JPS60175173A - Information processing system - Google Patents
Information processing systemInfo
- Publication number
- JPS60175173A JPS60175173A JP3067584A JP3067584A JPS60175173A JP S60175173 A JPS60175173 A JP S60175173A JP 3067584 A JP3067584 A JP 3067584A JP 3067584 A JP3067584 A JP 3067584A JP S60175173 A JPS60175173 A JP S60175173A
- Authority
- JP
- Japan
- Prior art keywords
- request
- access
- main memory
- input
- memory access
- 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
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
- G06F13/14—Handling requests for interconnection or transfer
- G06F13/16—Handling requests for interconnection or transfer for access to memory bus
- G06F13/18—Handling 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
Description
【発明の詳細な説明】
発明の為する技術分野
本発明は粗結合型マルチプロセッサで構成された情報処
理システムに関する。DETAILED DESCRIPTION OF THE INVENTION Technical Field The present invention relates to an information processing system configured with loosely coupled multiprocessors.
従来技術
複数台の処理装置を有するマルチプロセッサシステムは
、全土メモリ領域を共用する密結合型と主メモリ領域を
共用しない粗結合型とに分類される。粗結合型マルチプ
ロセッサは装置間の独立性か高く、耐故障性に優れてい
るが、密結合型システムは性能改善面で粗結合型より優
れている。一方通常運用は密結合で行い、新しいソフト
ウェアのデバッグ時、システムを粗結合運転し、業務の
運用と並行して独立なシステムでデバッグするという運
用力入も行なわれている0ところが粗結合システムを桐
、築するためには、各装置を完全に21に用意しなけれ
はならずハードウェア量が増加するという問題がある。BACKGROUND OF THE INVENTION Multiprocessor systems having a plurality of processing units are classified into tightly coupled types in which the entire memory area is shared, and loosely coupled types in which the main memory area is not shared. Coarsely coupled multiprocessors have high independence between devices and excellent fault tolerance, but tightly coupled systems are superior to loosely coupled systems in terms of improved performance. On the other hand, normal operations are performed in a tightly coupled system, and when debugging new software, the system is operated in a loosely coupled manner, and operation input is also performed by debugging on an independent system in parallel with business operations. In order to build a paulownia, each device must be completely prepared in 21 units, which poses a problem in that the amount of hardware increases.
すなわち、主メモリおよび主メモリへの演其処fMit
のアクセスを制御するシステム制御装置は完全に2重に
用意する必要がある。That is, the main memory and the input to the main memory fMit
It is necessary to prepare completely duplicate system control devices to control access to the system.
発明の目的
本発明の目的はハードウェア量の増加を最小にした粗結
合の情報処理システムを提供することにある。OBJECTS OF THE INVENTION An object of the present invention is to provide a loosely coupled information processing system that minimizes the increase in the amount of hardware.
発明の構成
すなわち、本発明のシステムは、複数の演算処理装置と
、複数の入出力処理装置と生メモリに接続され前記複数
の演算処理装置および入出力処理装置の主メモリアクセ
スと前記各処理装置間の通信を制御する1台のシステム
制御装置と、前記複数の演算処理装置が密結合運転状態
か粗結合運転状態かを保持する状態保持手段と、粗結合
運転状態で交情可能な前記演算処理装置と入出力装置と
の組合せを保持する接続制御回路とを有し、粗結合運転
状態では前記接続制御回路によって指定される前記演算
処理装置と前記入出力装置との通信のみを許各すること
を特徴とする。In other words, the system of the present invention includes a plurality of arithmetic processing units, a plurality of input/output processing units, and a raw memory connected to the main memory access of the plurality of arithmetic processing units and the input/output processing units, and each of the processing units. one system control device that controls communication between the two, a state holding means that maintains whether the plurality of arithmetic processing units are in a tightly coupled operating state or a loosely coupled operating state, and the arithmetic processing unit that is capable of intercourse in the loosely coupled operating state A connection control circuit that maintains a combination of the device and the input/output device, and in a loosely coupled operating state, only communication between the arithmetic processing device and the input/output device specified by the connection control circuit is allowed. It is characterized by
発明の実施例 次に本発明について、図面を参照して詳細に説明する。Examples of the invention Next, the present invention will be explained in detail with reference to the drawings.
