The development of efficient and scalable cache coherence protocols is a key aspect in the design of manycore chip multiprocessors. In this work, we review a kind of cache coherence protocols that, despite having been already implemented in the 90s for building large-scale commodity multiprocessors, have not been seriously considered in the current context of chip multiprocessors. In particular, we evaluate a directory-based cache coherence protocol that employs distributed simply-linked lists to encode the information about the sharers of the memory blocks. We compare this organization with two protocols that use centralized sharing codes, each one having different directory memory overhead: one of them implementing a non-scalable bit-vector sharing code and the other one implementing a more scalable limited-pointer scheme with a single pointer. Simulation results show that for large-scale chip multiprocessors, the protocol based on distributed linked lists obtains worse performance than the centralized approaches. This is due, principally, to an increase in the contention at the directory controller as a consequence of being blocked for longer time while updating the distributed sharing information.
展开▼
