JPS61231654A - Memory device - Google Patents

Memory device

Info

Publication number
JPS61231654A
JPS61231654A JP7240185A JP7240185A JPS61231654A JP S61231654 A JPS61231654 A JP S61231654A JP 7240185 A JP7240185 A JP 7240185A JP 7240185 A JP7240185 A JP 7240185A JP S61231654 A JPS61231654 A JP S61231654A
Authority
JP
Japan
Prior art keywords
processor
storage device
bank
data
memory device
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
JP7240185A
Other languages
Japanese (ja)
Inventor
Masayuki Koyama
児山 正之
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
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 filed Critical NEC Corp
Priority to JP7240185A priority Critical patent/JPS61231654A/en
Publication of JPS61231654A publication Critical patent/JPS61231654A/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
    • G06F13/16Handling requests for interconnection or transfer for access to memory bus
    • G06F13/18Handling requests for interconnection or transfer for access to memory bus based on priority control

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 prevent drop in processing ability by dividing a memory device into plural banks, and providing a bus exclusively used for a processor and a circuit controlling access competition from a common bus at every bank. CONSTITUTION:The memory device 5-1 of a processor 3 is divided into three banks 12-14, which are connected to a competition control circuit (9-11). When the processor 3 indicates a processor 2 to transfer data in an external memory device 1 to an address allocated to the bank 12, the processor 2 transfers the data to the bank 12. On the other hand, when the processor 3 reads an instruction out of the bank 12 and executes such a program as writing data in the bank 14, processing can be executed without competing the data transfer action of the processor 2.

Description

【発明の詳細な説明】 〔産業上の利用分野〕 本発明は複数のプロセッサによシ構成される情報処理装
置内の記憶装置に関する。
DETAILED DESCRIPTION OF THE INVENTION [Field of Industrial Application] The present invention relates to a storage device in an information processing device configured by a plurality of processors.

〔従来の技術〕[Conventional technology]

従来のマルチプロセッサシステムは、1つの共通バスに
複数のプロセッサが接続され、各プロセッサ間の通信は
共通バスに接続されている記憶装置を経由して行なう方
式が一般的であつ友。さらに、共通バスを使用する方式
では記憶装置を競合回路を経由して、記憶装置の使用頻
度の高いプロセッサの内部バスと、共通バスのそれぞれ
に接続し、該プロセッサのバス競合によるオーバーヘッ
ドをなくし処理能力の向上をはかつている。82図にそ
の従来システムの例を示す。
In a conventional multiprocessor system, a plurality of processors are connected to one common bus, and communication between the processors is generally performed via a storage device connected to the common bus. Furthermore, in the method that uses a common bus, the storage device is connected via a contention circuit to the internal bus of the processor that uses the storage device frequently and to the common bus, eliminating the overhead caused by bus contention for the processor. I am trying to improve my abilities. Figure 82 shows an example of the conventional system.

同図中、プロセッサ2.3が一つの共通バス6に接続さ
れておシ、プロセッサ3の記憶装置5は、一つの競合制
御回路4を介して一方は専用バス7を介してプロセッサ
3に、かつ他方は直接共通パス6にも接続されている。
In the figure, the processors 2.3 are connected to one common bus 6, and the storage device 5 of the processor 3 is connected to the processor 3 through one contention control circuit 4, and the other through a dedicated bus 7. And the other one is also directly connected to the common path 6.

プロセッサ3のプログ。Processor 3 program.

ラムは記憶装置5に格納される。プロセッサ3は常に命
令を読み出すために記憶装置5に頻−にア ゛クセスす
る。
The RAM is stored in the storage device 5. Processor 3 constantly accesses storage device 5 to read instructions.

今プロセッサ3がプロセッサ2に対し、共通パス6経由
でプロセッサ2の外部記憶装置1のデータを記憶装置5
の所定のアドレスに転送するように指示した場合を考え
る。プロセッサ2は、指示に従って記憶装置5上にデー
タを転送し始める。
Processor 3 now sends data from processor 2's external storage device 1 to processor 2 via common path 6 to storage device 5.
Consider the case where an instruction is given to forward the data to a predetermined address. Processor 2 begins transferring data onto storage device 5 according to the instructions.

