Exploring the performance implications of memory safety primitives in many-core processors executing multi-threaded workloads

Abstract

Security is a vital consideration for today's processor architectures, both at the software and hardware layers. However, security schemes are known to incur significant performance overheads. For example, buffer overflow protection schemes perform software checks for bounds on program data structures, and incur performance overheads that are up to several orders of magnitude. To mitigate these overheads, prior works focus on either changing the security scheme itself, or selectively apply the security scheme to minimize program vulnerabilities. Most of these works also focus primarily on single core processors, with no prior work done in the context of multicore processors. In this paper, we show how increasing thread counts can help hide the latency overheads of security schemes. We also analyze the architectural implications in the context of multucores, and the insights and challenges associated with applying these security schemes on mutithreaded workloads.