Address-aware Fences

Many modern multicore architectures support shared mem-ory for ease of programming and relaxed memory models to deliver high performance. With relaxed memory models, memory accesses can be reordered dynamically and seen by other processors. Therefore, fence instructions are provided to enforce the memory orderings that are critical to the cor-rectness of a program. However, fence instructions are costly as they cause the processor to stall. Prior works have ob-served that most of the executions of fence instructions are unnecessary. In this paper we propose address-aware fence, a hardware solution for reducing the overhead of fence in-structions without resorting to speculation. Address-aware fence only enforces memory orderings that are necessary to maintain the effect that the traditional fence strives to en-force. This is achieved by dynamically checking a condition for when an execution of a fence must take effect and delay the memory accesses following the fence. When a fence in-struction is encountered, first, necessary memory addresses are collected to form a watchlist, and then, only the mem-ory accesses to addresses that are contained in the watchlist are delayed. The memory accesses whose addresses are not contained in the watchlist are allowed to complete without waiting for the completion of pending memory accesses from before the fence. Our experiments conducted on a group of concurrent lock-free algorithms and SPLASH-2 benchmarks show that address-aware fence eliminates nearly all the over-head due to fences and achieves an average improvement of 12.2 % on programs with traditional fences