Abstract: A computer processor employing parallelism through pipelining and/or multiple functional units improved by Sequential Coherency Instruction Scheduling and/or Sequential Coherency Exception Handling. Sequential Coherency Instruction Scheduling establishes dependencies based on the sequential order of instructions, to execute those instructions in an order that may differ from that sequential order. Instructions are permitted to execute when all needed source operands will be available by the time required by the instruction and when all logically previous reads and writes of the destination will be accomplished before the time that the instruction will overwrite the destination. Sequential Coherency Exception Handling does not use checkpointing or in-order commit. Instead it permits out-of-order execution to actually update the permanent state of the machine out-of-order. It maintains and saves, when an exception is recognized, sequential flow information and completion information about the program execution.

Abstract: To increase the performance of a pipelined processor executing instructions, conditional instruction execution issues and executes instructions, including but not limited to branches, before the controlling conditions may be available and makes the decision to update the destination as late as possible in the pipeline.

Abstract: A VLSI chip is provided for use with six bidirectional data buses and may be programmed to operate in one of four modes as a bidirectinal bus multiplexer, an error correction assist circuit, a register stack addressing circuit for direct or indirect addressing, or a multiport file. Depending on the mode of operation, some data buses may be utilized for inputting control signals to the chip, hence only five terminals are required which are dedicated to control signal use only. The circuits utilized in the four modes of operation share enough commonality to make it feasible to build the chip with the capabilities for operating in all modes, and then controlling it to function in only a single desired mode.

Abstract: In a data processing system having a plurality of units and a priority controller for controlling access to a bus by any of the units, each of the units is provided with a lock register having a stage corresponding to each unit connected to the bus. Each word placed on the bus by a source unit includes a lock bit which, in each unit except the source and destination units, sets the stages of the lock registers corresponding to the source and destination units. When a stage of a lock register is set it prevents the unit in which the register is located from attempting to communicate with a unit whose stage of the lock registers is set. On the last transmission between two units the word placed on the bus has a false lock bit which resets the stages of all of the lock registers corresponding to the source and destination units.

Abstract: A large scale integrated circuit is designed to handle bus-to-bus data and address transfers, manipulation, and temporary storage. A key feature of the device is that it generates error correcting code parity bits on a byte wide basis so that ECC check bits for a multi-byte word can be generated externally with a minimum of hardware, and includes circuitry responsive to an error syndrome for correcting a single error within a byte. Data manipulation capabilities include standard logical operations, single bit shift operations, binary 2's complement arithmetic addition and subtraction, and decimal addition and subtraction. In addition, an input data byte on any bus can be passed unaltered or inverted to any other bus. The device is capable of receiving operands from one or two of three bidirectional data buses, performing a desired arithmetic or logical operation on the operand or operands, and returning the result to any one of the bidirectional buses including one which may have supplied one of the operands.

Abstract: A mechanism is provided which permits the insertion of elements into a list of positions determined by the rank of the elements and allows deletion of elements only from the top of the list. The arrangement provides dynamic aging of the priorities of the elements entered into the list.