JPS5971559A - Signal arbitorating device - Google Patents

Signal arbitorating device

Info

Publication number
JPS5971559A
JPS5971559A JP18232782A JP18232782A JPS5971559A JP S5971559 A JPS5971559 A JP S5971559A JP 18232782 A JP18232782 A JP 18232782A JP 18232782 A JP18232782 A JP 18232782A JP S5971559 A JPS5971559 A JP S5971559A
Authority
JP
Japan
Prior art keywords
processor
resource
signal
circuits
circuit
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
JP18232782A
Other languages
Japanese (ja)
Inventor
Tetsuo Omiya
大宮 哲夫
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.)
NEC Corp
Original Assignee
NEC Corp
Nippon Electric Co 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 NEC Corp, Nippon Electric Co Ltd filed Critical NEC Corp
Priority to JP18232782A priority Critical patent/JPS5971559A/en
Publication of JPS5971559A publication Critical patent/JPS5971559A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F13/00Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
    • G06F13/14Handling requests for interconnection or transfer
    • G06F13/36Handling requests for interconnection or transfer for access to common bus or bus system
    • G06F13/368Handling requests for interconnection or transfer for access to common bus or bus system with decentralised access control
    • G06F13/372Handling requests for interconnection or transfer for access to common bus or bus system with decentralised access control using a time-dependent priority, e.g. individually loaded time counters or time slot

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Multi Processors (AREA)

Abstract

PURPOSE:To allow a processor making the highest request to use a resource, by increasing the pulse frequency given to a counter circuit of each processor and processing the pulse, every time there comes request of use of the information resource from plural processors. CONSTITUTION:When the processors PC100-N00 make the request of use of the information resource asynchronizingly, a resource request signal is transmitted to individual control sections 130-N30 and a pulse of an oscillating circuit 30 is applied to counter circuits 110-N10. A common control section 20 operates a maximum value detecting circuit 10 at the same time, the circuit 10 detects the highest pulse number from the circuits 110-N10, gives the value to comparison circuits 120-N20 so as to compare this value with the value from the circuits 110-N10. A coincidence signal is given to one of the individual control section 130-N30 from the comparison circuits among the circuits 120-N20, where the both are coincident signal, and a resource use allowing signal is given from its control section to the processor.

Description

【発明の詳細な説明】 本発明は情報処理システムに関するものであり、特に複
数個の互いに独立な信号源から同一の情報資源に向って
非同期的に競争して信号が発生する場合を信号源におい
て最も多くの信号を出した信号源に対し優先的にして、
次々に順番に各信号を当該情報資源に伝え、又情報資源
からその応答信号を当該信号源に伝える機能を有する信
号調停器に関するものである。
DETAILED DESCRIPTION OF THE INVENTION The present invention relates to an information processing system, and particularly relates to a signal source in which signals are generated asynchronously from a plurality of mutually independent signal sources competing for the same information resource. Give priority to the signal source that outputs the most signals,
The invention relates to a signal arbiter having the function of sequentially transmitting each signal to the relevant information resource and transmitting a response signal from the information resource to the relevant signal source.

並列情報処理システムにおいては互いに全く独立して動
く複数個のプロセンサがメモリや工10装置等の情報資
源を共有して使用する。そのためいたる所で一つの情報
資源に対して二個以上のプロセッサからの使用要求が発
生する局面が生まれ要求信号の衝突が起こる。
In a parallel information processing system, a plurality of processors that operate completely independently of each other share and use information resources such as memory and equipment. As a result, there are situations in which two or more processors request the use of one information resource, resulting in collisions of request signals.

特に近年大型化されたシステムにおいてはこの様な局面
が随所にみられシステムの効率向上のためには、資源割
当て問題は最も重要な問題の一つとなっている。従来こ
の種の方式としては、各プロセッサの間に特定の優先度
を与えるポーリング方式あるいはディジーチェーン方式
、又最も早く要求を出したプロセッサに最初の使用を認
めるインターロック方式等があり、それぞれにその効果
の有効性が確かめられている。
Particularly in systems that have grown larger in recent years, such situations are often seen everywhere, and resource allocation has become one of the most important issues in order to improve system efficiency. Conventional methods of this type include polling methods or daisy chain methods that give specific priority to each processor, and interlock methods that grant first use to the processor that made the earliest request. The effectiveness of the effect has been confirmed.

