-
公开(公告)号：KR1020070034342A
公开(公告)日：2007-03-28
申请号：KR1020050088927
申请日：2005-09-23
Applicant: 삼성전자주식회사
CPC classification number: G06F9/445 , G06F9/30058 , G06F9/30065 , G06F9/30178 , G06F9/325 , G06F9/328 , G06F9/44557
Abstract: A method of reducing a code size of a program by controlling a control flow of the program using software in a computer system is disclosed. The method includes the steps of storing a first program count of a first instruction in a first buffer when an error occurs while the first instruction having an Operand including Offset and Length is being executed among a plurality of instructions loaded in the code memory, changing a current program count of the code memory to a second program count which is obtained by adding the Offset to the first program count, storing a second instruction, which is located at a position shifted from the second program count by a value of the Length, in a second buffer, replacing the second instruction with a third instruction, which is not recognized by a microprocessor, replacing the third instruction with the second instruction stored in the second buffer when an error occurs while the third instruction is being executed, and changing the current program count of the code memory to a predetermined program count next to the first program count stored in the first buffer.
Abstract translation: 公开了一种通过使用计算机系统中的软件来控制程序的控制流程来减小程序的代码大小的方法。 该方法包括以下步骤：当在加载在代码存储器中的多个指令中具有包括偏移和长度的操作数的第一指令发生错误时，将第一指令的第一编程计数存储在第一缓冲器中，改变 将代码存储器的当前程序计数转换为第二程序计数，该第二程序计数是通过将偏移量加到第一程序计数获得的;将位于从第二程序计数偏移了长度值的位置处的第二指令存储在 第二缓冲器，用第三指令代替第二指令，所述第三指令不被微处理器识别，当第三指令正被执行时发生错误时，用存储在第二缓冲器中的第二指令代替第三指令，并且改变当前的 将代码存储器的程序计数转换为存储在第一缓冲器中的第一程序计数的下一个预定程序计数。
-
公开(公告)号：KR100679050B1
公开(公告)日：2007-02-06
申请号：KR1020050121820
申请日：2005-12-12
Applicant: 삼성전자주식회사
Abstract: A method and a device for storing/restoring register context for fast context exchange between tasks are provided to reduce time and a memory required for storing and restoring the register context generated in the context exchange, and to improve an execution speed of entire system by increasing the speed of the context exchange. An active register analyzer(520) adds an update code for updating information of an activated register to a task file including a code of the task performing a specific function. A code converter(510) converts the task file including the update code into an execution file. An active register information storing part(530) stores activation information of the register. A CPU(540) executes the task by using the execution file, stores the information of the activated register to the active register information storing part by executing the update code, and stores the active register context according to the information of the stored activated register for the context exchange of the task. The CPU executes again the task by restoring the active register context of the task.
