JP2727615B2 - Logic simulation equipment - Google Patents
Logic simulation equipmentInfo
- Publication number
- JP2727615B2 JP2727615B2 JP1006162A JP616289A JP2727615B2 JP 2727615 B2 JP2727615 B2 JP 2727615B2 JP 1006162 A JP1006162 A JP 1006162A JP 616289 A JP616289 A JP 616289A JP 2727615 B2 JP2727615 B2 JP 2727615B2
- Authority
- JP
- Japan
- Prior art keywords
- simulation
- processor
- circuit
- time
- logic simulation
- 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.)
- Expired - Lifetime
Links
Landscapes
- Test And Diagnosis Of Digital Computers (AREA)
Description
【発明の詳細な説明】 〔産業上の利用分野〕 本発明は論理シミュレーション装置に関し、特にマル
チプロセッサ方式の論理シミュレーション装置に関す
る。Description: BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a logic simulation apparatus, and more particularly to a multiprocessor logic simulation apparatus.
近年のVLSI化技術の進歩による集積回路の大規模化,
高密度化に伴い、開発期間,コストの面から実際の集積
回路を製造する前の論理・タイミングの検証作業が必要
不可欠になりつつある。Recent advances in VLSI technology have increased the scale of integrated circuits,
With the increase in density, verification work of logic and timing before manufacturing an actual integrated circuit is becoming indispensable in terms of development period and cost.
初期の論理シミュレーションはソフトウェアにより実
現していたが、被検証回路の大規模化,高機能化に伴
い、ハードウェアで論理シミュレーションを実行する専
用エンジンが開発され、一部実用化されている。これら
の専用エンジンは一般に汎用の8〜32bitマイクロプロ
セッサを複数個用いたマルチプロセッサ方式を採用して
おり、被検証回路を複数の部分回路に分割してシミュレ
ーションを実行し、処理速度を向上させている。Initially, the logic simulation was realized by software, but with the increase in the scale and the functionality of the circuit to be verified, a dedicated engine for executing the logic simulation by hardware has been developed and partially put into practical use. These dedicated engines generally employ a multiprocessor system using a plurality of general-purpose 8- to 32-bit microprocessors. The simulation is performed by dividing the circuit under test into a plurality of partial circuits to improve the processing speed. I have.
上記のような論理シミュレーション方式では、処理速
度を向上させるために被検証回路の中で入力端子の状態
値が変化した素子のみを評価し、出力状態値に変化が生
じた時のみ状態値を接続先へ伝搬するセレクティブ・ト
レース法をシミュレーションアルゴリズムとして採用し
ている。In the logic simulation method as described above, to improve the processing speed, only the elements whose state values of the input terminals have changed in the circuit under test are evaluated, and the state values are connected only when the output state values change. The selective tracing method propagating to the front is adopted as a simulation algorithm.
上述した従来の論理シミュレーション装置では、評価
を状態値の伝搬順に実行するので、双方向素子を含む回
路を評価する場合には状態値が収束するまで素子を評価
しなければならず、多大な計算時間を必要とする。ま
た、各素子毎に評価の優先順位を付加してシミュレーシ
ョンを実行しても、回路データの各プロセッサへの割り
付け方によってはプロセッサ間通信が非同期に発生し、
各プロセッサがそのたびごとに同期をとらなければなら
ず、各プロセッサのむだ時間が多くなりシミュレーショ
ン速度が低下するという欠点がある。In the above-described conventional logic simulation apparatus, evaluations are performed in the order of propagation of state values. Therefore, when evaluating a circuit including bidirectional elements, elements must be evaluated until the state values converge, resulting in a large amount of calculation. Needs time. Also, even if a simulation is executed with the evaluation priority added to each element, inter-processor communication occurs asynchronously depending on how circuit data is allocated to each processor,
Each processor has to synchronize each time, and there is a disadvantage that the dead time of each processor increases and the simulation speed decreases.