本発明の目的はこの様に複数個の要求信号が非同期的に
競争して発生する場合、各信号の過去の発生回数いわゆ
る過去の履歴を調べ、最も早くかつ、最も多くの信号を
発生した信号源に対し資源使用の認知信号を与えて各信
号源の要求を処理するアルゴリズムを簡弔なハードウェ
アによって提供することにある。
The purpose of the present invention is to investigate the number of past occurrences of each signal, so-called past history, when a plurality of request signals are generated in competition with each other asynchronously as described above, and select the signal that generated the earliest and most signals. The object of the present invention is to provide an algorithm using simple hardware to process the requests of each signal source by giving a resource usage recognition signal to the source.

本発明の信号調停器は、複数個の互いに独立なプロセッ
サから同一の情報資源に向って非同期的に競争して前記
情報資源を獲得するシステムにおいて、前記プロセッサ
から前記情報資源に使用要求のある毎に前記各プロセッ
サ(C対応して配置される計数回路に供給されるパルス
の周波数を増加する手段と、前記複数の計数回路の内奄
大値を示すところのプロセッサに対し前記情報資源の使
用許可を与える手段とを有する。
In a system in which a plurality of mutually independent processors asynchronously compete for the same information resource and obtain the same information resource, the signal arbitrator of the present invention provides a signal arbitrator whenever there is a request from the processor to use the information resource. means for increasing the frequency of pulses supplied to counting circuits arranged corresponding to each of the processors (C); and permission to use the information resource to a processor that indicates the maximum value among the plurality of counting circuits. and a means for giving.

以下に本発明を図面を用いて詳細に説明する。The present invention will be explained in detail below using the drawings.

第1図は本発明の一実施例の構成を示すブロック図であ
り、第2図はとの実施例を説明するだめのタイムチャー
トである。
FIG. 1 is a block diagram showing the configuration of an embodiment of the present invention, and FIG. 2 is a time chart for explaining the embodiment.

まず1各ブロツクの機能と動作の概要を説明する。第1
図において100〜NOOはプロセッサを表わす。
First, an overview of the functions and operations of each block will be explained. 1st
In the figure, 100 to NOO represent processors.

プロセッサは互いに独立して非同期式に資源(図示せず
)を要求するものとする。30は発振回路である。発振
回路30は複数の異なる周波数のクロック信号を発する
ものであり、これらのクロック信号は各個別制御部13
0〜N30で選択されて計数回路110〜NIOを駆動
する。110〜N 10は計数回路であり、プロセッサ
100〜NOOの資源要求信号に対し発振回路30のク
ロック信号の供給を受けこれを計数するものである。
It is assumed that the processors request resources (not shown) independently of each other and asynchronously. 30 is an oscillation circuit. The oscillation circuit 30 emits a plurality of clock signals of different frequencies, and these clock signals are transmitted to each individual control section 13.
0 to N30 to drive the counting circuits 110 to NIO. Counting circuits 110 to N10 receive and count the clock signals of the oscillation circuit 30 in response to the resource request signals of the processors 100 to NOO.

最大値検出回路10は計数回路110〜NIOが示す値
の中から最大値を検出するものであり最大値検出回路1
0かも出力された値は、比較回路120〜N20に伝達
され計数回路110〜NIOの値と比較される。
The maximum value detection circuit 10 detects the maximum value from among the values indicated by the counting circuit 110 to NIO.
The output value of 0 is transmitted to comparison circuits 120 to N20 and compared with the values of counting circuits 110 to NIO.

従って最大値検出回路10の値と一致する計数回路に接
続されるプロセッサに資源使用権が与えられる。すなわ
ち最も多くの資源要求を行ったプロセッサが資源の使用
の許可を得る事である0個別制御部130〜N30はプ
ロセッサ100〜NOOの資源要求信号を受けつけると
、発振回路30のクロック信号のより高い周波数のクロ
ックを選択して計数回路110〜NIOに供給する機能
と、最大値検出回路10から送られてくる値と計数回路
110〜NIOの値が一致すると計数回路をリセットし
対応するプロセッサに資源許可信号を送ったり%資源要
求ライン40を介して共通制御部20に資源要求信号を
伝達する機能を有する。
Therefore, the right to use the resource is given to the processor connected to the counting circuit whose value matches the value of the maximum value detection circuit 10. In other words, the processor that has requested the most resources obtains permission to use the resource. When the 0 individual control units 130 to N30 receive the resource request signals from the processors 100 to NOO, the clock signal of the oscillation circuit 30 is set to a higher level. The function selects a frequency clock and supplies it to the counting circuit 110 to NIO, and when the value sent from the maximum value detection circuit 10 and the value of the counting circuit 110 to NIO match, the counting circuit is reset and resources are sent to the corresponding processor. It has a function of sending permission signals and transmitting resource request signals to the common control unit 20 via the resource request line 40.

