JPS60263255A - Processor synchronizing system - Google Patents

Processor synchronizing system

Info

Publication number
JPS60263255A
JPS60263255A JP59118167A JP11816784A JPS60263255A JP S60263255 A JPS60263255 A JP S60263255A JP 59118167 A JP59118167 A JP 59118167A JP 11816784 A JP11816784 A JP 11816784A JP S60263255 A JPS60263255 A JP S60263255A
Authority
JP
Japan
Prior art keywords
processor
processors
circuit
sequencer
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
JP59118167A
Other languages
Japanese (ja)
Inventor
Yoshitaka Ito
芳孝 伊藤
Fumiaki Ishino
文明 石野
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nippon Telegraph and Telephone Corp
Original Assignee
Nippon Telegraph and Telephone Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nippon Telegraph and Telephone Corp filed Critical Nippon Telegraph and Telephone Corp
Priority to JP59118167A priority Critical patent/JPS60263255A/en
Publication of JPS60263255A publication Critical patent/JPS60263255A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F15/00Digital computers in general; Data processing equipment in general
    • G06F15/16Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs
    • G06F15/163Interprocessor communication
    • G06F15/17Interprocessor communication using an input/output type connection, e.g. channel, I/O port

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Multi Processors (AREA)

Abstract

PURPOSE:To execute a synchronizing operation of a processor, even in case of a system have many processors, by forming a synchronizing signal line by a wired structure between many processors. CONSTITUTION:When a synchronizing request is read out by a micro-instruction register 5, an operation of a sequencer 3 is stopped, and a micro-instruction execution control is halted. A synchronizing signal line 2 is driven by a signal of an FF11, and when the synchronizing request is generated in all processors, a logical value becomes ''0''. Its fact is informed to the sequencer 3 through an AND circuit 13, the sequencer 3 starts its operation, and the next instruction is read out. An instruction for sending and receiving a data to and from other processor is written in the register 5, and by a signal of an output line 5-3, a data from an operator 6 or a memory 7 is transmitted to other processor through a bus 8, an AND circuit 15, and an interface line 14. Also, a data from other processor is stored in a buffer 17, read out to the bus 8 through an AND circuit 16, and stored in the operator 6 or the memory 7.

Description

【発明の詳細な説明】 (発明の属する分野) 本発明は、通常は非同期で動作している複数台のプロセ
ッサを、特定の時間のみ同期動作させるプロセッサ同期
方式に関するものである。
DETAILED DESCRIPTION OF THE INVENTION (Field of the Invention) The present invention relates to a processor synchronization method in which a plurality of processors, which normally operate asynchronously, are operated synchronously only at a specific time.

(従来の技術) 従来、複数台のプロセッサを同期動作させる場合にはプ
ロセッサに使用するクロックを一種とするとともに、メ
モリ装置に使用するICメモリのリフレッシュ動作も完
全に同期させるために、リフレッシュタイミングをプロ
セッサ間で同一にさせる等の制御を行なっていた。
(Prior Art) Conventionally, when multiple processors are operated synchronously, one type of clock is used for the processors, and the refresh timing is set in order to completely synchronize the refresh operation of the IC memory used in the memory device. Controls such as making them the same between processors were performed.

しかしながら、この種の同期方式ではプロセッサ台数が
増加すると、クロックを全プロセッサで同期させるため
のクロック分配系のタイミング調整が困難になるととも
に、リフレッシュタイミングを同期させるインタフェー
ス線も増加し、プロセッサ台数は2〜3台程度しか実現
できないという欠点があった。
However, with this type of synchronization method, as the number of processors increases, it becomes difficult to adjust the timing of the clock distribution system to synchronize the clocks among all processors, and the number of interface lines to synchronize refresh timing also increases. The drawback was that only about three units could be realized.

(発明の目的) 本発明はこれらの欠点を解決するためのもので、同期信
号線を多数のプロセッサ間でワイアドオアする構造とす
ることにより、1000台以上のプロセッサを有するシ
ステムにおいても、プロセッサの同期動作を可能とした
プロセッサ同期方式を提供しようとするものであり、以
下図面について詳細に説明する。
(Objective of the Invention) The present invention is intended to solve these drawbacks, and by using a structure in which the synchronization signal line is wired-ored between a large number of processors, it is possible to synchronize the processors even in a system having 1000 or more processors. The purpose is to provide a processor synchronization method that enables operation, and the drawings will be described in detail below.

