发布求助
文献互助 智能选刊 最新文献

Conference on Hypercube Concurrent Computers and Applications最新文献

筛选
英文 中文
Computational geometry on hypercube computers 超立方体计算机上的计算几何
Conference on Hypercube Concurrent Computers and Applications Pub Date : 1989-01-03 DOI: 10.1145/63047.63076
Russ Miller, Q. Stout
{"title":"Computational geometry on hypercube computers","authors":"Russ Miller, Q. Stout","doi":"10.1145/63047.63076","DOIUrl":"https://doi.org/10.1145/63047.63076","url":null,"abstract":"This paper gives hypercube algorithms for some simple problems involving geometric properties of sets of points. The properties considered emphasize aspects of convexity and domination. Efficient algorithms are given for both fine-grain and medium-grain hypercube computers. For both serial and parallel computers, sorting plays an important role in geometric algorithms for determining simple properties, often being the dominant component of the time. On a hypercube computer the time required to sort is still not fully understood, so the times of some of our algorithms for unsorted data are not completely determined. For the fine-grain model using worst case timing we show that if the data is presorted then faster algorithms are possible, if sorting one item per processor requires time growing faster than the dimension of the hypercube. For both models we show that faster algorithms are possible for point sets generated randomly, when time is measured using expected time. Our algorithms are developed for sets of planar points, with several of them extending to sets of points in spaces of higher dimension.","PeriodicalId":299435,"journal":{"name":"Conference on Hypercube Concurrent Computers and Applications","volume":"190 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123524048","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 5
Branch-and-bound algorithms on a hypercube 超立方体上的分支定界算法
Conference on Hypercube Concurrent Computers and Applications Pub Date : 1989-01-03 DOI: 10.1145/63047.63109
R. Pargas, D. Wooster
{"title":"Branch-and-bound algorithms on a hypercube","authors":"R. Pargas, D. Wooster","doi":"10.1145/63047.63109","DOIUrl":"https://doi.org/10.1145/63047.63109","url":null,"abstract":"The parallel implementation of branch-and-bound algorithms on multiprocessors has received an increasing amount of attention in recent years. This paper describes research currently being conducted at Clemson University. We study the job scheduling problem: given n jobs, each with processing time, p<subscrpt>i</subscrpt>, and due date, d<subscrpt>i</subscrpt>, schedule these jobs on a single machine such that total tardiness is minimized. Total tardiness, T, is defined as: T = n ∑ i=1 w<subscrpt>i</subscrpt> * max { 0, C<subscrpt>i</subscrpt> - d<subscrpt>i</subscrpt> } where C<subscrpt>i</subscrpt> is the completion time and w<subscrpt>i</subscrpt> is the weight of job i. The hypercube used is a Floating Point Systems T-20: sixteen INMOS Transputers, synchronous communication, programmed in OCCAM. We describe an implementation focusing specifically on efficient communication and load balancing algorithms.","PeriodicalId":299435,"journal":{"name":"Conference on Hypercube Concurrent Computers and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127448752","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 21
A concurrent on-board vision system for a mobile robot 一种用于移动机器人的并行车载视觉系统
Conference on Hypercube Concurrent Computers and Applications Pub Date : 1989-01-03 DOI: 10.1145/63047.63056
J. P. Jones
{"title":"A concurrent on-board vision system for a mobile robot","authors":"J. P. Jones","doi":"10.1145/63047.63056","DOIUrl":"https://doi.org/10.1145/63047.63056","url":null,"abstract":"Robot vision algorithms have been implemented on an 8-node NCUBE-AT hypercube system onboard a mobile robot (HERMIES) developed at Oak Ridge National Laboratory. Images are digitized using a framegrabber mounted in a VME rack. Image processing and analysis are performed on the hypercube system. The vision system is integrated with robot navigation and control software, enabling the robot to find the front of a mockup control panel, move up to the panel, and read an analog meter. Among the concurrent algorithms used for image analysis are a new component labeling algorithm and a Hough transform algorithm with load balancing.","PeriodicalId":299435,"journal":{"name":"Conference on Hypercube Concurrent Computers and Applications","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121669060","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 12
Multi-sensor integration on the NCUBE hypercube computer NCUBE超立方体计算机上的多传感器集成
Conference on Hypercube Concurrent Computers and Applications Pub Date : 1989-01-03 DOI: 10.1145/63047.63078
C. Glover
