JPH04333950A - Information processing system - Google Patents

Information processing system

Info

Publication number
JPH04333950A
JPH04333950A JP10535391A JP10535391A JPH04333950A JP H04333950 A JPH04333950 A JP H04333950A JP 10535391 A JP10535391 A JP 10535391A JP 10535391 A JP10535391 A JP 10535391A JP H04333950 A JPH04333950 A JP H04333950A
Authority
JP
Japan
Prior art keywords
data
processor
circuit
write
bus
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
JP10535391A
Other languages
Japanese (ja)
Inventor
Toshiaki Ono
大野 敏昭
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 JP10535391A priority Critical patent/JPH04333950A/en
Publication of JPH04333950A publication Critical patent/JPH04333950A/en
Pending legal-status Critical Current

Links

Landscapes

  • Bus Control (AREA)

Abstract

PURPOSE:To prevent a bus from being occupied for a long time and the ability of an input/output device and a processor from being affected by the occupation. CONSTITUTION:This information processing system is equipped with a processor 1 with a central processing circuit 11 to execute a processing according to instructions and data on a memory and a FIFO type write buffer 14 to successively hold data written from this central processing circuit and to successively supply the held written data to the outside. Further, a storage device 3 is provided with a first circuit 31 to primarily hold addresses and data written from the processor while being connected through a memory bus 2 to this processor, second circuit 33 to successively write the information from this first circuit to a storage area and a third circuit 32 to continuously fetch the data of the write buffer in the processor into the first circuit. Moreover, an input/output device 4 connected to the processor and the storage device by the bus is provided to control input/output with an external device, and the addresses and data written from the write buffer in the processor are transferred by one time of bus arbitration.

Description

【発明の詳細な説明】[Detailed description of the invention]

【0001】0001

【産業上の利用分野】本発明は情報処理システムに関す
る。
BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an information processing system.

【0002】0002

【従来の技術】従来、処理装置内にライトバッファを有
する情報処理システムでは、記憶装置内に一次保持の手
段がなく、バスを通して、1語ずつ書き込みアドレスお
よびデータを記憶装置に転送していた。この従来のシス
テム構成例を図3に示す。
2. Description of the Related Art Conventionally, in an information processing system having a write buffer in a processing device, there is no temporary storage means in the storage device, and write addresses and data are transferred word by word to the storage device through a bus. An example of this conventional system configuration is shown in FIG.

【0003】図3に示すシステムではプロセッサ11の
書き込みアドレスおよびデータは、ライトバッファ14
に順次蓄積され、記憶装置3内のメモリ制御回路36に
よって一語ずつ順次読み出され、メモリアレイ34に書
き込まれる。ここで処理装置1内のプロセッサ11と、
プロセッサバス12を通してのキャッシュ13およびラ
イトバッファ14とのやり取りは、プロセッサ11の処
理能力に対して十分高速であり、その処理能力の妨げと
ならないものとする。この従来システムにおいて2語の
連続した書き込み動作のメモリバス2上の時間関係を図
4に示す。
In the system shown in FIG. 3, the write address and data of the processor 11 are stored in the write buffer 14.
The data is sequentially stored in the memory array 34, read out word by word by the memory control circuit 36 in the storage device 3, and written into the memory array 34. Here, a processor 11 in the processing device 1,
It is assumed that the exchange with the cache 13 and the write buffer 14 via the processor bus 12 is sufficiently fast for the processing capacity of the processor 11, and does not interfere with the processing capacity of the processor 11. FIG. 4 shows the time relationship on the memory bus 2 of two consecutive word write operations in this conventional system.

【0004】0004

【発明が解決しようとする課題】従来のシステムでは、
図4からも明らかな通り、バスの調停、アドレスおよび
データの転送、書き込み、結果の報告を行なうため、デ
ータの書き込みのためにバスが長時間占有され、入出力
装置および処理装置の能力に影響を与えるという問題が
ある。
[Problem to be solved by the invention] In the conventional system,
As is clear from Figure 4, since bus arbitration, address and data transfer, writing, and result reporting are performed, the bus is occupied for a long time due to data writing, which affects the performance of input/output devices and processing devices. There is a problem of giving

【0005】[0005]

【課題を解決するための手段】本発明の情報処理システ
ムは、メモリ上の命令およびデータによって処理を行な
う中央処理回路と、この中央処理回路よりの書き込みデ
ータを順次保持し保持した書き込みデータを外部に順次
供給するFIFO型のライトバッファとを有する処理装
置と;この処理装置とバスを介して接続され、前記処理
装置からの書き込みアドレスおよびデータを一次保持す
る第1の手段と、この第1の手段より順次記憶領域内に
書き込む第2の手段と、前記処理装置内の前記ライトバ
ッファのデータを連続して前記第1の手段に取り込む第
3の手段とを有する記憶装置と;前記バスにより前記処
理装置および前記記憶装置に接続され、外部装置との入
出力をつかさどる入出力装置とを備え;前記処理装置内
の前記ライトバッファからの書き込みアドレスおよびデ
ータの転送を一回のバス調停で行なう。
[Means for Solving the Problems] The information processing system of the present invention includes a central processing circuit that performs processing based on instructions and data on a memory, and a central processing circuit that sequentially retains write data from the central processing circuit and transfers the retained write data to an external device. a processing device having a FIFO type write buffer that sequentially supplies data to the processor; a first means connected to the processing device via a bus and temporarily holding write addresses and data from the processing device; a storage device having a second means for sequentially writing into a storage area from the means; and a third means for successively fetching data from the write buffer in the processing device into the first means; The device includes a processing device and an input/output device connected to the storage device and in charge of input/output with an external device; transfer of a write address and data from the write buffer in the processing device is performed by one bus arbitration.

