JPS6232561A - Control system for multiprocessor system - Google Patents

Control system for multiprocessor system

Info

Publication number
JPS6232561A
JPS6232561A JP17120585A JP17120585A JPS6232561A JP S6232561 A JPS6232561 A JP S6232561A JP 17120585 A JP17120585 A JP 17120585A JP 17120585 A JP17120585 A JP 17120585A JP S6232561 A JPS6232561 A JP S6232561A
Authority
JP
Japan
Prior art keywords
message
processor
area
interrupt
communication area
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
JP17120585A
Other languages
Japanese (ja)
Inventor
Tetsuo Yano
矢野 哲雄
Takayoshi Hanabusa
英 隆義
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.)
Mitsubishi Electric Corp
Original Assignee
Mitsubishi Electric 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 Mitsubishi Electric Corp filed Critical Mitsubishi Electric Corp
Priority to JP17120585A priority Critical patent/JPS6232561A/en
Publication of JPS6232561A publication Critical patent/JPS6232561A/en
Pending legal-status Critical Current

Links

Landscapes

  • Multi Processors (AREA)

Abstract

PURPOSE:To improve the processing capability of the entire system by disposing a message-communication area on the two-port memory of respective processors. CONSTITUTION:In the communication areas C12-C32 of CPUs 1-3 a flag 101 indicates that a message from a message-issuing processor of the CPUs 1-3 is being processed or that the message is already processed, and a message area 102 stores an notification information from the issuing processor. Accordingly, an access to the memory from inside the processor is made possible, and the compitition for the common bus signal line is decreased, and an inter- processor message exchange is made possible.

Description

【発明の詳細な説明】 〔産業上の利用分野〕 この発明は、マルチプロセッサ間で情報交換が行なわれ
るマルチプロセッサシステムの制御方式%式% 〔従来の技術〕 第6図は1例えば特開昭55−39908号公報に示さ
れた従来の制御方式を示すものと同等のブロック図であ
り、図において1〜3は+1〜÷3のCPU、4は共通
バス信号線、5は共有メモリで、C12,C13,C2
1,C23,C31゜C32はこの共有メモリ5内にお
いて上記CPU1〜3の各プロセッサ間情報交換のため
の交信領域ヲ示している。6は各プロセッサ間を相互に
結合した単一割込要求信号である。
[Detailed Description of the Invention] [Industrial Field of Application] This invention relates to a control method for a multiprocessor system in which information is exchanged between multiprocessors. [Prior Art] FIG. This is a block diagram equivalent to that showing the conventional control method shown in Publication No. 55-39908, and in the figure, 1 to 3 are +1 to ÷3 CPUs, 4 is a common bus signal line, 5 is a shared memory, C12, C13, C2
Reference numerals 1, C23, C31 and C32 indicate communication areas within the shared memory 5 for exchanging information between the respective processors of the CPUs 1 to 3. 6 is a single interrupt request signal that interconnects each processor.

次に動作について第6図を参照しながら説明する。まず
+1のCPUIより+2のCPU2に通知すべき要因が
発生したものとする。◆1のCPU1は通知情報を共有
メモリ5の交信領域C21に書込み、この領域内のとジ
−フラグ、すなわち交信領域C21のメツセージが未処
理であることを示すフラグをセットする。その後、割込
要求を行なうため、割込要求線6に割込要求信号を出力
する。ここで+2のCPU2はこの割込入力により割込
処理として以下の動作を行なう。まず、交信領域C21
の内容をチェックし、ナ1のCPUIからの情報通知有
無を判定する。ここで、この従来例では+1のCPUI
からの情報が有るためこの情報を取込み、内容に応じた
処理を行なう。この場合、他のCPUI乃至3に対して
も割込入力が行なわれるため、各プロセッサは自分あて
の交信領域をチェックし、CPUI乃至3のプロセッサ
からのメツセージ有無を判定する。例えば、+3のCP
U3は交信領域C31,C32の内容をチェックし、例
えば自分あてのメツセージが無い場合は無効処理を行な
う。
Next, the operation will be explained with reference to FIG. First, it is assumed that a factor has occurred that should be notified from the +1 CPUUI to the +2 CPU2. ◆The CPU 1 writes notification information to the communication area C21 of the shared memory 5, and sets a toggle flag in this area, that is, a flag indicating that the message in the communication area C21 is unprocessed. Thereafter, an interrupt request signal is output to the interrupt request line 6 in order to issue an interrupt request. Here, the +2 CPU 2 performs the following operations as interrupt processing in response to this interrupt input. First, communication area C21
, and determines whether information has been notified from the CPU of Na1. Here, in this conventional example, +1 CPU
Since there is information from , this information is taken in and processing is performed according to the content. In this case, since interrupt input is also made to the other CPUs 3 to 3, each processor checks the communication area addressed to itself and determines whether there is a message from the processors 3 to 3. For example, +3 CP
U3 checks the contents of the communication areas C31 and C32, and performs invalidation processing if, for example, there is no message addressed to itself.

