This paper presents a new cache consistency scheme for hierarchically
structured shared-memory multiprocessors. The scheme is simple, fast a
nd efficient, and it does not require a large amount of state informat
ion to be maintained. The scheme exploits the broadcast capability of
these systems, but limits the extent of the broadcasts by means of a n
ovel filtering mechanism. As a specific example, it is shown how the p
roposed cache consistency scheme can be implemented on the Hector mult
iprocessor architecture. Using trace-driven simulations, we demonstrat
e that the scheme is scalable and performs well for common application
s.