(発明の構成および作用) 第1図は本発明のシステム構成を示す−・実施例図であ
り、1−1.1−2.・・・・・・、1−nはプロセッ
サ、2はプロセッサの同期信号線である。
(Configuration and operation of the invention) FIG. 1 is an embodiment diagram showing the system configuration of the present invention, and 1-1.1-2. ..., 1-n is a processor, and 2 is a synchronization signal line of the processor.

各プロセッサ1−1〜1−nは通常は非同期で動作して
おり、例えば、他のプロセッサからデータを授受したい
という同期要求が発生した場合、各プロセッサは同期信
号線2にその旨の信号を送出すると同時に、同期信号線
2を監視し、全プロセッサ1−1〜1−nが同期要求を
出していることを検知すると全プロセッサが同期したと
判断する。
Each processor 1-1 to 1-n normally operates asynchronously. For example, when a synchronization request to send and receive data from another processor occurs, each processor sends a signal to that effect to the synchronization signal line 2. At the same time as the transmission, the synchronization signal line 2 is monitored, and if it is detected that all the processors 1-1 to 1-n are issuing synchronization requests, it is determined that all the processors are synchronized.

第2図は本発明で使用する一つのプロセッサについてそ
の構成の詳細を示す一実施例のブロック図であり、1−
1及び1−2はプロセッサ、2は同期信号線を示すこと
は第1図と同じである。
FIG. 2 is a block diagram of an embodiment showing the details of the configuration of one processor used in the present invention.
As in FIG. 1, 1 and 1-2 are processors, and 2 is a synchronization signal line.

図中、3はマイクロプログラムのシーケンス制! 御を
行なうシーケンサ、4はマイクロプログラム命令を格納
するROM、5はROM4から読み出されたマイクロ命
令を格納するマイクロ命令レジスタ、5−1〜5−3は
マイクロ命令レジスタ5の出力線、6はシフタ及び加算
器等からなる演算器、7はユーザの書いたプログラム、
データを格納するメモリ装置、8は演算器6とメモリ装
置7を接続するバス、9 、10,13,15.16は
論理積回路、11はフリップフロップ、12はドライバ
、14は他のプロセッサへデータを送出するインタフェ
ース線、17は他のプロセッサからのデータを受信する
バッファである。
In the figure, 3 is a microprogram sequence system! 4 is a ROM that stores microprogram instructions; 5 is a microinstruction register that stores microinstructions read from ROM 4; 5-1 to 5-3 are output lines of the microinstruction register 5; 6 is a An arithmetic unit consisting of a shifter, an adder, etc., 7 a program written by the user,
A memory device for storing data, 8 a bus connecting the arithmetic unit 6 and the memory device 7, 9, 10, 13, 15.16 an AND circuit, 11 a flip-flop, 12 a driver, 14 to other processors. An interface line 17 for sending data is a buffer for receiving data from other processors.

以下プロセッサ1−1を代表例としてその動作を説明す
るがプロセッサ1−2〜1−nについても同様である。
The operation of the processor 1-1 will be described below as a representative example, but the same applies to the processors 1-2 to 1-n.

プロセッサ1−1は、メモリ装置7に格納された命令に
従い、シーケンサ3がROM4からマイクロ命令を読み
出し、マイクロ命令レジスタ5に格納し、マイクロ命令
レジスタ5の信号を各部に送出し動作しているマイクロ
プログラム制御処理装置である。
In the processor 1-1, according to the instructions stored in the memory device 7, the sequencer 3 reads microinstructions from the ROM 4, stores them in the microinstruction register 5, and sends signals from the microinstruction register 5 to each part of the operating microinstruction. It is a program controlled processing device.

マイクロ命令レジスタ5に同期要求が読み出されると、
マイクロ命令レジスタ5の出力線5−1→論理積回路9
を通してフリップフリップ11を点火すると共に、シー
ケンサ3の動作を停止させ、マイクロ命令実行制御を中
断する。
When the synchronization request is read into the microinstruction register 5,
Output line 5-1 of microinstruction register 5 → AND circuit 9
At the same time, the operation of the sequencer 3 is stopped, and microinstruction execution control is interrupted.

