Scheduler-Activated Dynamic Page Migration for Multiprogrammed DSM Multiprocessors

Abstract

The performance of multiprogrammed shared-memory multiprocessors suffers often from scheduler interventions that neglect data locality. On cachecoherent distributed shared-memory (DSM) multiprocessors, such scheduler interventions tend to increase the rate of remote memory accesses. This paper presents a novel dynamic page migration algorithm that remedies this problem in iterative parallel programs. The purpose of the algorithm is the early detection of pages that will most likely be accessed remotely by threads associated with them via a thread-to-memory affinity relation. The key mechanism that enables timely identification of these pages is a communication interface between the page migration engine and the operating system scheduler. The algorithm improves previously proposed competitive page migration algorithms in many aspects, including accuracy, timeliness and cost amortization. Most notably, the algorithm is not biased by obsolete memory access history that may be accumulated in the page access counters at runtime. Experiments on the SGI Origin2000 show that the algorithm outperforms by far the best static page placement algorithm and a customized page migration engine implemented in IRIX, the Origin2000 operating system. The algorithm is implemented at user-level and its functionality is orthogonal to the scheduling policy of the operating system. # 2002 Elsevier Science (USA)

ForestGOMP: An Efficient OpenMP Environment for NUMA Architectures

“…They have shown their approach can even be more efficient when the page migration engine and the operating system scheduler [22] are able to communicate. This pioneering research only suits OpenMP applications that have a regular memory access pattern while our approach favors many more applications.…”

Dynamic Task and Data Placement over NUMA Architectures: An OpenMP Runtime Perspective

“…Nikolopoulos et al [13] designed a mechanism to migrate memory pages automatically that relies on user-level code instrumentation performing a sampling analysis of the first loop iterations of OpenMP applications to determine thread and memory affinity relations. They have shown their approach can be even more efficient when the page migration engine and the operating system scheduler [14] are able to communicate. This pioneering research only suits OpenMP applications that have a regular memory access pattern while our approach favors many more applications.…”