JPH0512012A - Interruption control system for delay branch - Google Patents

Interruption control system for delay branch

Info

Publication number
JPH0512012A
JPH0512012A JP3164742A JP16474291A JPH0512012A JP H0512012 A JPH0512012 A JP H0512012A JP 3164742 A JP3164742 A JP 3164742A JP 16474291 A JP16474291 A JP 16474291A JP H0512012 A JPH0512012 A JP H0512012A
Authority
JP
Japan
Prior art keywords
instruction
branch
delay
interrupt
delayed
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
JP3164742A
Other languages
Japanese (ja)
Other versions
JP2636562B2 (en
Inventor
Takumi Maruyama
拓巳 丸山
Takahito Noda
敬人 野田
Yuji Kamisaka
裕士 神阪
Kazuyasu Nonomura
一泰 野々村
Toru Watabe
徹 渡部
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 JP3164742A priority Critical patent/JP2636562B2/en
Publication of JPH0512012A publication Critical patent/JPH0512012A/en
Application granted granted Critical
Publication of JP2636562B2 publication Critical patent/JP2636562B2/en
Anticipated expiration legal-status Critical
Expired - Fee Related legal-status Critical Current

Links

Landscapes

  • Advance Control (AREA)

Abstract

PURPOSE:To simplify an interruption handling in the same manner as the interruption handling of a computer which is not provided with a delay branching mechanism. CONSTITUTION:The compter provided with the delay branching mechanism to execute a delay instruction following a branching instruction to branch a program is provided with a means which detects the current instruction as a delay branching instruction (2) and stores it. When the delay branching instruction (2) is detected by this detecting and storage means, an interruption (3) detected at the time of the end of the delay branching instruction (2) is held till the end of execution of a next delay instruction (4) and is executed at the time of the end of the delay instruction (4).

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、遅延分岐機構を有する
計算機の割り込み制御方式に関する。近年のコンピュー
タシステムの分岐処理の高速化の要求に伴い、遅延分岐
機構が一般的になりつつある。
BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an interrupt control system for a computer having a delay branch mechanism. With the recent demand for high-speed branch processing in computer systems, a delayed branch mechanism is becoming common.

【0002】図4は、通常の分岐と遅延分岐との差を説
明する図であり、(a) は通常の分岐の動作を模式的に示
し、(b) は遅延分岐の動作を模式的に示している。上記
遅延分岐機構は、分岐命令によるパイプラインの乱れを
防ぐ機構である。
FIG. 4 is a diagram for explaining a difference between a normal branch and a delayed branch. (A) schematically shows the operation of the normal branch, and (b) schematically shows the operation of the delayed branch. Shows. The delay branch mechanism is a mechanism that prevents the pipeline from being disturbed by a branch instruction.

【0003】通常、命令フェッチ・デコード,実行をパ
イプライン化すると、分岐命令の実行時には、その実行
が完了するまで、次に実行する命令の番地が確定しな
い。従って、次の命令のフェッチ・デコードは、現在の
分岐命令の実行が完了して分岐番地が決定してからでな
いと行えない。{図4(a) 参照}そこで遅延分岐では、
図4(b) に示したように、遅延分岐命令の実行と並列
に、該遅延分岐命令の次の命令(これを遅延命令と呼
ぶ)のフェッチ・デコードを行ってしまい、遅延分岐命
令の実行完了後、上記遅延命令の実行と並列に分岐
番地mにある分岐先命令のフェッチ・デコードを行うよ
うにする機構が、上記遅延分岐機構である。
Normally, if instruction fetch / decode and execution are pipelined, when a branch instruction is executed, the address of the next instruction to be executed is not fixed until the execution is completed. Therefore, fetching and decoding of the next instruction can be performed only after the execution of the current branch instruction is completed and the branch address is determined. {See Fig. 4 (a)} Then, in the delayed branch,
As shown in FIG. 4 (b), in parallel with the execution of the delayed branch instruction, the instruction next to the delayed branch instruction (which is called a delayed instruction) is fetched and decoded, and the delayed branch instruction is executed. After completion, the delay branch mechanism is a mechanism for fetching / decoding the branch destination instruction at the branch address m in parallel with the execution of the delay instruction.