【0006】[0006]

【実施例】次に本発明の実施例について図面を参照して
説明する。本発明の一実施例を示す図1を参照すると、
この情報処理システムメモリバス2を介して相互に接続
される処理装置1,記憶装置3および入出力装置4から
構成される。処理装置1内のプロセッサ11は、記憶装
置3内のメモリアレイ34に格納された命令およびデー
タを読み出し制御回路35によって読み出し、メモリバ
ス2を介して処理装置1内のキャッシュ13に取り込ん
で、キャッシュ13よりプロセッサバス12を介して上
記の読み出し命令およびデータによって処理を実行する
。キャッシュ13はライトスルー型のキャッシュであり
、プロセッサ11からの書き込みデータはキャッシュ1
3に書き込まれると同時に記憶装置3内のメモリアレイ
34にも書き込む必要がある。一般に、記憶装置3を構
成するメモリアレイ34はプロセッサ11の処理速度に
対して十分低速であり、処理能力の妨げとなる。この速
度差の吸収のために処理装置1とメモリバス2との間に
FIFO型のライトバッファ14が置かれ、プロセッサ
11の書き込みアドレスおよびデータを順次蓄積し、ま
た順次メモリバス2へ出力する。さらに、記憶装置3内
に一回のバス調停で処理装置1内のライトバッファ14
に蓄積されたアドレスおよびデータを連続して読み出す
ことのできる連続読み出し回路32を設け、この読み出
されたアドレスおよびデータを一次保持するライトデー
タ保持回路31に一次蓄積し、順次書き込み回路33に
よってメモリアレイ34に書き込む。この情報処理シス
テムにおいて、ライトバッファ14に書き込みアドレス
およびデータが2語分蓄積された場合のメモリバス2上
の時間関係を図2に示す。この時間関係より明らかなよ
うに、従来技術によって10バスサイクル要していた2
語の書き込みが、4サイクルまで短縮され、メモリバス
2の占有率を著しく下げることが可能となる。これによ
り、メモリバス2上に接続された入出力装置4などの装
置からのデータ転送と、処理装置1からの書き込みとの
メモリバス2上の競合を減少することが可能となる。
Embodiments Next, embodiments of the present invention will be described with reference to the drawings. Referring to FIG. 1 illustrating one embodiment of the present invention,
The information processing system is composed of a processing device 1, a storage device 3, and an input/output device 4 that are interconnected via a memory bus 2. The processor 11 in the processing device 1 reads instructions and data stored in the memory array 34 in the storage device 3 using the read control circuit 35, takes them into the cache 13 in the processing device 1 via the memory bus 2, and stores them in the cache. 13 via the processor bus 12, processing is executed in accordance with the above-mentioned read command and data. The cache 13 is a write-through type cache, and write data from the processor 11 is sent to the cache 1.
It is necessary to write to the memory array 34 in the storage device 3 at the same time that the data is written to the memory array 34 in the storage device 3. Generally, the memory array 34 constituting the storage device 3 is sufficiently slow compared to the processing speed of the processor 11, and hinders the processing performance. In order to absorb this speed difference, a FIFO type write buffer 14 is placed between the processing device 1 and the memory bus 2, and it sequentially stores write addresses and data of the processor 11, and sequentially outputs them to the memory bus 2. Furthermore, the write buffer 14 in the processing device 1 is added to the storage device 3 by one bus arbitration.
A continuous readout circuit 32 is provided that can read addresses and data stored in the memory continuously, and the readout addresses and data are temporarily stored in a write data holding circuit 31 that temporarily holds the addresses and data stored in the memory. Write to array 34. In this information processing system, FIG. 2 shows the time relationship on the memory bus 2 when write addresses and data for two words are stored in the write buffer 14. As is clear from this time relationship, the conventional technology required 10 bus cycles2.
Word writing is shortened to 4 cycles, making it possible to significantly reduce the occupancy of the memory bus 2. This makes it possible to reduce contention on the memory bus 2 between data transfers from devices such as the input/output device 4 connected to the memory bus 2 and writes from the processing device 1 .

【0007】[0007]

【発明の効果】以上説明したように本発明によれば、バ
スの占有率を下げることができる。
As explained above, according to the present invention, the bus occupancy rate can be reduced.

