An analytic model of optimistic Software Transactional Memory
Armin Heindl, Gilles Pokam, Ali-Reza Adl-Tabatabai · 2009
An analytic model is proposed to assess the performance of optimistic software transactional memory (STM) systems with in-place memory updates for write operations. Based on an absorbing discrete-time Markov chain, closed-form analytic expressions are developed, which are quickly solved iteratively to determine key parameters of the STM system. The model covers complex implementation details such as read/write locking, data consistency checks and conflict management. It provides fundamental insight into the system behavior, when we vary input parameters like number and size of concurrent transactions or the number of the data objects. Numerical results are validated by comparison with a discrete-event simulation.