Corner-Boundary Processor Allocation for 3D Mesh-Connected Multicomputers

Efficient processor allocation strategies for mesh-connected multicomputers

A Fast and Efficient Strategy for Sub-mesh Allocation with Minimal Allocation Overhead in 3D Mesh Connected Multicomputers

This paper presents a fast and efficient contiguous allocation strategy for 3D mesh multicomputers, referred to as Turning Busy List (TBL for short), which can identify a free sub-mesh of the requested size as long as it exists in the mesh system. Turning means that the orientation of the allocation request is changed when no sub-mesh is available in the requested orientation. The TBL strategy ...

An Efficient Turning Busy List Sub-Mesh Allocation Strategy for 3D Mesh Connected Multicomputers

In this paper, a fast and efficient busy-list sub-mesh allocation strategy, referred to as Turning Busy List (TBL), is suggested for 3D mesh connected multicomputers. Turning means that the orientation of the allocation request is changed when no sub-mesh is available in the requested orientation. The TBL strategy considers only those available free sub-meshes that border from the left on some ...

Ubiquitous Computing and Communication Journal A Fast and Efficient Strategy for Sub-mesh Allocation with Minimal Allocation Overhead in 3D Mesh Connected Multicomputers

This paper presents a fast and efficient contiguous allocation strategy for 3D mesh multicomputers, referred to as Turning Busy List (TBL for short), which can identify a free sub-mesh of the requested size as long as it exists in the mesh system. Turning means that the orientation of the allocation request is changed when no sub-mesh is available in the requested orientation. The TBL strategy ...

Improving Performance of Mesh-connected Multicomputers by Reducing Fragmentation

Fragmentation is the main performance bottleneck of multicomputer systems. In this paper, we classify the fragmentation problems in multicomputer systems according to their causes. It is noted that among all kinds of fragmentation, physical fragmentation is seldom addressed by contemporary allocation schemes. Two novel processor allocation schemes that reduce physical fragmentation for the mesh...