JPH02257241A - Memory access competition improving system - Google Patents

Memory access competition improving system

Info

Publication number
JPH02257241A
JPH02257241A JP3030789A JP3030789A JPH02257241A JP H02257241 A JPH02257241 A JP H02257241A JP 3030789 A JP3030789 A JP 3030789A JP 3030789 A JP3030789 A JP 3030789A JP H02257241 A JPH02257241 A JP H02257241A
Authority
JP
Japan
Prior art keywords
memory
processor
dual port
time
processors
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
JP3030789A
Other languages
Japanese (ja)
Inventor
Tatsuya Iwano
岩野 達也
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 JP3030789A priority Critical patent/JPH02257241A/en
Publication of JPH02257241A publication Critical patent/JPH02257241A/en
Pending legal-status Critical Current

Links

Landscapes

  • Multi Processors (AREA)

Abstract

PURPOSE:To prevent the access competition from being generated at the time of read-out of data by providing memory circuits corresponding to the number of processors, rewriting simultaneously each memory circuit at the time of write, and reading out of the memory circuit of the processor concerned at the time of read-out. CONSTITUTION:Processors 00, 10 hold dual port memories 02, 12 in common, and the dual port memory 02 can execute read-out only from the processor 00, and the dual port memory 12 can execute read-out only from the processor 10. Also, memory write can be executed to each of the dual port memories 02, 12 from both the processors 00, 10. In this regard, the processor 00 and the processor 10 have a local memory 01 and a local memory 11, respectively. In such a way, waiting at the time of a memory access is not generated.

Description

【発明の詳細な説明】 〔産業上の利用分野〕 本発明はメモリに関し、特にマルチプロセッサにおける
共通メモリアクセス競合改善方式に関する。
DETAILED DESCRIPTION OF THE INVENTION [Field of Industrial Application] The present invention relates to memory, and more particularly to a method for improving common memory access contention in multiprocessors.

〔従来の技術〕[Conventional technology]

従来、共通メモリのアクセス競合は、一方がアクセス(
読み出し又は書き込み)時に他方が待ち合わせるように
し、矛盾が発生しない様にしている。
Traditionally, common memory access contention occurs when one side accesses (
(reading or writing), the other side waits to prevent conflicts from occurring.

〔発明が解決しようとする課題〕[Problem to be solved by the invention]

上述したように従来の共通メモリのアクセス競合方式で
は、いずれか一方が必ず待ち合わせをしなければならな
い、最近のメモリでは高集積化が進み、メモリアクセス
時に必ず上記の待ち合わせが発生し、システムとしての
スループットが低下している。
As mentioned above, in the conventional access contention method for common memory, one side must always wait.As recent memories have become highly integrated, the above-mentioned waiting always occurs when accessing memory, making it difficult for the system to function. Throughput is decreasing.

〔課題を解決するための手段〕[Means to solve the problem]

本発明のメモリアクセス競合改善方式は、複数のプロセ
ッサから独立にアクセスされるメモリ回路において、プ
ロセッサ台数分のメモリ回路を持ち、書き込み時には各
メモリ回路を同時に書き替え、読み出し時には該当する
プロセッサのメモリ回路から読み出すようにして構成さ
れる。
The memory access contention improvement method of the present invention is a memory circuit that is independently accessed by multiple processors, has memory circuits for the number of processors, and when writing, each memory circuit is rewritten simultaneously, and when reading, the memory circuit of the corresponding processor It is configured so that it can be read from.

〔実施例〕〔Example〕

第1図は本発明の一実施例を示す構成図である。 FIG. 1 is a block diagram showing an embodiment of the present invention.

同図においてメモリアクセス競合改善方式は2白のプロ
セッサ00,10がデュアルポートメモリ02,12を
共有しており、デュアルポートメモリ02はプロセッサ
OOからのみ読み出し可能でありデュアルポートメモリ
12はプロセッサ10からのみ読み出し可能であり、メ
モリ書込みは両方のプロセッサ00.10からデュアル
ポートメモリ02.12のそれぞれに対して可能である
In the figure, the memory access conflict improvement method is such that two white processors 00 and 10 share dual port memories 02 and 12, dual port memory 02 can be read only from processor OO, and dual port memory 12 can be read from processor 10. Memory writes are possible from both processors 00.10 to each of the dual port memories 02.12.

なおプロセッサ00はローカルメモリ01を、プロセッ
サ10はローカルメモリ11をそれぞれ有している。
Note that the processor 00 has a local memory 01, and the processor 10 has a local memory 11.

プロセッサ00側からのメモリ書き込みはAND回路0
3及び04を介してデュアルポートメモリ02,12に
対して行われる。この時、待ち合わされるのはプロセッ
サ10側からのデュアルポートメモリへの書き込みと読
み出しである。ここで同一プロセッサは同時に別の事を
できないので、この時プロセッサ00側からメモリ読み
出し信号は出力しない。
Memory writing from processor 00 side is AND circuit 0
3 and 04 to the dual port memories 02 and 12. At this time, what is awaited is writing and reading from the processor 10 to the dual port memory. Here, since the same processor cannot do different things at the same time, no memory read signal is output from the processor 00 side at this time.

