JPS581256A - Memroy access control system - Google Patents

Memroy access control system

Info

Publication number
JPS581256A
JPS581256A JP56099269A JP9926981A JPS581256A JP S581256 A JPS581256 A JP S581256A JP 56099269 A JP56099269 A JP 56099269A JP 9926981 A JP9926981 A JP 9926981A JP S581256 A JPS581256 A JP S581256A
Authority
JP
Japan
Prior art keywords
memory
data
read
flag
control unit
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.)
Granted
Application number
JP56099269A
Other languages
Japanese (ja)
Other versions
JPH035619B2 (en
Inventor
Masaaki Kobayashi
正明 小林
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.)
Fujitsu Ltd
Original Assignee
Fujitsu 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 Fujitsu Ltd filed Critical Fujitsu Ltd
Priority to JP56099269A priority Critical patent/JPS581256A/en
Publication of JPS581256A publication Critical patent/JPS581256A/en
Publication of JPH035619B2 publication Critical patent/JPH035619B2/ja
Granted legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F12/00Accessing, addressing or allocating within memory systems or architectures
    • G06F12/02Addressing or allocation; Relocation
    • G06F12/08Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
    • G06F12/0802Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches
    • G06F12/0844Multiple simultaneous or quasi-simultaneous cache accessing
    • G06F12/0855Overlapped cache accessing, e.g. pipeline
    • G06F12/0859Overlapped cache accessing, e.g. pipeline with reload from main memory

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Bus Control (AREA)
  • Memory System Of A Hierarchy Structure (AREA)

Abstract

PURPOSE:To improve the processing efficiency of a processing system, by reading out of a main storage data from a common bus side in parallel with the readout of data from a cash memory with the processor. CONSTITUTION:A flag f1(READ) is set to a flag 10 with a memroy access request B and a data in a cash memory 2 is read out to the processor 1. When a direct memory access DMA request A(READ) is transmitted from a common bus 7 during the data readout from the memory 2, a reception section 9 receives it to set a flag F1(READ) of a flag 11. The flags 10 and 11 are checked at a discrimination section 12 and while a bit signal H is effective, when the flags F1 and f1 are set, a readout instruction C is transmitted. Thus, the memory control section 4 reads out the data in a memory 5 and transmits it to a bus 7.

Description

【発明の詳細な説明】 本発明はメ峰すのデータの読出しを制御するメそりアク
セス制御方式に関する。
DETAILED DESCRIPTION OF THE INVENTION The present invention relates to a memory access control method for controlling the reading of data in a memory.

中ヤシェメモリを具備し九処理システAにおいては、内
部パスと共通(外部)パスとを有し、共通パスからのD
MA1!求と、処理装置からのメモシアクセス畳求との
競合を判定し、何れかの一方に内部パスの専有権を与え
る方式を採用している。
A nine-processing system A equipped with an internal storage memory has an internal path and a common (external) path, and D from the common path.
MA1! A method is adopted in which a conflict is determined between a request for memory access and a request for memory access from a processing device, and one of them is given exclusive rights to the internal path.

従来方式を図によって説明する。第1図は従来方式を説
明するブロック図であ!D、1社処理装置、2#′iキ
ヤシユメモリ、3は内部パス、4にメモリ制御部、5は
メモリ、6はパス制御部、7は共通パス% In入出力
装置、λFiDMA要求、Bはメモリアク竜ス要求、d
はデータである。第1図における中ヤシェメモリ2には
メ七り5内の一部のデータdが格納されている・第11
!1において、共通パス7側からのDMA[求人と、処
理装置1からのメそりアクセス要求Bとの競合をパス制
御部6が判定し、何れかの一方に、内部パスの専有を許
可する。このような処理システムにおいて、処理装置l
が中ヤシュメモリ2からデータdを読出しているとき、
共通パス7儒からDMA l!求人が発せられ九場合、
そのDMA[求AがREAD(メ峰す5からのデータの
胱出し)であれば、処m装置IKよる中ヤシュメモリ2
からのデータ読出しと並行して、前記READIIII
求を満たすことが可能である。DMA要求がWRITE
の場合には、前記キャシュメモリ2とメモリ5との双方
のデータを更新せねばならないが、REAI)め場合に
はメモリ5からデータを絖出すのみでよい゛からである
。このように並行読出しを可能とすれば、システムの処
理効率を著しく向上しうる。
The conventional method will be explained using figures. Figure 1 is a block diagram explaining the conventional method! D, 1 company processing device, 2#'i cache memory, 3 is internal path, 4 is memory control unit, 5 is memory, 6 is path control unit, 7 is common path% In input/output device, λFiDMA request, B is memory access Ryusu request, d
is data. In FIG. 1, the middle storage memory 2 stores part of the data d in the menu 5.
! 1, the path control unit 6 determines a conflict between the DMA job offer from the common path 7 side and the mesh access request B from the processing device 1, and permits one of them to exclusively use the internal path. In such a processing system, the processing device l
is reading data d from the middle memory 2,
Common path 7 Confucian to DMA l! If a job offer is issued,
If the DMA [request A is READ (output of data from Meminesu 5), the middle Yash memory 2 by processing device IK
In parallel with reading data from the READIII
It is possible to meet the requirements. DMA request is WRITE
In this case, the data in both the cache memory 2 and the memory 5 must be updated, but in the case of REAI, it is only necessary to retrieve the data from the memory 5. If parallel reading is possible in this way, the processing efficiency of the system can be significantly improved.

