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
    • 4. 发明授权
    • System and method for arbitrating between memory access requests
    • 在内存访问请求之间进行仲裁的系统和方法
    • US08171187B2
    • 2012-05-01
    • US12179799
    • 2008-07-25
    • Anton RozenRoman MostinskiMichael PrielLeonid Smolyansky
    • Anton RozenRoman MostinskiMichael PrielLeonid Smolyansky
    • G06F3/00
    • G06F13/1605Y02D10/14
    • A system having memory access capabilities, the system includes: (i) a dynamic voltage and frequency scaling (DVFS) controller, adapted to determine a level of a voltage supply supplied to a first memory access requester and a frequency of a clock signal provided to the first memory access requester and to generate a DVFS indication that is indicative of the determination; (ii) a hardware access request determination module, adapted to determine a priority of memory access request issued by the first memory access requester in response to the DVFS indication; and (iii) a direct memory access arbitrator, adapted to arbitrate between memory access requests issued by the first memory access requester and another memory access requester in response to priorities associated with the memory access requests.
    • 一种具有存储器访问能力的系统,该系统包括:(i)动态电压和频率缩放(DVFS)控制器,适于确定提供给第一存储器访问请求者的电压电平的电平和提供给 所述第一存储器访问请求器并且生成指示所述确定的DVFS指示; (ii)硬件访问请求确定模块,用于响应于所述DVFS指示确定由所述第一存储器访问请求者发出的存储器访问请求的优先级; 以及(iii)直接存储器访问仲裁器,适于响应于与所述存储器访问请求相关联的优先级,在由所述第一存储器访问请求者发出的存储器访问请求与另一存储器访问请求者之间进行仲裁。
    • 6. 发明授权
    • Integrated circuit and method for reducing violations of a timing constraint
    • 用于减少违反定时约束的集成电路和方法
    • US08706928B2
    • 2014-04-22
    • US13504737
    • 2009-11-26
    • Roman MostinskiLavi KochLeonid Smolyansky
    • Roman MostinskiLavi KochLeonid Smolyansky
    • G06F3/00G06F5/00
    • G06F13/1673G06F13/1605
    • An integrated circuit comprises a shared resource for providing data to a buffer. The buffer is coupled to a buffer level monitor and a filling circuit. An access-requesting circuit is coupled to the shared resource for receiving the data from the shared resource when the access-requesting circuit has access to the shared resource. An arbiter is coupled to the shared resource, the filling circuit, and the access-requesting circuit, for receiving access requests from the filling circuit and from the access-requesting circuit, and for granting to a selected one thereof access to the shared resource. A controller is coupled to the buffer level monitor and to the access-requesting circuit, for causing the access-requesting circuit to reduce a rate of access requests sent to the arbiter when a condition involving the monitored level of data in the buffer indicates an anticipated violation of a timing constraint.
    • 集成电路包括用于向缓冲器提供数据的共享资源。 缓冲器耦合到缓冲液位监视器和充电电路。 访问请求电路耦合到共享资源,用于当访问请求电路访问共享资源时从共享资源接收数据。 仲裁器耦合到共享资源,填充电路和访问请求电路,用于从填充电路和访问请求电路接收访问请求,并且向所选共享资源授予对共享资源的访问权限。 控制器耦合到缓冲器级监视器和访问请求电路,用于当涉及缓冲器中监视的数据级别的条件指示预期时,访问请求电路降低发送到仲裁器的访问请求的速率 违反时间限制。
    • 8. 发明申请
    • APPARATUS AND METHOD FOR REDUCING PROCESSOR LATENCY
    • 减少处理器延迟的装置和方法
    • US20130124800A1
    • 2013-05-16
    • US13812168
    • 2010-07-27
    • Michael PrielDan KuzminAnton RozenLeonid Smolyansky
    • Michael PrielDan KuzminAnton RozenLeonid Smolyansky
    • G06F12/08
    • G06F12/0802G06F12/0804G06F12/0811G06F12/0877G06F13/28
    • There is provided a data processing system comprising a central processing unit, a processor cache memory operably coupled to the central processing unit and an external connection operably coupled to the central processing unit and processor cache memory in which a portion of the data processing system is arranged to load data directly from the external connection into the processor cache memory and modify a source address of said directly loaded data. There is also provided a method of improving latency in a data processing system having a central processing unit operably coupled to a processor cache memory and an external connection operably coupled to the central processing unit and processor cache memory, comprising loading data directly from the external connection into the processor cache memory and modifying a source address for said data to become indicative of a location other than from the external connection.
    • 提供了一种数据处理系统,包括中央处理单元,可操作地耦合到中央处理单元的处理器高速缓冲存储器和可操作地耦合到中央处理单元和处理器高速缓存存储器的外部连接,其中数据处理系统的一部分被布置 将数据直接从外部连接加载到处理器高速缓冲存储器中,并修改所述直接加载数据的源地址。 还提供了一种改进数据处理系统中的等待时间的方法,该系统具有可操作地耦合到处理器高速缓冲存储器的中央处理单元和可操作地耦合到中央处理器和处理器高速缓存存储器的外部连接,包括直接从外部连接 进入处理器高速缓冲存储器并修改所述数据的源地址以变成指示来自外部连接的位置。