Abstract: A main memory unit for a data processing system has at least one memory board and allows each memory board to process data simultaneously. Each memory board may also include a plurality of memory array units which also can process data simultaneously. The main memory unit includes a memory interface unit, at least one memory board, and a memory unit bus for transferring address, data, command, and memory status signals between the memory boards and the memory interface unit.

Abstract: A system for implementing a repeater interlock scheme between a first and a second bus utilizes two repeaters. The first repeater coupled to the first bus includes an interlock state bit which is set upon the acceptance of an interlock transaction from a processor. No further interlock transactions will be accepted while the interlock state bit is set. The interlock transaction is passed to a transaction buffer in the second repeater which is coupled to memory through the second bus. The transaction buffer passes the interlock data for memory to the second bus while simultaneously loading a one deep interlock buffer. A confirmation is sent from the memory back to the transaction buffer. If the confirmation is interlock busy, then the interlock transaction is retried from the interlock buffer thus allowing the transaction buffer to process other commands. The interlock buffer waits for an unlock write signal before retrying an interlock transaction thus alleviating congestion on the second bus.

Abstract: For use in a data processing system, a main memory subsystem includes a plurality of memory boards for storing groups of logic signals. Each memory board includes an plurality of array units. Each array unit is adapted to store a group of logic signals that is equivalent in size to the field of data logic signals transferred on the system bus and has an address structure so that each addressable data signal group can be stored in a single array. The address field of each array unit is further adapted so that the probability of interfering activity in each array is low. The arrays are adapted process data signal groups independently, thus, activity involving several arrays can take place simultaneously. The memory subsystem is structured to provide a pipeline types of overlapping activity so that activity involving several array units can be in progress simultaneously.

Abstract: A system for implementing a bus window interlock scheme between a first and a second bus utilizes two bus window modules. The first bus window module coupled to the processor bus includes an interlock state bit which is set upon the acceptance of an interlock transaction from a processor. No further interlock transactions will be accepted while the interlock state bit is set. The interlock transaction is passed to a transaction buffer in the second bus window module which is coupled to memory through the memory bus. The transaction buffer passes the interlock data for memory to the memory bus while simultaneously loading a one deep interlock buffer. A confirmation is sent from the memory back to the transaction buffer. If the confirmation is interlock busy, then the interlock transaction is retried from the interlock buffer thus allowing the transaction buffer to process other commands.

Abstract: In a data processing system in which access to a second unit by a first unit through a system bus is determined by an arbitration unit, when a requesting unit that receives access to the system bus is unable to use that access for interaction with the second unit, a busy signal is provided to the arbitration unit and to the units. The busy signal causes the units to reinstitute a request for access to the system bus when the subsystem had an aborted transaction. The busy signal enforces a delay in the next arbitration for the system bus until a unit, with an aborted transaction as a result of the busy signal, can reassert the request for access signal. Moreover, apparatus can be included with the arbitration unit that permits rearbitrating access to the bus using the priority conditions in effect at the time of the original arbitration.

Abstract: In a data processing system having a multiple write command and a masked write command, a plurality of signal groups can be transferred from a data processing subsystem to a memory unit on consecutive system cycles. Associated with each signal group and applied to lines used to transfer mask signals are control signals that designate when the associated signal group is to stored in the memory unit. When the multiple write command is issued, the apparatus coupled to the mask signal lines is enabled and the control signals can be identified. When the control signals are identified, the operation storing the associated signal group is inhibited.

Abstract: Apparatus is disclosed for selecting a group of address signals to be applied to a memory unit array and for applying the address signals to the memory unit array to permit the activity associated with the address signals to be completed. The apparatus generates a multiplicity of signals controlling a latch-type buffer storage unit. The first generated signal insures that the signal controlling the buffer storage unit is active during application of the address signals to the system bus. The second generated signal overlaps the first generated signal and extends the signal controlling the buffer storage unit a small amount. The third generated signal overlaps the second generated signal and extends the signal controlling the buffer storage unit for the period of time necessary to utilize the memory unit array.