〔発明が解決しようとする問題点〕[Problem that the invention seeks to solve]

従来のマルチプロセッサシステムの制御方式は以上のよ
うに構成されているので、各CPUはそのつど共有メモ
リ5の領域をチェックしなければならず、さらに自分あ
てのメツセージ通知でなくても毎回割込発生毎に共有メ
モリの領域にアクセスすることが必要となる。このため
、共有バス信号線4の競合によるオーバーヘッドが増加
し、並びに不要な無効処理が実行されるという問題点が
あった。
Since the conventional multiprocessor system control method is configured as described above, each CPU must check the area of the shared memory 5 each time, and furthermore, it is necessary to interrupt each time even if the message notification is not addressed to itself. It is necessary to access an area of shared memory for each occurrence. Therefore, there are problems in that overhead due to contention on the shared bus signal line 4 increases and unnecessary invalidation processing is executed.

この発明は上記のような問題点を解消するためになされ
たもので、共有バス信号線の負荷を低減させると共に、
不要な無効処理を解消することができるマルチプロセッ
サシステムの制御方式を得ることを目的とする。
This invention was made to solve the above-mentioned problems, and it reduces the load on the shared bus signal line, and
The purpose of this invention is to obtain a control method for a multiprocessor system that can eliminate unnecessary invalid processing.

〔問題点を解決するための手段〕[Means for solving problems]

この発明に係るマルチプロセッサシステムの制御方式は
、プロセッサ間メツセージ交信領域を各プロセッサの2
ポートメモリ領域に配置し、さらにメツセージ通知時に
相手プロセッサに対してだけ割込みを発生させるだめの
割込要求回路を各プロセッサ内に備えたものである。
The control method for the multiprocessor system according to the present invention controls the inter-processor message communication area between two of each processor.
Each processor is provided with an interrupt request circuit located in the port memory area and for generating an interrupt only to the other processor when a message is notified.

〔作用〕[Effect]

この発明におけるメツセージ交信領域は、2ポートメモ
リ領域に配置されることにより、プロセッサ内からのメ
モリアクセスが可能となり共有バス信号線の競合を減少
させ、プロセッサ間のメツセージ交換を可能とする。
The message communication area in the present invention is arranged in a two-port memory area, thereby allowing memory access from within the processor, reducing contention on the shared bus signal line, and enabling message exchange between processors.

〔実施例〕〔Example〕

以下、この発明の一実施例を図について説明する。第1
図において−1〜3は÷1〜◆3のCPU、4は共有バ
ス信号線、7〜9は各CPUI〜3内に設けられた割込
要求回路である。第2図は各CPUI〜3の交信領域C
12〜C32の内容を示すもので7ラグ101はメツセ
ージ発行元プロセッサであるCPUI乃至3からのメツ
セージが処理中か、または処理済みであるかを示し、メ
ツセージ領域102は、発行元プロセッサからの通知情
報が格納される。第4図は上記割込要求回路7乃至9の
一例を示す詳細構成図であり1図において201は設定
スイッチ、202はアドレス一致回路、203はAND
回路である。
An embodiment of the present invention will be described below with reference to the drawings. 1st
In the figure, -1 to 3 are CPUs divided by 1 to ◆3, 4 is a shared bus signal line, and 7 to 9 are interrupt request circuits provided in each CPU I to 3. Figure 2 shows the communication area C of each CPUI~3.
12 to C32. A 7 lag 101 indicates whether a message from CPUI to 3, which is a message issuing processor, is being processed or has been processed, and a message area 102 indicates a notification from an issuing processor. Information is stored. FIG. 4 is a detailed configuration diagram showing an example of the interrupt request circuits 7 to 9. In FIG. 1, 201 is a setting switch, 202 is an address matching circuit, and 203 is an AND
It is a circuit.