本発明は上記の点に着目し次ものであり、処理システム
“の処理効率を向上するメモリアクセス制御方式の提供
を目的とする。
The present invention focuses on the above points and aims to provide a memory access control method that improves the processing efficiency of a processing system.

本線用は、入出力装置等が結ばれた共通パスを制御する
第1の制御部と、主記憶装置を制御する第2の制御部と
、前記第2の制御部とキャシュメモリとに結はれ九処理
装置とを有するデータ処理システムにおいて、前記処理
装置が前記キャシュメモリからデータを貌出し中に、前
記共通パスから前記第1の制御部に対しデータ続出しの
メ売りアク−に2要求を生じた際、前記主記憶数置から
のデータの読出しを可能とする手段を備え九ことをII
#徴とするメモリアクセス制御方式である◎以下、本発
明を図面によって説明する0第2Eは本発明の一実施f
lを説明するプロ11図であり、9は受付部−10,1
1はブック部、12は判別部、Cは読出指令、Hはヒツ
ト信号、F、、F、、ら、f。
For the main line, there is a first control unit that controls a common path connected to input/output devices, a second control unit that controls the main storage device, and a connection between the second control unit and the cache memory. In a data processing system having nine processing devices, while the processing device is extracting data from the cache memory, two requests are made from the common path to the first control unit for a continuous access to data. II.
◎The present invention will be explained below with reference to the drawings. 2.E is an embodiment of the present invention.
This is a professional 11 diagram explaining l, and 9 is a reception part-10,1
1 is a book part, 12 is a discrimination part, C is a read command, H is a hit signal, F, , F, , et al, f.

は7ラグ、その他は第1図と同様である。第211にお
いて、処理装置1からのメモリアクセス要求BKよシア
ラグ部10に7ラグら(READ)がセットされ、キャ
シュメモリ2内のデータdが処理装置lへと読出されて
処理が実行される。このキャシュメモリ2からのデータ
続出し中に、共通パス7側からDMA ill求A(R
EAD)が発せられると、受付部9がこれを受理して、
フラグ11のフラグP、(READ)をセットする。判
別部12F17′)グ部10及び11を調べ、ヒツト信
号Hが有効となっている間に7ラグF、とらとが設定さ
れ九ときに、読出指令Cを発する0この九めメモリ制御
部4はメモリ5内のデータを読出して共通パス7儒へ送
出する。一方、処理装置lによるキャン、メモリ2から
のデー/dの読出しはその11続行される。
is 7 lags, and the rest is the same as in FIG. At step 211, 7lags (READ) are set in the shearrag section 10 in response to the memory access request BK from the processing device 1, and the data d in the cache memory 2 is read out to the processing device 1 to be processed. During this continuous output of data from the cache memory 2, a DMA ill request A(R
EAD) is issued, the reception section 9 receives it and
Flag P, (READ) of flag 11 is set. Discrimination unit 12F17') checks the log units 10 and 11, and issues a read command C when the 7 lags F and torato are set while the hit signal H is valid. reads the data in the memory 5 and sends it to the common path 7. On the other hand, the scanning by the processing device 1 and the reading of data/d from the memory 2 continue for the 11th time.

以上のように本発明は、処理装置によるキャン、メモリ
からのデータの絖出しと並行して、共通パス側から主記
憶データの読出しを可能とするもので、処理システムの
処理効率を著しく向上する利点を有する。
As described above, the present invention enables the main memory data to be read from the common path side in parallel with the scanning by the processing device and the extraction of data from the memory, thereby significantly improving the processing efficiency of the processing system. has advantages.

