Loading...
Search for:
buffer-allocation
0.006 seconds
Power-performance analysis of networks-on-chip with arbitrary buffer allocation schemes
, Article IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems ; Vol. 29, issue. 10 , 2010 , p. 1558-1571 ; ISSN: 02780070 ; Sarbazi-Azad, H ; Sharif University of Technology
Abstract
End-to-end delay, throughput, energy consumption, and silicon area are the most important design metrics of networks-on-chip (NoCs). Although several analytical models have been previously proposed for predicting such metrics in NoCs, very few of them consider the effect of message waiting time in the buffers of network routers for predicting overall power consumptions and none of them consider structural heterogeneity of network routers. This paper introduces two inter-related analytical models to compute message latency and power consumption of NoCs with arbitrary topology, buffering structure, and routing algorithm. Buffer allocation scheme defines the buffering space for each individual...
Power-performance analysis of networks-on-chip with arbitrary buffer allocation schemes
, Article IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems ; Volume 29, Issue 10 , September , 2010 , Pages 1558-1571 ; 02780070 (ISSN) ; Sarbazi Azad, H ; Sharif University of Technology
2010
Abstract
End-to-end delay, throughput, energy consumption, and silicon area are the most important design metrics of networks-on-chip (NoCs). Although several analytical models have been previously proposed for predicting such metrics in NoCs, very few of them consider the effect of message waiting time in the buffers of network routers for predicting overall power consumptions and none of them consider structural heterogeneity of network routers. This paper introduces two inter-related analytical models to compute message latency and power consumption of NoCs with arbitrary topology, buffering structure, and routing algorithm. Buffer allocation scheme defines the buffering space for each individual...
Multi-Objective Simulation Optimization and its Application in Buffer Allocation Problem
,
M.Sc. Thesis
Sharif University of Technology
;
Mahlooji, Hashem
(Supervisor)
Abstract
This work attempts to address the buffer allocation problem in an unreliable, linear production line. We try to determine the optimal sizes of buffers between adjacent work stations in such a way that a measure of costs is minimized and the production rate is simultaneously maximized. We resort to simulation optimization in order to determine the best combination of input parameters that leads to a near optimal performance for the system. To achieve this purpose, we employ a multi-objective genetic algorithm (NSGAII) in the optimization phase along with simulation as the tool for evaluating the objective function. To determine the merits of the proposed method, we compare the performance of...
Application of Simulation Optimization in Buffer Allocation Problem Using Genetic Algorithm and Simulated Annealing
, M.Sc. Thesis Sharif University of Technology ; Kianfar, Farhad (Supervisor)
Abstract
Simulation optimization has been one of the most important topics in recent years. It is especially useful when the objective function cannot be computed directly or some of the parameters are stochastic. Buffer allocation problem is one of the important problems related to production lines. In this problem the objective is to determine the buffers between workstations so that the throughput is maximized. Non-linear and combinatorial nature of the problem, stochastic factors like machine breakdown or processing times and most importantly lack of a distinct relation for the objective function are the reasons of using simulation ...