【0004】このような遅延分岐機構を備えた計算機に
おいて、該遅延分岐命令を実行中に外部割り込みが発生
すると、割り込み処理が煩雑となる問題があり、該割り
込み処理を、該遅延分岐機構を備えていない計算機と同
等に簡素化できる割り込み制御方式が必要とされる。
In a computer having such a delay branch mechanism, if an external interrupt occurs during execution of the delay branch instruction, there is a problem that the interrupt processing becomes complicated. Therefore, the interrupt processing is provided with the delay branch mechanism. There is a need for an interrupt control method that can be as simple as a computer that does not.

【0005】[0005]

【従来の技術】図5,図6は、従来の割り込み制御方式
を説明する図であり、図5は、遅延分岐命令実行直後に
外部割り込みが生じた場合の、従来の割り込み処理方式
を示し、図6は遅延分岐命令実行直後に外部割り込みが
生じた場合の、従来の他の割り込み処理方式を示してい
る。
2. Description of the Related Art FIGS. 5 and 6 are diagrams for explaining a conventional interrupt control system, and FIG. 5 shows a conventional interrupt processing system when an external interrupt occurs immediately after execution of a delayed branch instruction. FIG. 6 shows another conventional interrupt processing method when an external interrupt occurs immediately after execution of a delayed branch instruction.

【0006】図5に示した割り込み処理ルーチンでは、 (1) 次命令アドレス(n+1),次々命令アドレス (=分岐先
アドレスm) をセーブする。
In the interrupt processing routine shown in FIG. 5, (1) the next instruction address (n + 1) and the next instruction address (= branch destination address m) are saved.

【0007】(2) 割り込み処理本体を実行する。 (3) 次命令アドレス(n+1) をリストアし、次番地(n+1)
の遅延命令を単独に実行する。
(2) The interrupt processing body is executed. (3) Restore the next instruction address (n + 1) to the next address (n + 1)
Executes the delay instruction of singly.

【0008】(3) 次々命令(分岐先命令)アドレス
(m) をリストアし、当番地へリターンする。 以上の処理を行う。
(3) The instruction (branch destination instruction) address (m) is restored one after another, and the operation returns to the address. The above processing is performed.

【0009】然し、当処理方法では、図5に示されてい
るように、リターン用に2つの命令アドレス{n+1番
地と,m番地)をセーブする必要があり、ハード量の増
大を招くという問題がある。又、割り込み処理からのリ
ターン前に次番地(n+1) の遅延命令を単独に実行する
工夫を必要とする。
However, in this processing method, as shown in FIG. 5, it is necessary to save two instruction addresses (address n + 1 and address m) for return, which causes an increase in the amount of hardware. There is. In addition, it is necessary to devise to execute the delay instruction at the next address (n + 1) independently before returning from the interrupt processing.

【0010】図6は、分岐命令実行直後に外部割り込み
が生じた場合の別の割り込み処理方式を示している。即
ち、この場合の割り込み処理ルーチンでは、 (1) 次命令アドレス(n+1),及び、分岐命令実行直後に外
部割り込みを生じた旨(Bフラグとする)をセーブす
る。
FIG. 6 shows another interrupt processing method when an external interrupt occurs immediately after the execution of a branch instruction. That is, in the interrupt processing routine in this case, (1) the next instruction address (n + 1) and the fact that an external interrupt has occurred immediately after the execution of the branch instruction (set as the B flag) are saved.

【0011】(2) 割り込み処理本体を実行する。 (3) 次命令アドレス(n+1) をリストアし、次番地(n+1)
の遅延命令を単独に実行する。
(2) The main body of interrupt processing is executed. (3) Restore the next instruction address (n + 1) to the next address (n + 1)
Executes the delay instruction of singly.

【0012】(4) Bフラグがoffならば、(n+2) 番地
へリターンするが、Bフラグがonならば、 ・n番地の遅延分岐命令をリード ・分岐先アドレス(m)を計算 ・次々命令アドレス(m) へリターン 以上の処理を行う。
(4) If the B flag is off, the program returns to the address (n + 2), but if the B flag is on, the delayed branch instruction at the address n is read. The branch destination address (m) is calculated. Return to instruction address (m) one after another The above processing is performed.

