Nearest‐neighbor algorithms for load‐balancing in parallel computers

Abstract

Abstract With nearest‐neighbor load‐balancing algorithms, a processor makes balancing decisions based on localized workload information and manages workload migrations within its neighborhood. The paper compares a couple of fairly well‐known nearest‐neighbor algorithms, the dimension‐exchange (DE) and the diffusion (DF) methods and their several variants—the average dimension‐exchange (ADE), optimally tuned dimension‐exchange (ODE), local average diffusion (ADF) and optimally tuned diffusion (ODF). The measures of interest are their efficiency in driving any initial workload distribution to a uniform distribution and their ability in controlling the growth of the variance among the processors' workloads. The comparison is made with respect to both one‐port and all‐port communication architectures and in consideration of various implementation strategies including synchronous/asynchronous invocation policies and static/dynamic random workload behaviors. It turns out that the dimension‐exchange method outperforms the diffusion method in the one‐port communication model. In particular, the ODE algorithm is best suited for statically synchronous implementations of a load‐balancing process regardless of its underlying communication models. The strength of the diffusion method is in asynchronous implementations in the all‐port communication model; the ODF algorithm performs best in that case. The underlying communication networks considered assume the most popular topologies, the mesh and the torus and their special cases: the hypercube and the k ‐ary n ‐cube.