Filters








1,662 Hits in 3.3 sec

Large-grain pipelining on hypercube multiprocessors

C-T. King, L. M. Ni
1988 Proceedings of the third conference on Hypercube concurrent computers and applications -  
A new paradigm. called large-grain pipelin-, ing, for developing efficient parallel algorithms on distributed-memory multiprocessors. cg.. hypercube machines, is introduced Large-grain pipelining attempts  ...  These hypercube machines arc characterized by a point-to-point, hypercube interprocessor connection.  ...  Even the concurrent computation depicted in Figure 2 (a) can be considered as a pipelined computation with 8 pipelines, each has only one stage.  ... 
doi:10.1145/63047.63119 fatcat:cp76u3vjrbd6rnv4tprncqfqqy

Parallel branch and bound algorithms on hypercube multiprocessors

T. S. Abdelrahman, T. N. Mudge
1988 Proceedings of the third conference on Hypercube concurrent computers and applications -  
This paper presents our work on implementing BB algorithms on hypercube multiprocessors.  ...  Two parallel implementations of the algorithm on hypercube multiprocessors are presented.  ...  Introduction Hypercube multiprocessors have been used successfully for a wide range of applications in science and engineering. These applications can be characterized to a large extent by: 1.  ... 
doi:10.1145/63047.63106 fatcat:zwohisaqpnczrlbwd2lzi3ddie

Implementation and performance analysis of parallel assignment algorithms on a hypercube computer

B. A. Carpenter, N. J. Davis
1988 Proceedings of the third conference on Hypercube concurrent computers and applications -  
The Intel iPSC Hypercube Computer The Intel iPSC hypercube computer is used for implementing the parallel as- 14 .  ...  . * either one or several of these processes can be assigned to separate nodes or processors in a parallel computer for concurrent processing.  ... 
doi:10.1145/63047.63077 fatcat:wjluoizfnzhlfitgl2dpwezsde

Hypercube implementation of the simplex algorithm

C. B. Stunkel, D. A. Reed
1988 Proceedings of the third conference on Hypercube concurrent computers and applications -  
This computational complexity, coupled with the wealth of research on the simplex method, make parallel solution of linear optimization problems an attractive research problem. t Supported in part by a  ...  This paper examines the performance of parallel variants of the simplex algorithm on a message-passing system.  ...  Kent Fuchs for his guidance during the experiments and the work on this paper.  ... 
doi:10.1145/63047.63104 fatcat:pnyghf2iy5dnley5jldjx75ale

Distributing resources in hypercube computers

M. Livingston, Q. F. Stout
1988 Proceedings of the third conference on Hypercube concurrent computers and applications Architecture, software, computer systems, and general issues -  
Efficient constructive techniques for distributing a resource are given for several performance requirements, along with upper and lower bounds on the total number of resource units required.  ...  In this setting, we also consider the problem of meeting the performance requirements at minimal cost when the subcube allocation system cannot allocate all possible subcubes and the requirements apply  ...  Comments We have considered some of the problems that arise when one is trying to satisfy a resource distribution requirement using a minimal number of resouce units.  ... 
doi:10.1145/62297.62324 fatcat:c4yekj2vwjhutjkjxilyzvgbjm

High performance hypercube communications

G. Buzzard, T. Mudge
1988 Proceedings of the third conference on Hypercube concurrent computers and applications Architecture, software, computer systems, and general issues -  
The scheme that we propose addresses these issues and leads to substantial performance improvements across a broad range of message loads.  ...  Techniques to achieve fast communications are essential in the application of hypercubes to problems with high degrees of data sharing.  ...  At the level of the application program one program statement should suffice to send a message of any size to any destination node.  ... 
doi:10.1145/62297.62376 fatcat:zvttgnw7gze2figviuwgku2kfe

Evaluation of a vector hypercube for seismic modelling

R. Renaut, J. Petersen
1988 Proceedings of the third conference on Hypercube concurrent computers and applications -  
Michelsen Institute thetic wave propagation code using explicit finite differences with absorbing boundary conditions has been implemented on an Intel Hypercube with 32 processors.  ...  A 2D syn-Rosemary Renautt and Johnny Petersent Chr.  ...  Clayton [3] implemented an algorithm for the solution of the acoustic wave equation on a concurrent processor.  ... 
doi:10.1145/63047.63072 fatcat:o5l2plrmifbnvp3qmkwozggvmi

The pebble crurching model for load balancing in concurrent hypercube ensembles

J. Barhen, S. Gulati, S. S. Iyengar
1988 Proceedings of the third conference on Hypercube concurrent computers and applications Architecture, software, computer systems, and general issues -  
The successful development of fifth generation systems require enormous computational capability and flexibility necessitating the ability to achieve operational responses in hard real-time through optimal  ...  We propose a graphtheoretic, receiver-initiated, distributed protocol for dynamic load balancing protocol in large-scale hypercube ensembles.  ...  Computations intended to run on concurrent computational ensembles are decomposed into set of tasks which could then be concurrently executed.  ... 
doi:10.1145/62297.62321 fatcat:y3ruvhnx7jby5hgt6q766lugv4