〔解決すべき問題点〕[Problems to be solved]

しかし、プロセッサ3は常に記憶装置5にアク 。 However, the processor 3 always accesses the storage device 5.

セスしているため、各アクセス毎にプロセッサ2のアク
セスと競合し、プロセッサ3,2共に処理能力が低下す
ると言う問題点があった。
Therefore, each access competes with the access of processor 2, resulting in a problem in that the processing performance of both processors 3 and 2 is reduced.

c問題点の解決手段〕 本発明は、上記問題点を解決したものであシ、専用パス
を持つ複数のプロセッサが、一つの共通バスに接続され
る構成のデータ処理装置内で、特定のプロセッサによる
専用パス経由のアクセスと該プロセッサ以外のプロセッ
サから共通パスを経由したア′クセスとが可能である記
憶装置において、該記憶装置を複数のバンクに分割し、
おのおのの・バンク毎に該プロセッサの専用バスと前記
共通バスからのアクセス競合を制御する回路とを設け、
該記憶装置に対する該プロセッサのアクセスと、該プロ
セッサ以外の他のプロセッサのアクセスとを同時に行な
う構成とし喪ものである。
Solution to Problem c] The present invention solves the above problem.In a data processing device configured in which a plurality of processors having dedicated paths are connected to one common bus, In a storage device that can be accessed by a processor via a dedicated path and accessed by a processor other than the processor via a common path, the storage device is divided into a plurality of banks,
A dedicated bus for the processor and a circuit for controlling access contention from the common bus are provided for each bank,
It is a bad idea to have a configuration in which the processor accesses the storage device and the processor other than the processor accesses the storage device at the same time.

〔実施例〕。〔Example〕.

次に1その実施例を第1図と共に説明す、る。Next, an embodiment thereof will be explained with reference to FIG.

第1図は本発明に係る記憶装置の一実施例を適用したマ
ルチプロセッサシステムのブロック図であシ、同図中、
第2図と同一部分には同一符号を付す。
FIG. 1 is a block diagram of a multiprocessor system to which an embodiment of the storage device according to the present invention is applied;
The same parts as in FIG. 2 are given the same reference numerals.

第1図中、プロセッサ3とプロセッサ2とが一つの共通
バス6に接続され、プロセッサ2には外部記憶装置lが
接続されている、プロセッサ3の記憶装w5−1は三つ
のバンク12,13.14に全開され、それぞれが競合
制御回路4−4(9,、1・0゜11)K接続される。
In FIG. 1, a processor 3 and a processor 2 are connected to one common bus 6, an external storage device l is connected to the processor 2, and a storage device w5-1 of the processor 3 has three banks 12, 13. .14, and each of them is connected to a competition control circuit 4-4 (9,, 1·0°11)K.

又各競合制御回路9.l、0゜11は夫々一方は専用パ
ス7−1を介して、プpセイサ3の内部バろと接続され
、他方は共通バス6に接続されている。バンク12には
プロセッサ3.、のイログラムが格納、される。 、1
.、・  ・今プロセッサ3がプロセッサ2に対して、
共通パス6経由でプロセッサ2Q外部記憶装置1のデー
タ、を記憶装置5−1内のバンク12に@p当て、ら4
れているアドレスへ転送す、るよう指示・した場合を考
える。プロセラ、す2は指示に従ってバンク12の所定
のアドレスへデーー転道を行なう。一方プロセツ?3は
バンク1,2から命令を読不出し、バンク14のデータ
を書くようなプログラムを実行している場合に、プロセ
ッサ2のデ、−タ・転送動、作と伺ら競合する事なく処
理、を実行で*、i、従、つてプi、セッサ3,2.・
共に競合による処理能力の低下6を少なくする事ができ
る。
Also, each competition control circuit 9. 1 and 0.degree. 11, one of which is connected to the internal valve of the processor 3 via a dedicated path 7-1, and the other connected to the common bus 6. Bank 12 includes processor 3. , is stored and displayed. ,1
.. ,... ・Processor 3 now says to processor 2,
The data of the processor 2Q external storage device 1 is applied to the bank 12 in the storage device 5-1 via the common path 6, and et al.
Consider the case where you instruct/direct to forward to an address that is Processor 2 transfers data to a predetermined address in bank 12 according to the instructions. Prosets on the other hand? 3, when executing a program that reads and writes instructions from banks 1 and 2 and writes data to bank 14, processing is performed without conflicting with the data transfer operation of processor 2. , by executing *, i, subordinate, point i, processor 3, 2 .・
In both cases, it is possible to reduce the decrease in processing capacity due to competition.

