The adaptation of software technology to distributed environments is an important challenge today. In this work we combine parallel and distributed search. By this way we add the potential speed-up of a parallel exploration in the processing of distributed problems. This paper extends DIBT, a distributed search procedure operating in distributed constraint networks [6]. The extension is twofold. First the procedure is updated to face delayed information problems upcoming in heterogeneous systems. Second, the search is extended to simultaneously explore independent parts of a distributed search tree. By this way we introduce parallelism into distributed search, which brings to Interleaved Distributed Intelligent BackTracking (IDIBT). Our results show that 1) insoluble problems do not greatly degrade performance over DIBT and 2) superlinear speed-up can be achieved when the distribution of solution is nonuniform.

Finding a good graph coloring quickly is often a crucial phase in the development of efficient, parallel algorithms for many scientific and engineering applications. In this paper we consider the problem of solving the graph coloring problem itself in parallel. We present a simple and fast parallel graph coloring heuristic that is well suited for shared memory programming and yields an almost linear speedup on the PRAM model. We also present a second heuristic that improves on the number of colors used. The heuristics have been implemented using OpenMP. Experiments conducted on an SGI Cray Origin 2000 super computer using very large graphs from finite element methods and eigenvalue computations validate the theoretical run-time analysis.

: The computation of good, balanced graph colorings is an essential part of many algorithms required in scientific and engineering applications. Motivated by an effective sequential heuristic, we introduce a new parallel heuristic, PLF, and show that this heuristic has the same expected runtime under the PRAM computational model as the scalable coloring heuristic introduced by Jones and Plassmann (JP). We present experimental results performed on the Intel DELTA that demonstrate that this new heuristic consistently generates better colorings and requires only slightly more time than the JP heuristic. In the second part of the paper we introduce two new parallel color-balancing heuristics, PDR(k) and PLF(k). We show that these heuristics have the desirable property that they do not increase the number of colors used by an initial coloring during the balancing process. We present experimental results that show that these heuristics are very effective in obtaining balanced colorings and, ...

We present the first efficient algorithm for a coarse grained multiprocessor that colors a graph G with a guarantee of at most D G +1 colors. 1

. Quantum mechanics often give rise to problems where one needs to find a few eigenvalues of very large sparse matrices. The size of the matrices is such that it is not possible to store them in main memory but instead they must be generated on the fly. In this paper the method of coordinate relaxation is applied to one class of such problems. A parallel algorithm based on graph coloring is proposed. Experimental results on a Cray Origin 2000 computer show that the algorithm converges fast ant that it also scales well as more processors are applied. Comparisons show that the convergence of the presented algorithm is much faster on the given test problems than using ARPACK [10]. Key words. sparse matrix algorithms, eigenvalue computation, parallel computing, graph coloring, Cray Origin 2000 AMS subject classifications. 05C50, 05C85, 15A18, 65F15, 65F50, 65Y05, 65Y20 1. Introduction. Frequently problems in quantum mechanics lead to the computation of a small number of extremal eigenval...

In large-scale parallel applications a graph coloring is often carried out to schedule computational tasks. In this paper, we describe a new distributedmemory algorithm for doing the coloring itself in parallel. The algorithm operates in an iterative fashion; in each round vertices are speculatively colored based on limited information, and then a set of incorrectly colored vertices, to be recolored in the next round, is identified. Parallel speedup is achieved in part by reducing the frequency of communication among processors. Experimental results on a PC cluster using up to 16 processors show that the algorithm is scalable.

Abstract. This paper presents new efficient parallel algorithms for finding approximate solutions to graph coloring problems. We consider an existing shared memory parallel graph coloring algorithm and suggest several enhancements both in terms of ordering the vertices so as to minimize cache misses, and performing vertex-to-processor assignments based on graph partitioning instead of random allocation. We report experimental results that demonstrate the performance of our algorithms on an IBM Regatta supercomputer when up to 12 processors are used. Our implementations use OpenMP for parallelization and Metis for graph partitioning. The experiments show that we get up to a 70 % reduction in runtime compared to the previous algorithm. 1

We present an efficient and scalable Coarse Grained Multicomputer (CGM) coloring algorithm that colors a graph G with at most D+ 1 colors where D is the maximum degree in G. This algorithm is given in two variants: randomized and deterministic. We show that on a p-processor CGM model the proposed algorithms require a parallel time of O( |G| p ) and a total work and overall communication cost of O(|G|). These bounds correspond to the average case for the randomized version and to the worst-case for the deterministic variant. Key words: graph algorithms, parallel algorithms, graph coloring, Coarse Grained Multicomputers 1

Assefaw Hadish Gebremedhin* Fredrik Manne i 1

Heterogeneous computers with processors and accelerators are becoming widespread in scientific computing. However, it is difficult to program hybrid architectures and there is no commonly accepted programming model. Ideally, applications should be written in a way that is portable to many platforms, but providing this portability for general programs is a hard problem. By restricting the class of programs considered, we can make this portability feasible. We present Liszt, a domainspecific language for constructing mesh-based PDE solvers. We introduce language statements for interacting with an unstructured mesh, and storing data at its elements. Program analysis of these statements enables our compiler to expose the parallelism, locality, and synchronization of Liszt programs. Using this analysis, we generate applications for multiple platforms: a cluster, an SMP, and a GPU. This approach allows Liszt applications to perform within 12 % of hand-written C++, scale to large clusters, and experience order-of-magnitude speedups on GPUs.