次に上記実施例の動作を図について説明する、第1図に
おいて、ナ1のCPUIから+2のCPU2に情報を通
知すべき状態になったとする。この時す1のCPUIは
、第3図のフローチャートで示すよう和、+2のCPU
2の2ポートメモリ上の交信領域C21のフラグ101
をチェックしくステップ301)、7ラグ101がセッ
トされていなければ、当該フラグ101をセットしくス
テップ302)、交信領域C21のメツセージ領域10
2に情報を書込み(ステップ303)、その後÷2のC
PU2に割込要求を行なう(ステップ304)。この割
込要求は、第4図のブロック図で示される割込要求回路
7乃至9により出力される。+1のCPUIが実行する
割込命令(OUT命令の実行)により+2のCPU2を
指定する。
Next, the operation of the above-mentioned embodiment will be explained with reference to the drawings. In FIG. 1, it is assumed that a state is reached in which information should be notified from the CPU 1 of Na1 to the CPU 2 of +2. At this time, the CPU of S1 is the sum of +2 CPU as shown in the flowchart of Figure 3.
Flag 101 of the communication area C21 on the 2-port memory of No.2
If the 7lag 101 is not set, set the flag 101 (step 302), the message area 10 of the communication area C21.
2 (step 303), then ÷2 C
An interrupt request is made to PU2 (step 304). This interrupt request is output by interrupt request circuits 7 to 9 shown in the block diagram of FIG. The +2 CPU2 is specified by the interrupt instruction (execution of the OUT instruction) executed by the +1 CPU.

第4図において、設定スイッチ201には上記指定値に
等しい値が設定されているため−◆2のCPU2のみが
割込命令をデコードして割込みを発生させる。設定スイ
ッチ201は、他のCPU1.3には別のユニークな値
が設定されている。
In FIG. 4, since a value equal to the specified value is set in the setting switch 201, only the CPU 2 of -◆2 decodes the interrupt instruction and generates an interrupt. The setting switch 201 is set to a different unique value for the other CPUs 1.3.

従って、CPUI、3には割込みが発生しない。Therefore, no interrupt occurs to CPUI,3.

割込の発生したす2のCPU2は、第5図のフローチャ
ートに示す割込処理を実行する。まず交信領域C21の
フラグ101をチェックしくステップ401)、セット
されていれば、す1のCPU1からの通知があったこと
を示すため交信領域C21のメツセージを取込み(ステ
ップ402)、メツセージ内容に基づいた処理を行なう
(ステップ403)。その後、交信領域C21のフラグ
101をリセットする(ステップ404)こと九より再
び+1のCPU1からのメツセージを受信可能としてお
く。なお、続けて交信領域C23のフラグチェックを行
ない(ステップ405)、ナ3のCPU3からのメツセ
ージがあれば同様に処理(ステップ406〜408)を
行なう。
When the interrupt occurs, the CPU 2 executes the interrupt process shown in the flowchart of FIG. First, the flag 101 in the communication area C21 is checked (step 401), and if it is set, the message in the communication area C21 is fetched to indicate that there has been a notification from the CPU 1 in step 1 (step 402), and based on the message content. Then, processing is performed (step 403). Thereafter, the flag 101 in the communication area C21 is reset (step 404), thereby making it possible to receive a message from the +1 CPU1 again from 9 onwards. Incidentally, the flag of the communication area C23 is subsequently checked (step 405), and if there is a message from the CPU 3 of the CPU 3, the same processing is performed (steps 406 to 408).

なお、上記実施例ではCPUを3台備えた場合について
示したが、さらに多くのプロセッサが共有バス信号線4
に接続されていても良く、相手プロセッサ毎にメツセー
ジ交信領域を持つようにしてもよい。
Note that although the above embodiment shows the case where three CPUs are provided, more processors are connected to the shared bus signal line 4.
Alternatively, each partner processor may have its own message communication area.

〔発明の効果〕〔Effect of the invention〕

以上のように、この発明によればメツセージ交信領域を
各プロセッサの2ポートメモリ上に配置して構成したの
で、共有バスの競合を防ぐことができ、またプロセッサ
間の割込要求を共有バス信号として持たず、プロセッサ
内の割込要求回路で実現でき、個別に割込通知を行なう
ことが可能となり、無意な割込処理を実行する必要がな
くなり、システム全体の処理能力が向上するという効果
がある。
As described above, according to the present invention, since the message communication area is arranged on the two-port memory of each processor, contention on the shared bus can be prevented, and interrupt requests between processors can be transmitted using the shared bus signal. It can be realized by the interrupt request circuit in the processor without having to have it as an interrupt request circuit, and it is possible to notify interrupts individually, eliminating the need to execute unexpected interrupt processing, and improving the processing capacity of the entire system. be.

