SCSTallocator: Sized and Call-Site Tracing-Based Shared Memory Allocator for False Sharing Reduction in Page-Based DSM Systems

摘要

False sharing is a result of co-location of unrelated data in the same unit of memory coherency, and is one source of unnecessary overhead being of no help to keep the memory coherency in multiprocessor systems. Moreover, the damage caused by false sharing becomes large in proportion to the granularity of memory coherency. To reduce false sharing in page-based DSM systems, it is necessary to allocate unrelated data objects that have different access patterns into the separate shared pages. In this paper we propose sized and call-site tracing-based shared memory allocator, shortly SCSTallocator. SCSTallocator expects that the data objects requested from the different call-sites may have different access patterns in the future. So SCSTallocator places each data object requested from the different call-sites into the separate shared pages, and consequently data objects that have the same call-site are likely to get together into the same shared pages. At the same time SCSTallocator places each data object that has different size into different shared pages to prohibit the different-sized objects from being allocated to the same shared page. We use execution-driven simulation of real parallel applications to evaluate the effectiveness of our SCSTallocator. Our observations show that our SCSTallocator outperforms the existing dynamic shared memory allocators. By combining the two existing allocation technique, we can reduce a considerable amount of false sharing misses.