A new processor allocation strategy with a high degree of contiguity in mesh-connected multicomputers

One of the principal-agent problems is the asymmetric information between fund managers and investors. To mitigate this issue, this study conducts the return-based style analysis on Private Retirement Scheme funds to their asset allocation strategy. Our results show: First, conservative funds have a strong focus on fixed income products rather than equity. Second, in terms of asset allocation to equity, on average, growth funds have a higher allocation to foreign equity of 16.28 per cent, followed by moderate funds of 9.18 per cent; Third, growth funds focus on large growth stocks, while moderate funds focus on large value stocks. However, three observations deserve our attention: First, a high degree of selection for the conservative fund will entail higher transaction cost; and second, in terms of the degree of style and selection, conservative funds do not vary much from growth funds. In other words, there is no distinct product differentiation between the two categories; Lastly, there is a wide disparity in asset allocation across the conservative funds. This implies some degree of risk-taking by some fund managers. These results suggest that the financial goals of retirees will be undermined if PRS funds do not focus on their mandate.

Download Full-text

A reliable processor-allocation strategy for mesh-connected parallel systems

Proceedings. Eighth International Conference on Parallel and Distributed Systems. ICPADS 2001 ◽

10.1109/icpads.2001.934826 ◽

2002 ◽

Author(s):

Kyung-Hee Seo ◽

Sung-Chun Kim

Keyword(s):

Parallel Systems ◽

Allocation Strategy ◽

Processor Allocation

Download Full-text

Traffic dynamics on two-layer multiplex networks with limited queue resource

International Journal of Modern Physics B ◽

10.1142/s0217979219503120 ◽

2019 ◽

Vol 33 (26) ◽

pp. 1950312

Author(s):

Jinlong Ma ◽

Huiling Wang ◽

Hao Ren ◽

Xiangyang Xu ◽

Dongwen Zhang ◽

...

Keyword(s):

Queue Length ◽

World Systems ◽

Allocation Strategy ◽

Traffic Dynamics ◽

Transport Efficiency ◽

Physical Layers ◽

Multiplex Networks ◽

Structure And Dynamics ◽

Traffic Capacity ◽

High Degree

Modeling multiple complex systems as multiplex networks has refreshed our opinions about the structure and dynamics of assorted real-world systems. By studying the traffic dynamics of two-layer multiplex networks, it can be found that the limited buffer queue length of each node in both the logical and physical layers is one of the factors that restrict the whole network traffic capacity. Since high degree nodes in the network may bear heavier load, it is necessary to allocate a larger buffer queue to them. In order to enhance the transport efficiency, a new queue allocation strategy is proposed to alleviate the congestion of the two-layer multiplex networks. By extensive computer simulations, the proposed strategy can effectively improve the traffic capacity of the multiplex networks.

Download Full-text

NOVEL PIPELINING AND PROCESSOR ALLOCATION STRATEGY FOR MONOID COMPUTATIONS ON UNSHUFFLE-EXCHANGE NETWORKS

Parallel Processing Letters ◽

10.1142/s012962649300023x ◽

1993 ◽

Vol 03 (02) ◽

pp. 189-193 ◽

Cited By ~ 1

Author(s):

KUO-LIANG CHUNG ◽

HSUN-WEN CHANG

Keyword(s):

Short Paper ◽

Allocation Strategy ◽

Processor Allocation ◽

Output Node ◽

Exchange Networks ◽

Processor Utilization ◽

Single Output ◽

Exchange Network ◽

Hypercube Network

This short paper presents a novel pipelining and processor allocation strategy for monoid computations on an unshuffle-exchange network. In the strategy, the processor utilization is near 1 and the communication is collision-free. With the characteristics of constant connections to each processor and only a single output node on the network, the method given here can compete with the method of Barnard and Skillicorn based on a hypercube network with multiple output nodes.

Download Full-text

A New Compacting Non-Contiguous Processor Allocation Algorithm for 2D Mesh Multicomputers

Journal of Information Technology Research ◽

10.4018/jitr.2015100104 ◽

2015 ◽

Vol 8 (4) ◽

pp. 57-75 ◽

Cited By ~ 4

Author(s):

Saad Bani-Mohammad ◽

Ismail M. Ababneh ◽

Mohammad Yassen

Keyword(s):

Performance Improvement ◽

Communication Overhead ◽

Allocation Strategy ◽

Processor Allocation ◽

Improve Performance ◽

Simulation Experiments ◽

Extensive Simulation ◽

System Utilization ◽

Selection Of ◽

Allocation Strategies

In non-contiguous allocation, a job request can be split into smaller parts that are allocated possibly non-adjacent free sub-meshes rather than always waiting until a single sub-mesh of the requested size and shape is available. Lifting the contiguity condition is expected to reduce processor fragmentation and increase system utilization. However, the distances traversed by messages can be long, and as a result the communication overhead, especially contention, is likely to increase. The extra communication overhead depends on how the allocation request is partitioned and assigned to free sub-meshes. In this paper, a new non-contiguous processor allocation strategy, referred to as Compacting Non-Contiguous Processor Allocation Strategy (CNCPA), is suggested for the 2D mesh multicomputers. In the proposed strategy, a job is compacted into free locations. The selection of the free locations has for goal leaving large free sub-meshes in the system. To evaluate the performance improvement achieved by the proposed strategy and compare it against well-known existing non-contiguous allocation strategies, the authors conducted extensive simulation experiments. The results show that the proposed strategy can improve performance in terms of job turnaround times and system utilization.

Download Full-text