Dynamic Feedback Load Balancing
    1.
    发明申请
    Dynamic Feedback Load Balancing 审中-公开
    动态反馈负载平衡

    公开(公告)号:US20120001925A1

    公开(公告)日:2012-01-05

    申请号:US13173995

    申请日:2011-06-30

    IPC分类号: G06F15/16

    摘要: A method for rendering a scene across N number of processors is provided. The method includes evaluating performance statistics for each of the processors and establishing load rendering boundaries for each of the processors, the boundaries defining a respective portion of the scene. The method also includes dynamically adjusting the boundaries based upon the establishing and the evaluating.

    摘要翻译: 提供了一种用于在N个处理器上渲染场景的方法。 该方法包括评估每个处理器的性能统计信息,并为每个处理器建立负载渲染边界,边界限定场景的相应部分。 该方法还包括基于建立和评估来动态调整边界。

    In-place A-MSDU aggregation for wireless systems
    3.
    发明授权
    In-place A-MSDU aggregation for wireless systems 有权
    针对无线系统的就地A-MSDU聚合

    公开(公告)号:US09148819B2

    公开(公告)日:2015-09-29

    申请号:US13669512

    申请日:2012-11-06

    摘要: A sub-frame is generated for each MSDU to be aggregated in an A-MSDU and the sub-frame is stored in place in memory. For each sub-frame, an MSDU descriptor identifying the memory location of the sub-frame is stored in a queue. When a transmit opportunity for an MPDU arises, a DMA engine sequentially transfers the components of sub-frames stored in memory to a PHY layer using a list or other sequence of DMA descriptors obtained from at least a subset of the MSDU descriptors. Thus, these MSDU descriptors allow the aggregation of A-MSDUs to be initiated while the MSDUs are in place in the same memory in which they were initially stored.

    摘要翻译: 为每个要在A-MSDU中聚合的MSDU生成子帧,并将子帧存储在存储器中的适当位置。 对于每个子帧,标识子帧的存储器位置的MSDU描述符被存储在队列中。 当发生MPDU的发送机会时,DMA引擎使用从至少MSDU描述符的子集获得的列表或其他序列的DMA描述符,顺序地将存储在存储器中的子帧的组件传送到PHY层。 因此,这些MSDU描述符允许在MSDU在最初存储它们的同一存储器中就位时启动A-MSDU的聚合。

    IN-PLACE A-MSDU AGGREGATION FOR WIRELESS SYSTEMS
    4.
    发明申请
    IN-PLACE A-MSDU AGGREGATION FOR WIRELESS SYSTEMS 有权
    无线系统的A-MSDU聚合

    公开(公告)号:US20140126559A1

    公开(公告)日:2014-05-08

    申请号:US13669512

    申请日:2012-11-06

    IPC分类号: H04W84/12

    摘要: A sub-frame is generated for each MSDU to be aggregated in an A-MSDU and the sub-frame is stored in place in memory. For each sub-frame, an MSDU descriptor identifying the memory location of the sub-frame is stored in a queue. When a transmit opportunity for an MPDU arises, a DMA engine sequentially transfers the components of sub-frames stored in memory to a PHY layer using a list or other sequence of DMA descriptors obtained from at least a subset of the MSDU descriptors. Thus, these MSDU descriptors allow the aggregation of A-MSDUs to be initiated while the MSDUs are in place in the same memory in which they were initially stored.

    摘要翻译: 为每个要在A-MSDU中聚合的MSDU生成子帧,并将子帧存储在存储器中的适当位置。 对于每个子帧,标识子帧的存储器位置的MSDU描述符被存储在队列中。 当发生MPDU的发送机会时,DMA引擎使用从至少MSDU描述符的子集获得的列表或其他序列的DMA描述符,顺序地将存储在存储器中的子帧的组件传送到PHY层。 因此,这些MSDU描述符允许在MSDU在最初存储它们的同一存储器中就位时启动A-MSDU的聚合。

    Seamless Integration of Multi-GPU Rendering
    5.
    发明申请
    Seamless Integration of Multi-GPU Rendering 审中-公开
    多GPU渲染的无缝集成

    公开(公告)号:US20120001905A1

    公开(公告)日:2012-01-05

    申请号:US13173958

    申请日:2011-06-30

    IPC分类号: G06F15/16

    CPC分类号: G06T1/20

    摘要: A computer based rendering system is provided. The computer based rendering system includes an abstraction mechanism to provide configuring instructions to two or more processors, the configuring instructions being operative to facilitate scene rendering. The configuring provides processor setup instructions to at least one driver. Each of the two or more processors renders a respective portion of the scene independent of the other of the processors.

    摘要翻译: 提供基于计算机的渲染系统。 基于计算机的呈现系统包括一个抽象机制,用于向两个或多个处理器提供配置指令,该配置指令可操作以便于场景呈现。 该配置向至少一个驱动程序提供处理器设置指令。 两个或更多个处理器中的每一个呈现与独立于处理器中的另一个的场景的相应部分。