共通制御部20は、各個別制御部130〜N30から送
信される資源要求信号を受信すると最大値検出回路10
の動作を停止させたり、個別制御部130〜N30に対
して計数回路110〜N10の動作指示を行なわせる様
態を有す。
When the common control unit 20 receives the resource request signal transmitted from each of the individual control units 130 to N30, the common control unit 20 activates the maximum value detection circuit 10.
, or instructs individual control units 130 to N30 to operate counting circuits 110 to N10.

次に実際の動作な説明する。Next, the actual operation will be explained.

説明を容易にするため3台のプロセッサ(プロセッサ1
00.プロセッサ200.プロセッサ300)が独立し
て一つの資源を要求した場合を説明する。今プロセッサ
100が最初に資源要求を行ったとしよう。プロセッサ
iooが資源要求を行うと資源要求信号は個別制御部1
30に伝達され計数回路110に発振回路30のクロッ
ク1が供給される。との際プロセッサ200及びプロセ
ッサ300からは資源要求がなされていないため共通制
御部20は最大値検出回路10を動作させる。最大値検
出回路10は計数回路110、計数回路210、計数回
路310の中の最大値を示す値を検出する。最大値検出
回路10では計数回路110が示している値を各比較回
路120.220゜320に転送する。各比較回路12
0,220゜230では前記比較回路に対応する計数回
路110゜210.310の値と比較され、比較回路1
20で一致信号が得られる。比較回路120から出力さ
れる。一致信号は個別制御部130に伝達され個別制御
部130からプロセッサ100に資源許可信号が送られ
る。比較動作が終了すると共通制御部20から個別制御
部130,230,330に対し計数開始指示が行なわ
れる。プロセッサ100に資源使用の許可が与えられる
と個別制御部130からは共通制御部20に対し資源要
求信号が伝達され資源の使用が行なわれる。共通制御部
20はプロセッサ100から資源要求信号が送信されて
いる間プロセッサ100にのみ資源許可信号を送シ続け
る。
For ease of explanation, three processors (processor 1
00. Processor 200. A case will be explained in which the processor 300) requests one resource independently. Suppose now that processor 100 makes a resource request for the first time. When processor ioo makes a resource request, the resource request signal is sent to the individual control unit 1.
30 and the clock 1 of the oscillation circuit 30 is supplied to the counting circuit 110. In this case, since no resource requests are made from the processors 200 and 300, the common control unit 20 operates the maximum value detection circuit 10. The maximum value detection circuit 10 detects a value indicating the maximum value among the counting circuit 110, the counting circuit 210, and the counting circuit 310. The maximum value detection circuit 10 transfers the value indicated by the counting circuit 110 to each comparison circuit 120, 220°, 320. Each comparison circuit 12
At 0.220°230, it is compared with the value of the counting circuit 110°210.310 corresponding to the comparison circuit, and the comparison circuit 1
A coincidence signal is obtained at 20. It is output from the comparison circuit 120. The coincidence signal is transmitted to the individual controller 130, and the individual controller 130 sends a resource grant signal to the processor 100. When the comparison operation is completed, the common control unit 20 instructs the individual control units 130, 230, and 330 to start counting. When the processor 100 is granted permission to use the resource, the individual control unit 130 transmits a resource request signal to the common control unit 20, and the resource is used. The common control unit 20 continues to send the resource grant signal only to the processor 100 while the resource request signal is being sent from the processor 100.

