Impact of Network Sharing in Multi-Core Architectures

As commodity components continue to dominate the realm of high-end computing, two hardware trends have emerged as major contributors—high-speed networking technologies and multi-core architectures. Communication middleware such as the Message Passing Interface (MPI) uses the network technol-ogy for communicating between processes that reside on dif-ferent physical nodes, while using shared memory for commu-nicating between processes on different cores within the same node. Thus, two conflicting possibilities arise: (i) with the ad-vent of multi-core architectures, the number of processes that reside on the same physical node and hence share the same physical network can potentially increase significantly, result-ing in increased network usage, and (ii) given the increase in intra-node shared-memory communication for processes resid-ing on the same node, the network usage can potentially de-crease significantly. In this paper, we address these two conflicting possibilities and study the behavior of network usage in multi-core environments with sample scientific applications. Specifically, we analyze trends that result in increase or decrease of network usage, and we derive insights into application performance based on these. We also study the sharing of different resources in the system in multi-core environments and identify the contribution of the network in this mix. In addition, we study different process allocation strategies and analyze their impact on such network sharing.