【0013】然し、当処理方法でも、割り込み処理から
のリターン前に、次番地(n+1) の遅延命令を単独に実
行する工夫を必要とし、更に、上記分岐命令実行直後に
外部割り込みを生じた旨(Bフラグ) が“オン”である
と、割り込み処理ルーチンで、n番地の分岐命令をリー
ドして分岐先アドレスを計算する必要がある。
However, even in this processing method, it is necessary to independently execute the delayed instruction at the next address (n + 1) before the return from the interrupt processing. Furthermore, an external interrupt is generated immediately after the execution of the branch instruction. When the effect (B flag) is "ON", it is necessary to read the branch instruction at address n and calculate the branch destination address in the interrupt processing routine.

【0014】[0014]

【発明が解決しようとする課題】従って、従来の割り込
み処理方式では、 ・リターンアドレスを複数覚えるか,乃至は、遅延分岐
命令直後の割り込みを示すフラグ(前述のBフラグ)
を記憶する必要ある。 ・割り込み処理からのリターン前に、次番地(n+1) の遅
延命令を単独に実行する工夫が必要である。 ・割り込み処理ルーチンで、遅延分岐命令をリードし
て、その分岐先アドレス(m)を計算する必要がある。 といった欠点、即ち、該割込み処理ルーチンが複雑にな
るという欠点がある。
Therefore, according to the conventional interrupt processing method, the following are required: -Remember a plurality of return addresses, or a flag indicating an interrupt immediately after a delayed branch instruction (the above-mentioned B flag).
Need to remember. -Before returning from interrupt processing, it is necessary to devise to execute the delayed instruction at the next address (n + 1) independently. -In the interrupt processing routine, it is necessary to read the delayed branch instruction and calculate the branch destination address (m). That is, there is a drawback that the interrupt processing routine becomes complicated.

【0015】本発明は上記従来の欠点に鑑み、遅延分岐
命令の次の遅延命令を実行して分岐する遅延分岐機
構を備えた計算機において、遅延分岐における外部割り
込み処理を煩雑にすることなく、該遅延分岐機構を備え
てない計算機の割り込み処理と同様に簡素化することが
できる遅延分岐における割り込み制御方式を提供するこ
とを目的とするものである。
In view of the above-mentioned conventional drawbacks, the present invention provides a computer equipped with a delay branch mechanism for executing and branching a delay instruction subsequent to a delay branch instruction without complicating external interrupt processing in the delay branch. An object of the present invention is to provide an interrupt control method in a delay branch that can be simplified similarly to the interrupt processing of a computer that does not have a delay branch mechanism.

【0016】[0016]

【課題を解決するための手段】図1は、本発明の原理説
明図である。上記の問題点は下記の如くに構成した遅延
分岐の割り込み制御方式によって解決される。
FIG. 1 illustrates the principle of the present invention. The above problem is solved by the delay branch interrupt control system configured as follows.

【0017】分岐命令の次の遅延命令を実行して分岐す
る遅延分岐機構を備えた計算機において、現命令が遅延
分岐命令であることを検出して、記憶する手段,9を
設けて、該検出・記憶手段,9で、遅延分岐命令を検
出したとき、該遅延分岐命令の終了時点(T1)で検出し
た割込みを、次の遅延命令の実行終了時点(T2)まで
抑止して、該遅延命令の終了時点(T2)で割り込ませる
ように制御する。
In a computer equipped with a delay branch mechanism for executing a delayed instruction next to a branch instruction and branching, a means (9) for detecting and storing the current instruction as a delayed branch instruction is provided, and the detection is performed. When the memory means 9 detects a delayed branch instruction, the interrupt detected at the end point (T1) of the delayed branch instruction is suppressed until the execution end point (T2) of the next delayed instruction Control to interrupt at the end point (T2).

