JPS5894035A - Data processing system - Google Patents
Data processing systemInfo
- Publication number
- JPS5894035A JPS5894035A JP56192640A JP19264081A JPS5894035A JP S5894035 A JPS5894035 A JP S5894035A JP 56192640 A JP56192640 A JP 56192640A JP 19264081 A JP19264081 A JP 19264081A JP S5894035 A JPS5894035 A JP S5894035A
- Authority
- JP
- Japan
- Prior art keywords
- program
- signal line
- connection
- data processing
- arithmetic 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.)
- Pending
Links
- 238000010586 diagram Methods 0.000 description 5
- 102100023882 Endoribonuclease ZC3H12A Human genes 0.000 description 1
- 101710112715 Endoribonuclease ZC3H12A Proteins 0.000 description 1
- 108700012364 REG1 Proteins 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- QGVYYLZOAMMKAH-UHFFFAOYSA-N pegnivacogin Chemical compound COCCOC(=O)NCCCCC(NC(=O)OCCOC)C(=O)NCCCCCCOP(=O)(O)O QGVYYLZOAMMKAH-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/30—Arrangements for executing machine instructions, e.g. instruction decode
- G06F9/30181—Instruction operation extension or modification
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Advance Control (AREA)
- Executing Machine-Instructions (AREA)
- Complex Calculations (AREA)
Abstract
Description
【発明の詳細な説明】
α) 発明の属する分野の説明
本発明は、データ処理システム、特にプログラムの命令
によりデータ処理装置の内部構成を可変とし得るように
したデータ処理システムに関するものである。DETAILED DESCRIPTION OF THE INVENTION α) Description of the field to which the invention pertains The present invention relates to a data processing system, and particularly to a data processing system in which the internal configuration of a data processing device can be changed by instructions from a program.
■ 従来の技術の説明
従来のむの種装置においては、レジスタ(副)、演算ユ
ニット(AIIT)、ユニットバス(BU8 )相互間
の接続が固定されており、変更不可能のように構成され
ていたので、ベクトル演算のように多数のALUを並列
に実行させることにより処理速度を向上させ得る場合と
、ALUを直列に配置して連続的な演算を実行すること
により処理速度を向上させ得る場合といったようK、プ
ログラムで指示される演算内容が大きく変わった際に、
いずれか一方の演算において処理能力が低下するという
欠点があった。■ Explanation of the conventional technology In conventional microcontrollers, the connections between the register (sub), the arithmetic unit (AIIT), and the unit bus (BU8) are fixed and are configured in such a way that they cannot be changed. Therefore, there are cases where processing speed can be improved by executing many ALUs in parallel, such as vector operations, and cases where processing speed can be improved by arranging ALUs in series and executing continuous operations. For example, when the calculation contents instructed by the program change significantly,
There was a drawback that processing power was reduced in either one of the calculations.
(3) 発明の目的
本発明は、これらの欠点を除去するため、1つ又は複数
のBEG、ALU、BUS 相互間の接続をプログラム
の命令により変更可能とし、プログラムで実行指示され
る演算内容に常に適合した内部構成で演算を実行し、処
理速度の向上を図ることを目的としており、以下図面に
ついて詳細に説明する。(3) Purpose of the Invention In order to eliminate these drawbacks, the present invention makes it possible to change the connection between one or more BEGs, ALUs, and BUSs by instructions from a program, and to change the connection between one or more BEGs, ALUs, and BUSs according to the contents of calculations instructed to be executed by the program. The purpose is to improve processing speed by always executing calculations with an adapted internal configuration, and the drawings will be described in detail below.
