64 research outputs found
Fault-tolerant adaptive wormhole routing in 2D mesh
No full textA fault-tolerant wormhole routing algorithm on mesh-connected processors is proposed. The proposed algorithm is based on the solid fault model and allows the fault polygons to be overlapped. The algorithm compares the position of fault region relative to current channel with the fault direction held of a misrouted message to route around overlapped fault polygons. A node deactivating algorithm to convert non-solid fault region into solid fault region is also proposed. The proposed routing algorithm uses four virtual channels and is deadlock and livelock free
Fault-tolerant wormhole routing in mesh with overlapped solid fault regions
No full textA fault-tolerant wormhole routing algorithm on mesh-connected processors is proposed. The proposed algorithm is based on the solid fault model and allows the fault polygons to be overlapped. The algorithm utilizes the position of fault region relative to the current channel to route a message around overlapped fault polygons. A node deactivating algorithm to convert a non-solid fault region into a solid fault region is also proposed. The proposed routing algorithm uses four virtual channels and is deadlock- and livelock-free. (C) 1997 Elsevier Science B.V
Analyzing Stack Flows to Compare Java Programs
No full textThis paper presents a method for comparing and detecting clones of Java programs by analyzing program stack flows. A stack flow denotes an operational behavior of a program by describing individual instructions and stack movements for performing specific operations. We analyze stack flows by simulating the operand stack movements during execution of a Java program. Two programs for detection of clones of Java programs are compared by matching similar pairs of stack flows in the programs. Experiments were performed on the proposed method and compared with the earlier approaches of comparing Java programs, the Tamada, k-gram, and stack pattern based methods. Their performance was evaluated with real-world Java programs in several categories collected from the Internet. The experimental results show that the proposed method is more effective than earlier methods of comparing and detecting clones of Java programs
A bottom-up pointer analysis using the update history
No full textPointer analysis is an important part for the source code analysis of C programs. In this paper, we propose a bottom-up and flow- and context-sensitive pointer analysis algorithm, where bottom-up refers to the ability to perform the analysis from callee modules to caller modules. Our approach is based on a new modular pointer analysis domain named the update history that can abstract memory states of a procedure independently of the information on aliases between memory locations and keep the information on the order of side effects performed. Such a memory representation not only enables the analysis to be formalized as a bottom-up analysis, but also helps the analysis to effectively identify killed side effects and relevant alias contexts. The experiments performed on a pilot implementation of the method shows that our approach is effective for improving the precision of a client analysis. (C) 2008 Elsevier B.V. All rights reserved.This research was supported by the MKE (Ministry of Knowledge Economy), Korea, under the ITRC (Information Technology Research Center) support program supervised by the institute of information technology advancement (IITA-2008-C1090-0801-0020)
- …
