Fig 6 - uploaded by Chiou-Yng Lee
Content may be subject to copyright.
Source publication
In microprocessor-based systems, such as the cloud computing infrastructure, high reliability is essential. As multiprocessor
systems become more widespread and increasingly complex, system-level diagnosis will increasingly be adopted to determine their
robustness. In this paper, we consider a pessimistic diagnostic strategy for hypermesh multiproc...
Contexts in source publication
Context 1
... we show an example of the algorithm Pessimistic Diagnosis. Fig. 6 represents a part of HM 4;3 . In this figure, we construct a dual tree of order 13 rooted at u ¼ 0022 and v ¼ 1022. Clearly, the state of v is unknown (i.e. v is in W ). Moreover, given the syndrome in Fig. 6, we can calculate that n 0;0 ðuÞ ¼ 4, n 0;1 ðuÞ ¼ 2, n 0;0 ðvÞ ¼ 3, and n 0;1 ðvÞ ¼ 2. Since n 0;0 ðuÞ þ n 0;1 ðvÞ ¼ 6 > 5 ¼ n ...
Context 2
... we show an example of the algorithm Pessimistic Diagnosis. Fig. 6 represents a part of HM 4;3 . In this figure, we construct a dual tree of order 13 rooted at u ¼ 0022 and v ¼ 1022. Clearly, the state of v is unknown (i.e. v is in W ). Moreover, given the syndrome in Fig. 6, we can calculate that n 0;0 ðuÞ ¼ 4, n 0;1 ðuÞ ¼ 2, n 0;0 ðvÞ ¼ 3, and n 0;1 ðvÞ ¼ 2. Since n 0;0 ðuÞ þ n 0;1 ðvÞ ¼ 6 > 5 ¼ n 0;1 ðuÞ þ n 0;0 ðvÞ and ðu; vÞ ¼ 1, we can conclude that v is faulty. Next, the Pessimistic Diag- nosis algorithm will check all the neighbors of v in W . Using this process, we can identify that ...
Citations
Compared with accurate diagnosis, the system's self-diagnosing capability can be greatly increased through the t/k-diagnosis strategy at most k vertexes to be mistakenly identified as faulty under the comparison model, where k is typically a small number. Based on the Preparata, Metze, and Chien (PMC) model, the n-dimensional hypercube network is proved to be t/k-diagnosable. In this paper, based on the Maeng and Malek (MM)* model, a novel t/k-fault diagnosis (1 ≤ k ≤ 4) algorithm of n-dimensional hypercube, called t/k-MM*-DIAG, is proposed to isolate all faulty processors within the set of nodes, among which the number of fault-free nodes identified wrongly as faulty is at most k. The time complexity in our algorithm is only O(2
<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</sup>
n
<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>
).
Fault tolerance is especially important for interconnection networks, vastly influencing the performance of the parallel processing systems underlying the corresponding networks. This paper studies the fault tolerance of radix-k n-dimensional hypermesh optical interconnection networks, determines the connectivity of partial hypermesh, and derives the conditional connectivity of hypermesh provided that each adjacent set cannot be faulty simultaneously. Under this condition, the hypermesh networks can tolerate up to 2n(k-1)-k-1 fault processors without being disrupted, implying that when the number of dimension n (respectively, radix-k) is a fixed value in the hypermesh network, the larger the value of radix-k (respectively, dimension n) is, the higher the reliability and availability of the network becomes.
