会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 21. 发明授权
    • Multiprocessor shared pipeline cache memory with split cycle and
concurrent utilization
    • 具有分段周期和并发利用率的多处理器共享流水线缓存
    • US4695943A
    • 1987-09-22
    • US655473
    • 1984-09-27
    • James W. KeeleyThomas F. Joyce
    • James W. KeeleyThomas F. Joyce
    • G06F12/08G06F13/00G11C7/00
    • G06F12/084
    • A cache memory unit is constructed to have a two-stage pipeline shareable by a plurality of sources which include two independently operated central processing units (CPUs). Apparatus included within the cache memory unit operates to allocate alternate time slots to the two CPUs which offset their operations by a pipeline stage. This permits one pipeline stage of the cache memory unit to perform a directory search for one CPU while the other pipeline stage performs a data buffer read for the other CPU. Each CPU is programmed to use less than all of the time slots allocated to it. Thus, the processing units operate conflict-free while pipeline stages are freed up for processing requests from other sources, such as replacement data from main memory or cache updates.
    • 高速缓冲存储器单元被构造成具有可由包括两个独立操作的中央处理单元(CPU)的多个源共享的两级流水线。 包括在高速缓冲存储器单元内的装置用于向两个CPU分配备用时隙,这两个CPU通过流水线阶段来抵消它们的操作。 这允许高速缓冲存储器单元的一个流水线阶段对一个CPU执行目录搜索,而另一个流水线级对另一个CPU执行数据缓冲器读取。 每个CPU被编程为使用少于分配给它的所有时隙。 因此,处理单元无冲突运行,而流水线阶段被释放以处理来自其他来源的请求,例如来自主存储器或高速缓存更新的替换数据。
    • 25. 发明授权
    • On-board diagnostic testing
    • 车载诊断测试
    • US5548713A
    • 1996-08-20
    • US272893
    • 1994-07-08
    • Keith L. PetryThomas S. HirschJames W. Keeley
    • Keith L. PetryThomas S. HirschJames W. Keeley
    • G06F11/22G06F11/00
    • G06F11/2273G06F11/22
    • A processing unit couples to a system bus and includes a microprocessor which tightly couples to a local memory. The processing unit also includes an addressable electrically erasable programmable read only memory (EEPROM) unit which couples to the microprocessor and to the system bus. The EEPROM unit stores in first and second separate regions, on-board diagnostic (OBD) routines and boot routines, respectively. The OBD routines are organized into a plurality of categories or phases. The processing unit includes a register accessible only by the microprocessor which, under the control of the OBD routines, is loaded with a number of predetermined values at the beginning of each individual OBD routine for identifying a particular phase and subphase of testing to be performed. Means coupled to the register is directly connected to display a first phase portion of the contents of the register for indicating during which phase of testing a failure occurred. The phase and subphase contents of the register are used to identify the actual test which failed. This information provides an index into a test dictionary which indicates the specific component or group of components which failed.
    • 处理单元耦合到系统总线并且包括紧密耦合到本地存储器的微处理器。 处理单元还包括可寻址的电可擦除可编程只读存储器(EEPROM)单元,其耦合到微处理器和系统总线。 EEPROM单元分别存储在第一和第二分离区域中,车载诊断(OBD)程序和引导程序。 OBD例程被组织成多个类别或阶段。 处理单元包括只能由微处理器访问的寄存器,在OBD程序的控制下,在每个单独的OBD程序的开始处加载多个预定值,用于识别要执行的特定阶段和次级测试。 连接到寄存器的装置被直接连接以显示寄存器的内容的第一相位部分,用于指示在发生故障的测试阶段。 寄存器的相位和相位内容用于识别失败的实际测试。 该信息为测试字典提供索引,该索引指示失败的组件的特定组件或组。
    • 28. 发明授权
    • Power-on sequencing apparatus for initializing and testing a system
processing unit
    • 用于初始化和测试系统处理单元的上电排序装置
    • US5491790A
    • 1996-02-13
    • US231856
    • 1994-04-22
    • James W. KeeleyRichard A. LemayChester M. Nibby, Jr.Keith L. PetryThomas S. Hirsch
    • James W. KeeleyRichard A. LemayChester M. Nibby, Jr.Keith L. PetryThomas S. Hirsch
    • G06F1/00G06F9/06G06F9/445G06F11/22G06F11/267
    • G06F11/2236G06F11/22G06F9/4403
    • A processing unit couples to a system bus in common with a peer processor, a main memory, in addition to other units, and includes a microprocessor which tightly couples to a local memory also accessible from such bus. The processing unit also includes an addressable electrically erasable programmable read only memory (EEPROM) unit which is coupled to the microprocessor and the system bus. The EEPROM unit stores in first and second separate regions, both of which occupy the same address space normally allocated for storing the microprocessor's boot code, on-board diagnostic (OBD) routines and operating system boot routines, respectively. EEPROM control circuits at power-up, condition the EEPROM unit to address the first region for executing OBD routines to verify that the processing unit is operating properly, including the ability to properly issue commands to units connected to the system bus. Following loading of the peer processor operating system, the EEPROM control circuits, in response to commands from the system bus, enable the microprocessor to address the second region for executing boot routines for loading its operating system.