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

【図1】本発明の一実施例を示す構成図である。FIG. 1 is a configuration diagram showing an embodiment of the present invention.

【図2】同実施例の動作を説明する図である。FIG. 2 is a diagram illustrating the operation of the embodiment.

【図3】従来例を示す構成図である。FIG. 3 is a configuration diagram showing a conventional example.

【図4】従来例の動作を説明する図である。FIG. 4 is a diagram illustrating the operation of a conventional example.

【符号の説明】[Explanation of symbols]

1    処理装置 2    メモリバス 3    記憶装置 4    入出力装置 11    プロセッサ 14    ライトバッファ 31    ライトデータ保持回路 32    連続読み出し回路 33    書き込み回路 34    メモリアレイ 35    読み出し制御回路 1 Processing equipment 2 Memory bus 3. Storage device 4 Input/output device 11 Processor 14 Write buffer 31 Write data holding circuit 32 Continuous readout circuit 33 Write circuit 34 Memory array 35 Readout control circuit

Claims (1)

【特許請求の範囲】[Claims] 【請求項1】  メモリ上の命令およびデータによって
処理を行なう中央処理回路と、この中央処理回路よりの
書き込みデータを順次保持し保持した書き込みデータを
外部に順次供給するFIFO型のライトバッファとを有
する処理装置と;この処理装置とバスを介して接続され
、前記処理装置からの書き込みアドレスおよびデータを
一次保持する第1の手段と、この第1の手段より順次記
憶領域内に書き込む第2の手段と、前記処理装置内の前
記ライトバッファのデータを連続して前記第1の手段に
取り込む第3の手段とを有する記憶装置と;前記バスに
より前記処理装置および前記記憶装置に接続され、外部
装置との入出力をつかさどる入出力装置とを備え;前記
処理装置内の前記ライトバッファからの書き込みアドレ
スおよびデータの転送を一回のバス調停で行なうことを
特徴とする情報処理システム。
Claim 1: It has a central processing circuit that performs processing according to instructions and data on a memory, and a FIFO type write buffer that sequentially holds write data from the central processing circuit and sequentially supplies the held write data to the outside. a processing device; a first means connected to the processing device via a bus and temporarily holding write addresses and data from the processing device; and a second means for sequentially writing into the storage area from the first means. and a third means for successively fetching the data of the write buffer in the processing device into the first means; connected to the processing device and the storage device by the bus, and connected to the external device. 1. An information processing system, comprising: an input/output device that controls input/output to and from the processing device; and transfers a write address and data from the write buffer in the processing device by one bus arbitration.
JP10535391A 1991-05-10 1991-05-10 Information processing system Pending JPH04333950A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP10535391A JPH04333950A (en) 1991-05-10 1991-05-10 Information processing system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP10535391A JPH04333950A (en) 1991-05-10 1991-05-10 Information processing system

Publications (1)

Publication Number Publication Date
JPH04333950A true JPH04333950A (en) 1992-11-20

Family

ID=14405367

Family Applications (1)

Application Number Title Priority Date Filing Date
JP10535391A Pending JPH04333950A (en) 1991-05-10 1991-05-10 Information processing system

Country Status (1)

Country Link
JP (1) JPH04333950A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5887195A (en) * 1994-12-09 1999-03-23 Nec Corporation Bus arbitration between an I/O device and processor for memory access using FIFO buffer with queue holding bus access flag bit
KR100265056B1 (en) * 1997-11-17 2000-09-01 김영환 Interface method between processor and serial input/output controller

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5887195A (en) * 1994-12-09 1999-03-23 Nec Corporation Bus arbitration between an I/O device and processor for memory access using FIFO buffer with queue holding bus access flag bit
KR100265056B1 (en) * 1997-11-17 2000-09-01 김영환 Interface method between processor and serial input/output controller

Similar Documents

Publication Publication Date Title
JP3598321B2 (en) Buffering data exchanged between buses operating at different frequencies
JPH05173932A (en) Data transfer device
JPH01320564A (en) Parallel processor
JPH0146946B2 (en)
JPH03189843A (en) System and method for processing data
JPH04333950A (en) Information processing system
JPH0222748A (en) Non-volatile memory control circuit
JPH03204753A (en) Dma controller
JPH07182849A (en) Fifo memory
JP2581144B2 (en) Bus control device
JP2699482B2 (en) Data transfer control device
JPH07160655A (en) Memory access system
JPH04278651A (en) Main storage device
JP3063501B2 (en) Memory access control method
JPS59135684A (en) Data bypass system between buffer memories
JPH0370816B2 (en)
JPS63217460A (en) Buffer control circuit
JPH02211571A (en) Information processor
EP0597296A2 (en) Cache architecture for high speed memory-to-I/0 data transfers
JPH0652516B2 (en) Bus interface device
JPS6269347A (en) Direct memory access controller
JPS61117651A (en) Interface device
JPS5816326A (en) Data channel controlling system
JPS6383854A (en) Data transfer circuit
JPS62226366A (en) Shared memory system