第1図を参照すると、本発明の一実施例は、演算処理装
置(以下CPU)2および3;入出力処理装k(以下l
0P)4および5;主記憶装置(以下MMU)6および
CPU2.3とl0P4.5のMMU6へのアクセスと
CPU2.3およびl0P4.5の間の通イBを制御す
るシステム%jlJ御装負(以下’5CU)1から構成
されている。Referring to FIG. 1, one embodiment of the present invention includes arithmetic processing units (hereinafter referred to as CPU) 2 and 3; input/output processing unit k (hereinafter referred to as l);
0P) 4 and 5; Main memory device (hereinafter referred to as MMU) 6 and system control load that controls access to MMU 6 of CPU 2.3 and l0P4.5 and communication between CPU2.3 and l0P4.5. (hereinafter referred to as '5CU).
5CUIの動作は密結合モードと粗結合モードとで異な
る。このモードは初期設定時に設定される。The operation of 5CUI differs between tightly coupled mode and loosely coupled mode. This mode is set during initial setup.
密結合モードにおいてはCPU2,3および10P4゜
5は任慈の主記憶エリヤ、任意めプロセッサにアクセス
できるが、粗結合モードにおいてはCPU1はl0P4
と、CPU2はl0P5とのみ交信可能であシ、CPU
IおよびCPU2間の通信は禁止される。アクセスでき
る主記憶の領域も限定される。以下粗結合モードでの動
作を第2図を参照して説明する。第2図は5CUIの概
略構成を示す図である。In tightly coupled mode, CPUs 2, 3 and 10P45 can access Renci's main memory area and any processor, but in loosely coupled mode, CPU1 can access l0P4.
, CPU2 can only communicate with l0P5.
Communication between I and CPU2 is prohibited. The area of main memory that can be accessed is also limited. The operation in the coarse coupling mode will be explained below with reference to FIG. FIG. 2 is a diagram showing a schematic configuration of 5CUI.
谷装に2〜5からのメモリアクセス要求は8CU1のリ
クエスト受付回路20.21,22および23にセット
される。リクエスト受付回路20〜23は、各処理装置
2〜5がアクセス可能な主記憶の領域を記憶するレジス
タを有する。本実施例ではアクセス可能領域を開始番地
とサイズの形で指定する2組のレジスタを各リクエスト
受付回路20〜23は備えており、初期設定時にその値
が設定される。Memory access requests from units 2 to 5 are set in request receiving circuits 20, 21, 22 and 23 of 8CU1. The request reception circuits 20 to 23 have registers that store areas of main memory that can be accessed by each of the processing devices 2 to 5. In this embodiment, each of the request reception circuits 20 to 23 includes two sets of registers for specifying an accessible area in the form of a start address and size, and the values thereof are set at the time of initial setting.
第3図を参照すると、MMU5の記憶領域は分割され、
CPIJ2.l0P4およびcpu3. Iop5専川
の領域と全処珍装伽が共通にアクセスできる領域とに分
けられる。Referring to FIG. 3, the storage area of the MMU 5 is divided into
CPIJ2. l0P4 and cpu3. It is divided into the area of Iop5 Senkawa and the area that can be accessed in common by all the places.