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

第1図はこの発明の一実施例によるブロック図、第2図
はこの発明におけるメツセージ形式を示す状態図、第3
図はこの発明の一実施例を説明するためのフローチャー
ト、第4図は第1図の割込要求回路5乃至9の詳細を説
明するための詳細構成図、第5図はこの発明の一実施例
を説明するためのフローチャート、第6図は従来の制御
方式のブロック図である。 1〜3はCPU(プロセッサ)、7〜9は割込要求回路
部、C12,C13,C21,C23゜C31,C32
は交信領域(メツセージ交換領域)である。 なお、各図中、同一符号は同一、又は相当部分を示す。
FIG. 1 is a block diagram according to an embodiment of the present invention, FIG. 2 is a state diagram showing a message format in this invention, and FIG.
4 is a detailed configuration diagram for explaining details of the interrupt request circuits 5 to 9 in FIG. 1, and FIG. 5 is an embodiment of the invention. A flowchart for explaining an example, and FIG. 6 is a block diagram of a conventional control method. 1 to 3 are CPUs (processors), 7 to 9 are interrupt request circuit units, C12, C13, C21, C23° C31, C32
is a communication area (message exchange area). In each figure, the same reference numerals indicate the same or equivalent parts.

Claims (1)

【特許請求の範囲】[Claims] 共通バス信号線に結合される複数のプロセッサを有する
マルチプロセッサシステムの制御方式において、前記各
プロセッサ間のメッセージ交換領域を該各プロセッサの
2ポートメモリ領域に配置とするとともに、前記各プロ
セッサ内に割り込みを発生する割込要求回路を夫々備え
、前記各プロセッサ間の情報交換を、該各プロセッサ上
の2ポートメモリを交信領域として行ない、かつこの交
信領域に伝達情報を予め書き込んだ後に前記割込要求回
路から相手プロセッサに割込要求を発生して行なうよう
にしたことを特徴とするマルチプロセッサシステムの制
御方式。
In a control method for a multiprocessor system having a plurality of processors connected to a common bus signal line, a message exchange area between the processors is arranged in a 2-port memory area of each processor, and an interrupt is generated in each processor. The two-port memory on each processor is used as a communication area to exchange information between the respective processors, and after writing the transmission information in this communication area in advance, the interrupt request circuit generates an interrupt request circuit. A control method for a multiprocessor system characterized in that an interrupt request is generated from a circuit to a partner processor.
JP17120585A 1985-08-05 1985-08-05 Control system for multiprocessor system Pending JPS6232561A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP17120585A JPS6232561A (en) 1985-08-05 1985-08-05 Control system for multiprocessor system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP17120585A JPS6232561A (en) 1985-08-05 1985-08-05 Control system for multiprocessor system

Publications (1)

Publication Number Publication Date
JPS6232561A true JPS6232561A (en) 1987-02-12

Family

ID=15918971

Family Applications (1)

Application Number Title Priority Date Filing Date
JP17120585A Pending JPS6232561A (en) 1985-08-05 1985-08-05 Control system for multiprocessor system

Country Status (1)

Country Link
JP (1) JPS6232561A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS63255760A (en) * 1987-04-14 1988-10-24 Mitsubishi Electric Corp Control system

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS63255760A (en) * 1987-04-14 1988-10-24 Mitsubishi Electric Corp Control system

Similar Documents

Publication Publication Date Title
US6789183B1 (en) Apparatus and method for activation of a digital signal processor in an idle mode for interprocessor transfer of signal groups in a digital signal processing unit
JPS6232561A (en) Control system for multiprocessor system
JP2000298652A (en) Multiprocessor
JPS5925258B2 (en) processor control system
JPH056333A (en) Multi-processor system
JPH0342762A (en) Inter-processor communication method for multiprocessor system
JPS6240565A (en) Memory control system
JPH0314136A (en) Mutual diagnostic system for microprocessor system
JPS61264467A (en) Control system for multi-processor system
KR100208281B1 (en) Peripheral processor in the switching system
JPS63201854A (en) Address converting buffer invalidating system
JPH0215152Y2 (en)
KR100253790B1 (en) Method of interface for controller board in medium and large computer
JP2504515B2 (en) Test channel instruction execution control method
JPS61208160A (en) Dual processor system using common bus
JPS633358A (en) Multiprocessor
JPH0232432A (en) Control system for dual port memory
JPH05108553A (en) Bus coupling device
JPH05342026A (en) Multiprocessor and synchronization control system for multiprocessor
JPS62266639A (en) Interface device for input/output device
JPH01319849A (en) Interrupting circuit
JPS63128464A (en) Processor circuit
JPS6322676B2 (en)
JPH03100853A (en) Inter-processor communication system
JPH022179B2 (en)