摘要:
A processor performs a pipelined parallel processing by an operand effective address calculation unit for calculating an operand effective address necessary to execute an instruction and an instruction execution unit for executing the instruction. A 64 bit width data operation is performed in such a way that a high order 32 bit operation is performed in an arithmetic device in the operand effective address unit and a low order 32 bit operation is performed in another arithmetic device in the instruction execution unit. A carry is transferred from the low order 32 bit arithmetic device to the high order 32 bit arithmetic device. The arithmetic devices thus joined can perform the 64 bit with data operation as an arithmetic device.
摘要:
A bus-coupler or bus window in an information transport system for connecting a plurality of buses, to each of which a plurality of arithmetic units, a plurality of memory or storage units and a plurality of input-output units are connected separately through stations. The bus coupler includes a dead-lock control circuit for preventing a dead-lock which could possibly occur in communication between the buses.
摘要:
A data processing system having flexibility coping with parallelism of a program comprises a plurality of processor elements for executing instructions, a main memory shared by the plurality of processor elements, and a plurality of parallel operation control facilities for enabling the plurality of processor elements to operate in synchronism. The plurality of parallel operation control facilities are provided in correspondence to the plurality of processor elements, respectively. The data processing system further comprises a multiprocessor operation control facility for enabling the plurality of processor elements to operate independently, and a flag for holding a value indicating which of the parallel operation mode or the multiprocessor mode is to be activated. The shared cache memory is implemented in a blank instruction and controlled by a cache controller so that inconsistency of the data stored in the cache memory is eliminated.
摘要:
An information processing system having an original clock oscillator for delivering at least one original clock signal K defined as a first clock signal and a plurality of information processing units supplied with the original clock signal K, wherein each information processing unit comprises clock generating means for generating at least one second clock signal K.sub.1 which is phase-locked with the original clock signal K and which has a predetermined duty cycle and a logic device whose operation timing is controlled by the second clock signal K.sub.1, and the operation timing of an interface provided between at least one pair of logic devices is synchronously controlled by the clock signal K.sub.1.
摘要:
High-speed inference method and system for a production system represented by an expert system. A knowledge base comprised of a rule and a fact possessing a plurality of attributes is converted into machine language instructions executable by a processor to execute inference. The machine language instruction of the fact has the function of transferring a value of the fact to a specified location and the machine language instruction of the rule has the function of performing matching decision by referring to the specified location. The number of pattern matching operations can be decreased and the interpretation overhead can be reduced to ensure high-speed inference.
摘要:
An information processing system having an original clock oscillator for delivering at least one original clock signal K defined as a first clock signal and a plurality of information processing units supplied with the original clock signal K, wherein each information processing unit comprises clock generating means for generating at least one second clock signal K1 which is phase-locked with the original clock signal K and which has a predetermined duty cycle and a logic device whose operation timing is controlled by the second clock signal K1 and the operation timing of an interface provided between at least one pair of logic devices is synchronously controlled by the clock signal K1.
摘要:
An information processing system having an original clock oscillator for delivering at least one original clock signal K defined as a first clock signal and a plurality of information processing units supplied with the original clock signal K, wherein each information processing unit comprises clock generating means for generating at least one second clock signal K.sub.1 which is phase-locked with the original clock signal K and which has a predetermined duty cycle and a logic device whose operation timing is controllled by the second clock signal K.sub.1, and the operation timing of an interface provided between at least one pair of logic devices is synchronously controlled by the clock signal K.sub.1.
摘要:
When executing successive processing of conventional software, a parallel processing apparatus turns a processing state discrimination flag off, increases a program count by 1 at a time, reads out one instruction, and processes that instruction in an arithmetic unit. When executing parallel processing for new software, the parallel processing apparatus turns the processing state discrimination on, increases the program count by m at a time, reads out m instructions, and exercises parallel processing over m instructions in m arithmetic units. In order to select either of the above described two kinds of processing, a discrimination changeover instruction having function of changing over the processing state discrimination flag is added. Instructions are processed in arithmetic unit(s) in accordance with the processing state discrimination flag. In this way, successive processing and parallel processing are provided with compatibility and are selectively executed. Further, the parallel processing apparatus making great account of compatibility of a great part of software reads out m instructions without using the processing state flag, decodes the m instructions, checks whether a branch instruction exists in the k-th instruction, then executes the first to the (k+1)-th instructions in k+1 arithmetic units, and prevent execution of the (k+ 2)-th to m-th instructions. By executing the k-th branch instruction, the parallel processing apparatus calculates an address nm+h of its branch destination, performs calculation to check whether the condition is satisfied or not, then prevents execution of instructions of addresses nm to nm+h-1, and executes instructions of addresses nm+h to (n+1)m. In this way, the parallel processing apparatus executes a plurality of instructions and successively executes branch instructions.
摘要:
A data processing apparatus which allows a large number of micro instructions to be read at high speeds by storing frequently used micro instructions in the on-chip ROM and those less frequently used in the off-chip memory. From the address of the micro instruction to be accessed, it is determined whether the micro instruction is stored in the on-chip ROM or the off-chip memory, and the micro instruction is accessed on the basis of this determination. A cache memory may also be provided on the chip for providing high speed repeat access to micro instructions stored in the off-chip memory.
摘要:
A data processing system having flexibility coping with parallelism of a program comprises a plurality of processor elements for executing instructions, a main memory shared by the plurality of processor elements, and a plurality of parallel operation control facilities for enabling the plurality of processor elements to operate in synchronism. The plurality of parallel operation control facilities are provided in correspondence to the plurality of processor elements, respectively. The data processing system further comprises a multiprocessor operation control facility for enabling the plurality of processor elements to operate independently, and a flag for holding a value indicating which of the parallel operation mode or the multiprocessor mode is to be activated. The shared cache memory is implemented in a blank instruction and controlled by a cache controller so that inconsistency of the data stored in the cache memory is eliminated.