【0018】[0018]

【作用】即ち、本発明の遅延分岐における割り込み制御
方式においては、遅延分岐命令を実行中は、外部割込
みを受け付けない機構、具体的には、該遅延分岐命令
の終了時点 T1 で割り込みを受け付けないようにし
て、次の遅延命令の終了時点 T2 で、該外部割込み
を受け付ける機構を設けることにより、該遅延分岐命令
と、遅延命令の実行を終了した時点 T2 で割り込み
処理に入ることができるようになる結果、該割り込み処
理は、 (1) 次命令アドレス(m番地の分岐先命令のアドレス)
をセーブする。
That is, in the interrupt control method in the delay branch of the present invention, a mechanism that does not accept an external interrupt during execution of a delayed branch instruction, specifically, does not accept an interrupt at the end point T1 of the delayed branch instruction. By providing a mechanism for accepting the external interrupt at the end time T2 of the next delay instruction, the interrupt processing can be started at the time T2 when the execution of the delay branch instruction and the delay instruction is completed. As a result, the interrupt processing is as follows: (1) Next instruction address (address of branch destination instruction at address m)
To save.

【0019】(2) 割り込み処理本体を実行する。 (3) 次命令アドレス(m)をリストアし、m番地へリタ
ーンする。処理に簡略化される。
(2) The main body of interrupt processing is executed. (3) Restore the next instruction address (m) and return to address m. The process is simplified.

【0020】このような割り込み処理では、当該遅延分
岐機構を備えない、通常の計算機における割り込み処理
と同等であり、割り込み処理を簡素化できる効果があ
る。
Such an interrupt process is equivalent to the interrupt process in an ordinary computer that does not have the delay branch mechanism, and has the effect of simplifying the interrupt process.

【0021】[0021]

【実施例】以下本発明の実施例を図面によって詳述す
る。前述の図1は、本発明の原理説明図であり、図2,
図3は、本発明の一実施例を示した図であり、図2は構
成例を示し、図3は動作タイムチャートを示している。
Embodiments of the present invention will now be described in detail with reference to the drawings. The above-mentioned FIG. 1 is a diagram for explaining the principle of the present invention.
FIG. 3 is a diagram showing an embodiment of the present invention, FIG. 2 shows a configuration example, and FIG. 3 shows an operation time chart.

【0022】本発明においては、分岐命令の次の遅延命
令を実行して分岐する遅延分岐機構を備えた計算機に
おいて、現命令が遅延分岐命令であることを検出し
て、記憶する手段,9を設けて、該検出・記憶手段,9
で、遅延分岐命令を検出したとき、該遅延分岐命令
の終了時点(T1)で検出した割込みを、次の遅延命令
の実行終了時点(T2)まで抑止する手段が、本発明を実施
するのに必要な手段である。尚、全図を通して同じ符号
は同じ対象物を示している。
According to the present invention, in a computer having a delay branch mechanism for executing and branching a delay instruction next to a branch instruction, means 9 for detecting and storing the current instruction as a delayed branch instruction is provided. Is provided with the detection / storage means, 9
When a delayed branch instruction is detected, a means for suppressing the interrupt detected at the end point (T1) of the delayed branch instruction until the execution end point (T2) of the next delayed instruction is to implement the present invention. It is a necessary means. The same reference numerals denote the same objects throughout the drawings.

【0023】以下、図1を参照しながら、図2によっ
て、本発明の遅延分岐における割り込み制御方式の動作
を説明する。先ず、本実施例においては、簡便のため
に、命令フェッチ・デコード,実行の2段パイプライン
を仮定とする。
The operation of the interrupt control system in the delay branch according to the present invention will be described below with reference to FIG. 2 while referring to FIG. First, in the present embodiment, for simplicity, a two-stage pipeline of instruction fetch / decode and execution is assumed.