(4) 発明の構成および作用の説明第1図は本発明
の実施例で、BUSが4本、ALUが2個、REGが6
個存在する場合のものである。図中の符号1〜4はBU
S1ないしBUS4.5〜8はOOGとパスとを接続す
る信号線、9は接続制御部(OOG)であってプログラ
ムの命令により、BUS、RBG、ALU の入出力信
号線の相互接続を行うもの、lOはプログラムの命令に
よりBUS、ALU、REG相互間の接続変更を00G
K指示するための信号線、11.12.15゜16はA
LUへの入力信号線、13.17はALU l 。(4) Explanation of the structure and operation of the invention Figure 1 shows an embodiment of the invention, in which there are 4 BUSs, 2 ALUs, and 6 REGs.
This is the case when there are more than one. Codes 1 to 4 in the figure are BU
S1 to BUS4.5 to 8 are signal lines that connect OOG and paths, and 9 is a connection control unit (OOG) that interconnects the input/output signal lines of BUS, RBG, and ALU according to program instructions. , IO changes the connection between BUS, ALU, and REG according to program instructions.
Signal line for indicating K, 11.12.15゜16 is A
Input signal line to LU, 13.17 is ALU l.
2であり、14.18はALUl、2の出力信号線、1
9〜24はREGI〜RgG6の出力信号線、31〜3
6はREGl〜REG6への入力信号線、25〜30は
REGI 5−BEG6である。プログラムの命令にし
たがってOOGへの接続を指示する信号線10によって
、OOGへ接続されているBLIS 、 RBG 。2, 14.18 is ALU1, 2 output signal line, 1
9-24 are output signal lines of REGI-RgG6, 31-3
6 is an input signal line to REG1 to REG6, and 25 to 30 are REGI 5 to BEG6. BLIS, RBG are connected to the OOG by a signal line 10 which indicates the connection to the OOG according to the instructions of the program.
ALUの各入出力信号線をCOG内部で接続する。Each input/output signal line of the ALU is connected inside the COG.
00Gの一構成例を第2図、第3図に示す。第2図にお
いて、プログラムの命令によりCOGの接続を指示する
信号(信号線10)はデコーダ(DIXJ)により復号
化され、DEOの出力信号301〜436の値が0又は
1にセットされる。この出力信号線は、BUS、ALU
、RgGからの出力信号線8〜24とBUS、ALU、
REGへの入力信号I!8〜31との交点101〜23
6 の接続を各々制御する。第3図に交点101の構成
例を示す。交点101の制御を行う信号線301の値が
1の場合、AND回路501とOR回路502とにより
、信号線18と31とが接続状態となる。信号線301
の値がOのとき、信号線18の値と無関係に信号線50
3の値は0となり、信号線18と31の接続は断となる
。第2図の他の交点102〜236 も第3図と同様の
構成である。OOGは1ケ所に集中配置されている必要
はなく、データ処理装置内部に分散設置することも可能
である。このような構造になっているため、プロプラム
の命令による信号線10により、ALUl、2を並列に
動作するように構成する場合、OOG内部で信号線24
と15.23と16.18と33.21と11.20と
12.36と14.8と31と22.7と32.6と3
4と19.5と35 をそれぞれ接続することにより第
4図に示す構成が実現され、BUS 1〜4からの入力
データによりAL、Ul。An example of the configuration of 00G is shown in FIGS. 2 and 3. In FIG. 2, a signal (signal line 10) instructing the connection of COG according to a program command is decoded by a decoder (DIXJ), and the values of DEO output signals 301 to 436 are set to 0 or 1. This output signal line is BUS, ALU
, output signal lines 8 to 24 from RgG, BUS, ALU,
Input signal I to REG! Intersection points 101-23 with 8-31
6 connections respectively. FIG. 3 shows an example of the configuration of the intersection 101. When the value of the signal line 301 that controls the intersection 101 is 1, the AND circuit 501 and the OR circuit 502 connect the signal lines 18 and 31. Signal line 301
When the value of is O, the signal line 50 is
The value of 3 becomes 0, and the connection between the signal lines 18 and 31 is disconnected. Other intersection points 102 to 236 in FIG. 2 have the same configuration as in FIG. 3. The OOG does not need to be centrally located at one location, and can be distributed in a distributed manner within the data processing device. Because of this structure, when configuring ALUs 1 and 2 to operate in parallel using the signal line 10 according to program commands, the signal line 24 is connected inside the OOG.
and 15.23 and 16.18 and 33.21 and 11.20 and 12.36 and 14.8 and 31 and 22.7 and 32.6 and 3
The configuration shown in FIG. 4 is realized by connecting BUS 4, 19.5, and 35, respectively.
