PROTECTION INFORMATION INITIALIZATION
    91.
    发明申请
    PROTECTION INFORMATION INITIALIZATION 有权
    保护信息初始化

    公开(公告)号:US20140325144A1

    公开(公告)日:2014-10-30

    申请号:US13889424

    申请日:2013-05-08

    申请人: LSI CORPORATION

    发明人: Allen B. Kelton

    IPC分类号: G06F3/06

    摘要: M number of physical drives are divided into a plurality of strips. The plurality of strips each has an equal number of blocks on each of the M physical drives. Each of the strips has a first logical block address associated with a first block of the strip. The plurality of strips are grouped across the M physical drives into a plurality of stripes. Each of the stripes is configured use one strip from each of the M physical drives. A first stripe of the plurality of strips has M total strips configured as M−1 data strips and one parity strip. Protection information parity values are calculated for the parity strip in the first stripe using the respective first logical block addresses of the M−1 data strips.

    摘要翻译: M个物理驱动器被分成多个条带。 多个条每个在每个M个物理驱动器上具有相等数量的块。 每个条具有与条的第一块相关联的第一逻辑块地址。 多个条带跨M个物理驱动器分组成多条。 每个条带都配置为使用每个M物理驱动器中的一个条带。 多个条带中的第一条带具有配置为M-1个数据条带和一个奇偶校验条带的M个总条带。 使用M-1数据条的各自的第一逻辑块地址,为第一条带中的奇偶校验条计算保护信息奇偶校验值。

    System and method of automated design augmentation for efficient hierarchical implementation
    92.
    发明授权
    System and method of automated design augmentation for efficient hierarchical implementation 有权
    自动设计增加的系统和方法,用于高效的分层实施

    公开(公告)号:US08875079B2

    公开(公告)日:2014-10-28

    申请号:US13248807

    申请日:2011-09-29

    申请人: Douglas J. Saxon

    发明人: Douglas J. Saxon

    IPC分类号: G06F17/50

    CPC分类号: G06F17/5072

    摘要: A hierarchical interface module includes an assessment unit configured to identify a hierarchical implementation incompatibility of an integrated circuit (IC) partitioned block. Additionally, the hierarchical interface module includes an interface unit configured to substitute a directly registered hierarchical interface structure for the hierarchical implementation incompatibility of the IC partitioned block. A method of interfacing hierarchically and a hierarchical implementation system are also included.

    摘要翻译: 分级接口模块包括被配置为识别集成电路(IC)分区块的分级实现不兼容性的评估单元。 此外,分级接口模块包括被配置为将直接注册的分层接口结构替换为IC分区块的分级实现不兼容性的接口单元。 还包括分级接口和分层实现系统的方法。

    Systems and methods for pattern detection
    93.
    发明授权
    Systems and methods for pattern detection 有权
    模式检测的系统和方法

    公开(公告)号:US08874410B2

    公开(公告)日:2014-10-28

    申请号:US13113210

    申请日:2011-05-23

    摘要: Various embodiments of the present invention provide systems and methods related to pattern detection. As an example, a system for sample selection is disclosed that includes a difference calculation circuit, a comparator circuit, and an output selector circuit. The difference calculation circuit is operable to calculate a first difference between a first value corresponding to a first digital sample and a second value corresponding to a second digital sample, and to calculate a second difference between a third value corresponding to a third digital sample and a fourth value corresponding to a fourth digital sample. The comparator circuit is operable to compare the first difference with the second difference to yield a comparison output. The output selector circuit is operable to select one of the second value and the fourth value as an output based at least upon the comparison output.

    摘要翻译: 本发明的各种实施例提供了与模式检测有关的系统和方法。 作为示例,公开了一种用于样本选择的系统,其包括差分计算电路,比较器电路和输出选择器电路。 差分计算电路可操作以计算对应于第一数字样本的第一值与对应于第二数字样本的第二值之间的第一差,并计算与第三数字样本相对应的第三值和 第四值对应于第四数字样本。 比较器电路可操作以将第一差异与第二差值进行比较以产生比较输出。 输出选择器电路可操作以至少基于比较输出来选择第二值和第四值之一作为输出。

    Task queuing in a multi-flow network processor architecture
    94.
    发明授权
    Task queuing in a multi-flow network processor architecture 有权
    任务在多流网络处理器架构中排队

