Abstract: A uniprocessing computer system is provided with an original CPU and an upgrade socket for receiving an additional processor that need not be of a single predetermined type. On system RESET, the original CPU determines if an upgrade processor is resident in the upgrade socket and, if so, what kind of upgrade processor is present. Each upgrade processor is equipped with a programmed data word for identifying the upgrade type and its features. The system includes a mechanism for communicating this upgrade information from the upgrade processor to the original CPU. The processors cooperatively configure the system properly according to the identity and features of the upgrade processor.

Abstract: A method and apparatus for upgrading a uniprocessor system to a multiprocessing system simply by the insertion of a second microprocessor integrated circuit. The computer system is provided with an upgrade socket for receiving the second processing unit, as well as a private communications bus between the upgrade socket and the existing processor for handling interprocessor communications, bus arbitration and cache coherency, etc. The addition of the second processor is transparent to the system which maintains its memory management unit and caching system and other arrangements as though it were still a uniprocessing system. Therefore, an inexpensive method and apparatus are provided for greatly enhancing the speed of a uniprocessing system to that of a multiprocessing system without the cost traditionally associated with multiprocessing systems.

Abstract: A second level cache memory controller, implemented as an integrated circuit unit, operates in conjunction with a secondary random access cache memory and a main memory (system) bus controller to form a second level cache memory subsystem. The subsystem is interfaced to the local processor (CPU) bus and to the main memory bus providing independent access by both buses, thereby reducing traffic of the main memory bus when the data required by the CPU is located in secondary cache. Similarly, CPU bus traffic is minimized when secondary cache access by the main memory bus for snoops and write-backs to main memory. Snoop latches interfaced with the main memory bus provide snoop access to the cache memory via the cache directory in the secondary cache controller unit. The controller also supports parallel look-up in the controller tag array and the secondary cache using most-recently-used (MRU) main memory write-through and pipelining of memory bus cycle requests.