Abstract translation: 提供了用于在任务之间进行快速上下文交换的存储/恢复寄存器上下文的方法和设备，以减少存储和恢复在上下文交换中生成的寄存器上下文所需的时间和存储器，并且通过增加整个系统的执行速度 上下文交换的速度。 有效寄存器分析器（520）将用于更新激活的寄存器的信息的更新代码添加到包括执行特定功能的任务的代码的任务文件。 代码转换器（510）将包括更新代码的任务文件转换成执行文件。 有效寄存器信息存储部分（530）存储寄存器的激活信息。 CPU（540）通过使用执行文件来执行任务，通过执行更新代码将激活的寄存器的信息存储到激活的寄存器信息存储部分，并且根据所存储的激活的寄存器的信息来存储激活的寄存器上下文 任务的上下文交换。 CPU通过恢复任务的活动寄存器上下文来再次执行任务。
-
公开(公告)号：KR100475000B1
公开(公告)日：2005-04-14
申请号：KR1019970048061
申请日：1997-09-22
Applicant: 삼성전자주식회사
IPC: H01L21/3205
Abstract: 플루오라이드계 가스에 의한 후처리를 포함하는 금속 배선 형성 방법에 관하여 개시한다. 본 발명에서는 반도체 기판상에 TiN/Ti막을 형성하고, 상기 TiN/Ti막 위에 W막을 형성하고, 상기 W막 위에 감광막 패턴을 형성하고, 상기 감광막 패턴을 식각 마스크로 하여 상기 W막 및 TiN/Ti막을 식각하여 배선층을 형성하고, 상기 배선층이 형성된 결과물을 플루오라이드계 가스를 사용하여 발생된 플라즈마를 사용하여 후처리한다. 상기 후처리 단계는 플루오라이드계 가스로서 CFx 가스를 사용하여 행하고, 상기 W막 및 TiN/Ti막의 식각 직후에 동일 챔버 내에서 인시튜(
in situ )로 행한다.-
公开(公告)号：KR1020010037023A
公开(公告)日：2001-05-07
申请号：KR1019990044299
申请日：1999-10-13
Applicant: 삼성전자주식회사
Inventor： 김운기
IPC: H04B1/38
CPC classification number: H04B1/40 , G10L19/0019
Abstract: PURPOSE: A digital cordless telephone set of a direct spreading pattern is provided to increase channel efficiency using a short spreading code and to offer a simplified spreading/despreading modem. CONSTITUTION: A digital cordless telephone set of a direct spreading pattern is provided with a voice codec(12), a spreading/despreading modem(14,15) and a wireless modem(16). The voice codec(12) executes sampling for a transmitting analog voice signal(AV_TX) inputted through a microphone(M) as 64Kbps. Also the voice codec(12) converts the sampled signal into an ADPCM(Adaptive Differential Pulse Code Modulation) signal and generates a compressed transmitting digital voice signal(DV_TX). A receiving digital voice signal(DV_RX) inputted from a despreading part(14) of the spreading/despreading modem(14,15) is first decoded into a receiving analog voice signal(AV_RX) and then outputted to a speaker(S). The spreading/despreading modem(14,15) is composed of the spreading part(14) and a despreading part(15). The spreading part(14) directly spreads the transmitting digital voice signal(DV_TX) into a transmitting spreading signal(SS_TX) using a spreading code of 22 chips every 2 bits. The despreading part(15) despreads a receiving spreading signal(SS_RX) into the receiving digital voice signal(DV_RX). The wireless modem(16) modulates the receiving spreading signal(SS_RX) into a transmitting RF signal(RF_TX) and demodulates a receiving RF signal into the receiving spreading signal(SS_RX).
Abstract translation: 目的：提供一种直接扩展模式的数字无绳电话机，以增加使用短扩展码的信道效率，并提供简化的扩展/解扩调制解调器。 构成：具有直接扩展模式的数字无绳电话机配有语音编解码器（12），扩展/解扩调制解调器（14,15）和无线调制解调器（16）。 语音编解码器（12）对通过麦克风（M）输入的发送模拟语音信号（AV_TX）执行64Kbps的采样。 语音编解码器（12）也将采样信号转换为ADPCM（自适应差分脉码调制）信号，并生成压缩的发送数字语音信号（DV_TX）。 从扩展/解扩调制解调器（14,15）的解扩部分（14）输入的接收数字语音信号（DV_RX）首先被解码为接收模拟语音信号（AV_RX），然后输出到扬声器（S）。 扩展/解扩调制解调器（14,15）由扩展部分（14）和解扩部分（15）组成。 扩展部分（14）使用每2位的22个码片的扩展码将发送数字语音信号（DV_TX）直接扩展成发送扩展信号（SS_TX）。 解扩部分（15）将接收扩展信号（SS_RX）解扩展到接收数字语音信号（DV_RX）中。 无线调制解调器（16）将接收扩展信号（SS_RX）调制成发射RF信号（RF_TX），并将接收RF信号解调为接收扩展信号（SS_RX）。