    公开(公告)号:US08873550B2

    公开(公告)日:2014-10-28

    申请号:US13687772

    申请日:2012-11-28

    申请人: LSI Corporation

    摘要: Described embodiments generate tasks corresponding to each packet received by a network processor. A destination processing module receives a task and determines, based on the task size, a queue in which to store the task, and whether the task is larger than space available within a current memory block of the queue. If the task is larger, an address of a next memory block in a memory is determined, and the address is provided to a source processing module of the task. The source processing module writes the task to the memory based on a provided offset address and the address of the next memory block, if provided. If a task is written to more than one memory block, the destination processing module preloads the address of the next memory block to a local memory to process queued tasks without stalling to retrieve the address of the next memory block.

    摘要翻译: 所描述的实施例生成与由网络处理器接收的每个分组相对应的任务。 目的地处理模块接收任务,并且基于任务大小确定其中存储任务的队列,以及该任务是否大于队列的当前存储块内的可用空间。 如果任务较大,则确定存储器中的下一个存储块的地址,并将该地址提供给任务的源处理模块。 源处理模块根据提供的偏移地址和下一个存储块的地址(如果提供)将任务写入存储器。 如果任务被写入多个存储块,则目的地处理模块将下一个存储器块的地址预加载到本地存储器,以处理排队的任务而不停顿以检索下一个存储块的地址。

    Sampling-phase acquisition based on channel-impulse-response estimation
    95.
    发明授权
    Sampling-phase acquisition based on channel-impulse-response estimation 有权
    基于信道脉冲响应估计的采样相位采集

    公开(公告)号:US08873180B2

    公开(公告)日:2014-10-28

    申请号:US13856210

    申请日:2013-04-03

    申请人: LSI Corporation

    IPC分类号: G11B5/09 G11B27/30 H04L7/033

    摘要: Embodiments of the invention can be manifested as methods for converting analog waveforms into digital sampled signals. In at least one such embodiment, the method includes (i) sampling, based on a sampling-clock signal, an analog waveform received from a transmission channel to generate a digital sampled signal, (ii) generating a digital target signal by applying a specified reference data pattern to a model of the transmission channel, and (iii) adjusting the sampling-clock signal by comparing the digital sampled signal to the digital target signal. Embodiments of the invention can also be manifested as apparatuses that convert analog waveforms into digital sampled signals.

    摘要翻译: 本发明的实施例可以表现为将模拟波形转换为数字采样信号的方法。 在至少一个这样的实施例中,该方法包括(i)基于采样时钟信号对从传输信道接收的模拟波形进行采样以产生数字采样信号,(ii)通过应用指定的 参考数据模式到传输信道的模型,以及(iii)通过将数字采样信号与数字目标信号进行比较来调整采样时钟信号。 本发明的实施例也可以表现为将模拟波形转换为数字采样信号的装置。

    Speculative task reading in a traffic manager of a network processor
    96.
    发明授权
    Speculative task reading in a traffic manager of a network processor 有权
    在网络处理器的流量管理器中进行投机任务读取

    公开(公告)号:US08869156B2

    公开(公告)日:2014-10-21

    申请号:US13250865

    申请日:2011-09-30

    摘要: Described embodiments provide for scheduling packets for transmission by a network processor. The network processor generates tasks corresponding to received packets associated with a data flow. A traffic manager of the network processor receives tasks provided by a processing module of the network processor and generates a tree scheduling hierarchy having one or more scheduling levels. Each received task is queued in a queue of the scheduling hierarchy associated with the received task, the queue having a corresponding parent scheduler in each level of the scheduling hierarchy, forming a branch of the scheduling hierarchy. A parent scheduler selects a child node to transmit a task. A task read module determines a thread corresponding to the selected child node to read corresponding packet data from a shared memory. The traffic manager forms one or more output tasks for transmission based on the packet data corresponding to the thread.