ALU2がそれぞれ並列動作可能となり、ベクトル演算
等の配列データ相互の高速演算が可能となる。Each of the ALUs 2 can operate in parallel, and high-speed operations on mutual array data such as vector operations become possible.
また、プログラムの命令による信号線10により、AL
Ul、2を直列に動作するように構成する場合、00G
内部で信号線24と15.23と16.18と33゜2
2と11.21と12.14と35.6と31と20.
5と32゜7と34を各々接続することにより第5図に
示す構成を実現することができ、複数データの連続的な
演爽の高速実行が可能となる。なお、第4図、第5図で
は説明の便宜上、COGとその制御信号線10、未接続
となるREGとその入出力信号線などは省略して示され
ている。本実施例はREG 。Also, by the signal line 10 according to the command of the program, AL
When configuring Ul,2 to operate in series, 00G
Internally signal lines 24, 15.23, 16.18 and 33°2
2 and 11.21 and 12.14 and 35.6 and 31 and 20.
5, 32.degree., 7, and 34, the configuration shown in FIG. 5 can be realized, and it is possible to perform continuous performance of a plurality of data at high speed. In FIGS. 4 and 5, for convenience of explanation, the COG and its control signal line 10, the unconnected REG and its input/output signal line, etc. are omitted. This example is REG.
ALU が各々6個と2個との如く少数の場合であるが
、多数のBEG、ALIJ を用いて同様な構成を採る
ことにより、実行したい演算毎にR[G、入LU。Although the number of ALUs is small, such as 6 and 2, by adopting a similar configuration using a large number of BEGs and ALIJs, R[G, input LUs are used for each operation to be executed.
BUS の組み合せを各種に変更することができ、デー
タ処理装置の内部構成がそれぞれに最適な形をとって演
算を実行させることが可能となりプログラム実行時間の
大幅な短縮が可能となる。The combination of BUS can be changed in various ways, and the internal configuration of the data processing device can take the optimal form for each to execute calculations, making it possible to significantly shorten the program execution time.
6) 効果の説明
以上説明したように本発明によれば、プログラムの命令
によりデータ処理装置の内部構成が変更可能であるため
各種の演算実行制御形態の異なるプログラム、例えばノ
イマン形計算機に適したプログラムと非ノイマン形計算
機に適したプログラムなどを同一のデータ処理システム
で効率を損わずに実行することが可能となる利点がある
。更に、データ処理装置をLSI化した場合、内部の構
成を変更することは不可能に近いが、本発明の構成を実
現することにより、例えLSI化されていても内部構成
の変更が可能となる利点もある。6) Description of Effects As explained above, according to the present invention, the internal configuration of the data processing device can be changed by program commands, so that various programs with different arithmetic execution control forms, such as programs suitable for a Neumann type computer, can be used. This has the advantage that programs suitable for non-Neumann type computers can be executed on the same data processing system without loss of efficiency. Furthermore, when a data processing device is implemented as an LSI, it is almost impossible to change the internal configuration, but by implementing the configuration of the present invention, it becomes possible to change the internal configuration even if the data processing device is implemented as an LSI. There are also advantages.