-
公开(公告)号：KR1019990026086A
公开(公告)日：1999-04-15
申请号：KR1019970048061
申请日：1997-09-22
Applicant: 삼성전자주식회사
IPC: H01L21/3205
Abstract: 플루오라이드계 가스에 의한 후처리를 포함하는 금속 배선 형성 방법에 관하여 개시한다. 본 발명에서는 반도체 기판상에 TiN/Ti막을 형성하고, 상기 TiN/Ti막 위에 W막을 형성하고, 상기 W막 위에 감광막 패턴을 형성하고, 상기 감광막 패턴을 식각 마스크로 하여 상기 W막 및 TiN/Ti막을 식각하여 배선층을 형성하고, 상기 배선층이 형성된 결과물을 플루오라이드계 가스를 사용하여 발생된 플라즈마를 사용하여 후처리한다. 상기 후처리 단계는 플루오라이드계 가스로서 CFx 가스를 사용하여 행하고, 상기 W막 및 TiN/Ti막의 식각 직후에 동일 챔버 내에서 인시튜(
in situ )로 행한다.-
Patent Agency Ranking
公开(公告)号：KR1019990025240A
公开(公告)日：1999-04-06
申请号：KR1019970046801
申请日：1997-09-11
Applicant: 삼성전자주식회사
IPC: H01L21/28
Abstract: 2단계 식각 방법에 의하여 단차가 있는 반도체 기판상에서 텅스텐 배선층을 형성하는 방법에 관하여 개시한다. 본 발명에서는 반도체 기판상에 텅스텐막을 형성하고, 상기 텅스텐막 위에 감광막 패턴을 형성하고, 상기 감광막 패턴을 식각 마스크로 하여 SF
6 가스와 N
2 가스를 사용하여 상기 텅스텐막을 식각하여 텅스텐막 패턴을 형성하고, SF
6 가스와 Ar가스를 사용한 식각에 의하여 텅스텐 잔류물을 완전히 제거한다.-
公开(公告)号：KR100770034B1
公开(公告)日：2007-10-26
申请号：KR1020060020115
申请日：2006-03-02
Applicant: 삼성전자주식회사
IPC: G06F9/48
CPC classification number: G06F9/462
Abstract: 본 발명은 문맥 교환 방법 및 시스템에 관한 것으로서, 더욱 상세하게는 복수의 레지스터 파일을 상태 전환하여 문맥 교환하고 문맥의 복구, 저장 작업을 분산시켜 수행함으로써 동적으로 생성된 태스크나 동적 링크에 대해서도 문맥 교환을 빠르게 수행할 수 있는 문맥 교환 방법 및 시스템에 관한 것이다. 본 발명의 문맥 교환 방법은 복수의 레지스터 파일을 유지하는 단계, 상기 복수의 레지스터 파일은 각각 프리패치 상태, 커런트 상태, 스토어 상태 중 하나의 상태로 설정하는 단계 및 문맥 교환 시, 상기 복수의 레지스터 파일의 상태를 각각 프리패치 상태, 커런트 상태, 스토어 상태 중 하나로 전환하여 설정하는 단계를 포함하고, 상기 프리패치 상태에서는 상기 레지스터 파일이 다음으로 수행할 태스크의 문맥을 읽어올 메모리 주소를 판단하고, 상기 커런트 상태에서는 상기 레지스터 파일의 태스크 문맥으로 중앙 처리 장치가 태스크를 수행하고, 상기 스토어 상태에서는 상기 레지스터 파일을 메모리에 저장하는 것을 특징으로 한다.
문맥 교환, 레지스터 파일, RTOS(Real Time Operating System), 태스크-
公开(公告)号：KR1020070090418A
公开(公告)日：2007-09-06
申请号：KR1020060020115
申请日：2006-03-02
Applicant: 삼성전자주식회사
IPC: G06F9/48
CPC classification number: G06F9/462
Abstract: A method and a system for exchanging context by using a plurality of register files are provided to prevent increase of using a memory bus at once by differently setting a state of each register file, and quickly exchange the context by distributing and performing context restoring/storing task. A memory interface module(204) sets each register file(201-203) to a prefetch, current, or store state, and switches the state of each register file into another one of the prefetch, current, or store state. The memory interface module determines a memory address for reading the context of the next task performed by the register file of the prefetch state The memory interface module enables a CPU to process the task with the context of the register file of the current state. The memory interface module stores the register file of the store state to a memory(208).
