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
    • 2. 发明授权
    • Glitchless frequency-adjustable ring oscillator
    • 无毛刺频率可调环形振荡器
    • US5471176A
    • 1995-11-28
    • US255162
    • 1994-06-07
    • James A. HensonScott E. RichmondWilliam R. Akin, Jr.
    • James A. HensonScott E. RichmondWilliam R. Akin, Jr.
    • H03K3/02G06F1/08H03K3/03H03K3/78H03L7/06H04L7/00H04L7/033H03L7/00
    • G06F1/08H03K3/0315H04L7/0083H04L7/0337
    • A clock generation circuit includes a reference clock for putting out a stable reference clocking signal. A digital ring oscillator includes a series circuit loop having at least one inverting gate and a programmable delay line of plural delays formed a series of tapped digital transmission gates connected between an output and an input of the inverting gate. A multiplexer selects among the series of taps in accordance with a tap selection signal. A clock monitoring circuit is connected to compare the clock output with a stable reference clocking signal to produce a digital clock cycle count. A programmed microcontroller generates the tap selection value as a function of the digital clock cycle count and a desired clock output frequency set point. And, a synchronization circuit synchronizes tap selection value applied to the multiplexer in relation to the present, adjustable clocking signal, and to a logical state of a successor, adjustable clocking signal to be put out by the digital ring oscillator following the tap selection, in order to avoid glitches and without interrupting oscillation.
    • 时钟生成电路包括用于输出稳定的参考时钟信号的参考时钟。 数字环形振荡器包括串联电路回路,其具有至少一个反相门和多个延迟的可编程延迟线,形成连接在反相门的输出端和输入端之间的一系列抽头数字传输门。 多路复用器根据抽头选择信号在一系列抽头之间进行选择。 连接时钟监控电路,将时钟输出与稳定的参考时钟信号进行比较,以产生数字时钟周期计数。 编程的微控制器根据数字时钟周期计数和期望的时钟输出频率设定点产生抽头选择值。 并且,同步电路将应用于多路复用器的抽头选择值与当前可调整的时钟信号相同步,并且与随后的数字环形振荡器在抽头选择之后被放出的后继可调时钟信号的逻辑状态同步, 以避免毛刺和不中断振荡。
    • 4. 发明授权
    • Method of arbitrating requests for access to a single buffer memory in a disk drive
    • 仲裁访问磁盘驱动器中单个缓冲存储器的请求的方法
    • US06760820B2
    • 2004-07-06
    • US09982646
    • 2001-10-18
    • James A. HensonMinnie T. UppuluriGregory R. Kahlert
    • James A. HensonMinnie T. UppuluriGregory R. Kahlert
    • G06F1206
    • G06F3/0613G06F3/0656G06F3/0659G06F3/0674
    • A single microprocessor (22) hard disk drive (10) having a shared buffer memory (40) for storing sector data as well as microprocessor variables and code includes a buffer manager (38) for arbitrating requests from various channels or clients for access to the shared buffer memory. The buffer manager arranges channels including a disk data channel (32, 140), a host interface channel (50, 140), and microprocessor channels (144, 148) into a round-robin circular priority queue, with the disk data channel normally assigned the highest priority for buffer access. A state machine carries out an arbitration cycle by sequentially servicing access requests pending within the queue. The state machine senses (139) a servo interrupt (SVOINT) to elevate the priority of any pending microprocessor access requests to the shared buffer, such that the requests are serviced and cleared rapidly to allow the servo interrupt servicing routine to start sooner. The servo interrupt is preferably asserted during a spoke gate (100) time when a head (16) is sensing a disk (12) servo region (S). During this time data transfers between the disk and the shared buffer memory are stopped, pending buffer memory data transfers can be paused, and head seeking and tracking is controlled. This technique reduces the uncertainty delay in starting the servo interrupt service routine by 10 percent, which restores otherwise lost processing time and reduces head positioner servo (20) phase jitter, thereby improving head tracking and seeking performance.