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

第1図は従来方式を説明するブロック図、第2図は本発
明の一実施例を説明するブロック図であシ、図中に用い
た符号は次の通りである。 lは処理装置、2はキャシュメモリ、3は内部パス、4
はメモリ制御部、5はメモリ、6はパス制御部、7は共
通パス、8は入出力装置、9は受付部、10.11はフ
ラグ部、12は判別部、AはDMA要求、Bはメモリア
クセス要求、Cは読出指令、dはデータ、Eはデータバ
ス、F、、?、、f、if、はフラグ、Hはヒツト信号
を示す。 第j[!] 葉d
FIG. 1 is a block diagram illustrating a conventional system, and FIG. 2 is a block diagram illustrating an embodiment of the present invention. Reference symbols used in the figures are as follows. l is the processing unit, 2 is the cache memory, 3 is the internal path, 4
is a memory control unit, 5 is a memory, 6 is a path control unit, 7 is a common path, 8 is an input/output device, 9 is a reception unit, 10.11 is a flag unit, 12 is a determination unit, A is a DMA request, and B is a Memory access request, C is read command, d is data, E is data bus, F...? , , f, if are flags, and H is a hit signal. No. j[! ] leaf d

Claims (1)

【特許請求の範囲】[Claims] 入出力装置勢が結ばれ良共通バスを制御する第10制御
部と、主記憶装置を制御する第2の制御部と、前記第2
の制御部とキャシュメモリとに結ばれた処理装置とを有
するデータ処理システムにおいて、前記処理装置が前記
キャシュメモリからデータを読出し中に1前記共通バス
から前記第1の制御部に対しデータ読出しのメモリアク
セス畳求を生じた際、前記主記憶装置からのデータの読
出し一可能とする手段を備えたことを特徴とするメモリ
アクセス制御方式0
a tenth control unit that controls a common bus connected to input/output devices; a second control unit that controls a main storage device;
in a data processing system having a control unit connected to a cache memory, and a processing unit connected to a cache memory, while the processing unit is reading data from the cache memory, 1 transmitting a data read request from the common bus to the first control unit; A memory access control method 0 characterized in that it comprises means for enabling reading of data from the main storage device when a memory access request occurs.
JP56099269A 1981-06-26 1981-06-26 Memroy access control system Granted JPS581256A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP56099269A JPS581256A (en) 1981-06-26 1981-06-26 Memroy access control system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP56099269A JPS581256A (en) 1981-06-26 1981-06-26 Memroy access control system

Publications (2)

Publication Number Publication Date
JPS581256A true JPS581256A (en) 1983-01-06
JPH035619B2 JPH035619B2 (en) 1991-01-28

Family

ID=14242962

Family Applications (1)

Application Number Title Priority Date Filing Date
JP56099269A Granted JPS581256A (en) 1981-06-26 1981-06-26 Memroy access control system

Country Status (1)

Country Link
JP (1) JPS581256A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS61190435U (en) * 1985-05-21 1986-11-27

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS55153024A (en) * 1979-05-15 1980-11-28 Toshiba Corp Bus control system
JPS5671129A (en) * 1979-11-15 1981-06-13 Fujitsu Ltd Data processing system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS55153024A (en) * 1979-05-15 1980-11-28 Toshiba Corp Bus control system
JPS5671129A (en) * 1979-11-15 1981-06-13 Fujitsu Ltd Data processing system

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS61190435U (en) * 1985-05-21 1986-11-27

Also Published As

Publication number Publication date
JPH035619B2 (en) 1991-01-28

Similar Documents

Publication Publication Date Title
JPS581256A (en) Memroy access control system
JPH02500692A (en) Integration of computational elements in multiprocessor computers
JPS59173828A (en) Data processing system
JP3307331B2 (en) Network file system data transfer method
JPH0844659A (en) Data transfer controller
JPS6130300B2 (en)
JP2501393B2 (en) Direct memory access device
JP2594673B2 (en) Data processing method
JP3442099B2 (en) Data transfer storage device
JP2552025B2 (en) Data transfer method
JPH05250310A (en) Data processor
JP2552015B2 (en) Data transfer device
JP3219422B2 (en) Cache memory control method
JPS6411984B2 (en)
JPH07334453A (en) Memory access system
JPH0573473A (en) Industrial computer system
JPH01144151A (en) Information processor
JPS6037933B2 (en) Computer memory access method
JPH0795312B2 (en) Remote display terminal control system
JPH0471224B2 (en)
JPH02301851A (en) System bus accessing system
JPH04352047A (en) Method and device for controlling address conversion
JPS63281545A (en) Method for transmitting serial data
JPS6240748B2 (en)
JPH0334043A (en) Information processor including master and slave devices connected to each other via system bus