Implementing functional programs on a hypercube multiprocessor

B. Goldberg, P. Hudak
1988 Proceedings of the third conference on Hypercube concurrent computers and applications Architecture, software, computer systems, and general issues -  
It is based on a heterogeneous abstract machine model consisting of both graph reduction and stack oriented execution. Alfalfa has two major components, a compiler and a run-time system.  ...  Alfalfa is an implementation of a functional language on the Intel iPSC multiprocessor.  ...  Reduction in execution time: We are investigating whether a functional program can run significantly faster on a hypercube multiprocessor than on a sequential (uniprocessor) computer.  ... 
doi:10.1145/62297.62356 fatcat:txdlwi6icjc73ezkjqzd36cuta

Performance analysis of the hypercube line switch

K. Bratbergsengen
1988 Proceedings of the third conference on Hypercube concurrent computers and applications Architecture, software, computer systems, and general issues -  
The hypercube line rwltchlng node has one communlcatlon path to each neighbor (D lines In a D dlmenslonal cube) and two paths to the node computer.  ...  We have Investigated path setup using two mathematical model8 and one computer simulation model.  ... 
doi:10.1145/62297.62375 fatcat:s7jr6uwa6nfcxby34xfmkuuhtu

A message-passing model for highly concurrent computation

A. J. Martin
1988 Proceedings of the third conference on Hypercube concurrent computers and applications Architecture, software, computer systems, and general issues -  
the data needed, and completing and reviewing the collection of information.  ...  Public reporting burden for the collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining  ...  TITLE AND SUBTITLE A Message-Passing Model for Highly Concurrent Computation 5a. CONTRACT NUMBER 5b. GRANT NUMBER 5c. PROGRAM ELEMENT NUMBER 6. AUTHOR(S) 5d. PROJECT NUMBER 5e.  ... 
doi:10.1145/62297.62360 fatcat:bbztrrz7v5dohfdug2bmb2xboi

Hypercube message routing in the presence of faults

F. M. Gordon, Q. F. Stout
1988 Proceedings of the third conference on Hypercube concurrent computers and applications Architecture, software, computer systems, and general issues -  
We discuss the problem of routing messages on hypercubes which have faulty processors and/or communication links.  ...  As such, we may also consider communications hot spots as node faults, and our results also apply to routing in congested hypercubes.  ...  To copy otherwise, or to republish, requires a fee and/or specfic permission. 1 Introduction and Definitions Hypercubes have recently emerged as a viable and practical parallel computer architecture ([  ... 
doi:10.1145/62297.62332 fatcat:nvoxb4mmmjbcbacwtyqnjpq24e

Transputer systems for the Macintosh

1988 Proceedings of the third conference on Hypercube concurrent computers and applications Architecture, software, computer systems, and general issues -  
The Transptier (transistor-computer) is a 32-bit high speed reduced instruction set computer (RISC), based on VLSI technology, and designed for parallel processing applications. lt is manufactured by lnmos  ...  Just about every major computer company has looked at it and developed a prototype system based on the Transputer. IBM is building a system of 128 T8CO processors to study molecular structures.  ... 
doi:10.1145/62297.62421 fatcat:rbbpglsajfdcdmmjmaadxcbnde

PC-CUBE, a personal computer based hypercube

A. Ho, G. C. Fox, D. W. Walker, S. Snyder, D. Chang, S. Chen, M. Breaden, T. Cole
1988 Proceedings of the third conference on Hypercube concurrent computers and applications Architecture, software, computer systems, and general issues -  
Some application programs which ate taken parallel system, an IBM PC-based entry-level hypezfrom the book Solving Problems on Concurrent cube, as an instructional and developmental tool for Processors  ...  have learned and done and their effects on performance.  ...  Applications that are written for PC-Cube will also run on larger and faster commer-components: cial hypercubes with little or no modification. (1) One IBM PC or compatible for each node in the hypercube  ... 
doi:10.1145/62297.62309 fatcat:azdhxsoxora2tmmqfnydit6da4

Distributed programs and subroutines for multiprocessors

E. P. DeBenedictis
1988 Proceedings of the third conference on Hypercube concurrent computers and applications Architecture, software, computer systems, and general issues -  
To change this consensus, this paper develops distributed analogies to important and well known programming techniques found in conventional computers --namely modular programming and variable scoping.  ...  There seems to be a consensus that multiprocessors are harder to program than conventional computers.  ...  The two programs at the bottom each have four subprograms --two applications and one server for each application.  ... 
doi:10.1145/62297.62348 fatcat:g7cz6jmegbaj5ba4he2g6ttlza
« Previous Showing results 1 — 15 out of 1,662 results