JPS6220043A - Random access memory capable of asynchronous simultaneous access for multiprocessor - Google Patents

Random access memory capable of asynchronous simultaneous access for multiprocessor

Info

Publication number
JPS6220043A
JPS6220043A JP16090485A JP16090485A JPS6220043A JP S6220043 A JPS6220043 A JP S6220043A JP 16090485 A JP16090485 A JP 16090485A JP 16090485 A JP16090485 A JP 16090485A JP S6220043 A JPS6220043 A JP S6220043A
Authority
JP
Japan
Prior art keywords
plane
memory
address
read
multiprocessor
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
JP16090485A
Other languages
Japanese (ja)
Inventor
Yukihiro Taguchi
田口 之博
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.)
Individual
Original Assignee
Individual
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 Individual filed Critical Individual
Priority to JP16090485A priority Critical patent/JPS6220043A/en
Publication of JPS6220043A publication Critical patent/JPS6220043A/en
Pending legal-status Critical Current

Links

Abstract

PURPOSE:To access a memory asynchronously and simultaneously by providing memory planes with address busses and data busses individually for microprocessors constituting a multiprocessor system. CONSTITUTION:For example, two memory planes (an upper memory plane A and a lower memory plane B) are provided and are connected to microprocessors by address busses (1) and (2) and data busses (3) and (4). As long as memory planes are read by processors, memory planes are not connected and are operated as memories independent of each other. If write is performed on either plane, for example, the plane B, a storage cell 9 in the selected address on the plane B is connected to the storage cell in the same address of each plane, and its contents are written on all planes.

Description

【発明の詳細な説明】 (イ)産業上の利用分野 情報゛処理機器におけるメモリー回路、特にマルチプロ
セッサーシステムに向く。
DETAILED DESCRIPTION OF THE INVENTION (a) Industrial application field: Memory circuits in information processing equipment, particularly suitable for multiprocessor systems.

(ロ)従来の技術 従来マルチプロセッサシステムにおける記憶回路は、記
憶回路からのデータ、アドレスバスが1つしかなく、こ
れを切り換えてプロセッサに接続していたために9時間
の無駄が多く高速動作ができない、また、同期待ちの無
駄な時間があり、プロセッサーの数が増すに従ってこの
無駄が、増える。
(B) Conventional technology The memory circuit in a conventional multiprocessor system has only one address bus for data from the memory circuit, and this is connected to the processor by switching, which wastes 9 hours and does not allow high-speed operation. In addition, there is wasted time waiting for synchronization, and this waste increases as the number of processors increases.

くハ)発明が解決しようとする問題点 同期待ちの無駄な時間を取り除く事と、タイミング設計
を容易にする事。
(c) Problems that the invention seeks to solve: Eliminate wasted time waiting for synchronization and facilitate timing design.

(ニ)問題点を解決するための手段 この方式を用いると、プロセッサを幾つ接続しても非同
期に同時にアクセスできるので、非常に高速である。原
理は2図1のように各メモリープレーンがあり、それぞ
れマイクロプロセッサにアドレスバス、データバスがつ
ながっている。そしてプロセッサから読みだしをする限
りにおいては、各メモリー間の接続は行われず、全く独
立したメモリーとして働く、シかし、どこかのプレーン
で書き込みが行われた場合、仮にプレーンBで行われた
とすると、プレーンBで選択されたアドレスの記憶セル
が、各プレーンの同一アドレスの記憶セルと接続されて
、その内容が全てのプレーンに書きこまれる。この接続
は、プレーンBで選択されたアドレスのみが行われるの
で、プレーンBから書き込みをしている間、他のメモリ
ーは読みだしを同時に行うことができる。このときプレ
ーンBと同じアドレスを他のプレーンで読み出すと、プ
レーンBへ書き込む内容がそのままよみだされる。
(d) Means for solving the problem If this method is used, no matter how many processors are connected, they can be accessed simultaneously asynchronously, so it is very fast. The principle is 2. As shown in Figure 1, each memory plane has an address bus and a data bus connected to the microprocessor. As far as reading is performed from the processor, there is no connection between each memory, and each memory acts as a completely independent memory. However, if a write is performed on any plane, it will be assumed that it was performed on plane B. Then, the memory cell at the selected address in plane B is connected to the memory cell at the same address in each plane, and its contents are written to all planes. This connection is made only for the address selected on plane B, so while writing from plane B, other memories can read simultaneously. At this time, if the same address as plane B is read on another plane, the contents written to plane B will be read out as is.

また、異なったアドレスに同時に書き込みをすることが
できる。ただ、同一アドレス書き込みが行われた時は、
書き込み終了が一番最後だった内容が優先され、同時に
終了したときは、内容は不定となる。
Also, it is possible to write to different addresses at the same time. However, when writing to the same address is performed,
Priority is given to the content that was written last, and if they are finished at the same time, the content will be undefined.

(ホ)実施例 図2は、具体的な回路例で、メモリーの1ビツト記憶部
分である。使用している3ステートバツフアーは、オー
ブンコレクタタイプで、これを使ったのは、配線を簡単
にするためである。
(E) Embodiment FIG. 2 shows a specific example of a circuit, which is a 1-bit storage part of a memory. The 3-state buffer I'm using is an oven collector type, and I used it to simplify wiring.