【0024】図2中、1はメモリであり、命令・データ
を格納する。2は中央処理装置 (以下、CPU という) で
ある。3はメモリバスであり、上記メモリ 1と、CPU 2
間で命令・データの転送に使用する。上記CPU 2 は、上
記メモリ 1から命令をフェッチし、デコードする命令フ
ェッチ&デコード部 4と,命令のデコード結果に従っ
て、各命令を実行する命令実行部 5と,外部割り込み(E
XINT) を受け付け可能か否かを判断する割込処理部 6
とから構成される。7はCPU 2 に対する上記外部割り込
み要求信号(EXINT) である。8は次に実行すべき命令
が遅延分岐命令である(分岐命令がフェッチ・デコー
ドサイクルにある)ことを示す制御信号(DCBRN) であ
り、上記命令フェッチ&デコード部 4から、上記割込処
理部 6に出力され、該遅延分岐命令のフェッチ・デコ
ードサイクルが終了した時点で“オフ”となる。
In FIG. 2, reference numeral 1 is a memory, which stores instructions and data. 2 is a central processing unit (hereinafter referred to as CPU). 3 is a memory bus, and the above memory 1 and CPU 2
Used to transfer instructions and data between The CPU 2 fetches an instruction from the memory 1 and decodes it, an instruction fetch & decode unit 4, an instruction execution unit 5 that executes each instruction according to the instruction decoding result, and an external interrupt (E
Interrupt processing unit 6 that determines whether or not (XINT) can be accepted
Composed of and. Reference numeral 7 is the external interrupt request signal (EXINT) to the CPU 2. Reference numeral 8 is a control signal (DCBRN) indicating that the next instruction to be executed is a delayed branch instruction (the branch instruction is in the fetch / decode cycle). From the instruction fetch & decode unit 4 to the interrupt processing unit It is output to 6, and becomes "off" at the time when the fetch / decode cycle of the delayed branch instruction is completed.

【0025】ラッチ(EXBRN) 9 は遅延分岐命令を実行
中(該遅延分岐命令が実行サイクルにある)を示す制
御フラグ(B) であり、当フラグ(B) が“オン”の間、上
記外部割り込み要求信号(EXINT) 7は無視される。
A latch (EXBRN) 9 is a control flag (B) indicating that a delayed branch instruction is being executed (the delayed branch instruction is in an execution cycle), and while the flag (B) is "on", the external Interrupt request signal (EXINT) 7 is ignored.

【0026】割込処理部 6においては、上記外部割り込
み要求{即ち、外部割り込み要求信号(EXINT) 7が
“オン”}があり、且つ、上記制御フラグ(B) 9 が“オ
フ”になって、上記遅延分岐命令の実行が終了した時
点 T1 で、当要求を受付可能なことを示す信号(INT) を
命令実行部 5に出力する。
In the interrupt processing unit 6, the external interrupt request {that is, the external interrupt request signal (EXINT) 7 is "ON"} and the control flag (B) 9 is "OFF". At the time T1 when the execution of the delayed branch instruction is completed, a signal (INT) indicating that this request can be accepted is output to the instruction execution unit 5.

【0027】従って、該外部割り込み要求信号(EXINT)
7は、次の遅延命令の実行が終了した時点 T2 にお
いて、命令実行部 5に送出され、実際の割り込み処理に
入るように動作する。
Therefore, the external interrupt request signal (EXINT)
7 is sent to the instruction execution unit 5 at the time T2 when the execution of the next delay instruction is completed, and operates so as to start the actual interrupt processing.

【0028】このときの動作タイムチャートを図3に示
す。本図から明らかなように、サイクル3で外部割り込
み要求信号(EXINT) 7が“オン”となるが、当サイク
ルは分岐命令を実行中(上記ラッチ(EXBRN) 9 が“オ
ン”)のため、該割り込み要求は受け付けられず、次の
サイクル4で命令実行部 5に割り込みが通知されること
になる。
An operation time chart at this time is shown in FIG. As is clear from this figure, the external interrupt request signal (EXINT) 7 turns on in cycle 3, but since the branch instruction is being executed (latch (EXBRN) 9 above is on) in this cycle, The interrupt request is not accepted and the instruction execution unit 5 is notified of the interrupt in the next cycle 4.

【0029】従って、該割り込み処理は、前述のよう
に、 (1) 次命令アドレス(m番地の分岐先命令のアドレス)
をセーブする。 (2) 割り込み処理本体を実行する。
Therefore, as described above, the interrupt processing is as follows: (1) Next instruction address (address of branch destination instruction at address m)
To save. (2) Execute the interrupt processing body.

