JPH0644190A - Multi-processor system - Google Patents

Multi-processor system

Info

Publication number
JPH0644190A
JPH0644190A JP23337391A JP23337391A JPH0644190A JP H0644190 A JPH0644190 A JP H0644190A JP 23337391 A JP23337391 A JP 23337391A JP 23337391 A JP23337391 A JP 23337391A JP H0644190 A JPH0644190 A JP H0644190A
Authority
JP
Japan
Prior art keywords
message
processor
processors
transmitted
control
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
JP23337391A
Other languages
Japanese (ja)
Inventor
Takashi Yamazaki
高志 山▲崎▼
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.)
HOKKAIDO NIPPON DENKI SOFTWARE KK
NEC Solution Innovators Ltd
Original Assignee
HOKKAIDO NIPPON DENKI SOFTWARE KK
NEC Software Hokkaido Ltd
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 HOKKAIDO NIPPON DENKI SOFTWARE KK, NEC Software Hokkaido Ltd filed Critical HOKKAIDO NIPPON DENKI SOFTWARE KK
Priority to JP23337391A priority Critical patent/JPH0644190A/en
Publication of JPH0644190A publication Critical patent/JPH0644190A/en
Pending legal-status Critical Current

Links

Landscapes

  • Information Transfer Systems (AREA)
  • Multi Processors (AREA)

Abstract

PURPOSE:To enable transmitting plural messages at a time by providing a means which executes the buffering of a message transmitted and received between processors and also plural pairs of its control information in a message area so as to control them. CONSTITUTION:A system is constituted of the plural processors which are provided with an interruption issuing control part 2 which issues inter-program interruption to a issueing source, an interruption reception control part 3 which receives inter-processor interruption from another processor and a transmission side message control part 1 and a reception side message control part 4 which control the message area where the message and the control information transmitted and received between one of the issuing side processors and one of the reception side processors are stored. Moreover, the transmission side message control part 1 and the reception side message control part 4 execute the buffering of the message and the plural pairs of its control information which are transmitted and received between the processors in the message area so as to control them. Thus, the opening stand-by of the message area is eliminated so that plural messages can be transmitted at a time.

Description

【発明の詳細な説明】Detailed Description of the Invention

【0001】[0001]

【産業上の利用分野】本発明は、マルチプロセッサ情報
処理システムに利用する。特に、プロセッサ間通信手段
に関する。
The present invention is used in a multiprocessor information processing system. In particular, it relates to inter-processor communication means.

【0002】[0002]

【従来の技術】従来例では、図5に示すように、送信側
プロセッサと受信側プロセッサのメッセージエリアの関
係は一対一にあるので、一度に一回のメッセージしか送
信できなかった。そのために、メッセージが受信側で引
き取られない限りメッセージエリアは解放されず、メッ
セージを送信することができなかった。また、メッセー
ジエリア解放待ちによる時間や送信側および受信側でメ
ッセージのロギングをとるための処理時間等のプロセッ
サ間通信処理に多少なりとも時間を費やした。
2. Description of the Related Art In the conventional example, as shown in FIG. 5, since there is a one-to-one relationship between the message areas of the transmitting side processor and the receiving side processor, only one message can be transmitted at a time. Therefore, the message area was not released and the message could not be sent unless the message was picked up by the receiver. In addition, some time was spent on inter-processor communication processing such as waiting time for releasing the message area and processing time for logging messages on the transmitting side and the receiving side.

【0003】[0003]

【発明が解決しようとする課題】このように、従来例で
は一度に一つしかメッセージを送信できず、そのために
送信側プロセッサでメッセージエリアの解放待ちが少な
からず発生しており、また、システムでのプロセッサ間
通信の動作状態(コマンド、メッセージ詳細情報、シス
テムクロック等)の時間的推移を記録するために送受信
側プロセッサにメッセージのロギング処理を行う必要が
あり、多大な処理時間を費やしていた。
As described above, in the conventional example, only one message can be transmitted at a time, which causes a considerable amount of waiting for the message area to be released in the transmitting side processor. In order to record the temporal transition of the operating state (command, message detailed information, system clock, etc.) of the inter-processor communication of the above, it is necessary to perform message logging processing on the transmitting and receiving side processor, and a great deal of processing time was spent.