第1図は本発明の一実施例ブロック図、第2図は第1図
図示のOOGの一実施例内部構成図、第3図はOOG内
部の接続回路の一実施例構成図、第4図はOOGの接続
条件にもとづいて、2つの演算ユニットを並列に動作す
るよう接続した状態を説明する説明図、第5図は同じく
2つの演算ユニットを直列に動作するよう接続した状態
を説明する説明図を示す〇
図中、1〜4はデータ・パス(HUS)、5〜8はデー
タ・パスと000間の信号線、9は接続制御部(OOG
)、lOは接続制御信号線、13.17は演算ユニット
(ALU)、25〜30はレジスタ(RJX))。
41はデコーダを表わす。
特許出願人 日本電信電話公社
代理人弁理士 森 1) 寛FIG. 1 is a block diagram of an embodiment of the present invention, FIG. 2 is an internal configuration diagram of an embodiment of the OOG shown in FIG. 1, FIG. 3 is a configuration diagram of an embodiment of the connection circuit inside the OOG, and FIG. 4 is an explanatory diagram illustrating a state in which two arithmetic units are connected to operate in parallel based on the OOG connection conditions, and FIG. 5 is an explanatory diagram illustrating a state in which two arithmetic units are similarly connected to operate in series. In the figure, 1 to 4 are data paths (HUS), 5 to 8 are signal lines between the data path and 000, and 9 is connection control unit (OOG).
), IO is a connection control signal line, 13.17 is an arithmetic unit (ALU), and 25 to 30 are registers (RJX)). 41 represents a decoder. Patent applicant Hiroshi Mori, patent attorney representing Nippon Telegraph and Telephone Public Corporation
Claims (1)
むオペランド・データを格納する複数個の記憶部、1つ
または複数個の演算ユニット、上記記憶部と上記演算ユ
ニットとの1部または全部とを接続し得る1つまたは複
数個のデータ転送手段を少なくとも有するデータ処理シ
ステムにおいて、上記配憶部に対する入出力信号線と上
記演算ユニットに対する入出力信号線と上記データ転送
手段に対する入出力信号線とが集められてプログラムの
命令によりて上記各入出力信号線相互間の接続を変更可
能に制御する接続制御部をもうけ。 上記配憶部と演算ユニットと上記データ転送手段との間
の接続態様をプログラムの命令によって制御するよう構
成したことを特徴とするデータ処理システム。[Scope of Claims] A plurality of storage units storing operand data including program addresses or operation results during processing, one or more arithmetic units, and a portion of the storage unit and the arithmetic unit. In a data processing system having at least one or more data transfer means capable of connecting all of A connection control section is provided in which the signal lines are collected and the connections between the input and output signal lines can be changed according to instructions from a program. A data processing system characterized in that a connection mode between the storage section, the arithmetic unit, and the data transfer means is controlled by instructions of a program.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP56192640A JPS5894035A (en) | 1981-11-30 | 1981-11-30 | Data processing system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP56192640A JPS5894035A (en) | 1981-11-30 | 1981-11-30 | Data processing system |
Publications (1)
Publication Number | Publication Date |
---|---|
JPS5894035A true JPS5894035A (en) | 1983-06-04 |
Family
ID=16294606
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP56192640A Pending JPS5894035A (en) | 1981-11-30 | 1981-11-30 | Data processing system |
Country Status (1)
Country | Link |
---|---|
JP (1) | JPS5894035A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS6024634A (en) * | 1983-07-21 | 1985-02-07 | Matsushita Electric Ind Co Ltd | Digital signal processing device |
JPS6073736A (en) * | 1983-09-29 | 1985-04-25 | Fujitsu Ltd | Information processor |
JPS6074038A (en) * | 1983-09-30 | 1985-04-26 | Fujitsu Ltd | Information processor |
JPS60235238A (en) * | 1984-05-09 | 1985-11-21 | Nec Corp | Large-scale integrated circuit |
JPH0228890A (en) * | 1988-07-19 | 1990-01-30 | Hitachi Ltd | signal processing circuit |
JPH05189200A (en) * | 1992-07-23 | 1993-07-30 | Matsushita Electric Ind Co Ltd | Digital signal processor |