本発明の論理シミュレーション装置は、被検証回路を
構成する素子の遅延値に従って前記素子に評価の優先順
位を付与する手段と、遅延値を持つ前記素子の出力端子
で前記被検証回路を複数の部分回路に分割する手段と、
シミュレーションを実行するプロセッサ群へ前記部分回
路を割りつける手段と、シミュレーション時刻を管理す
る手段と、シミュレーション実行時の各時刻毎にプロセ
ッサ間のイベント通信を行ないプロセッサ同期をとる手
段と、各時刻毎に前記優先順位に従い前記素子を評価す
る手段とを含む。The logic simulation apparatus according to the present invention comprises: means for assigning an evaluation priority to the element according to a delay value of an element constituting the circuit under test; Means for dividing into circuits;
Means for allocating the partial circuit to a processor group for executing a simulation, means for managing a simulation time, means for performing event communication between processors at each time at the time of simulation execution, and means for processor synchronization, Means for evaluating the device according to the priority order.
次に、本発明の実施例について図面を参照して詳細に
説明する。Next, embodiments of the present invention will be described in detail with reference to the drawings.
第1図は本発明の論理シミュレーション装置の一実施
例を示す構成図である。同図において論理シミュレーシ
ョン装置10はプロセッサ群1と共有メモリ2と共通バス
3とを有し、汎用計算機20に接続されている。FIG. 1 is a block diagram showing an embodiment of a logic simulation apparatus according to the present invention. In FIG. 1, a logic simulation apparatus 10 has a processor group 1, a shared memory 2, and a common bus 3, and is connected to a general-purpose computer 20.
汎用計算機20は被検証回路の回路データおよび入力パ
タンデータをプロセッサ群1へダウンロードし、プロセ
ッサ群1からシミュレーション結果を入力して主記憶へ
格納する。The general-purpose computer 20 downloads the circuit data of the circuit to be verified and the input pattern data to the processor group 1, inputs the simulation result from the processor group 1, and stores it in the main memory.
共有メモリ2はプロセッサ群1のいづれのプロセッサ
からでもアクセスが可能なマルチポートメモリであり、
プロセッサ群1が同期をとるためのフラグ類を格納す
る。共通バス3は汎用計算機20とプロセッサ群1,または
プロセッサ群1の中に任意の2つのプロセッサ群が相互
に通信するための通信経路である。プロセッサ群1は被
検証回路を分割した部分回路群及び入力パタンを入力
し、各時刻毎にプロセッサ間通信を行い部分回路群をシ
ミュレートし、結果を汎用計算機20へ送出する。The shared memory 2 is a multi-port memory that can be accessed from any processor in the processor group 1.
The processor group 1 stores flags for synchronization. The common bus 3 is a communication path through which the general-purpose computer 20 and the processor group 1 or any two of the processor group 1 communicate with each other. The processor group 1 inputs the partial circuit group obtained by dividing the circuit to be verified and the input pattern, performs inter-processor communication at each time to simulate the partial circuit group, and sends the result to the general-purpose computer 20.
第2図は上記の論理シミュレーション装置の動作を示
す流れ図である。同図において評価優先順位付与手段21
は被検証回路を構成する素子に(1)零遅延素子,
(2)双方向素子,(3)遅延素子の順に優先順位を付
与する。FIG. 2 is a flowchart showing the operation of the above logic simulation apparatus. In the figure, evaluation priority assigning means 21
Are the elements constituting the circuit under test (1) zero delay element,
Priorities are assigned in the order of (2) bidirectional elements and (3) delay elements.
部分回路へ分割する手段22は被検証回路を遅延素子の
出力端で分割し、複数の部分回路データを生成する。The means for dividing into sub-circuits 22 divides the circuit under test at the output terminal of the delay element to generate a plurality of sub-circuit data.
部分回路を各プロセッサへ割りつける手段23は生成さ
れた部分回路データをプロセッサ群1へダウンロードす
る。The means 23 for allocating the partial circuit to each processor downloads the generated partial circuit data to the processor group 1.