【0004】本発明は、このような欠点を除去するもの
で、一度に複数のメッセージの送信を可能にする手段を
もつマルチプロセッサ方式を提供することを目的とす
る。
The present invention eliminates such drawbacks, and an object of the present invention is to provide a multiprocessor system having means capable of transmitting a plurality of messages at one time.

【0005】[0005]

【課題を解決するための手段】本発明は、発行先へプロ
グラム間割込みを発行する割込み発行部と、他プロセッ
サからのプロセッサ間割込みを受信する割込み受信制御
部と、発行側プロセッサのひとつと受信側プロセッサの
ひとつとの間で授受されるメッセージおよびその制御情
報が格納されるメッセージエリアを管理するメッセージ
管理部とを備えた複数個のプロセッサで構成されたマル
チプロセッサ方式において、上記メッセージ管理部は、
上記メッセージエリアにプロセッサ間で授受されるメッ
セージおよびその制御情報の複数組をバッファリングし
て管理する手段を含むことを特徴とする。
According to the present invention, an interrupt issuing unit for issuing an inter-program interrupt to an issue destination, an interrupt receiving control unit for receiving an inter-processor interrupt from another processor, and one of the issuing side processors are provided. In a multiprocessor system composed of a plurality of processors including a message management unit that manages a message area in which a message transmitted and received to and from one of the side processors is stored, the message management unit is ,
It is characterized in that the message area includes means for buffering and managing a plurality of sets of messages transmitted and received between processors and their control information.

【0006】[0006]

【作用】発行側プロセッサのひとつと受信側プロセッサ
のひとつとの間で授受されるメッセージおよびその制御
情報が格納されるメッセージエリアをマルチバッファリ
ングする。これにより、メッセージエリアの開放待ちを
無くして一度に複数個のメッセージを送信することがで
きる。
A message area for storing a message transmitted and received between one of the issuing side processor and one of the receiving side processor and its control information is multi-buffered. This makes it possible to send a plurality of messages at once without waiting for the message area to be released.

【0007】[0007]

【実施例】以下、本発明一実施例を図面を参照して説明
する。図1は、この実施例を示す構成図である。この実
施例は送信側で、発行先へ送信するメッセージを格納す
るメッセージ管理部1と、発行先へプロセッサ間割込み
を発行する割込み発行制御部2と、受信側で、プロセッ
サ間割込みを受信する割込み受信制御部3と、送信され
たメッセージを引き取り処理する受信側メッセージ管理
部4とから構成される。すなわち、この実施例は、図1
に示すように、発行先へプログラム間割込みを発行する
割込み発行制御部2と、他プロセッサからのプロセッサ
間割込みを受信する割込み受信制御部3と、発行側プロ
セッサのひとつと受信側プロセッサのひとつとの間で授
受されるメッセージおよびその制御情報が格納されるメ
ッセージエリアを管理する送信側メッセージ管理部1お
よび受信側メッセージ管理部4とを備えた複数個のプロ
セッサで構成され、さらに、本発明の特徴とする手段と
して、送信側メッセージ管理部1および受信側メッセー
ジ管理部4は、上記メッセージエリアにプロセッサ間で
授受されるメッセージおよびその制御情報の複数組をバ
ッファリングして管理する手段を含む。
DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below with reference to the drawings. FIG. 1 is a block diagram showing this embodiment. In this embodiment, on the transmission side, a message management unit 1 for storing a message to be transmitted to an issuing destination, an interrupt issuing control unit 2 for issuing an interprocessor interrupt to the issuing destination, and an interrupt for receiving an interprocessor interrupt on the receiving side. The reception control unit 3 and the reception side message management unit 4 that receives and processes the transmitted message are configured. That is, this embodiment is similar to FIG.
, An interrupt issue control unit 2 for issuing an inter-program interrupt to an issue destination, an interrupt reception control unit 3 for receiving an inter-processor interrupt from another processor, one issuing processor and one receiving processor. And a receiving side message managing section 4 that manages a message area in which messages sent and received between the sending side and the control information thereof are stored. As a characteristic means, the transmission side message management section 1 and the reception side message management section 4 include means for buffering and managing a plurality of sets of messages and their control information exchanged between the processors in the message area.