{"title":"Multi-sensor integration on the NCUBE hypercube computer","authors":"C. Glover","doi":"10.1145/63047.63078","DOIUrl":"https://doi.org/10.1145/63047.63078","url":null,"abstract":"This paper presents the quantitative performance results obtained from converting a large sequential Multi-Sensor Integration (MSI) program into a concurrent form, and executing the program on an NCUBE hypercube computer for several test case scenarios. Each sensor track was assigned to a different node of the hypercube where computationally intensive calculations were performed, A 4-node hypercube was found to be the optimal size for the test case scenario discussed here, where speed-up factors of 1.5 to 1.7 were obtained. A completely concurrent MSI algorithm is also presented.","PeriodicalId":299435,"journal":{"name":"Conference on Hypercube Concurrent Computers and Applications","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124653885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
A hypercube Ray-tracer 超立方体射线追踪器
Conference on Hypercube Concurrent Computers and Applications Pub Date : 1989-01-03 DOI: 10.1145/63047.63073
J. Salmon, J. Goldsmith
{"title":"A hypercube Ray-tracer","authors":"J. Salmon, J. Goldsmith","doi":"10.1145/63047.63073","DOIUrl":"https://doi.org/10.1145/63047.63073","url":null,"abstract":"We describe a hypercube ray-tracing program for rendering computer graphics. For small models, which fit in the memory of a single processor, the ray-tracer uses a scattered decomposition of pixels to balance the load, and achieves a very high efficiency. The more interesting case of large models, which cannot be stored in a single processor, requires a decomposition of the model data as well as the pixels. We present algorithms for constructing a decomposition based upon information about the frequency with which different elements of the model are accessed. The resulting decomposition is approximately optimized to minimize communication and achieve load balance.","PeriodicalId":299435,"journal":{"name":"Conference on Hypercube Concurrent Computers and Applications","volume":"365 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120940400","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 58
Prefix algorithms for tridiagonal systems on hypercube multiprocessors 超立方多处理机上三对角系统的前缀算法
Conference on Hypercube Concurrent Computers and Applications Pub Date : 1989-01-03 DOI: 10.1145/63047.63112
Ö. Eğecioğlu, Ç. Koç, A. Laub
{"title":"Prefix algorithms for tridiagonal systems on hypercube multiprocessors","authors":"Ö. Eğecioğlu, Ç. Koç, A. Laub","doi":"10.1145/63047.63112","DOIUrl":"https://doi.org/10.1145/63047.63112","url":null,"abstract":"The recursive doubling algorithm as developed by Stone can be used to solve a tridiagonal linear system of size <italic>n</italic> on a parallel computer with <italic>n</italic> processors using <italic>&Ogr;</italic> ( log <italic>n</italic> ) parallel arithmetic steps. Here we describe a limited processor version of the recursive doubling algorithm for the solution of tridiagonal linear systems using <italic>&Ogr;</italic> ( <italic>n / p</italic> + log <italic>p</italic> ) parallel arithmetic steps on a parallel computer with <italic>p < n</italic> processors. The main technique relies on fast parallel prefix algorithms, which can be efficiently mapped on the hypercube architecture using the binary-reflected Gray code. For <italic>pn</italic> this algorithm achieves linear speed-up and constant efficiency over its sequential implementation as well as over the sequential LU decomposition algorithm. These results are confirmed by numerical experiments obtained on an Intel iPSC/d5 hypercube multiprocessor.","PeriodicalId":299435,"journal":{"name":"Conference on Hypercube Concurrent Computers and Applications","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126707888","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Waveform relaxation for concurrent dynamic simulation of distillation columns 精馏塔同步动态模拟的波形松弛
Conference on Hypercube Concurrent Computers and Applications Pub Date : 1989-01-03 DOI: 10.1145/63047.63060
A. Skjellum, M. Morari, S. Nattisson
{"title":"Waveform relaxation for concurrent dynamic simulation of distillation columns","authors":"A. Skjellum, M. Morari, S. Nattisson","doi":"10.1145/63047.63060","DOIUrl":"https://doi.org/10.1145/63047.63060","url":null,"abstract":"The need for cost-effective, high-speed computing is essential in many aspects of chemical engineering practice, notably for the simulation of large-scale dynamic systems. The arrival of powerful, highly concurrent message-passing multicomputers potentially offers such economical large-scale computing capability [13,14]. Development of appropriate, efficient algorithms which realize this potential must therefore become an important area of ongoing research and development in chemical engineering. Desired orders-of-magnitude speedup strongly motivates the use of novel algorithmic approaches for large-scale simulation. Initially, we are developing a simplified binary distillation simulation using the waveform relaxation paradigm [1-7]. Waveform relaxation has proven successful for the concurrent simulation of large-scale VLSI circuits [1-3,6,7] and is therefore a