この間計数回路210及び310は、プロセッサ200
及びプロセッサ300の資源要求信号を逐次計数できる
状態である。プロセッサ100の使用が終了するとプロ
セッサ100から共通制御部20に出されていた資源要
求信号の送信が停止し、それに伴い共通制御部20から
プロセンサ100に送信されていた資源許可信号が停止
しさらに最大値検出回路10が動作を開始する。
During this time, the counting circuits 210 and 310 are connected to the processor 200.
and a state in which the resource request signals of the processor 300 can be counted sequentially. When the use of the processor 100 is finished, the transmission of the resource request signal sent from the processor 100 to the common control unit 20 stops, and accordingly, the resource permission signal sent from the common control unit 20 to the processor 100 stops, and the maximum The value detection circuit 10 starts operating.

今プロセッサ100が資源使用中、7’o−+=ッサ2
00及びプロセッサ300から第2図に示すタイミング
で資源要求がなされたとしよう。
Processor 100 is currently using resources, 7'o-+ = processor 2
Assume that resource requests are made from the processor 00 and the processor 300 at the timing shown in FIG.

第2図の1はプロセッサ100に対する資源許可信号、
2はプロセッサ200からの資源要求信号、3と4はプ
ロセッサ300からの資源要求信号である。
1 in FIG. 2 is a resource grant signal to the processor 100;
2 is a resource request signal from the processor 200, and 3 and 4 are resource request signals from the processor 300.

プロセッサ200から出力された資源要求信号2により
プロセンサ200の計数回路210はクロック1で計数
される。
The counting circuit 210 of the processor 200 counts with the clock 1 based on the resource request signal 2 outputted from the processor 200.

又、プロセッサ300から出力された資源要求信号3に
よりプロセッサ300の計数回路310はクロック1で
計数され、さらに資源要求信号4によりプロセッサ30
0の計数回路310はクロック2で計数される。
Further, the counting circuit 310 of the processor 300 is counted by the clock 1 according to the resource request signal 3 outputted from the processor 300, and further, the counting circuit 310 of the processor 300 is counted by the resource request signal 4.
The zero counting circuit 310 counts with clock 2.

なお、クロック1とクロック2との関係は、クロック1
の周波数〈クロック2の周波数である。従ってプロセッ
サ100に資源許可信号が与えられている間に、プロセ
ッサ200の計数回路210け、 クロック1の周波数x(t、+−t2)だけ計数し、又
、プロセッサ300の計数回路310は、 クロック1の周波数X(t8−t、)+クロック2の周
波数x(t4−ts)だけ計数している。
Note that the relationship between clock 1 and clock 2 is as follows:
frequency <frequency of clock 2. Therefore, while the resource grant signal is given to the processor 100, the counting circuit 210 of the processor 200 counts by the frequency x(t, +-t2) of the clock 1, and the counting circuit 310 of the processor 300 counts the frequency x(t, +-t2) of the clock 1. 1 frequency X(t8-t,)+clock 2 frequency x(t4-ts) is counted.

今、クロック1の周波数を5Hz、クロック2の周波数
を10Hz、 tl、 t!+ t3およびt4をそれ
ぞれ、1秒、2秒、3秒、および4秒とすると、計数回
路210は1oだけ計数し、一方、計数回路310は2
0だけ計数する。従って、最大検出回路10によって計
数回路310に対応するプロセッサ300に資源使用の
許可が与えられる。
Now, set the frequency of clock 1 to 5Hz, the frequency of clock 2 to 10Hz, tl, t! + If t3 and t4 are 1 second, 2 seconds, 3 seconds, and 4 seconds, respectively, counting circuit 210 counts by 1o, while counting circuit 310 counts by 2o.
Count only 0. Therefore, the maximum detection circuit 10 grants permission to the processor 300 corresponding to the counting circuit 310 to use the resource.

以上プロセッサ3台による動作の詳細を説明したがN台
の場合も全く同様である。本実施例では資源使用の許可
を与えたプロセッサの計数回路をリセットして優先度を
最下位にしているが、資源使用の許可を与えたプロセッ
サの計数回路を一定数だけ減する方法は容易に考えられ
る。
The details of the operation using three processors have been described above, but the same applies to the case where N processors are used. In this embodiment, the counting circuit of the processor that has been given permission to use resources is reset to give it the lowest priority, but it is easy to reduce the counting circuit of the processor that has been given permission to use resources by a certain number. Conceivable.