【0008】図2は、この実施例のメッセージエリアの
構造を、図3は、送信側プロセッサの動作についての流
れ図を、図4は、受信側プロセッサの動作についての流
れ図を示す。次に、本実施例の操作について説明する。
FIG. 2 shows the structure of the message area of this embodiment, FIG. 3 shows a flow chart of the operation of the transmitting side processor, and FIG. 4 shows a flow chart of the operation of the receiving side processor. Next, the operation of this embodiment will be described.

【0009】プロセッサ間通信を行う場合に、送信側プ
ロセッサで相手プロセッサに送信するメッセージの個数
を求め(ステップS212)、対象プロセッサのメッセ
ージエリアのポインタを得る(ステップS213)。次
に、制御情報内の制御フラグをチェックする(ステップ
S214)。制御フラグがオンでなければ割込み発行制
御フラグをオン(ステップS215)にし、メッセージ
の格納等の処理(ステップS216〜ステップS21
7)を行い、メッセージエリアのポインタを更新する
(ステップS218)。送信メッセージの個数がゼロに
なるまで繰り返す。その後に受信側プロセッサに対して
通信要求を示すビットを通信要求テーブル(以下、P−
TBLという)にセット(ステップS220)し、プロ
セッサ間割込みを発行する(ステップS221)。制御
フラグがオンであれば、割込み発行制御フラグの状態に
よりプロセッサ間割込みの発行等が行われる。受信側プ
ロセッサでは、プロセッサ間割込み発生時に、P−TB
Lをリード(ステップS311)することにより通信要
求のあるプロセッサを知る。P−TBLから送信プロセ
ッサ番号を特定し(ステップS314)、対象プロセッ
サのメッセージエリアのポインタをリード(ステップS
316)する。メッセージエリアより情報を引取り、プ
ロセッサ間通信コマンドを実行する(ステップS318
〜ステップS320)。次に、メッセージエリアのポイ
ンタを更新し(ステップS321)、制御フラグがオフ
になるまでプロセッサ間通信コマンドを実行する。
When performing inter-processor communication, the number of messages to be transmitted to the partner processor is obtained by the transmitting processor (step S212), and the pointer of the message area of the target processor is obtained (step S213). Next, the control flag in the control information is checked (step S214). If the control flag is not on, the interrupt issue control flag is turned on (step S215), and processing such as message storage (steps S216 to S21) is performed.
7) is performed to update the pointer in the message area (step S218). Repeat until the number of sent messages reaches zero. After that, a bit indicating a communication request to the receiving processor is added to the communication request table (hereinafter, P-
TBL) (step S220) and issue an inter-processor interrupt (step S221). If the control flag is on, the inter-processor interrupt is issued depending on the state of the interrupt issue control flag. At the receiving processor, when an inter-processor interrupt occurs, P-TB
By reading L (step S311), the processor having the communication request is known. The transmission processor number is specified from the P-TBL (step S314), and the pointer of the message area of the target processor is read (step S314).
316). Information is taken from the message area and the inter-processor communication command is executed (step S318).
-Step S320). Next, the pointer in the message area is updated (step S321), and the interprocessor communication command is executed until the control flag is turned off.

【0010】[0010]

【発明の効果】本発明は、以上説明したように、メッセ
ージエリアをマルチバッファリングすることにより送信
側からのメッセージエリアの解放待ちを無くし、また、
一度に複数個のメッセージを送信できる効果がある。そ
れに加え、メッセージエリア情報が自動的にロギング情
報になるので、メッセージのロギングをする必要がな
く、プロセッサ間通信処理性能の向上が図られる効果が
ある。
As described above, the present invention eliminates the waiting for the release of the message area from the sending side by multi-buffering the message area, and
The effect is that multiple messages can be sent at one time. In addition, since the message area information automatically becomes logging information, it is not necessary to log the message, and the inter-processor communication processing performance can be improved.

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

【図1】本発明実施例の構成を示すブロック構成図。FIG. 1 is a block configuration diagram showing a configuration of an embodiment of the present invention.

【図2】本発明実施例のメッセージエリアの構成を示す
図。
FIG. 2 is a diagram showing the structure of a message area according to the embodiment of the present invention.

【図3】本発明実施例の動作を示すフローチャート。FIG. 3 is a flowchart showing the operation of the embodiment of the present invention.

【図4】本発明実施例の動作を示すフローチャート。FIG. 4 is a flowchart showing the operation of the embodiment of the present invention.

