A. K. Gupta and S. E. Hambrusch. Load balanced tree embeddings. To Appear in Parallel Computing, 1992. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Abstraction and Performance in the Design of Parallel Programs - Gorlatch (1997) (1 citation) (Correct)
....based on paper [H3] we develop a new interconnection topology, called N graph, whose purpose is to implement efficiently the binary divide and conquer on a bounded number of processors. 35 In the literature, mainly two tree like topologies with a bounded number of nodes have been considered [33, 34, 55]. The complete binary tree has the drawback that the load is not balanced: only half of the processors are busy with computation of the coarse grain base case; this entails a 50 loss of speedup. An alternative, binomial tree, has a better balanced load, but we run into another problem: the node ....
A. K. Gupta and S. E. Hambrusch. Load balanced tree embeddings. Parallel Computing, 18:595--614.
N-Graphs: A Topology for Parallel Divide-and-Conquer on.. - Gorlatch, Lengauer (Correct)
....arise. The problem of mapping divide and conquer algorithms efficiently onto fixed size multiprocessor networks with a constant degree topology has been studied for years. There have been attempts to embed binary trees into 2D meshes [1] 3D meshes [10] and into binary trees of a smaller size [11]. In every case, either load balance is sacrificed or the embedding has a non unit dilation, i.e. neighbour nodes of the virtual binary tree are not always neighbours in the physical network and, thus, the communication is not local. In this paper, we address the problem of implementing the ....
A. K. Gupta and S. E. Hambrusch. Load balanced tree embeddings. Parallel Computing, 18:595--614.
Multiple Network Embeddings into Hypercubes - Gupta, Hambrusch (1996) (6 citations) Self-citation (Gupta Hambrusch) (Correct)
....problem with a totally unbalanced load distribution can be viewed as embedding an n node guest network G i into an m PE host with m = n=r, where the m PE host is now a subcube of the hypercube H. Embeddings of a single network into one of smaller size, but the same topology, are described in [2, 7, 8, 9, 10, 20]. 19 We first describe how to embed r complete binary trees into H with a dilation of 2 and a congestion of 2. Recall that the congestion was 5 in the balanced load embedding. The main idea in the embedding is to contract the guest networks and then embed the contracted networks into H. Let T 0 ....
A. K. Gupta and S. E. Hambrusch. Load balanced tree embeddings. To Appear in Parallel Computing, 1992.
On Embedding Ternary Trees into Boolean Hypercubes (Extended.. - Gupta, al. Self-citation (Gupta) (Correct)
....the congestion of the embedding. The expansion ffl is defined to be the ratio of the number of PEs in H to the number of nodes in G. Graph embeddings minimizing ffi, and ffl for various pairs of graphs G and H and their implications to parallel processing have recently been studied extensively [1, 2, 3, 7, 10, 11, 13, 15, 14, 19]. In this paper our main focus is to study the problem of embedding when G is a complete ternary (3 ary) tree and H is a boolean hypercube. The problem of efficiently embedding a k ary tree into hypercube with k 3 has largely remained unsolved, even though optimal embeddings (i.e. embeddings ....
A. K. Gupta and S. E. Hambrusch. Load balanced tree embeddings. Parallel Computing, (18)1992, 595-614.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC