• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.4
• /
• pp.81-86
• /
• 2003

Current growth of VLSI design depends critically on the research and development of automatic layout tool. Automatic layout is composed of placement assigning a specific shape to a block and arranging the block on the layout surface and routing finding the interconnection of all the nets. Algorithms performing placement and routing impact on performance and area of VLSI design. Switchbox routing is a problem interconnecting each terminals on all four sides of the region, unlike channel routing. In this paper we propose a genetic algorithm searching solution space for switchbox routing problem. We compare the performance of proposed genetic algorithm(GA) for switchbox routing with that of other switchbox routing algorithm by analyzing the results of each implementation. Consequently experimental results show that out proposed algorithm reduce routing length and number of the via over the other switchbox routing algorithms.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.30A no.3
• /
• pp.104-113
• /
• 1993

A new switchbox router, called CONQUEROR, is proposed in this paper. The proposed CONQUEROR efficiently routes large switchbox routing area using divide-and-conquer technique. The CONQUEROR consists of three phases` namely, partition of large routing area and assignment of optimal pins of sub-area, detailed routing of each sub-ared, reassignment of pins after rip-up. First, large switchbox routing area is partitioned into several sub-areas and each sub-area contains 4-6 detailed grids. Then pins are assigned on boundary of sub-area by the estimated weight. Secondly, when global pin assignment is completed on all sub-areas, each sub-area is routed using detailed router. Also, detailed routing consists of three pases` layerless maze routing, assignment of layer using coloring, and rip-up and reroute. Lastly, if detailed routing of any sub-area fails,reassignment of pins after rip-up is invoked. Detailed routing is performed for the failed sub-area again. Benchmark test cases have been run, and on all the benchmark data known in the literature CONQUEROR has performed as well as or better than existing switchbox routers.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.30A no.12
• /
• pp.135-146
• /
• 1993

A ner general multi-layer area router, called DINOSAUR, is presented in this paper. DINOSAUR can route various types of routing areas, such as L-shaped channel, switchbox with/without obstacles, and rectilinear area with/without internal modules/terminals. The DINOSAUR algorithm consists of three major stages: layerless maze routing, layering by coloring, and rip-up and reroute. In layerless maze roution stage, the route of each net is determined by modified maze algorithm without taking the conflicts(short. circuits) into account. In layering by coloring stage, the layer of each net is determinde by a heuristic coloring algorithm. When the conflicts are not removed, rip-up and reroute process is invoded. In rip-up and reroute stage, the conflicts are removed iteratively. Many test cases have been run, and on all the benchmark data known in the literature DINOSAUR has performed either better than or comparable to the other routers.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.25 no.3
• /
• pp.17-33
• /
• 2000

We consider the Steiner tree packing problem. For a given undirected graph G =(V, E) with positive integer capacities and non-negative weights on its edges, and a list of node sets(nets), the problem is to find a connection of nets which satisfies the edge capacity limits and minimizes the total weights. We focus on the switchbox routing problem in knock-knee model and formulate this problem as an integer programming using Steiner tree variables. The model contains exponential number of variables, but the problem can be solved using a polynomial time column generation procedure. We test the algorithm on some standard test instances and compare the performances with the results using cutting plane approach. Computational results show that our algorithm is competitive to the cutting plane algorithm presented by Grotschel et al. and can be used to solve practically sized problems.