Abstract: In a memory device capable of processing a small amount of data in a high speed, this memory device is suitable for various sorts of systems in which a plurality of access requests for continuous addresses are mixed with each other, and are issued as irregular requests to a memory subsystem. A data array is provided in a memory device having a memory cell. This data array may be arranged as a virtual register array having an arbitrary number of arbitrary word length. The data register array is accessed by employing a virtual register number and a virtual word number, which are supplied from an external circuit provided outside the memory device. In the memory device, both the virtual register number and the virtual word number, which are supplied from the external circuit, are converted into both an absolute register number and an absolute word number by an internally-provided converting circuit so as to access the data register array.

Abstract: A memory system for use in a high-speed computer system, such as a super computer, has synchronous-type storage elements organized in groups for storing data. A storage control section has a clock generator circuit that generates parallel transfer clock signals that compensate for overall transfer delay when data is transferred to the storage elements. Each of the storage elements groups has a phase-locked locked loop circuit that outputs timing signals for accepting data, including address and control signals, etc., at the storage elements. Data is read out from the storage elements to a return data holding circuit of the storage control section using return parallel transfer clock signals, which are controlled by a control section phase-locked loop circuit that receives as an input a timing output of the phase-locked loop circuit of one of the storage element groups. A clock distribution circuit controls the supply of clock signals to a flip-flop group in the return data holding circuit.

Abstract: In an information processing system, a main storage access request issued from a processor is input to an access buffer mechanism provided in a memory control device, and sent via an operation request issue control mechanism to a main storage device constituted of a plurality of memory units (banks). In the memory control device, the operation status of each bank constituting the main storage device is managed and the number of banks under operation is counted. The predetermined number (operation bank limit number) of banks required to operate at a minimum is compared with the number (operation bank number) of banks under operation.

Abstract: Each of processors in a multiprocessor system has a circuit for sending a synchronizing signal to a storage controller (SC) connected thereto when executing a synchronization instruction such as a start, end or barrier synchronization instruction. Each of the SCs has a circuit for notifying the corresponding processor of establishment of a synchronization upon detection of completion of a check to be made by an address management table FAA and of the issuing of necessary cache cancel requests corresponding to a store instruction issued before the synchronization instruction and upon recognition of the fact that all the processors have sent their synchronizing signals and that the issuing of all the cache cancel requests have been complete.

Abstract: An instruction processor is employed which performs a cache coherence control according to a request from the storage controller. The storage controller is provided with a cache coherence control processing circuit, which performs the cache coherence control for the addresses which are the destinations of main memory accesses occurring with a data transfer. At the same time, the cache coherence control processing circuit performs the cache coherence control processing once for each cache line in the process of data transfer. The cache coherence control processing performed by software in connection with data transfer is obviated, improving the data transfer efficiency including the cache memory control and reducing limitations on program.

Abstract: In an information processing system, a main storage access request issued from a processor is input to an access buffer mechanism provided in a memory control device, and sent via an operation request issue control mechanism to a main storage device constituted of a plurality of memory units (banks). In the memory control device, the operation status of each bank constituting the main storage device is managed and the number of banks under operation is counted. The predetermined number (operation bank limit number) of banks required to operate at a minimum is compared with the number (operation bank number) of banks under operation.

Abstract: A transmission apparatus capable of transferring data between a transmitting and a receiving device using a small-scale, low-cost hardware implementation for high-speed data transmission, the apparatus being conducive to reducing the amount of system design work on a target system. The transmitting device sends to the receiving device both data and a reference signal generated by a reference signal generation circuit. On the receiving side, a phase adjustment circuit delays the reference signal and a phase determination/phase amount control circuit brings the delayed signal into phase with a receiving-side clock signal. A data signal group is given the same amount of delay as the reference signal. The scheme allows data signals to be received directly in keeping with the receiving-side clock signal, eliminating the need for strict clock skew management, massive detours of data transmission lines or a wasteful wait time required for signal values to be established.

Abstract: An information processing system is connected to a common storage and executes programs by use of processors. This system includes a common storage; a plurality of processors, connected to the common storage.

Abstract: In a multiprocessor computer system, individual vector processors are provided with priority switching signal control circuits, respectively, and a storage control unit incorporating a priority control circuit. Priority bit information is provided for priority circuits incorporated in the storage control unit. Paths for priority switching signal issued in accordance with a number of requests as generated and types of instruction generating the requests are provided between the priority switching signal control circuits and the priority control circuit of the storage control unit, while paths for the priority switching signal as generated are provided between the priority control circuit and all the priority circuits.

Abstract: In transmitting and receiving signals between a plurality of units in a information processing system, signals can be transmitted and received between circuits operated by asynchronous clocks which are the same in period (frequency) but not necessarily to be the same in phase, thereby permitting the information processing system to operate with a shorter clock period. A delay circuit arranged in the communication path is so controllable that the data sent out in synchronism with the clock signal of a transmitting unit is correctly retrieved in synchronism with the clock signal of a receiving unit. Further, data having a predetermined simple pattern is sent out in synchronism with the clock signal of the transmitting unit, and it is decided whether the data has been correctly received by the receiving unit. The delay circuit is automatically controlled by use of the result of decision.

