Abstract: A data processing system includes at least a first processor and a second processor that each have a respective translation lookaside buffer (TLB). In response to detection by the second processor of a TLB entry invalidation request, the second processor marks at least one memory referent instruction that is being processed by the second processor and invalidates a TLB entry in the TLB of the second processor. In response to receipt of a synchronization request at the second processor, the second processor indicates to the first processor that the second processor has invalidated the TLB entry if the second processor has completed processing the marked instruction. During the interval between receipt of the synchronization request and indicating to the first processor that the second processor has invalidated the TLB entry, the second processor continues to process instructions, including fetching instructions for processing.

Abstract: A method and apparatus are provided for generating a ratioed clock signal. A first clock signal having a first frequency is output. At least one gating signal indicating ratio is output. In response to the first clock signal and the gating signal, a second clock signal is output. The second clock signal has a frequency that is substantially related to the first frequency by the ratio.

Abstract: A check is made to determine if a copy of a cache line is currently resident in the level-one data cache of a microprocessor system. If, in response to the check, it is determined that a copy of such cache line in fact is not currently resident, the cache line is created as the least-recently used cache line. Then, for set-associative data caches, the next used of the associative set will replace the most recently zeroed line. In this way, zeroing operations can replace only one .div. (number of associative sets) of the data cache for zeroing operations, thereby leaving the most frequently used data intact. By doing so, the data-cache is not wasted on zeroed cache lines which may be infrequently reused from the data cache, thereby significantly improving system performance. In other words the net effect is to reduce probability of data cache misses on subsequent instructions because more of the cache is thereby made available for more frequently reused data.