シミュレーション時刻を管理する手段24はシミュレー
ション実行時に時刻を管理し、シミュレーション終了時
刻までシミュレーションが進んだ時にシミュレーション
を打ち切る。そうでない場合には時刻を1単位インクメ
ントし、処理を継続させる。The simulation time management means 24 manages the time when the simulation is executed, and terminates the simulation when the simulation has advanced to the simulation end time. Otherwise, the time is incremented by one unit, and the process is continued.
プロセッサ間の通信及び同期手段25は遅延素子の出力
端を監視し、現在処理中の時刻に変化が生じるか否かを
判定する。変化が生じる場合、その遅延素子の接続先が
他のプロセッサにわりふられているときにはプロセッサ
間通信を行う。そして全ての遅延素子の出力端を評価し
た後に共有メモリ2の中の自プロセッサにわりあてられ
たフラグをONにし、プロセッサ間通信処理が終了したこ
とを通知し、他プロセッサにわりふられたフラグが全て
ONになるまて待つ。The communication and synchronization means 25 between the processors monitors the output end of the delay element and determines whether or not a change occurs in the time currently being processed. When a change occurs, communication between processors is performed when the connection destination of the delay element is replaced by another processor. Then, after evaluating the output terminals of all the delay elements, the flag assigned to the own processor in the shared memory 2 is turned on to notify that the inter-processor communication processing has been completed, and the flag assigned to the other processor is set. all
Wait for it to turn ON.
各時刻毎に優先順位に従った素子評価をする手段26は
共有メモリ2の各プロセッサにわりふられたフラグが全
てONになった後、優先順位の高い素子で入力端に状態値
の変化がある素子から順に評価し、出力状態値を演算す
る。出力状態値に変化が生じた場合、状態値を接続先へ
伝搬する。The means 26 for performing element evaluation in accordance with the priority at each time is such that after all the flags assigned to the respective processors in the shared memory 2 are turned on, a change in the state value at the input terminal of the element having a higher priority is performed. The evaluation is performed in order from a certain element, and the output state value is calculated. When a change occurs in the output state value, the state value is propagated to the connection destination.
上記の処理を評価する素子がなくなるまでくり返す。 The above processing is repeated until there are no more elements to be evaluated.
本発明の論理シミュレーション装置は被検証回路を構
成する素子に優先順位を付与して優先順位順に評価する
ので、双方向素子を含む回路をむだな評価をせずにシミ
ュレーションする事ができる。また、プロセッサ間同期
は各時刻毎にたかだか1回しか発生しないので、各プロ
セッサのむだ時間を低減しシミュレーション速度を向上
させる事ができるという効果がある。Since the logic simulation apparatus of the present invention assigns priorities to the elements constituting the circuit to be verified and evaluates them in order of priority, it is possible to simulate the circuit including the bidirectional elements without performing unnecessary evaluation. Further, since the synchronization between the processors occurs at most once at each time, there is an effect that the dead time of each processor can be reduced and the simulation speed can be improved.
第1図は本発明による論理シミュレーション装置の一実
施例を示す構成図、第2図は処理動作を示す流れ図であ
る。 1…プロセッサ群、2…共有メモリ、3…共通バス、10
…論理シミュレーション装置、20…汎用計算機、21…評
価優先順位付与手段、22…部分回路へ分割する手段、23
…部分回路を各プロセッサへ割りつける手段、24…シミ
ュレーション時刻を管理する手段、25…プロセッサ間の
通信及び同期手段、26…各時刻毎に優先順位に従った素
子評価をする手段。FIG. 1 is a block diagram showing one embodiment of a logic simulation apparatus according to the present invention, and FIG. 2 is a flowchart showing a processing operation. DESCRIPTION OF SYMBOLS 1 ... Processor group, 2 ... Shared memory, 3 ... Common bus, 10
... Logic simulation device, 20 ... General-purpose computer, 21 ... Evaluation priority assigning means, 22 ... Division into partial circuits, 23
... means for allocating a partial circuit to each processor, 24 ... means for managing simulation time, 25 ... means for communication and synchronization between processors, 26 ... means for evaluating elements in accordance with priority at each time.
