PIPELINED SNOOPING OF MULTIPLE L1 CACHE LINES

摘要

A cache system provides for accessing set associative caches with no increase in criticalpath delay, for reducing the latency penalty for cache accesses, for reducing snoop busytime, and for responding to MRU misses and cache misses. A two level cache subsystemincluding an L1 cache and an L2 cache is provided. A cache directory is accessed for asecond snoop request while a directory access from a first snoop request is beingevaluated. During a REQUEST stage, a directory access snoop to the directory of the L1cache is requested; and responsive thereto, during a SNOOP stage, the directory isaccessed; during an ACCESS stage, the cache arrays are accessed while processingresults from the SNOOP stage. If multiple data transfers are required out of the L1 cache,a pipeline hold is issued to the REQUEST and SNOOP stages, and the ACCESS stage isrepeated. During a FLUSH stage, cache data read from the L1 cache during the ACCESSstage is sent to the L2 cache.