promising approach. Rather than an end in itself, however, we expect that results of this research effort will prove relevant to more general concurrent dynamic simulation including rigorous multicomponent distillation and chemical process flowsheeting. We describe the implementation effort (which generalizes the pre-existing CONCISEVLSI circuit simulator, [6]), the simplified distillation model, design issues and current status including a sketch of the underlying waveform relaxation algorithm and its realization. Elsewhere we report further observations as well as speedup results [15].","PeriodicalId":299435,"journal":{"name":"Conference on Hypercube Concurrent Computers and Applications","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114743965","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 9
A dynamic load balancer for a parallel branch and bound algorithm 一种并行分支定界算法的动态负载均衡器
Conference on Hypercube Concurrent Computers and Applications Pub Date : 1989-01-03 DOI: 10.1145/63047.63108
R. Ma, F. Tsung, Meixiu Ma
{"title":"A dynamic load balancer for a parallel branch and bound algorithm","authors":"R. Ma, F. Tsung, Meixiu Ma","doi":"10.1145/63047.63108","DOIUrl":"https://doi.org/10.1145/63047.63108","url":null,"abstract":"This paper presents a load-balancing scheme for a parallel branch and bound (PBB) algorithm utilizing a dynamic load balancer (DLB). The PBB algorithm is used to solve a resource scheduling problem on the Hypercube. The DLB is included in the PBB algorithm and is distributed to each node to balance the workload during run time. The DLB is evaluated by implementing two PBB algorithms, with DLB and without DLB. Results show that the PBB with DLB is 3.14 times faster than the algorithm without DLB.","PeriodicalId":299435,"journal":{"name":"Conference on Hypercube Concurrent Computers and Applications","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133749076","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 14
A Schwarz splitting variant of cubic spline collocation methods for elliptic PDEs 椭圆偏微分方程的三次样条配置方法的Schwarz分裂变体
Conference on Hypercube Concurrent Computers and Applications Pub Date : 1989-01-03 DOI: 10.1145/63047.63133
E. Houstis, J. R. Rice, E. Vavalis
{"title":"A Schwarz splitting variant of cubic spline collocation methods for elliptic PDEs","authors":"E. Houstis, J. R. Rice, E. Vavalis","doi":"10.1145/63047.63133","DOIUrl":"https://doi.org/10.1145/63047.63133","url":null,"abstract":"We consider the formulation of the Schwarz alternating method for a new class of elliptic cubic spline collocation discretization schemes. The convergence of the method is studied using Jacobi and Gauss-Seidel iterative methods for implementing the interaction among subdomains. The Schwarz Cubic Spline Collocation (SCSC) method is formulated for hypercube architectures and implemented on the NCUBE (128 processors) machine. The performance and convergence of the hypercube SCSC algorithm is studied with respect to domain partition and subdomain overlapping area. The numerical results indicate that the partition and mapping of the SCSC on the NCUBE is almost optimal while the speedup obtained is similar to other domain decomposition techniques.","PeriodicalId":299435,"journal":{"name":"Conference on Hypercube Concurrent Computers and Applications","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133495242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 8
Reliability mechanisms for ADAMS ADAMS的可靠性机制
Conference on Hypercube Concurrent Computers and Applications Pub Date : 1989-01-03 DOI: 10.1145/63047.63095
S. Son, J. Pfaltz
{"title":"Reliability mechanisms for ADAMS","authors":"S. Son, J. Pfaltz","doi":"10.1145/63047.63095","DOIUrl":"https://doi.org/10.1145/63047.63095","url":null,"abstract":"The goal of checkpointing in database management systems is to save database states on a separate secure device so that the database can be recovered when errors and failures occur. This paper presents a non-interfering checkpointing mechanism being developed for ADAMS. Instead of waiting for a consistent state to occur, our checkpointing approach constructs a state that would result by completing the transactions that are in progress when the global checkpoint begins. The checkpointing algorithm is executed concurrently with transaction activity while constructing a transaction-consistent checkpoint on disk, without requiring the database quiesce. This property of non-interference is highly desirable to real-time applications, where restricting transaction activity during the checkpointing operation is in many cases not feasible. Two main properties of this checkpointing algorithm are global consistency and reduced interference, both of which are crucial for achieving high availability.","PeriodicalId":299435,"journal":{"name":"Conference on Hypercube Concurrent Computers and Applications","volume":"494 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133366403","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信