    • 具有用于存储扇区数据的共享缓冲存储器(40)以及微处理器变量和代码的单个微处理器(22)硬盘驱动器(10)包括缓冲器管理器(38),用于仲裁来自各种通道或客户端的访问 共享缓冲存储器。 缓冲器管理器将包括磁盘数据通道(32,140),主机接口通道(50,140)和微处理器通道(144,148)的通道排列成循环循环优先级队列,其中盘数据通道正常地被分配 缓冲区访问的最高优先级。 状态机通过在队列内顺序维护待处理的访问请求来执行仲裁周期。 状态机感测(139)伺服中断(SVOINT)以将任何待处理的微处理器访问请求的优先级提升到共享缓冲器,使得请求被快速清理和清除,以允许伺服中断服务程序更早地启动。 当头(16)感测到盘(12)伺服区(S)时,优选地在轮辐门(100)期间断言伺服中断。 在此期间,磁盘和共享缓冲存储器之间的数据传输停止,暂停缓冲存储器数据传输,并且控制磁头寻找和跟踪。 这种技术将启动伺服中断服务程序的不确定性延迟降低了10%,从而恢复了处理时间,同时降低了磁头定位器伺服(20)的相位抖动,从而提高了磁头跟踪和寻线性能。
    • 7. 发明授权
    • Interrupt signal prioritized shared buffer memory access system and method
    • 中断信号优先共享缓冲存储器访问系统和方法
    • US06378051B1
    • 2002-04-23
    • US09332543
    • 1999-06-14
    • James A. HensonMinnie T. UppuluriGregory R. Kahlert
    • James A. HensonMinnie T. UppuluriGregory R. Kahlert
    • G06F1206
    • G06F3/0613G06F3/0656G06F3/0659G06F3/0674
    • A single microprocessor (22) hard disk drive (10) having a shared buffer memory (40) for storing sector data as well as microprocessor variables and code includes a buffer manager (38) for arbitrating requests from various channels or clients for access to the shared buffer memory. The buffer manager arranges channels including a disk data channel (32, 140), a host interface channel (50, 140), and microprocessor channels (144, 148) into a round-robin circular priority queue, with the disk data channel normally assigned the highest priority for buffer access. A state machine carries out an arbitration cycle by sequentially servicing access requests pending within the queue. The state machine senses (139) a servo interrupt (SVOINT) to elevate the priority of any pending microprocessor access requests to the shared buffer, such that the requests are serviced and cleared rapidly to allow the servo interrupt servicing routine to start sooner. The servo interrupt is preferably asserted during a spoke gate (100) time when a head (16) is sensing a disk (12) servo region (S). During this time data transfers between the disk and the shared buffer memory are stopped, pending buffer memory data transfers can be paused, and head seeking and tracking is controlled. This technique reduces the uncertainty delay in starting the servo interrupt service routine by 10 percent, which restores otherwise lost processing time and reduces head positioner servo (20) phase jitter, thereby improving head tracking and seeking performance.
    • 具有用于存储扇区数据的共享缓冲存储器(40)以及微处理器变量和代码的单个微处理器(22)硬盘驱动器(10)包括缓冲器管理器(38),用于仲裁来自各种通道或客户端的访问 共享缓冲存储器。 缓冲器管理器将包括磁盘数据通道(32,140),主机接口通道(50,140)和微处理器通道(144,148)的通道排列成循环循环优先级队列,其中盘数据通道正常地被分配 缓冲区访问的最高优先级。 状态机通过在队列内顺序维护待处理的访问请求来执行仲裁周期。 状态机感测(139)伺服中断(SVOINT)以将任何待处理的微处理器访问请求的优先级提升到共享缓冲器,使得请求被快速清理和清除,以允许伺服中断服务程序更早地启动。 当头(16)感测到盘(12)伺服区(S)时,优选地在轮辐门(100)期间断言伺服中断。 在此期间,磁盘和共享缓冲存储器之间的数据传输停止,暂停缓冲存储器数据传输,并且控制磁头寻找和跟踪。 这种技术将启动伺服中断服务程序的不确定性延迟降低了10%,从而恢复了处理时间,同时降低了磁头定位器伺服(20)的相位抖动,从而提高了磁头跟踪和寻线性能。
    • 10. 发明授权
    • Embedded cache manager
    • 嵌入式缓存管理器
    • US6141728A
    • 2000-10-31
    • US327293
    • 1999-06-07
    • Horia Cristian SimionescuLuan Kha BuiJames A. HensonClifford M. Gold
    • Horia Cristian SimionescuLuan Kha BuiJames A. HensonClifford M. Gold
    • G06F12/08G06F12/12
    • G06F12/0866
    • A method for managing data blocks in a cache buffer defining date block segments, and for automatically transferring data into and out of the cache buffer. A cache list comprises a plurality of entries each including information identifying a corresponding cache segment, and a set of consecutive data blocks stored in the cache segment. Providing cache status for a requested set of date blocks includes traversing the cache list to locate entries identifying the starting data block in the requested set, and consecutive data blocks successively following the starting data block without interruption, and identifying as a missing data block the first data block in said succession, including said starting data block, not identified in any entry. The missing data block is used to provide status: a full hit if the missing data block is not in the requested set; a miss if the missing data block is the starting data block in the requested set, or a partial hit otherwise. In response to a write command for a new set of data, the cache list is traversed to locate all entries identifying sets of data blocks overlapping the new set. If a located entry identifies a set of data blocks fully overlapping the new set, there is a full hit. If no entry is located, there is miss. Otherwise, there is a partial hit. The new set can be automatically transferred into a predesignated buffer area selected by the cache manager.
    • 一种用于管理高速缓冲存储器中的数据块的方法,用于定义日期块段,并用于将数据自动传入和传出高速缓冲存储器。 高速缓存列表包括多个条目,每个条目包括标识对应的高速缓存段的信息和存储在高速缓存段中的一组连续的数据块。 为所请求的一组日期块提供高速缓存状态包括遍历高速缓存列表以定位标识所请求集合中的起始数据块的条目,以及连续地在起始数据块之后不间断的连续数据块,并将第一 所述连续的数据块,包括所述起始数据块,在任何条目中未被识别。 丢失的数据块用于提供状态:如果丢失的数据块不在请求的集合中,则完整命中; 如果丢失的数据块是请求的集合中的起始数据块,否则将导致部分命中。 响应于新的数据集合的写入命令,遍历高速缓存列表以定位识别与新集合重叠的数据块集合的所有条目。 如果所定位的条目标识与新集合完全重叠的一组数据块,则完整命中。 如果没有条目找到,那就是错过。 否则有部分打击。 新集可以自动转移到由缓存管理器选择的预先指定的缓冲区中。