Improving load balance with flexibly assignable tasks
Pinar, A; Hendrickson, B
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 16 (10): 956-965 OCT 2005
In many applications of parallel computing, distribution of the data unambiguously implies distribution of work among processors. But, there are exceptions where some tasks can be assigned to one of several processors without altering the total volume of communication. In this paper, we study the problem of exploiting this flexibility in assignment of tasks to improve load balance. We first model the problem in terms of network flow and use combinatorial techniques for its solution. Our parametric search algorithms use maximum flow algorithms for probing on a candidate optimal solution value. We describe two algorithms to solve the assignment problem with logW(T) and \P\ probe calls, where W-T and \P\, respectively, denote the total workload and number of processors. We also define augmenting paths and cuts for this problem, and show that any algorithm based on augmenting paths can be used to find an optimal solution for the task assignment problem. We then consider a continuous version of the problem and formulate it as a linearly constrained optimization problem, i.e., min parallel to Ax parallel to(infinity); s: t: Bx = d. To avoid solving an intractable infinity-norm optimization problem, we show that, in this case, minimizing the 2-norm is sufficient to minimize the infinity-norm, which reduces the problem to the well-studied linearly constrained least squares problem. The continuous version of the problem has the advantage of being easily amenable to parallelization. Our experiments with molecular dynamics and overlapped domain decomposition applications proved the effectiveness of our methods with significant improvements in load balance. We also discuss how our techniques can be extended to heterogeneous parallel computers.
Return to Publications page