Hitachi, Ltd.

Hitachi Microcomputer Engineering, Ltd.

Ikuo Yoshihara

Akira Muramatsu

Kazuo Nakao

Teruo Tanaka

Shigeo Nagashima

Takehisa Hayashi

Naoki Hamanaka

Makoto Nohmi

Kousuke Sakoda

Hideo Ohata

Masahiro Ishida

Yasuyuki Takahashi

In a parallel computer including L=n.sub.1 .times.n.sub.2 .times. - - - .times.n.sub.N processor element or external devices (hereafter represented by processor elements), an interconnection network of processor elements using L.times.(1/n.sub.1 +1/n.sub.2 + - - - +1/n.sub.N) crossbar switches in total comprises N dimensional lattice coordinates (i.sub.1, i.sub.2, - - - , i.sub.N), 0.ltoreq.i.sub.1 .ltoreq.n.sub.1 -1, 0.ltoreq.i.sub.2 .ltoreq.n.sub.2 -1; - - - , 0.ltoreq.i.sub.N ; and .ltoreq.n.sub.N -1 given to each processor element as the processor element number, crossbar switches for decoding a dimensional field in a processor element number having specific position and length depending upon the number of lattice points of a particular dimension and for performing the switching operation with regard to the dimension, interconnection of n.sub.k processor elements having processor element numbers, which are different only in the k-th dimensional coordinate for arbitrary k, i.e., having processor element numbers ##EQU1## by using one of the crossbar switches, each of the crossbar switches having n.sub.k inputs and n.sub.k outputs, and the interconnection performed with respect to all (L/n.sub.k sets) of coordinates (i.sub.1, i.sub.2, - - - , i.sub.k-1, i.sub.k+1, - - - , i.sub.N) of N-1 dimensional subspace excluding the k-th dimension, the interconnection being further performed for all values of k (1.ltoreq.k.ltoreq.N).

Interconnection network and crossbar switch for the same

In a parallel computer including L=n.sub.1 x n.sub.2 x - - - x n.sub.N processor element or external devices (hereafter represented by processor elements), an interconnection network of processor elements using L x (1/n.sub.1 +1/n.sub.2 +- - - +1/n.sub.N) crossbar switches in total comprises N dimensional lattice coordinates (i.sub.1, i.sub.2, - - - , i.sub.N) , 0.ltoreq.i.sub.1 .ltoreq.n.sub.1-1, 0.ltoreq.i.sub.2 .ltoreq.n.sub.2-1, - - - , 0.ltoreq.i.sub.n .ltoreq.n.sub.N-1 given to each processor element as the processor element number, crossbar switches for decoding a dimensional field in a processor element number having specific position and length depending upon the number of lattice points of a particular dimension and for performing the switching operation with regard to the dimension, interconnection of n.sub.k processor elements having processor element numbers, which are different only in the k-th dimensional coordinate for arbitrary k, i.e., having processor element numbers ##EQU1## by using one of the crossbar switches, each of the crossbar switches having n.sub.k inputs and n.sub.k outputs, and the interconnection performed with respect to all (L/n.sub.k sets) of coordinates

A parallel computer has an operation request function and a plurality of processor elements. Each processor element has a sharable distributed memory for holding data, and is interconnected to a network to permit communication. Each processor element comprises a request sent unit for sending an operation request message for causing another processor element connected to a memory module to execute a recursive defining operation. The memory module stores data to be recursively defined. Each processor element further comprises an operation request execution element for accepting a message from another processor, temporarily stopping any other operation of the processor element in accordance with the content of the message, and executing the requested operation. Registers are also used for executing the operation requested by the other processor in addition to the general purpose registers and floating point registers.

Method and apparatus for executing an operation request signal in a

A plurality of elemental processors each include a local memory for storing data and task programs and an execution section for executing the task programs. A communications section transfers data among the processors. In a method of parallel processing with these elemental processors, a task program is executed in one of the processors. A detection operation is conducted to determine whether the data from the task program is to be copied to the local memories of other processors. The detection is based on predetermined information which is stored in the local memory of the processor which performs the task program and indicates which of the other processors will need the data. The detection also determines which of the other processors that will require access to the data are ready to receive the data. Concurrently and in parallel with the execution of the task program, the data is transmitted to each of the elemental processors that are awaiting the data with only a write instruction and without any communications instruction.

Method of parallel processing for avoiding competition control problems

In accessing a memory, each element processor executes a program constructed so as to designate an address belonging to a predetermined local address area for each element processor. When a memory write instruction is executed by an element processor, it is detected if the memory address designated by the instruction coincides with a predetermined address. If detected, a predetermined address belonging to a local address space of another element processor and assigned to the first-mentioned predetermined address, and the data written in response to the write instruction, are sent to the other element processor to instruct the data to be written therein as a copy data. A next task to be executed is decided independently for each element processor.

Parallel computer with distributed shared memories and distributed task

In an analysis processor which utilizes a parameter table for setting a processing condition and analyzes data in accordance with the content of table, a process for registering/correcting the parameter table is standarized for various analysis processing programs so that each of the analysis processing programs is divided into an analysis processing procedure instruction section and a parameter table section. Thus, a plurality of different analysis process can be performed in one analysis processor. Any table in the analysis processing programs may be readily referred to by an instruction through a keyboard of the analysis processor and may be registered and corrected. Thus, a user can alter the analysis processing program as he/she desires.

Growing community of inventors

Tama, Japan

Ikuo Yoshihara