またプロセッサ00側からのメモリ読み出しはAND回
路05を介してデュアルポートメモリO2に対して行わ
れる。この時、待ち合わされるのはプロセッサ10側か
らのデュアルポートメモリへの書き込みである。
Further, memory reading from the processor 00 side is performed via the AND circuit 05 to the dual port memory O2. At this time, what is awaited is the write to the dual port memory from the processor 10 side.

同様に、プロセッサ10側からのメモリ書き込みはAN
D回路13及び14を介してデュアルポートメモリ02
,12に対して行われる。この時、待ち合わされるのは
プロセッサ00側からのデュアルポートメモリへの書き
込みと読み出しである。
Similarly, memory writing from the processor 10 side is AN
Dual port memory 02 via D circuits 13 and 14
, 12. At this time, what is awaited is writing and reading from the processor 00 side to the dual port memory.

またプロセッサ10側からのメモリ読み出しはAND回
路15を交してデュアルポートメモリ12に対して行わ
れる。この時、待ち合わされるのはプロセッサ00側か
らのデュアルポートメモリへの書き込みである。
Further, memory reading from the processor 10 side is performed to the dual port memory 12 through an AND circuit 15. At this time, what is awaited is the write to the dual port memory from the processor 00 side.

〔発明の効果〕〔Effect of the invention〕

以上説明した様に、本発明はプロセッサ分のメモリ回路
を用意しデータの読み出し時に各プロセッサ用のメモリ
から個々に読み出せる様にする事により、データの読み
出し時のアクセス競合が発生しなくなり、システムのス
ルーブツトが向上する効果がある。
As explained above, the present invention prepares memory circuits for processors and allows data to be read from the memory for each processor individually when reading data. This eliminates access contention when reading data, and the system This has the effect of improving throughput.

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

第1図は本発明の一実施例を示す構成図である。 00.10・・・プロセッサ、01.11・・・ローカ
ルメモリ、0,2 、、、12・・・デュアルポートメ
モリ、03.04,05.13.14.15・・・論理
回路。
FIG. 1 is a block diagram showing an embodiment of the present invention. 00.10...Processor, 01.11...Local memory, 0,2,,,12...Dual port memory, 03.04,05.13.14.15...Logic circuit.

Claims (1)

【特許請求の範囲】[Claims] 複数のプロセッサから独立にアクセスされるメモリ回路
において、プロセッサ台数分のメモリ回路を持ち、書き
込み時には各メモリ回路を同時に書き替え、読み出し時
には該当するプロセッサのメモリ回路から読み出すこと
を特徴とするメモリアクセス競合改善方式。
In a memory circuit that is independently accessed by multiple processors, it has memory circuits for the number of processors, and when writing, each memory circuit is rewritten at the same time, and when reading, the memory circuit is read from the memory circuit of the corresponding processor. Improvement method.
JP3030789A 1989-02-08 1989-02-08 Memory access competition improving system Pending JPH02257241A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP3030789A JPH02257241A (en) 1989-02-08 1989-02-08 Memory access competition improving system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP3030789A JPH02257241A (en) 1989-02-08 1989-02-08 Memory access competition improving system

Publications (1)

Publication Number Publication Date
JPH02257241A true JPH02257241A (en) 1990-10-18

Family

ID=12300116

Family Applications (1)

Application Number Title Priority Date Filing Date
JP3030789A Pending JPH02257241A (en) 1989-02-08 1989-02-08 Memory access competition improving system

Country Status (1)

Country Link
JP (1) JPH02257241A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0573470A (en) * 1991-09-12 1993-03-26 Nec Corp Dual port storage device

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0573470A (en) * 1991-09-12 1993-03-26 Nec Corp Dual port storage device

Similar Documents

Publication Publication Date Title
JPH01320564A (en) Parallel processor
JPH02257241A (en) Memory access competition improving system
JPH0546527A (en) Dual port memory circuit
JPH06259114A (en) Programmable controller
JPS645341B2 (en)
JPS60195661A (en) Data processing system
JPS60237566A (en) Interprocessor communication system
JPH01293456A (en) Shared memory
JPS6029139B2 (en) Connection method between processing units
JPH08249289A (en) Memory controller and its control method
JPH02257249A (en) Information processing system
JP2606824Y2 (en) Multiport memory device
JPH10254767A (en) Memory controller and memory system by the controller
JPS63183678A (en) Multi-port memory device
JPH01154272A (en) Multiprocessor device
KR960007835B1 (en) Common memory access device for multi-processor
JPS62186344A (en) Address mapped register
JPS62251829A (en) Symbolic processing system and method
JPH0214741B2 (en)
JPS60247767A (en) Simultaneous input and output system for reading-out and writing-in operation of shared memory
JPH01194052A (en) Data input/output circuit for digital signal processing processor
JPH04117697A (en) Multiport memory circuit
JPH01169564A (en) Inter-processor synchronizing system
JPS6095667A (en) High speed access system in external address space
JPH11328010A (en) Digital signal processor