ラ フリップフロップ11の信号はドイバ12を通して論理
値II OIIとなり、プロセッサの同期信号線2を駆
動する。同期信号線2は全プロセッサ間でワイアドオア
されており、全プセッサで同期要求が発生するまで論理
値は1′1”となっている。全プロセッサで同期要求が
発生すると同期信号線2の論理値はII OIIとなり
、論理積回路13を介してシーケンサ3にその旨を通知
すると共に、メモリ装置7に対してリフレッシュ動作の
停止を指示する。
The signal of the rough flip-flop 11 becomes a logical value II OII through the driver 12 and drives the synchronization signal line 2 of the processor. The synchronization signal line 2 is wired-ORed between all processors, and the logical value is 1'1'' until a synchronization request is generated in all processors.When a synchronization request is generated in all processors, the logical value of the synchronization signal line 2 is becomes II OII, and notifies the sequencer 3 of this via the AND circuit 13 and instructs the memory device 7 to stop the refresh operation.

シーケンサ3はこれにより動作を開始し、次のマイクロ
命令を読み出す。この場合、マイクロ命令レジスタ5に
は他のプロセッサとのデータ授受の命令が書かれており
、その出力線5−3からの信号により演算器6またはメ
モリ装置7からのデータが、バス8→論理積回路15→
インタフェース線14を介して他のプロセッサへ送信さ
れると共に、他のプロセッサからのデータは、バッファ
17に格納され、論理積回路16を介してバス8に読み
出され、演算器6またはメモリ装置7に格納される。
The sequencer 3 starts its operation and reads out the next microinstruction. In this case, an instruction for exchanging data with another processor is written in the microinstruction register 5, and a signal from the output line 5-3 causes the data from the arithmetic unit 6 or the memory device 7 to be transferred from the bus 8 to the logic Product circuit 15→
Data is transmitted to other processors via the interface line 14, and data from the other processors is stored in the buffer 17, read out to the bus 8 via the AND circuit 16, and sent to the arithmetic unit 6 or memory device 7. is stored in

シーケンサ3は、次に、同期要求を解除するマイクロ命
令をROM4から読み出し、マイクロ命令レジスタ5に
設定する。これによりマイクロ命令レジスタの出力線5
−2が駆動され論理積回路10を介してフリップフリッ
プ11をリセットし論理値を′0″とする。引き続き同
期信号線2、論理積回路13が論理値111”となり、
メモリ装置7に印加されていたリフレッシュ動作の停止
が解除される。
The sequencer 3 then reads a microinstruction for canceling the synchronization request from the ROM 4 and sets it in the microinstruction register 5. This causes the output line 5 of the microinstruction register to
-2 is driven to reset the flip-flip 11 through the AND circuit 10 and set the logic value to '0''.Subsequently, the synchronization signal line 2 and the AND circuit 13 become the logic value 111'',
The suspension of the refresh operation applied to the memory device 7 is released.

以上のように、同期信号線2を全プロセッサ1−1〜1
−n間でワイアドオアする構造となっているため、多数
のプロセッサ台数を有するシステムにおいても、容易に
全プロセッサを同期動作させることが可能となる。
As described above, the synchronization signal line 2 is connected to all processors 1-1 to 1-1.
Since it has a wired-OR structure between -n, even in a system having a large number of processors, it is possible to easily synchronize all the processors.

(効 果) 以上説明したように本発明は、1本のインタフェース線
を設けることにより多数のプロセッサ間で同期動作が可
能となるため、全プロセッサでりロックを同期させる必
要がなく、クロック分配系のタイミング調整が不用とな
り、また、メモリ装置にICメモリを用いた場合に、リ
フレッシュタイミングをプロセッサ間で通信することが
不用となる等の利点がある。
(Effects) As explained above, the present invention enables synchronized operation among a large number of processors by providing one interface line, so there is no need to synchronize the locks of all processors, and the clock distribution system This eliminates the need for timing adjustment, and also eliminates the need to communicate refresh timing between processors when an IC memory is used as the memory device.