【0030】(3) 次命令アドレス(m)をリストアし、
m番地へリターンする。処理で事足りる。このように、
本発明においては、遅延分岐命令の次の遅延命令を
実行して分岐する遅延分岐機構を備えた計算機におい
て、現命令が遅延分岐命令であることを検出して、記
憶する手段,9を設けて、該検出・記憶手段,9で、遅
延分岐命令を検出したとき、該遅延分岐命令の終了
時点(T1)で検出した外部割込み(EXINT) を、次の遅延
命令の実行終了時点(T2)まで抑止するようにしたとこ
ろに特徴がある。
(3) Restore the next instruction address (m),
Return to address m. Processing is enough. in this way,
In the present invention, in a computer having a delay branch mechanism for executing and branching a delay instruction next to a delay branch instruction, means for detecting that the current instruction is a delay branch instruction and storing the means, 9 is provided. , When the delay branch instruction is detected by the detecting / storing means 9, the external interrupt (EXINT) detected at the end point (T1) of the delay branch instruction until the execution end point (T2) of the next delay instruction The feature is that it was deterred.

【0031】[0031]

【発明の効果】以上、詳細に説明したように、本発明の
遅延分岐による割り込み制御方式は、遅延分岐命令の
次の遅延命令を実行して分岐する遅延分岐機構を備え
た計算機において、現命令が遅延分岐命令であること
を検出して、記憶する手段を設け、該検出・記憶手段
で、遅延分岐命令を検出したとき、該遅延分岐命令
の終了時点(T1)で検出した割込みを、次の遅延命令
の実行終了時点(T2)まで抑止して、該遅延命令の終了
時点(T2)で割り込ませるようにしたものであるので、遅
延分岐機構を備えた計算機における割り込み処理を、当
該機構を備えていない計算機の割り込み処理と同様の処
理に簡素化することができる効果がある。
As described above in detail, in the interrupt control system by delay branching of the present invention, the current instruction is executed in the computer having the delay branching mechanism for executing the branching instruction next to the delaying branching instruction and branching it. Is provided as a delayed branch instruction, and means for storing the same is provided, and when the delayed branch instruction is detected by the detecting / storing means, the interrupt detected at the end point (T1) of the delayed branch instruction is The execution of the delay instruction is stopped until the end time (T2) of the delay instruction, and the interrupt is executed at the end time (T2) of the delay instruction. There is an effect that the processing can be simplified to the same processing as the interrupt processing of a computer not provided.

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

【図1】本発明の原理説明図FIG. 1 is an explanatory diagram of the principle of the present invention.

【図2】本発明の一実施例を示した図(その1)FIG. 2 is a diagram showing an embodiment of the present invention (No. 1).

【図3】本発明の一実施例を示した図(その2)FIG. 3 is a diagram showing an embodiment of the present invention (part 2).

【図4】通常の分岐と遅延分岐との差を説明する図FIG. 4 is a diagram explaining a difference between a normal branch and a delayed branch.

【図5】従来の割り込み制御方式を説明する図(その
1)
FIG. 5 is a diagram for explaining a conventional interrupt control system (No. 1)

【図6】従来の割り込み制御方式を説明する図(その
2)
FIG. 6 is a diagram for explaining a conventional interrupt control system (part 2).

【符号の説明】[Explanation of symbols]

1 メモリ 2 中央処理
装置(CPU) 3 メモリバス 4 命令フェ
ッチ&デコード部 5 命令実行部 6 割込処理
部 7 外部割り込み要求信号(EXINT) 制御信号(DCBRN) 遅延分岐命令 遅延命令
1 memory 2 central processing unit (CPU) 3 memory bus 4 instruction fetch & decode unit 5 instruction execution unit 6 interrupt processing unit 7 external interrupt request signal (EXINT) control signal (DCBRN) delayed branch instruction delayed instruction

フロントページの続き (72)発明者 野々村 一泰 神奈川県川崎市中原区上小田中1015番地 富士通株式会社内 (72)発明者 渡部 徹 神奈川県川崎市中原区上小田中1015番地 富士通株式会社内Front page continuation (72) Inventor Kazuyasu Nonomura 1015 Kamiodanaka, Nakahara-ku, Kawasaki-shi, Kanagawa, Fujitsu Limited (72) Inventor Toru Watanabe 1015, Kamedotachu, Nakahara-ku, Kawasaki, Kanagawa

Claims (1)