〔発明の効果〕〔Effect of the invention〕

以上説明した如く、本発明は、記憶装置を複数のバンク
に分割し、おのおののバンクが競合制御回路、5を持ち
プロセッサ専用パスと、システムの共通バスに接続され
るようにしているため、記憶装置をアクセスする時の競
合を少なくシ、プロセッサの処理能力の低下を少なぐす
ることができるという効果がある。。 ゛
As explained above, the present invention divides a storage device into a plurality of banks, and each bank has a contention control circuit 5 and is connected to a dedicated processor path and a common bus of the system. This has the effect of reducing contention when accessing a device and reducing a decrease in processor processing performance. .゛

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

篤1図は本発明に係る記憶装置の一実施例を適用したマ
ルチプロセッサシステムのブロック図、第2図は従来の
記憶装置を適用したマルチプロ、セッサシステムのブロ
ック図である。
FIG. 1 is a block diagram of a multiprocessor system to which an embodiment of the storage device according to the present invention is applied, and FIG. 2 is a block diagram of a multiprocessor system to which a conventional storage device is applied.

Claims (1)

【特許請求の範囲】 専用バスを持つ複数のプロセッサが、一つの共通バスに
接続される構成のデータ処理装置内で、特定のプロセッ
サによる専用バス経由のアクセスと該プロセッサ以外の
プロセッサから共通バスを経由したアクセスとが可能で
ある記憶装置において、 該記憶装置を複数のバンクに分割し、おのおののバンク
毎に該プロセッサの専用バスと前記共通バスからのアク
セス競合を制御する回路とを設け、該記憶装置に対する
該プロセッサのアクセスと、該プロセッサ以外の他のプ
ロセッサのアクセスとを同時に行なう構成としたことを
特徴とする記憶装置。
[Claims] In a data processing device configured such that a plurality of processors each having a dedicated bus are connected to one common bus, access by a specific processor via the dedicated bus and access from processors other than the common bus to the common bus is possible. In a storage device that can be accessed via A storage device characterized in that the storage device is configured such that the processor accesses the storage device and the processor other than the processor accesses the storage device at the same time.
JP7240185A 1985-04-05 1985-04-05 Memory device Pending JPS61231654A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP7240185A JPS61231654A (en) 1985-04-05 1985-04-05 Memory device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP7240185A JPS61231654A (en) 1985-04-05 1985-04-05 Memory device

Publications (1)

Publication Number Publication Date
JPS61231654A true JPS61231654A (en) 1986-10-15

Family

ID=13488215

Family Applications (1)

Application Number Title Priority Date Filing Date
JP7240185A Pending JPS61231654A (en) 1985-04-05 1985-04-05 Memory device

Country Status (1)

Country Link
JP (1) JPS61231654A (en)

Similar Documents

Publication Publication Date Title
JPH04348451A (en) Parallel computer
JP3688835B2 (en) Data storage system and data transfer method applied to the system
US4691280A (en) High performance multi-processor system
JPS61231654A (en) Memory device
JP2618223B2 (en) Single chip microcomputer
JPS616753A (en) Common memory device
JPH07160655A (en) Memory access system
JPH04117697A (en) Multiport memory circuit
JP2511012B2 (en) Task termination method
JPS6383854A (en) Data transfer circuit
JPS61201326A (en) Information processor
JPS62186344A (en) Address mapped register
JPS635461A (en) Multiprocessor system
JPS63733A (en) Program execution processing system
JPS62272352A (en) Memory control circuit
JPH01154272A (en) Multiprocessor device
JPS60129855A (en) Signal processor
JPH04154346A (en) Circuit controller
JPH07129519A (en) Dual cpu system
JPH0467240A (en) Data processor
JPH04205452A (en) Dma controller
JPS63228365A (en) Multiprocessor system
JPS63133257A (en) Multi-processor system
JPS6243737A (en) Interruption control system
JPH04326453A (en) Multi-processor system