of agent based systems over the Grid. © 2006 ieee.

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

distributed wisdom: What's wrong with us?

引用

ieee distributed Systems Online 2006年第5期7卷 3-3页

作者： Shapiro, Marc INRIA Rocquencourt LIP6

the efforts of EuroSys, the professional society for European systems community, towards researching distributed systems, are discussed. As far as publishing about distributed systems is concerned European are way behind the US. the symposium on Operating Systems Design and Implementation, ACM Transactions on Computer Systems, and the ACM symposium on Operating Systems Principles rank 1st, 8th, and 11th on the CiteSeer impact list. the ACM sigops European workshop is 216th, the International Conference on distributed Computing Systems is 217th, the International symposium on Fault-Tolerant Computing is 270th, and the European Conference on Parrallel processing is 491st. Researchers are trying to change the system from within by creating the Euro Sys professional society, holding workshops, launching the EuroSys conference series, networking and exchanging information, and so on.

关键词： distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

parallelizing post-placement timing optimization 06

Parallelizing post-placement timing optimization

引用

International symposium on parallel and distributed processing (IPDPS)

作者： Jiyoun Kim M.C. Papaefthymiou J.L. Neves Advanced Computer Architecture Laboratory University of Michigan Ann Arbor MI USA IBM Server Group Poughkeepsie NY USA

ISBN: (纸本)9781424400546

this paper presents an efficient modeling scheme and a partitioning heuristic for parallelizing VLSI post-placement timing optimization. Encoding the paths with timing violations into a task graph, our novel modeling scheme provides an efficient representation of the timing and spatial relations among timing optimization tasks. Our new partitioning algorithm then assigns the task graph into multiple sessions of parallel processes, so that interprocessor communication is completely eliminated during each session. this partitioning scheme is especially useful for parallelizing processes with heavily connected tasks and, therefore, high communication requirements. For circuits with 20-130 thousand cells, the partitioning heuristic achieves speedups in excess of 5times without degrading solution quality by dynamically utilizing 1-8 processors

关键词： Timing Design optimization Very large scale integration Degradation Delay Partitioning algorithms Circuits parallel processing Design automation Computer architecture

来源：评论

学校读者我要写书评

暂无评论

parallel implementation of the replica exchange molecular dynamics algorithm on Blue Gene/L 06

Parallel implementation of the replica exchange molecular dy...

引用

International symposium on parallel and distributed processing (IPDPS)

作者： M. Eleftheriou A. Rayshubski J.W. Pitera B.G. Fitch R. Zhou R.S. Germain IBM Thomas J. Watson Research Center Yorktown Heights NY USA IBM Almaden Research Center Saint Jose CA USA

ISBN: (纸本)9781424400546

the replica exchange method is a popular approach for studying the folding thermodynamics of small to modest size proteins in explicit solvent, since it is easily parallelized. However, replica exchange can become computationally expensive for large-scale studies, due to the number of replicas needed as well as interprocess or communication requirements both between and within replicas. In this paper, we discuss an implementation of replica exchange molecular dynamics on Blue Gene/L for performing large scale simulation studies of systems of biological interest. the algorithm is tuned with an awareness of the physical network topology and hardware performance features of the Blue Gene/L architecture. Performance measurements for replica exchange using the blue matter molecular dynamics application are presented on Blue Gene/L hardware with up to 256 replicas simulated on 8,192 compute nodes. Both scalability and performance are achieved with this implementation.

关键词： Heuristic algorithms Large-scale systems Biological system modeling Computational modeling Hardware thermodynamics Proteins Solvents Biology computing Network topology

来源：评论

学校读者我要写书评

暂无评论

On-the-fly kernel updates for high-performance computing clusters 06

On-the-fly kernel updates for high-performance computing clu...

引用

International symposium on parallel and distributed processing (IPDPS)

作者： K. Makris Kyung Dong Ryu Department of Computer Science and Engineering Arizona State University Tempe AZ USA IBM Thomas J. Watson Research Center Yorktown Heights NY USA

ISBN: (纸本)9781424400546

High-performance computing clusters running long-lived tasks currently cannot have kernel software updates applied to them without causing system downtime. these clusters miss opportunities for increased performance via specialized kernel support, cannot benefit from new kernel features, and continue to operate with kernel security holes unpatched, at least until the next scheduled maintenance date. We developed a system enabling dynamic kernel updates in parallel computing clusters to address these problems. Our system, DynAMOS, is founded on execution flow high-jacking through function cloning. It enables commodity operating systems popularly used in clusters gain adaptive and mutative capabilities. To demonstrate the efficacy of our system, we illustrate our experience in dynamically updating and extending a Linux cluster. We introduce adaptive memory paging for efficient gang-scheduling; extend the kernel's process scheduler to support unobtrusive fine-grain cycle stealing, apply public security fixes, and inject performance monitoring functionality to a selection of kernel functions. Our benchmarks show that the overhead imposed by DynAMOS is mostly in the range of 1-8% for common Linux kernel functions

关键词： Kernel Operating systems Magnetohydrodynamic power generation Linux Security parallel processing Processor scheduling Cloning Instruments Application software

来源：评论

学校读者我要写书评

暂无评论

Shared receive queue based scalable MPI design for InfiniBand clusters 06

Shared receive queue based scalable MPI design for InfiniBan...