【図5】従来例のメッセージエリアの構成を示す図。FIG. 5 is a diagram showing a configuration of a message area of a conventional example.

【符号の説明】[Explanation of symbols]

1 送信側メッセージ管理部 2 割込み発行制御部 3 割込み受信制御部 4 受信側メッセージ管理部 1 Sending side message management section 2 Interrupt issuing control section 3 Interrupt receiving control section 4 Receiving side message management section

Claims (1)

【特許請求の範囲】[Claims] 【請求項1】 発行先へプログラム間割込みを発行する
割込み発行部と、他プロセッサからのプロセッサ間割込
みを受信する割込み受信制御部と、発行側プロセッサの
ひとつと受信側プロセッサのひとつとの間で授受される
メッセージおよびその制御情報が格納されるメッセージ
エリアを管理するメッセージ管理部とを備えた複数個の
プロセッサで構成されたマルチプロセッサ方式におい
て、 上記メッセージ管理部は、上記メッセージエリアにプロ
セッサ間で授受されるメッセージおよびその制御情報の
複数組をバッファリングして管理する手段を含むことを
特徴とするマルチプロセッサ方式。
1. An interrupt issuing unit that issues an inter-program interrupt to an issue destination, an interrupt reception control unit that receives an inter-processor interrupt from another processor, and one of the issuing processor and one of the receiving processors. In a multiprocessor system including a plurality of processors having a message management unit that manages a message area in which messages to be transmitted and received and control information thereof are stored, the message management unit is provided in the message area between the processors. A multiprocessor system including means for buffering and managing a plurality of sets of messages to be transmitted and received and control information thereof.
JP23337391A 1991-09-12 1991-09-12 Multi-processor system Pending JPH0644190A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP23337391A JPH0644190A (en) 1991-09-12 1991-09-12 Multi-processor system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP23337391A JPH0644190A (en) 1991-09-12 1991-09-12 Multi-processor system

Publications (1)

Publication Number Publication Date
JPH0644190A true JPH0644190A (en) 1994-02-18

Family

ID=16954099

Family Applications (1)

Application Number Title Priority Date Filing Date
JP23337391A Pending JPH0644190A (en) 1991-09-12 1991-09-12 Multi-processor system

Country Status (1)

Country Link
JP (1) JPH0644190A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8058553B2 (en) 2009-12-25 2011-11-15 Kabushiki Kaisha Toshiba Electronic device
US9183817B2 (en) 2013-08-27 2015-11-10 Leto R&D Corporation Reed affixing device for wind instruments

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8058553B2 (en) 2009-12-25 2011-11-15 Kabushiki Kaisha Toshiba Electronic device
US9183817B2 (en) 2013-08-27 2015-11-10 Leto R&D Corporation Reed affixing device for wind instruments

Similar Documents

Publication Publication Date Title
US6711643B2 (en) Method and apparatus for interrupt redirection for arm processors
US6247091B1 (en) Method and system for communicating interrupts between nodes of a multinode computer system
JP2005182754A (en) Inter-process communication mechanism
JPH0772889B2 (en) Information processing system
JPH0425960A (en) Mutual communication system in multi-processor system
JP3322754B2 (en) Parallel computer
US5901328A (en) System for transferring data between main computer multiport memory and external device in parallel system utilizing memory protection scheme and changing memory protection area
US6578115B2 (en) Method and apparatus for handling invalidation requests to processors not present in a computer system
CN113590362A (en) Inter-process message processing method and device, electronic equipment and storage medium
JPH0644190A (en) Multi-processor system
GB2409302A (en) Data Communication Mechanism
JP2539436B2 (en) Communication method between processors
JPH05257796A (en) Distributed and shared memory managing system
JP3252464B2 (en) Virtual computer system
JP3443787B2 (en) Autonomous decentralized plant control man-machine device
JP2812274B2 (en) Transaction load balancing system for loosely coupled multi-computer systems
JPH01261766A (en) Data communication system
JP2699604B2 (en) Bus connection device
KR101371506B1 (en) Method for dead-lock avoidance for 2-processor data communication system
JPH0346052A (en) Inter-processor communication method
KR100693601B1 (en) Apparatus and method for transceiving a data between the processors
JPH10232825A (en) Cache memory control system
JPH02118841A (en) Input queue control system
JPH06149753A (en) Semaphore control method
JPH03252851A (en) Inter-processor communication system