書び第2図を参照すると、リクエスト受付(ロ)路20
.21.22および23は受付けたメモリアクセス要求
のアドレスが、指定された領域内かどうかをチェックす
る。もしアクセス範囲外であれば、領域外アクセスエラ
ーを要求元装置に対し、応答回路24t?介して報告す
る。アクセス要求が指定された領域内であれは、制御回
路27は谷リクエスト受付回路20〜23からの信号に
従いその優先順位を判定し、最も優先順位の尚いリクエ
ストを選びリクエスト送出回路25を介してMMLJ6
に送出する。MMU5はリクエストに従って書込もしく
は読出動作を行い、その結果をメモリリグライ(ロ)路
26に送出する。さらにリプライは応答回路24を介し
て賛求元装伽に送出される。Referring to Figure 2, request reception (b) road 20
.. 21, 22 and 23 check whether the address of the accepted memory access request is within the specified area. If it is outside the access range, the response circuit 24t? sends an out-of-range access error to the requesting device. Report via. If the access request is within the designated area, the control circuit 27 determines its priority according to the signals from the valley request reception circuits 20 to 23, selects the request with the lowest priority, and sends the request to the request transmission circuit 25. MMLJ6
Send to. The MMU 5 performs a write or read operation according to the request and sends the result to the memory rewrite path 26. Further, the reply is sent to the customer via the response circuit 24.
処理装置間の通信は次のように行なわれる。各処趣装(
至)−からの通イ♂袈求(CPUからのI(JP起動ま
たはIOPからのCPUへの割込報告)はメモリアクセ
スと同様リクエスト受付回路20 、21 。Communication between processing devices is performed as follows. Each place (
The communication request from the CPU (I (JP startup or interrupt report to the CPU from the IOP) from the CPU) is processed by the request reception circuits 20 and 21 in the same way as memory access.
22および23にセットされる。各リクエスト受付回に
’i’r20.2’l、22および23は粗結合モード
で針される処理装置間通信かどうかを、初期設定情報に
もとづきチェックする。違反するアクセスはメモリの領
域外アクセスエラーと同様にアクセス違反を要求元装置
に報告する。許されたアクセスであれは制御回路27に
よる優先順位の判定を行い、最もプライオリティが尚け
れば応答回路24を介して、その要求は要求先処理装置
に送出される。22 and 23. Each time a request is accepted, 'i'r20.2'1, 22 and 23 check based on the initial setting information whether the communication between the processing devices is performed in the coarse coupling mode. Violating accesses are reported to the requesting device in the same manner as memory out-of-area access errors. If the access is permitted, the priority is determined by the control circuit 27, and if the priority is lower, the request is sent to the request destination processing device via the response circuit 24.
本実施例ではCPU3およびl0P5はMMU6のn帯
地〜(2n−1)番地、2n番地からm番地までアクセ
ス可能である。この主メモリアドレスとプログラムアド
レスとの対応は、プログラムの発生する仮想アドレスを
主メモリの実アドレスへの変侠の過程で使用する公知の
ページ表を用いてCPU内で行なわれる。In this embodiment, the CPU 3 and l0P5 can access addresses n to (2n-1) and addresses 2n to m of the MMU 6. This correspondence between main memory addresses and program addresses is performed within the CPU using a known page table that is used in the process of converting virtual addresses generated by a program to real addresses in main memory.
本実施例ではSCUが1つのシステムについて説明した
が、第4図に示される28CUのシステムにも適用可能
なことは明らかであり、第4図に示される例では最大4
つのオペレーティングシステムの粗結合連転が可能とな
る。Although this embodiment describes a system with one SCU, it is obvious that it can also be applied to a system with 28 CUs shown in FIG. 4, and in the example shown in FIG.
This enables coarse-coupled interlocking of two operating systems.
発明の効果
本発明には1台のSCUで粗結合運転システムを構築で
きるため、ノ\−ドウエアの大幅削減ができるという効
果がある。Effects of the Invention The present invention has the advantage that a coarsely coupled operation system can be constructed with one SCU, so that the amount of node hardware can be significantly reduced.