Abstract translation: 提供了通过使用多个寄存器文件来交换上下文的方法和系统，以通过不同地设置每个寄存器文件的状态来一次性增加使用存储器总线，并且通过分发和执行上下文恢复/存储来快速地交换上下文 任务。 存储器接口模块（204）将每个寄存器文件（201-203）设置为预取，当前或存储状态，并将每个寄存器文件的状态切换到预取，当前或存储状态中的另一个。 存储器接口模块确定用于读取由预取状态的寄存器文件执行的下一任务的上下文的存储器地址。存储器接口模块使CPU能够利用当前状态的寄存器文件的上下文来处理任务。 存储器接口模块将存储状态的寄存器文件存储到存储器（208）。
-
公开(公告)号：KR100692976B1
公开(公告)日：2007-03-12
申请号：KR1020060012227
申请日：2006-02-08
Applicant: 삼성전자주식회사
Abstract: A method and a system for transferring data between processors are provided to maximize data transfer efficiency by transferring the data with application of an optimal encoding mode for each area of a virtual address space and realize a stable operation of entire system by minimizing power consumption of a bus. A storing part(701) sets up the encoding mode to each area of the virtual address space of the first processor and stores the set encoding mode. A data transfer control module(702) determines the area of the virtual address space corresponding to the data to be transferred to the second processor, determines the encoding mode corresponding to the area of the determined virtual address space by referring to the storing part, and transfers the data to the second processor according to the determined encoding mode. The second processor decodes the transferred data by referring to information for the encoding mode, and the storing part is a TLB(Translation Look-aside Buffer).
Abstract translation: 提供了用于在处理器之间传送数据的方法和系统，以通过针对虚拟地址空间的每个区域应用最优编码模式来传送数据来最大化数据传送效率，并且通过最小化虚拟地址空间的功耗来实现整个系统的稳定操作 总线。 存储部件（701）为第一处理器的虚拟地址空间的每个区域设置编码模式并存储设置的编码模式。 数据传送控制模块（702）确定与要传送到第二处理器的数据相对应的虚拟地址空间的区域，通过参考存储部分确定与确定的虚拟地址空间的区域相对应的编码模式，并且 根据确定的编码模式将数据传送到第二处理器。 第二处理器通过参考用于编码模式的信息来解码传送的数据，并且存储部分是TLB（翻译后备缓冲器）。
-
公开(公告)号：KR1020050007906A
公开(公告)日：2005-01-21
申请号：KR1020030047538
申请日：2003-07-12
Applicant: 삼성전자주식회사
IPC: G06F9/45
CPC classification number: G06F8/54 , G06F9/44563 , G06F9/4486 , G06F8/40
Abstract: PURPOSE: A shared library system without an MMU(Memory Management Unit) and a method for constructing the same are provided to use a shared library without support of hardware such as the MMU by using a compiler, a runtime loader, and a library builder, and reduce a manufacturing cost of a system by reducing use of memory. CONSTITUTION: A data section base register(160) sets up a data section start address of an application program(100) and a start address of a data section allotted for the application program in the shared library. The compiler(100) complies an executed program(102) and libraries(104) of a source code form with a PIC(Position Independent Code) option, and defines functions included to each library. The library builder(120) generates shared libraries(124a) and address libraries(124b). An application program builder(130) makes the compiled program(105) into the application program of an execution file form. The runtime loader(140) loads the application program and the shared library to a main memory(180), and determines the final address of the symbol.
Abstract translation: 目的：提供一种没有MMU（内存管理单元）的共享库系统及其构建方法，通过使用编译器，运行时加载程序和库构建器，不需要支持诸如MMU等硬件的共享库， 并通过减少存储器的使用来降低系统的制造成本。 构成：数据部分基址寄存器（160）设置应用程序（100）的数据段起始地址和为共享库中的应用程序分配的数据段的起始地址。 编译器（100）使用PIC（位置独立代码）选项来执行源代码形式的执行程序（102）和库（104），并且定义包括在每个库中的功能。 库构建器（120）生成共享库（124a）和地址库（124b）。 应用程序构建器（130）使编译程序（105）进入执行文件形式的应用程序。 运行时加载器（140）将应用程序和共享库加载到主存储器（180），并确定符号的最终地址。
-
-
-
-
-
-
-
-
-
Search Results
21
records
(took 0.024 seconds)
