Abstract: A bus bridge is disclosed that handles bus transactions that must be completed on a destination bus before being completed on an originating bus by indicating a retry to delay such bus transactions on the originating bus while completing such bus transactions on the destination bus.

Abstract: A distributed variable-size cache placement architecture includes plural cache storage units (CSUs), each of which includes a CSU control logic, an address director, a data director, a placement array, placement logic (i.e., distribution controller), and a set associative memory for caching data. All CSUs in the architecture are connected over a communication network to a single processor interface and mainstore and which provides information to all CSUs about the status of each of the other CSUs. Any number of CSUs may be connected in parallel to provide a variable size cache. All CSUs sharing a processor interface utilize the same placement block size, contain the same number of sets of cache elements and use the same CSU placement mechanism.

Abstract: A method of handling processor to processor interrupt requests in a multiprocessing computer bus environment is described. This method allows a multiple-tiered, increasing priority, interrupt request scheme. This method also allows processor to processor directed interrupt requests, processor to one processor of a group of processors interrupt requests, and processor to all processors of a group of processors interrupt requests.

Abstract: A distributed method for arbitrating access to a common bus in a multiple processor environment is described. This method provides for fairness where multiple processors are vying for access to a global memory. An apparatus for arbitrating access to a common bus in a multiple processor environment is also described. This apparatus provides for priority determination of each processor upon system reset and provides for fairness where multiple processors are vying for access to a global memory.

Abstract: A method of transferring data in response to a read command in a computer system having a plurality of processors coupled to an address bus, a command bus and a data bus is described. A first processor generates and sends the read command to read a first data from a second processor. The second processor then determines with which one of (1) the first data and (2) a read response command and the first data it desires to respond to the read command. If the second processor determines to respond with the first data, then it acknowledges receipt of the read command and performs an ordered response in which the command and address buses are released and only the first data is later sent to the first processor via the data bus when available.