第1図は本発明の一実施例を示す図、第2図はシステム
制御@C負の桐成例を示すブロック図、第3図は主メモ
リ領域の割当を示す図、および第4図は本発明の他の実
施例を示す図でめる。
第1図から第4図において、1.7・・・・・・システ
ム制御装置、2,3,8.9・・・・・・演算処理装置
、4.5,9.11・・・・・・入出力処理装置鉦、6
.12・・・・・・主メモリ。
MMul−。
第 3 図
Cptl 2. l0p4
アクPスげ食Q師風j
cptn、rθP、、5
ア’/ffスqa、@域゛
C,pu2.3 ’、l0p4.6
1りPス可能預域゛FIG. 1 is a diagram showing an embodiment of the present invention, FIG. 2 is a block diagram showing an example of system control @C negative Kirin, FIG. 3 is a diagram showing main memory area allocation, and FIG. Figure 3 is a diagram showing another embodiment of the invention. 1 to 4, 1.7... system control device, 2, 3, 8.9... arithmetic processing unit, 4.5, 9.11... ...I/O processing device key, 6
.. 12... Main memory. MMul-. Figure 3 Cptl 2. l0p4 Aku P Suugekiku Q Shifu j cptn, rθP,, 5 A'/ff Sqa, @ area゛C, pu2.3', l0p4.6 1riPs possible storage area゛
Claims (1)
記入出力処理装置の主メモリアクセスと前記各処理装置
間の通信とを制御する1台のシステム制御装置と、 前記複数の演算処理装置が密結合運転状態か粗結合運転
状態かを保持する状態保持手段と、粗結合運転状態で間
借可能な前記演算処理装置と入出力処理装置との組合せ
を保持する接続制御回路とを有し、 粗結合運転状態では前記接続制御回路によって指定され
る前記演算処理装置と前記入出力装置との通信のみを許
容することを特徴とする情報処理システム。[Claims] A plurality of arithmetic processing units and a plurality of input/output processing units. a system control device that is connected to a main memory and controls a plurality of arithmetic processing units, main memory access of the input/output processing device, and communication between the respective processing devices; a state holding means for maintaining either a tightly coupled operating state or a loosely coupled operating state; and a connection control circuit that maintains a combination of the arithmetic processing unit and the input/output processing device that can be borrowed in the loosely coupled operating state; An information processing system characterized in that in a coupled operating state, only communication between the arithmetic processing unit and the input/output device specified by the connection control circuit is allowed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP3067584A JPS60175173A (en) | 1984-02-21 | 1984-02-21 | Information processing system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP3067584A JPS60175173A (en) | 1984-02-21 | 1984-02-21 | Information processing system |
Publications (1)
Publication Number | Publication Date |
---|---|
JPS60175173A true JPS60175173A (en) | 1985-09-09 |
Family
ID=12310285
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP3067584A Pending JPS60175173A (en) | 1984-02-21 | 1984-02-21 | Information processing system |
Country Status (1)
Country | Link |
---|---|
JP (1) | JPS60175173A (en) |
-
1984
- 1984-02-21 JP JP3067584A patent/JPS60175173A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US6986005B2 (en) | Low latency lock for multiprocessor computer system | |
US20030131067A1 (en) | Hardware support for partitioning a multiprocessor system to allow distinct operating systems | |
JPH0760422B2 (en) | Memory lock method | |
JPH10228458A (en) | Multiprocessor computer having configurable hardware system domain | |
JPH01200466A (en) | Variable resource zoning apparatus and method for data processing system | |
KR100268655B1 (en) | Multiple bus architecture | |
US6339812B1 (en) | Method and apparatus for handling invalidation requests to processors not present in a computer system | |
JPS63175962A (en) | Direct memory access controller | |
JPS60175173A (en) | Information processing system | |
JPS60173655A (en) | Memory system of multiprocessor | |
JPS60175170A (en) | Information processing system | |
JP3187446B2 (en) | Cache memory controller | |
JPH11338833A (en) | Multiprocessor type controller and scalable controller system | |
JPS60175172A (en) | Information processing system | |
JPS61165170A (en) | Bus controlling system | |
JPS60175171A (en) | Information processing system | |
JPH01501660A (en) | Intercomputer communication control device and method | |
JP2929631B2 (en) | Communication device between processors | |
JP3112280B2 (en) | Computer system | |
JPH056333A (en) | Multi-processor system | |
JP3219422B2 (en) | Cache memory control method | |
KR100251849B1 (en) | I/o control board having multiplexing function | |
JPS5935221A (en) | Discrimination system for different kind of board of computer system | |
JPS61269545A (en) | Computer system | |
JPH0342762A (en) | Inter-processor communication method for multiprocessor system |