    • 除了其他单元之外,处理单元与对等处理器,主存储器共同地耦合到系统总线,并且包括紧密耦合到也可从这样的总线访问的本地存储器的微处理器。 处理单元还包括可寻址的电可擦除可编程只读存储器(EEPROM)单元,其耦合到微处理器和系统总线。 EEPROM单元存储在第一和第二分离区域中,两者分别占据通常分配用于存储微处理器引导代码,车载诊断(OBD)例程和操作系统引导例程的相同地址空间。 EEPROM控制电路在上电时,使EEPROM单元处理第一个区域以执行OBD例程,以验证处理单元是否正常工作,包括正确向连接到系统总线的单元发出命令的能力。 在加载对等处理器操作系统之后,响应于来自系统总线的命令,EEPROM控制电路使得微处理器能够寻址用于执行用于加载其操作系统的引导例程的第二区域。
    • 29. 发明授权
    • Fast synchronization of asynchronous signals with a synchronous system
    • 异步信号与同步系统的快速同步
    • US5487163A
    • 1996-01-23
    • US148030
    • 1993-11-04
    • James W. Keeley
    • James W. Keeley
    • H03K5/135H03K5/13H03K19/003
    • H03K5/135
    • A method and apparatus provides fast synchronization of asynchronous signals to use by a synchronously operated device by quantizing the delay of an input clocked bistable device which receives and stores the asynchronous signal in response to a first synchronous clock pulse so that such input clocked bistable device has a metastable time period which is less than a predetermined maximum delay period. The output signal of the input clocked bistable device is connected directly to as an input to an asynchronously operated logic circuit part selected to provide a resulting output signal corresponding to the result of performing a logical operation on the output signal within a predetermined minimum time period. The resulting output signal is directly applied to the input of another synchronously operated bistable device which stores the resulting output signal in response to the next occurring synchronous clock pulse corresponding to a time period which is greater than the time of the metastable time period, minimum delay of the logic part and preset of time of such bistable device.
    • 方法和装置通过量化响应于第一同步时钟脉冲接收和存储异步信号的输入时钟双稳态器件的延迟量化同步操作器件的异步信号来提供异步信号的快速同步,使得这种输入时钟双稳态器件具有 亚稳态时间段小于预定的最大延迟周期。 输入时钟双稳态器件的输出信号直接连接到异步操作的逻辑电路部分的输入,该部分被选择以在预定的最小时间周期内提供与对输出信号执行逻辑运算的结果相对应的结果输出信号。 所得到的输出信号被直接施加到另一个同步操作的双稳态器件的输入端,该双稳态器件存储响应于下一个发生的同步时钟脉冲的输出信号,该时钟周期大于亚稳态时间段的时间段,最小延迟 的逻辑部分和这种双稳态设备的时间预设。
    • 30. 发明授权
    • Processor bus access
    • 处理器总线访问
    • US5341501A
    • 1994-08-23
    • US771582
    • 1991-10-04
    • James W. KeeleyRichard A. LemayChester M. Nibby, Jr.
    • James W. KeeleyRichard A. LemayChester M. Nibby, Jr.
    • G06F13/368G06F9/46
    • G06F13/368
    • A high performance microprocessor bus state machine couples to a synchronous local bus in common with another state machine for accessing a local memory according to a preestablished bus protocol. Circuit means cosines the state of a predetermined protocol bus signal indicating the release of the local bus and transitions of the clock signal which are not used for synchronizing the operations of the state machines. The resulting signal applies required address and control signals in advance to the local bus enabling the non-microprocessor state machine to generate the required address strobe to local memory on the next clock which follows the release of the local bus by the microprocessor which eliminates a clock cycle whenever local bus control passes from the microprocessor bus state machine to another state machine.
    • 高性能微处理器总线状态机根据预先建立的总线协议与另一状态机共同连接到同步局部总线,用于访问本地存储器。 电路意味着使指示本地总线的释放和不用于同步状态机的操作的时钟信号的转换的预定的协议总线信号的状态。 所产生的信号预先将所需的地址和控制信号施加到本地总线,使得非微处理器状态机能够在微处理器释放本地总线之后的下一个时钟产生所需的地址选通脉冲,从而消除时钟 当本地总线控制从微处理器总线状态机传递到另一状态机时,循环。