【図面の簡単な説明】[Brief explanation of drawings]

第1図は本発明のシステム構成を示す一実施例図、第2
図は本発明で使用するプロセッサの構成の詳細を示す一
実施例のブロック向である。 1−1〜1−n ・・・プロセッサ、 2 ・・・同期
信号線、 3 ・・・シーケンサ、 4 ・・・ROM
、5 ・・・マイクロ命令レジスタ、 6 ・・・演算
器、7・・・メモリ装置、 8・・・バス、 9 、1
0,13゜15.16・・・論理積回路、11・・・フ
リップフロップ、12・・・ ドライバ、14・・・イ
ンタフェース線、 17・・・バッファ。 第1図
FIG. 1 is an embodiment diagram showing the system configuration of the present invention, and FIG.
The figure is a block diagram of an embodiment showing details of the configuration of a processor used in the present invention. 1-1 to 1-n...Processor, 2...Synchronization signal line, 3...Sequencer, 4...ROM
, 5... Microinstruction register, 6... Arithmetic unit, 7... Memory device, 8... Bus, 9, 1
0,13°15.16...AND circuit, 11...Flip-flop, 12...Driver, 14...Interface line, 17...Buffer. Figure 1

Claims (1)

【特許請求の範囲】[Claims] 複数のプロセッサが結合された処理システムにおいて、
その複数のプロセッサの全てとの間でワイアドオアする
構造とした同期信号線を有し、同期発生要求を自プロセ
ッサ内に表示する第1の手段と、全プロセッサの同期発
生要求をワイアドオアする第2の手段と、そのワイアド
オアした第2の手段を自プロセッサ内で読み出す第3の
手段とを有し、第1の手段発生から第3の手段発生まで
プロセッサの制御を停止させるようにしたことを特徴と
するプロセッサ同期方式。
In a processing system that combines multiple processors,
A first means has a synchronization signal line configured to wire-OR between all of the plurality of processors and displays a synchronization generation request within its own processor, and a second means for wire-ORing the synchronization generation requests of all the processors. and a third means for reading out the wired-ored second means within its own processor, and the control of the processor is stopped from the generation of the first means to the generation of the third means. processor synchronization method.
JP59118167A 1984-06-11 1984-06-11 Processor synchronizing system Pending JPS60263255A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP59118167A JPS60263255A (en) 1984-06-11 1984-06-11 Processor synchronizing system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP59118167A JPS60263255A (en) 1984-06-11 1984-06-11 Processor synchronizing system

Publications (1)

Publication Number Publication Date
JPS60263255A true JPS60263255A (en) 1985-12-26

Family

ID=14729770

Family Applications (1)

Application Number Title Priority Date Filing Date
JP59118167A Pending JPS60263255A (en) 1984-06-11 1984-06-11 Processor synchronizing system

Country Status (1)

Country Link
JP (1) JPS60263255A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS62232065A (en) * 1986-04-02 1987-10-12 Sharp Corp Synchronization system for plural processors
JPH01181134A (en) * 1988-01-13 1989-07-19 Nec Corp Microcomputer

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS5713565A (en) * 1980-06-27 1982-01-23 Toshiba Corp Synchronizing method of multiprocessor computer system

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS5713565A (en) * 1980-06-27 1982-01-23 Toshiba Corp Synchronizing method of multiprocessor computer system

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS62232065A (en) * 1986-04-02 1987-10-12 Sharp Corp Synchronization system for plural processors
JPH01181134A (en) * 1988-01-13 1989-07-19 Nec Corp Microcomputer

Similar Documents

Publication Publication Date Title
US5920714A (en) System and method for distributed multiprocessor communications
CA2002895A1 (en) Arithmetic unit
JPS60263255A (en) Processor synchronizing system
EP0223849A1 (en) Super-computer system architectures.
JPS6315628B2 (en)
JPH0668040A (en) Queue control system for interprocessor communication
JPH11238042A (en) Decentralized simulation control unit
JPH03177953A (en) Data transfer system
JPH1185673A (en) Method and device for controlling shared bus
JPS61175834A (en) Data processor provided with microprogram debug function
JPH0318958A (en) Multiprocessor system
KR950008393B1 (en) Arbeiter delay circuit for multiprocessor system
JP2965133B2 (en) Processor system
JPH0586571B2 (en)
JPS6033654A (en) Inter-microprocessor data transferring system
JPH027099B2 (en)
JP3039918B2 (en) Processor system
JPS6095678A (en) Multi-processor system
JPH0573507A (en) Reliefing device in message communication between electronic computers
JPS62251829A (en) Symbolic processing system and method
JPH02171096A (en) Time synchronizing system for multi-processor exchange system
JPH01142846A (en) Cache memory control system for information processor
JPS5847743B2 (en) Inter-microprocessor communication control method
JPS62168231A (en) Data processor
Cai et al. 290 Transputer Research and Applications 6 S. Atkins and AS Wagner, Eds. IOS Press, 1993