引用

International symposium on parallel and distributed processing (IPDPS)

作者： S. Sur Lei Chai Hyun-Wook Jin D.K. Panda Network-Based Computing Laboratory The Ohio State University USA

ISBN: (纸本)9781424400546

Clusters of several thousand nodes interconnected with InfiniBand, an emerging high-performance interconnect, have already appeared in the Top 500 list. the next-generation InfiniBand clusters are expected to be even larger with tens-of-thousands of nodes. A high-performance scalable MPI design is crucial for MPI applications in order to exploit the massive potential for parallelism in these very large clusters. MVAPICH is a popular implementation of MPI over InfiniBand based on its reliable connection oriented model. the requirement of this model to make communication buffers available for each connection imposes a memory scalability problem. In order to mitigate this issue, the latest InfiniBand standard includes a new feature called shared receive queue (SRQ) which allows sharing of communication buffers across multiple connections. In this paper, we propose a novel MPI design which efficiently utilizes SRQs and provides very good performance. Our analytical model reveals that our proposed designs take only 1/10 th the memory requirement as compared to the original design on a cluster sized at 16,000 nodes. Performance evaluation of our design on our 8-node cluster shows that our new design was able to provide the same performance as the existing design while requiring much lesser memory. In comparison to tuned existing designs our design showed a 20% and 5% improvement in execution time of NAS Benchmarks (Class A) LU and SP, respectively. the high performance Linpack was able to execute a much larger problem size using our new design, whereas the existing design ran out of memory

关键词： Sun Large-scale systems Computer networks Laboratories Computer science parallel processing Scalability Communication standards Analytical models Radio access networks

来源：评论

学校读者我要写书评

暂无评论

An efficient distributed algorithm for constructing delay- and degree-bounded application-level multicast tree

An efficient distributed algorithm for constructing delay- a...

引用

8th International symposium on parallel Architectures, Algorithms and Networks, I-SPAN 2005

作者： Feng, Liu Jingshu, Huang Xicheng, Lu Yuxing, Peng National Laboratory for Parallel and Distributed Processing Changsha 410073 China School of Electrical and Computer Engineering Purdue University West Lafayette IN 47907-2035 United States

ISBN: (纸本)0769525091

In this paper we investigate the problem of finding a delay- and degree-bounded maximum sum of nodes application level multicast tree. We then proved the problem is NP-hard, and its relationship with the well-studied degree-bounded minimum maximum-delay multicast tree problem. We propose a distributed algorithm - OverStream, which adopts PPAF heuristic for father node to choose optimal child nodes based on multiple network parameters. Simulation results show that our algorithm is better than OMNI, SpreadIt, HMTP, and Zigzag in general. © 2005 ieee.

关键词： Algorithms

来源：评论

学校读者我要写书评

暂无评论

Robust detection of distributed CA-CFAR in presence of extraneous targets and non-Gaussian clutter

Robust detection of distributed CA-CFAR in presence of extra...

引用

8th International symposium on Signal processing and its Applications, ISSPA 2005

作者： Messali, Z. Sahmoudi, M. Soltani, F. Electronic Departement Constantine University Algeria TSI Telecom-Paris 37-39 rue Dareau 75014 Paris France

ISBN: (纸本)0780392434

this paper deals with distributed CA-CFAR detection in presence of Gaussian and non-Gaussian clutter. In Gaussian environment, we propose to apply a wavelet transform based on soft-thresholding in multisensor CA-CFAR systems employing parallel decision fusion in both homogeneous and non homogeneous background in the sense of the Neyman-Pearson (N-P) test. In that context, we propose two approaches to combine the data from the different CA-CFAR detectors to achieve even better detection performance. In the non-Gaussian environment, we propose another preprocessing approach, based on a non-linear compressing filter, to reduce the noise effect. the three proposed new methods are shown to provide better detection performance, especially in lower SNR and in the presence of extraneous targets and heavy-tailed noise. © 2005 ieee.

关键词： Signal detection

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：