【特許請求の範囲】 【請求項1】分岐命令の次の遅延命令を実行して分岐す
る遅延分岐機構を備えた計算機において、現命令が遅延
分岐命令 () であることを検出して、記憶する手段
(,9) を設けて、 該検出・記憶手段 (,9) で、遅延分岐命令 ()を検
出したとき、該遅延分岐命令 () の終了時点で検出し
た割込み () を、次の遅延命令 () の実行終了時点
まで抑止して、該遅延命令 () の終了時点で割り込ま
せるように制御することを特徴とする遅延分岐における
割り込み制御方式。
Claim: What is claimed is: 1. A computer equipped with a delay branch mechanism for executing a delayed instruction next to a branch instruction to branch, and stores the current instruction as a delayed branch instruction (). Means to do
When the delayed branch instruction () is detected by the detecting / storing means (, 9) by providing (, 9), the interrupt () detected at the end of the delayed branch instruction () An interrupt control method in a delayed branch, which is characterized in that the execution is stopped until the end of execution of () and the interrupt is controlled at the end of the delayed instruction ().
JP3164742A 1991-07-05 1991-07-05 calculator Expired - Fee Related JP2636562B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP3164742A JP2636562B2 (en) 1991-07-05 1991-07-05 calculator

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP3164742A JP2636562B2 (en) 1991-07-05 1991-07-05 calculator

Publications (2)

Publication Number Publication Date
JPH0512012A true JPH0512012A (en) 1993-01-22
JP2636562B2 JP2636562B2 (en) 1997-07-30

Family

ID=15799048

Family Applications (1)

Application Number Title Priority Date Filing Date
JP3164742A Expired - Fee Related JP2636562B2 (en) 1991-07-05 1991-07-05 calculator

Country Status (1)

Country Link
JP (1) JP2636562B2 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH06246514A (en) * 1993-02-26 1994-09-06 Star Micronics Co Ltd Automatic lathe
JP2007188527A (en) * 2007-03-19 2007-07-26 Ricoh Co Ltd Interruption processing method for information processor

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0275023A (en) * 1988-09-09 1990-03-14 Fujitsu Ltd Interruption system for delayed branch instruction

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0275023A (en) * 1988-09-09 1990-03-14 Fujitsu Ltd Interruption system for delayed branch instruction

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH06246514A (en) * 1993-02-26 1994-09-06 Star Micronics Co Ltd Automatic lathe
JP2007188527A (en) * 2007-03-19 2007-07-26 Ricoh Co Ltd Interruption processing method for information processor
JP4564025B2 (en) * 2007-03-19 2010-10-20 株式会社リコー Interrupt processing method in information processing apparatus

Also Published As

Publication number Publication date
JP2636562B2 (en) 1997-07-30

Similar Documents

Publication Publication Date Title
US5127091A (en) System for reducing delay in instruction execution by executing branch instructions in separate processor while dispatching subsequent instructions to primary processor
US5404552A (en) Pipeline risc processing unit with improved efficiency when handling data dependency
EP0423906B1 (en) Method of and apparatus for nullifying an instruction
US6301655B1 (en) Exception processing in asynchronous processor
US6275903B1 (en) Stack cache miss handling
JPH07104841B2 (en) Interrupt control method for multiprocessing system
JPH056894B2 (en)
US3553655A (en) Short forward conditional skip hardware
JPH0512012A (en) Interruption control system for delay branch
US6170050B1 (en) Length decoder for variable length data
EP0324952B1 (en) Branching circuit for a pipelined processor
JP2771374B2 (en) Processor cross-page processing method
JP2894438B2 (en) Pipeline processing equipment
JP2783285B2 (en) Information processing device
JP2908096B2 (en) Coprocessor control method
JP2944335B2 (en) Information processing device
JP3123946B2 (en) Microcomputer
JP3017866B2 (en) Interrupt processing method
JP3798180B2 (en) Method and system for buffering instructions in a processor
JP2702137B2 (en) Vector operation instruction processing method
JPH02206836A (en) Data processor
JPS6232507B2 (en)
JPH0774992B2 (en) Data processing device
JPH0740226B2 (en) Branch instruction control method
JPH05298091A (en) Method for information processing and device therefor

Legal Events

Date Code Title Description
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 19970311

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20080425

Year of fee payment: 11

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20090425

Year of fee payment: 12

LAPS Cancellation because of no payment of annual fees