    摘要翻译: 描述的实施例提供了调度分组以供网络处理器进行传输。 网络处理器生成对应于与数据流相关联的接收分组的任务。 网络处理器的流量管理器接收由网络处理器的处理模块提供的任务,并生成具有一个或多个调度级别的树调度层次。 每个接收的任务被排队在与所接收的任务相关联的调度层次的队列中,该队列具有调度层次结构的每个级别中的对应的父调度器,形成调度层次结构的分支。 父调度程序选择一个子节点来发送一个任务。 任务读取模块确定对应于所选择的子节点的线程以从共享存储器读取相应的分组数据。 流量管理器基于与线程相对应的分组数据形成用于传输的一个或多个输出任务。

    Interrupt queuing in a media controller architecture
    98.
    发明授权
    Interrupt queuing in a media controller architecture 有权
    在媒体控制器架构中中断排队

    公开(公告)号:US08868809B2

    公开(公告)日:2014-10-21

    申请号:US12952206

    申请日:2010-11-23

    摘要: Described embodiments provide a media controller for servicing contexts corresponding to data transfer requests from host devices. The media controller includes a context generator for generating contexts corresponding to the data transfer requests and a buffer for storing one or more context pointers, each pointer corresponding to a context and an action by a system module associated with the context. A context processor is configured to complete a context when the action by a media controller module associated with the context is complete, remove each pointer from the buffer associated with the completed context, and determine whether an interrupt corresponds to the completed context and removed pointer. If no interrupt corresponds to the completed context, the completed context is cleared. If an interrupt corresponds to the completed context, the interrupt is provided to a master processor and a completed context recycler for recycling the completed context pointer to the context generator.

    摘要翻译: 描述的实施例提供了一种媒体控制器,用于为来自主机设备的数据传输请求对应的上下文进行服务。 媒体控制器包括用于生成对应于数据传送请求的上下文的上下文生成器和用于存储一个或多个上下文指针的缓冲器,每个指针对应于上下文以及与上下文相关联的系统模块的动作。 上下文处理器被配置为当与上下文相关联的媒体控制器模块的动作完成时,完成上下文,从与完成的上下文相关联的缓冲器中移除每个指针,并且确定中断是否对应于完成的上下文和删除的指针。 如果没有中断对应于完成的上下文,则完成的上下文被清除。 如果中断对应于完成的上下文,则将中断提供给主处理器和完成的上下文回收器,以将完成的上下文指针回收到上下文生成器。

    Methods and structure for hardware management of serial advanced technology attachment (SATA) DMA Non-Zero Offsets in a serial attached SCSI (SAS) expander
    99.
    发明授权
    Methods and structure for hardware management of serial advanced technology attachment (SATA) DMA Non-Zero Offsets in a serial attached SCSI (SAS) expander 有权
    串行高级技术附件(SATA)的硬件管理方法和结构串行连接SCSI(SAS)扩展器中的非零偏移

    公开(公告)号:US08868806B2

    公开(公告)日:2014-10-21

    申请号:US14050997

    申请日:2013-10-10

    申请人: LSI Corporation

    IPC分类号: G06F13/10 G06F3/06

    摘要: Methods and structure for enhanced SAS expander functionality to store and forward buffered information transmitted from a SATA end device to an STP initiator device while managing use of Non-Zero Offset (“NZO”) field values in DMA Setup FISs transmitted by the SATA end device. The enhanced expander establishes a connection between an STP initiator and a SATA end device. The expander forwards a read command from the initiator to the end device. If NZO use is supported and enabled in the end device, the end device may return read data in any order by use of the NZO field values in multiple DMA Setup FISs. The expander is further adapted to store received data and the associated multiple DMA Setup FISs from the end device in its buffer and forwards the stored data to the initiator device. In another embodiment, use of NZO in the end device is disabled.

    摘要翻译: 用于增强SAS扩展器功能的方法和结构,用于存储和转发从SATA终端设备发送到STP启动器设备的缓冲信息,同时管理在SATA终端设备传输的DMA设置FIS中使用非零偏移(“NZO”)字段值 。 增强型扩展器建立STP启动器和SATA终端设备之间的连接。 扩展器将读命令从启动器转发到终端设备。 如果在终端设备中支持并启用NZO使用,终端设备可以通过使用多个DMA设置FIS中的NZO字段值以任何顺序返回读取数据。 扩展器进一步适于将接收到的数据和相关联的多个DMA设置FIS从终端设备存储在其缓冲器中,并将存储的数据转发到启动器设备。 在另一个实施例中,在终端设备中使用NZO被禁用。