Netrace: dependency-driven trace-based network-on-chip simulation

Abstract

Chip multiprocessors (CMPs) and systems-on-chip (SOCs) are expected to grow in core count from, a few today to hundreds or more. Since efficient on-chip communication is a primary factor in the performance of large core-count systems, the research community has directed substantial attention to networks-on-chip (NOCs). Current NOC evaluation methodologies include analytical modeling, network simulation, and full-system simulation. However, as core count and system complexity grow, the deficiencies of each of these methods will limit their ability to meet the demands of developers and researchers. Developing efficient NOCs requires high-fidelity, low-overhead NOC evaluation techniques and metrics. To address these challenges, this paper describes a new trace-based network simulation methodology that captures dependencies between network messages observed in full-system simulation of multithreaded applications. We also introduce Netrace, a library of tools and traces that enables targeted NOC simulators to track and replay network messages and their dependencies.