144 Hits in 4.8 sec

A radar simulation program for a 1024-processor hypercube

J. L. Gustafson, R. E. Benner, M. P. Sears, T. D. Sullivan
1989 Proceedings of the 1989 ACM/IEEE conference on Supercomputing - Supercomputing '89  
These techniques increase performance and appear to have general applicability for massive parallelism.  ...  ., load balance) a large ensemble. The ensemble is used in a heterogeneous manner, with different programs on different parts of the hypercube.  ...  Flowchart Figure 4 . 4 Parallel SRIM Flowchart Figure 5 . 5 Call Tree for Radar Image Generation Figure 7 . 7 Manager-GIFT Load Balancer vs. a CRAY CPU)/(4 CPUs) = 23.7 times and the cost performance  ... 
doi:10.1145/76263.76274 dblp:conf/sc/GustafsonBSS89 fatcat:5dy73ytbjfbd5ij7nxd35uxk2e

Many-Objective Optimization Design of a Public Building for Energy, Daylighting and Cost Performance Improvement

Cheng Sun, Qianqian Liu, Yunsong Han
2020 Applied Sciences  
The energy performance of buildings especially public buildings needs to be optimized together with environmental, social and cost performance, which can be achieved by the multiobjective optimization  ...  Practical projects of complex public building design usually involve many-objective optimization problems in which more than three objectives are considered.  ...  ., Q.L. and Y.H. conceived the research, developed the model and analyzed the data. All the authors were engaged in final manuscript preparation and writing.  ... 
doi:10.3390/app10072435 fatcat:nqcjyf5akvampdx572xkqkwqam

Topological comparison of perfect shuffle and hypercube

Ran Ginosar, David Egozi
1989 International journal of parallel programming  
These and other measures are employed for a comparative analysis of such networks. The goal of this analysis is to predict network effectiveness, without resorting to execution benchmark techniques.  ...  We specifically find that the hypercube is capable of somewhat better performance than perfect-shuffle-nearest-neighbor, but the latter is significantly more cost-effective.  ...  Ordinarily, cost is divided by performance to achieve cost-effectiveness; as explained earlier, looseness may be considered as inversely proportional to performance, and therefore cost/performance is proportional  ... 
doi:10.1007/bf01409745 fatcat:7u2aiknaprhwrcyx3quajlvqti

Augmented binary hypercube: a new architecture for processor management

H. Lalgudi, L.F. Akyildiz, S. Yalamanchili
1996 IEEE transactions on computers  
processor allocation (PA), and 2) load balancing (LB).  ...  Augmented Binary Hypercube (AH) architecture consists of the binary hypercube processor nodes (PNs) and a hierarchy of management nodes (MNs).  ...  The cost, performance and sensitivity of the algorithms indicate the following: Intermediate Update algorithm performs better than Lazy and Immediate Update algorithms, with Lazy Update suitable for fine  ... 
doi:10.1109/12.536241 fatcat:gc57uxbagvbkra66egcpa5xuwq

Complex Performance Modeling of Parallel Algorithms

Peter Hanuliak
2014 American Journal of Networks and Communications  
In this sense the paper is devoted to a complex performance evaluation of chosen PA.  ...  In general radix -q DFFT is computed by splitting the input sequence of size s into q sequences each of them in size n/q, computing faster their q smaller DFFT's, and then combining the results.  ...  Acknowledgements This work was done within the project "Modeling, optimization and prediction of parallel computers and algorithms" at University of Zilina, Slovakia.  ... 
doi:10.11648/j.ajnc.s.2014030501.12 fatcat:caoaxcniqngwldv7bkozec5af4

Analysis of Buffer Arrangements in Low and High Dimensional Networks

N. Alzeidi
2010 The Journal of Engineering Research  
There have been few studies attempting to address this issue, however, these studies have so far resorted to simulation experiments and focused on deterministic routing algorithms.  ...  Section 3 lists the assumptions used in the analysis and the main equations of the analytical model while Section 4 presents the cost-performance model.  ...  The Cost Performance Model To make a fair and concrete comparison, the intra router delay (ie. the time to cross the router) must be considered as the complexity of the router might affect the overall  ... 
doi:10.24200/tjer.vol7iss2pp80-90 fatcat:3mtk5yd2trg65cgzyvjhvqtuzm

Errata: Parallel Solution of Dense Linear Systems on the K-ary n-Cube Networks

Abdel-Elah Al-Ayyoub, Khaled Day
1997 International journal of high speed computing  
This is better than the best known results for the hypercube, O(N log k n ), and the mesh, O(N √ k n ), each with approximately k n nodes.  ...  The proposed algorithm is of O(N 3 /k n ) computation complexity and uses O(Nn) communication time to factorize a matrix of order N on the k-ary n-cube.  ...  Also we have conducted a cost-performance analysis of the proposed algorithm. Fig. 1 . 1 The 3-ary 2-cube. Fig. 2 . 2 Two different partitionings of the 3-ary 2-cube.  ... 
doi:10.1142/s0129053397000222 fatcat:3alul6lpdnajnmlvazbqkxiiuu