JPH06131155A (en) * | 1991-01-29 | 1994-05-13 | Analogic Corp | Sequential processing apparatus which can be reconstituted |
JPH08234963A (en) * | 1995-02-24 | 1996-09-13 | Nec Corp | Arithmetic unit |
US6292881B1 (en) | 1998-03-12 | 2001-09-18 | Fujitsu Limited | Microprocessor, operation process execution method and recording medium |
JP2007058571A (en) * | 2005-08-24 | 2007-03-08 | Fujitsu Ltd | Circuit and circuit connection method |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS5690342A (en) * | 1979-12-20 | 1981-07-22 | Ibm | Processor |
-
1981
- 1981-11-30 JP JP56192640A patent/JPS5894035A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS5690342A (en) * | 1979-12-20 | 1981-07-22 | Ibm | Processor |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS6024634A (en) * | 1983-07-21 | 1985-02-07 | Matsushita Electric Ind Co Ltd | Digital signal processing device |
JPS6073736A (en) * | 1983-09-29 | 1985-04-25 | Fujitsu Ltd | Information processor |
JPH0232649B2 (en) * | 1983-09-29 | 1990-07-23 | Fujitsu Ltd | |
JPS6074038A (en) * | 1983-09-30 | 1985-04-26 | Fujitsu Ltd | Information processor |
JPH0232650B2 (en) * | 1983-09-30 | 1990-07-23 | Fujitsu Ltd | |
JPS60235238A (en) * | 1984-05-09 | 1985-11-21 | Nec Corp | Large-scale integrated circuit |
JPH0228890A (en) * | 1988-07-19 | 1990-01-30 | Hitachi Ltd | signal processing circuit |
JPH06131155A (en) * | 1991-01-29 | 1994-05-13 | Analogic Corp | Sequential processing apparatus which can be reconstituted |
JPH05189200A (en) * | 1992-07-23 | 1993-07-30 | Matsushita Electric Ind Co Ltd | Digital signal processor |
JPH08234963A (en) * | 1995-02-24 | 1996-09-13 | Nec Corp | Arithmetic unit |
US6292881B1 (en) | 1998-03-12 | 2001-09-18 | Fujitsu Limited | Microprocessor, operation process execution method and recording medium |
JP2007058571A (en) * | 2005-08-24 | 2007-03-08 | Fujitsu Ltd | Circuit and circuit connection method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP0031889B1 (en) | Processor on a single semiconductor substrate | |
JPH0922404A (en) | Array processor communication architecture with broadcast communication processor instruction | |
JPS6211960A (en) | Processor array | |
JPH05233281A (en) | Electronic computer | |
US20030046513A1 (en) | Arrayed processor of array of processing elements whose individual operations and mutual connections are variable | |
JPH01150963A (en) | IPL method on computer | |
JPS5894035A (en) | Data processing system | |
CN110059797B (en) | Computing device and related product | |
JPH11307725A (en) | Semiconductor integrated circuit | |
KR20080106129A (en) | Method and apparatus for connecting multiple multi-mode processors | |
JPH01155459A (en) | Processors and parallel computers | |
JPS5935451B2 (en) | General purpose register access method | |
JPH02500692A (en) | Integration of computational elements in multiprocessor computers | |
JPH0636060A (en) | Array-processor used for slide-network | |
JP2717850B2 (en) | Parallel computer with high-speed communication mechanism | |
JP2845666B2 (en) | Microcomputer | |
JP2744152B2 (en) | Data driven data processor | |
JPH0683618A (en) | Flag control circuit | |
JPS588371A (en) | Data processor | |
JP2504535B2 (en) | Bus unit configuration method | |
JPH03189883A (en) | Lsi configuration system for parallel computer | |
JPH04177527A (en) | Arithmetic processing circuit | |
JPH0293852A (en) | Computer system | |
JPH01263732A (en) | Special action processing system for microprocessor | |
US20050108438A1 (en) | Heterogeneous synergetic computing system |