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

図1は原理図。 1、プレーンへのアドレスバス。 2、プレーンBのアドレスバス。 3、プレーンAのデータバス。 4、プレーンBのデータバス。 5、プレーンへの読みだし端子。 6、プレーンBの読みだし端子。 7、プレーンAの書き込み端子。 8、プレーンBの書き込み端子。 9.1ビツト記憶セル。 図2は実際の回路例。 1、プレーンAの読みだし端子。 2、プレーンBの読みだし端子。 3、プレーンAの書き込み端子。 4、プレーンBの書き込み端子。 5、プレーンAのマトリクス回路に接続6、プレーンB
のマトリクス回路に接続7、プレーンAのデータ人出力
線。 8、プレーンBのデータ入出力線。 9、オーブンコレクタタイプの3ステートバツフアー・ 10、プレーンA 11、プレーンB
Figure 1 is a diagram of the principle. 1. Address bus to plane. 2. Plane B address bus. 3. Plane A data bus. 4. Plane B data bus. 5. Read terminal to plane. 6. Read terminal of plane B. 7. Plane A write terminal. 8. Plane B write terminal. 9.1 bit storage cell. Figure 2 is an example of an actual circuit. 1. Read terminal of plane A. 2. Read terminal of plane B. 3. Plane A write terminal. 4. Plane B write terminal. 5. Connect to the matrix circuit of plane A 6. Plane B
Connect to the matrix circuit of 7, the data output line of plane A. 8. Plane B data input/output line. 9. Oven collector type 3-state buffer 10. Plain A 11. Plain B

Claims (1)

【特許請求の範囲】 マルチプロセッサシステム用の記憶回路で 各マイクロプロセッサに対しアドレスバス データバス共に用意されたメモリープレー ンが有り、読みだしをするかぎりにおいて は全く独立した記憶回路であるが、どこか のプレーンで書き込みを行った時には、各 メモリープレーンで、そのアドレス部分だ け接続が行われ、その書き込み情報が全て のプレーンの各ビット記憶部分に直接セッ トされ、どのプロセッサからも読みだし書 き込みが、随時行う事ができる方式で、理 論的には、任意数のプロセッサーを接続で きる方式。[Claims] A memory circuit for multiprocessor systems. Address bus for each microprocessor Memory play included with data bus As long as there is a button and reading is a completely independent memory circuit, but somewhere When writing in the plane of It's the memory plane, and it's the address part. connection is made, and all the written information is Each bit of the plane is set directly to the storage part of the plane. read and write from any processor. It is a method that allows data to be read at any time, and it is easy to understand. Logically, you can connect any number of processors. How to do it.
JP16090485A 1985-07-19 1985-07-19 Random access memory capable of asynchronous simultaneous access for multiprocessor Pending JPS6220043A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP16090485A JPS6220043A (en) 1985-07-19 1985-07-19 Random access memory capable of asynchronous simultaneous access for multiprocessor

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP16090485A JPS6220043A (en) 1985-07-19 1985-07-19 Random access memory capable of asynchronous simultaneous access for multiprocessor

Publications (1)

Publication Number Publication Date
JPS6220043A true JPS6220043A (en) 1987-01-28

Family

ID=15724853

Family Applications (1)

Application Number Title Priority Date Filing Date
JP16090485A Pending JPS6220043A (en) 1985-07-19 1985-07-19 Random access memory capable of asynchronous simultaneous access for multiprocessor

Country Status (1)

Country Link
JP (1) JPS6220043A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100895073B1 (en) * 2001-10-31 2009-04-27 삼성전자주식회사 3-d-memory device for large storage capacity

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100895073B1 (en) * 2001-10-31 2009-04-27 삼성전자주식회사 3-d-memory device for large storage capacity

Similar Documents

Publication Publication Date Title
EP0081358A2 (en) Data processing system providing improved data transfer between modules
JPS6220043A (en) Random access memory capable of asynchronous simultaneous access for multiprocessor
US4803655A (en) Data processing system employing a plurality of rapidly switchable pages for providing data transfer between modules
CA1284388C (en) Time partitioned bus arrangement
JPH0450625B2 (en)
RU1810891C (en) Multichannel equipment to exchange data between modules of computer system
JP2634609B2 (en) Data transfer device
JPS6120172A (en) Multi-microprocessor system
JPS61153770A (en) Image processor
JPS6244352B2 (en)
KR100446282B1 (en) System bus interface circuit, especially related to operating both read and write processes at one cycle
JPS60134956A (en) Information processing system
JPS63225846A (en) Multiport memory with address conversion mechanism
KR910005381B1 (en) Method and apparatus for ragion distinction of virtual memory
JPS6136854A (en) Memory switching device
JPH03223950A (en) Bus conversion circuit
JPS61161560A (en) Memory device
JPS5836380B2 (en) Direct memory access method in multiprocessor systems
JPS63183678A (en) Multi-port memory device
JPH0652516B2 (en) Bus interface device
JPH02211571A (en) Information processor
JPS58101358A (en) Memory controlling system
JPH0267414U (en)
JPH02191028A (en) Digital signal processing circuit
JPS598057A (en) Memory device