Flattened butterfly

John Kim, William J. Dally, Dennis Abts
2007 SIGARCH Computer Architecture News  
On benign (load-balanced) traffic, the flattened butterfly approaches the cost/performance of a butterfly network and has roughly half the cost of a comparable performance Clos network.  ...  and hypercube topologies.  ...  Acknowledgments The authors would like to thank the anonymous reviewers and CVA members for their insightful comments.  ... 
doi:10.1145/1273440.1250679 fatcat:ynemsajd7jajzaz36b6lpzh6ji

Flattened butterfly

John Kim, William J. Dally, Dennis Abts
2007 Proceedings of the 34th annual international symposium on Computer architecture - ISCA '07  
On benign (load-balanced) traffic, the flattened butterfly approaches the cost/performance of a butterfly network and has roughly half the cost of a comparable performance Clos network.  ...  and hypercube topologies.  ...  Acknowledgments The authors would like to thank the anonymous reviewers and CVA members for their insightful comments.  ... 
doi:10.1145/1250662.1250679 dblp:conf/isca/KimDA07 fatcat:q7zie2mb2fdghejrj7epaf6d6i

Page 1187 of Mathematical Reviews Vol. , Issue 90B [page]

1990 Mathematical Reviews  
Also, some cost-performance analysis is presented for the case when the num- ber of processors n is fixed and the size of the blocks k is a free parameter.  ...  Systems analysis and simulation 1988, I (Berlin, 1988), 356-359, Math. Res., 46, Akademie-Verlag, Berlin, 1988.  ... 

A Volume Integral Equation Stokes Solver for Problems with Variable Coefficients

Dhairya Malhotra, Amir Gholami, George Biros
2014 SC14: International Conference for High Performance Computing, Networking, Storage and Analysis  
Compared to finite element methods, our formulation decouples the velocity and pressure, generates velocity fields that are by construction divergence free to high accuracy and its performance does not  ...  As an application example, we simulate Stokes flow in a porous medium with highly complex pore structure using a penalty formulation to enforce the no slip condition.  ...  This material is based upon work supported by AFOSR grants FA9550-12-10484 and FA9550-11-10339; and NSF grants CCF-1337393, OCI-1029022, and OCI-1047980; and by the U.S.  ... 
doi:10.1109/sc.2014.13 dblp:conf/sc/MalhotraGB14 fatcat:6ir3iweejbclrmy2kssnhern7m


Jung Ho Ahn, Nathan Binkert, Al Davis, Moray McLaren, Robert S. Schreiber
2009 Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis - SC '09  
To meet the need, we consider an extension of the hypercube and flattened butterfly topologies, the HyperX, and give an adaptive routing algorithm, DAL.  ...  Our analysis of efficiency, performance, and packaging demonstrates that the HyperX is a strong competitor for exascale networks.  ...  At this scale, the interconnection networks in these systems will have a major impact on their cost, performance, power, fault tolerance, and complexity.  ... 
doi:10.1145/1654059.1654101 dblp:conf/sc/AhnBDMS09 fatcat:jcqdixooe5grlgj2rqrbyedta4

Properties and performance of the block shift network

Yi Pan, H.Y.H. Chuang
1997 IEEE Transactions on Circuits and Systems I Fundamental Theory and Applications  
Actually, many popular networks such as the hypercube, the shuffle-exchange, and the complete networks are instances of the BSN.  ...  As an interconnection network, hypercube topology offers certain advantages such as high data bandwidth and low message latency to achieve computational efficiency.  ...  All the cost-performance measures derived in this paper are dependent on the network parameters and and in fact many famous networks such as the shuffle-exchange, the hypercube, and the complete network  ... 
doi:10.1109/81.554320 fatcat:yvgukltjbvdmle3oy2ac25eju4

Block-cyclic matrix triangulation on the Cartesian product of star graphs

A.-E. Al-Ayyoub, K. Day
1998 Computers and Mathematics with Applications  
The proposed techniques for matrix decomposition and mapping are of general use and can be applied to design other matrixbased algorithms on the Cartesian product of star graphs.  ...  Due to its reduced diameter, the star graph theoretically supports more efficient communication than popular networks such as the hypercube and the mesh.  ...  The above analysis indicates that the hyperstar based BCMT algorithm achieves better cost/ performance ratio than both the hypercube and the star graph based BCMT.  ... 
doi:10.1016/s0898-1221(98)00154-0 fatcat:zka3mjl3gzeqddi2wbdekudpre

On isomorphisms and similarities between generalized Petersen networks and periodically regular chordal rings

Behrooz Parhami
2008 Information Processing Letters  
and offering greater flexibility in cost-performance tradeoffs.  ...  Generalized Petersen (GP) networks and periodically regular chordal (PRC) rings have been proposed independently to ameliorate the high latency and extreme fragility of simple ring networks.  ...  and offering greater flexibility in cost-performance tradeoffs.  ... 
doi:10.1016/j.ipl.2008.03.005 fatcat:erun3mqv45fzriz6hhsmzvgyfy
« Previous Showing results 1 — 15 out of 144 results