Abstract: In a parallel processor system comprising a plurality of processor elements constituting a network, a source processor element wishing to broadcast data to a plurality of destination processor elements sends a broadcast request message containing the target data to a broadcast exchanger. The broadcast exchanger converts the received message into a broadcast message and sends it over the network to the destinations. A plurality of broadcast request messages, if transmitted parallelly to the broadcast exchanger, are serialized thereby so that only one broadcast message will be transmitted at a time over the network. This prevents deadlock from occurring between different broadcast messages. The routes for transmitting broadcast request messages and those for transmitting broadcast messages are arranged so as not to overlap with one another. This suppresses deadlock between any broadcast request message and broadcast message. The broadcast exchanger is replaced alternatively with one of the partial networks.

Abstract: A parallel computer system includes a plurality of processor units, a data transfer network for interconnecting the processor units, a synchronizing network for allowing program execution to be performed synchronously by the individual processor units, a connecting unit for connecting the individual processor units and the synchronizing network, and an input unit connected to the synchronizing network. The connecting unit connects selectively the individual processor units to the synchronizing network in accordance with information inputted via the input unit. With the parallel computer system, a program can be executed synchronously in parallel by using a desired number of processor units of those incorporated in the system, whereby availability of processor resources of the system can be enhanced.

Abstract: In transmitting and receiving signals between a plurality of units in a information processing system, signals can be transmitted and received between circuits operated by asynchronous clocks which are the same in period (frequency) but not necessarily to be the same in phase, thereby permitting the information processing system to operate with a shorter clock period. A delay circuit arranged in the communication path is so controllable that the data sent out in synchronism with the clock signal of a transmitting unit is correctly retrieved in synchronism with the clock signal of a receiving unit. Further, data having a predetermined simple pattern is sent out in synchronism with the clock signal of the transmitting unit, and it is decided whether the data has been correctly received by the receiving unit. The delay circuit is automatically controlled by use of the result of decision.

Abstract: In a multiprocessor computer system, individual vector processors are provided with priority switching signal control circuits, respectively, and a storage control unit incorporating a priority control circuit. Priority bit information is provided for priority circuits incorporated in the storage control unit. Paths for priority switching signal issued in accordance with a number of requests as generated and types of instruction generating the requests are provided between the priority switching signal control circuits and the priority control circuit of the storage control unit, while paths for the priority switching signal as generated are provided between the priority control circuit and all the priority circuits.

Abstract: When a processor generates an access request to a plurality of continuous addresses to an RAM through a memory control apparatus, in order to enable a high speed process, a register which holds an address for accessing a memory cell and a register which holds an address for accessing a data buffer are separately provided in an RAM having memory cells and a plurality of row correspondence data buffers of the memory cells. A signal line to instruct the presence or absence of the use of the data buffer is provided between the processor and the memory control apparatus. The memory cell and the data buffer are accessed in parallel, thereby realizing a high processing speed. The processor designates so as to preferentially use the data buffer for an RAM access having an address continuity, thereby enabling the data to be accessed at a high speed.

Abstract: A memory control unit connected to a scalar processor having a buffer for storing a copy of block data of a main storage and a vector processor having a store requester for writing data into the main storage is disclosed. The memory control unit has a block valid memory having a one-bit valid bit for all blocks. The valid bit represents that the copy of the block data corresponding to said bit is in the buffer of the scalar processor. The memory control unit further has a block group valid table which has a block group bit for each block group. The block group bit represents whether any one of the block valid bits of the block belonging to the corresponding group is valid or not. When the vector processor stores the data into the main storage by the store requester, the memory control unit first searches the block group valid table to check whether the block group valid bit of the block group including the store address is valid or not.

Abstract: A store control method for a computer system having a storage with independently accessible plural store banks, plural access request controllers for issuing access requests to the storage, and a store controller for transmitting the access requests to each store bank. The store controller has an access request priority determining circuit of plural stages for selecting the access requests in the order of higher priority for each store bank so as to determine the order of priority between the access requests in multiple stages on the basis of the access requests. Further, plural priority control circuits of each stage are provided for stepwise performing control of priority of the main store access requests issued by the vector data processor for each of the store banks. Access is made to the main storage by assuring the order between the vector elements constituting vector data by allowing each first priority control circuit to send the access requests to the priority control circuit of next stage.

Abstract: A plurality of storage control units are employed in the storage control unit section; moreover, two requester modules are adopted in association with these storage control units. Each memory module is constituted with as many access bank groups as there are storage control units. The access bank groups operate in concurrent fashion and are accessible from any one of the storage control units. In the element assignment, a plurality of request control units in each requester module and a plurality of vector data controllers in each vector register unit are respectively assigned with serial numbers beginning from zero. For a vector data controller, a number assigned thereto is divided by the request module count to attain a remainder such that the vector data controller is assigned to a request module having a number identical to the value of the remainder.

Abstract: A storage control apparatus of a computer system having a plurality of transfer pipelines issuing access requests to a plurality of memory banks of a storage device. Each memory bank is independently accessible in response to an access instruction from a vector processing device. Each of the transfer pipelines includes a plurality of access request control devices to which the access instruction from the vector processing device is allocated in association with elements of a vector. The access request control devices simultaneously issue in response to an access instruction a plurality of access requests. Each transfer pipeline also includes a priority decision device which detects whether or not the access requests forecasted to be issued from the plural access request control devices contend with the access requests issued from the plural access request control devices of another transfer pipeline.

Abstract: Disclosed is a computer system containing plural processors, a shared storage shared by the plural processors, a buffer storage for storing a copy of a portion of data of the shared storage disposed in each of the plural processors, and a storage controller having a communication buffer storage disposed halfway between the buffer storage and the shared storage for storing a copy of a portion of data of the shared storage as an object for storing only an operand data of a particular instruction. This computer system can implement communication of data of the shared storage between the plural processors by using the communication buffer storage in an efficient way.