本発明は、この様に複数個の互いに独立な信号源から同
一の情報資源に向って非同期的に使用要求信号が発生す
る場合、信号源において早くまた多くの使用要求信号を
発生した信号源に対し資源使用許可を与える信号調停器
を提供するもので実用に供してきわめて有効である。
In this way, when use request signals are generated asynchronously toward the same information resource from a plurality of mutually independent signal sources, the signal source that has generated many use request signals is It provides a signal arbiter for granting permission to use resources, and is extremely effective in practical use.

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

第1図は本発明の信号調停器の一実施例を示す構成図お
よび第2図は上記実施例を説明するためのタイムチャー
トである。
FIG. 1 is a block diagram showing one embodiment of the signal arbitrator of the present invention, and FIG. 2 is a time chart for explaining the above embodiment.

Claims (1)

【特許請求の範囲】[Claims] 複数個の互いに独立なプロセッサから同一の情報資源に
向って非同期的に競争して前記・情報資源を獲得するシ
ステムにおいて、前記プロセッサ75)ら前記情%資源
に使用要求のある毎に前言己各プロセッサに対応して配
置される計数回路に供給されるパルスの周波数を増加す
る手段と、前n己複蔽の計数回路の内最大値を示すとこ
ろのプロセッサに対し前記情報資源の使用許可を与える
手段とを有することを特徴とする信号調停器。
In a system in which a plurality of mutually independent processors asynchronously compete for the same information resource and acquire the information resource, each time the processor 75 makes a request to use the information resource, means for increasing the frequency of pulses supplied to a counting circuit disposed corresponding to the processor, and granting permission to use the information resource to the processor that exhibits the maximum value among the counting circuits of the previous n-self-duplication; A signal arbitrator comprising: means.
JP18232782A 1982-10-18 1982-10-18 Signal arbitorating device Pending JPS5971559A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP18232782A JPS5971559A (en) 1982-10-18 1982-10-18 Signal arbitorating device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP18232782A JPS5971559A (en) 1982-10-18 1982-10-18 Signal arbitorating device

Publications (1)

Publication Number Publication Date
JPS5971559A true JPS5971559A (en) 1984-04-23

Family

ID=16116363

Family Applications (1)

Application Number Title Priority Date Filing Date
JP18232782A Pending JPS5971559A (en) 1982-10-18 1982-10-18 Signal arbitorating device

Country Status (1)

Country Link
JP (1) JPS5971559A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4943862A (en) * 1987-02-12 1990-07-24 Mitsubishi Denki Kabushiki Kaisha Cathode-ray tube with multi-layer resin coating on faceplate providing implosion protection

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4943862A (en) * 1987-02-12 1990-07-24 Mitsubishi Denki Kabushiki Kaisha Cathode-ray tube with multi-layer resin coating on faceplate providing implosion protection

Similar Documents

Publication Publication Date Title
US5388228A (en) Computer system having dynamically programmable linear/fairness priority arbitration scheme
US4969120A (en) Data processing system for time shared access to a time slotted bus
US5745708A (en) Method for and apparatus for operating a local communications module in arbitrating for mastership of a data transfer across a back plane bus in industrial automation controller
US4901234A (en) Computer system having programmable DMA control
US20100318706A1 (en) Bus arbitration circuit and bus arbitration method
US4556939A (en) Apparatus for providing conflict-free highway access
KR930002787B1 (en) Universal peripheral controller self-configuring bootloadable ramware
US20070067527A1 (en) Data transfer bus system connecting a plurality of bus masters
US5680554A (en) Method and apparatus for arbitrating among processors for access to a common bus
US5787263A (en) Method of an apparatus for controlling data transfer
JPS5971559A (en) Signal arbitorating device
US7162557B2 (en) Competition arbitration system
JPS598059A (en) Signal mediator
JPS6019819B2 (en) Bus right control method
KR920000480B1 (en) Arbitration method of interrupt bus
JPH0343658B2 (en)
JPS62259157A (en) Interruption system
JP2000010934A (en) Bus arbitration system in multi-cpu system
JPS5818727A (en) Method and apparatus for self-control of dispersion type priority competition
JP2003006146A (en) Bus arbitration circuit
JPS60168240A (en) Interrupt processing circuit
JP2002091903A (en) Bus system
JPS58163031A (en) Bus allotment controlling system
JPH06131307A (en) Load distributing system for multi cpu system
CN116010308A (en) DMA data flow arbiter design