Claims (1)
て前記素子に評価の優先順位を付与する手段と、遅延値
を持つ前記素子の出力端子で前記被検証回路を複数の部
分回路に分割する手段と、シミュレーションを実行する
プロセッサ群へ前記部分回路を割りつける手段と、シミ
ュレーション時刻を管理する手段と、シミュレーション
実行時の各時刻毎にプロセッサ間のイベント通信を行な
いプロセッサ同期をとる手段と、各時刻毎に前記優先順
位に従い前記素子を評価する手段とを含むことを特徴と
する論理シミュレーション装置。1. A means for assigning evaluation priorities to said elements in accordance with delay values of elements constituting a circuit to be verified, and dividing said circuit to be verified into a plurality of partial circuits at an output terminal of said element having a delay value. Means for allocating the partial circuit to a processor group for executing simulation, means for managing simulation time, means for performing processor-based event communication between processors at each time of simulation execution, Means for evaluating the element in accordance with the priority at each time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP1006162A JP2727615B2 (en) | 1989-01-12 | 1989-01-12 | Logic simulation equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP1006162A JP2727615B2 (en) | 1989-01-12 | 1989-01-12 | Logic simulation equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JPH02186447A JPH02186447A (en) | 1990-07-20 |
| JP2727615B2 true JP2727615B2 (en) | 1998-03-11 |
Family
ID=11630833
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP1006162A Expired - Lifetime JP2727615B2 (en) | 1989-01-12 | 1989-01-12 | Logic simulation equipment |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JP2727615B2 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2918975B2 (en) | 1990-04-04 | 1999-07-12 | 甲府日本電気株式会社 | Logic simulation model creation system |
-
1989
- 1989-01-12 JP JP1006162A patent/JP2727615B2/en not_active Expired - Lifetime
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2918975B2 (en) | 1990-04-04 | 1999-07-12 | 甲府日本電気株式会社 | Logic simulation model creation system |
Also Published As
| Publication number | Publication date |
|---|---|
| JPH02186447A (en) | 1990-07-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6058492A (en) | Method and apparatus for design verification using emulation and simulation | |
| Agrawal et al. | A hardware logic simulation system | |
| US7050958B1 (en) | Method and apparatus for accelerating hardware simulation | |
| CN111767121B (en) | Operation method, device and related product | |
| WO2025218680A1 (en) | Intelligent training simulation transaction acceleration method and apparatus for data center, device, and medium | |
| JP2727615B2 (en) | Logic simulation equipment | |
| Wang et al. | Casta: Cuda-accelerated static timing analysis for VLSI designs | |
| Raghavan et al. | Logic simulation on vector processors | |
| JPS6141017B2 (en) | ||
| JP2663893B2 (en) | Architecture simulator | |
| George et al. | An Integrated Simulation Environment for Parallel and Distributed System Prototying | |
| JP2003503800A (en) | Logic event simulation | |
| JPH0916642A (en) | Data processor architecture evaluation method | |
| Ren et al. | Efficient latency bound analysis for data chains of real-time tasks in multiprocessor systems | |
| Kormicki et al. | Parallel logic simulation on a network of workstations using parallel virtual machine | |
| Gregorek et al. | A transaction-level framework for design-space exploration of hardware-enhanced operating systems | |
| JP2876636B2 (en) | Circuit data division method for logic simulation | |
| Qin et al. | CINOC: Computing in Network-On-Chip With Tiled Many-Core Architectures for Large-Scale General Matrix Multiplications | |
| JP4205525B2 (en) | Parallel simulation apparatus and parallel simulation method | |
| Tessier | Multi-FPGA systems: Logic emulation | |
| JPH0371362A (en) | Parallel computer for logical simulation | |
| JP2923893B1 (en) | Hardware logic simulation device | |
| JP2756143B2 (en) | Multi-output operation processing method | |
| Joshua | Review of Patents Issued to Computer Architecture Companies in 2021—Part II | |
| Chen et al. | Effect of architecture configuration on software reliability and performance estimation |