Strict priority distributed coordination function in wireless networks
    3.
    发明授权
    Strict priority distributed coordination function in wireless networks 有权
    无线网络中严格优先分配协调功能

    公开(公告)号:US07180861B2

    公开(公告)日:2007-02-20

    申请号:US09991281

    申请日:2001-11-15

    申请人: Tomasz Janczak

    发明人: Tomasz Janczak

    IPC分类号: H04J1/16 H04J3/14

    CPC分类号: H04W74/0866

    摘要: A system and method for prioritizing the transmission of packets in a wireless local area network. A station selects a packet from local priority queuing and identifies the priority bits of the packet. The station declares the priority of the selected packet based on the binary value of the priority bits. If the station detects that another station has selected a packet with a higher priority, then the station ceases to contend for transmission during the current transmission cycle.

    摘要翻译: 一种用于在无线局域网中优先分发分组的系统和方法。 站点从本地优先级排队中选择一个分组,并识别分组的优先级位。 该站基于优先级位的二进制值来声明所选数据包的优先级。 如果站检测到另一台站选择了较高优先级的分组,则在当前的传输周期内该站不再进行传输。

    Register allocation with SIMD architecture using write masks
    5.
    发明授权
    Register allocation with SIMD architecture using write masks 有权
    使用写掩码的SIMD架构进行寄存器分配

    公开(公告)号:US08434074B2

    公开(公告)日:2013-04-30

    申请号:US12711319

    申请日:2010-02-24

    IPC分类号: G06F9/45

    CPC分类号: G06F8/441

    摘要: A single instruction multiple data processor may accomplish register allocation by identifying live ranges that have incompatible write masks during compilation. Then, edges are added in an interference graph between live ranges that have incompatible masks so that those live ranges will not be assigned to the same physical register.

    摘要翻译: 单个指令多数据处理器可以通过在编译期间识别具有不兼容的写入掩码的实际范围来完成寄存器分配。 然后,在具有不兼容掩码的实时范围之间的干涉图中添加边,以使这些实时范围不被分配给相同的物理寄存器。

    Register Allocation With SIMD Architecture Using Write Masks
    6.
    发明申请
    Register Allocation With SIMD Architecture Using Write Masks 有权
    使用写掩码的SIMD架构注册分配

    公开(公告)号:US20110209127A1

    公开(公告)日:2011-08-25

    申请号:US12711319

    申请日:2010-02-24

    IPC分类号: G06F9/45

    CPC分类号: G06F8/441

    摘要: A single instruction multiple data processor may accomplish register allocation by identifying live ranges that have incompatible write masks during compilation. Then, edges are added in an interference graph between live ranges that have incompatible masks so that those live ranges will not be assigned to the same physical register.

    摘要翻译: 单个指令多数据处理器可以通过在编译期间识别具有不兼容的写入掩码的实际范围来完成寄存器分配。 然后,在具有不兼容掩码的实时范围之间的干涉图中添加边,以使这些实时范围不被分配给相同的物理寄存器。

    APPARATUS AND METHOD FOR ASYNCHRONOUS TEXEL SHADING

    公开(公告)号:US20190087992A1

    公开(公告)日:2019-03-21

    申请号:US16080298

    申请日:2016-04-01

    IPC分类号: G06T11/40 G06T11/00

    摘要: An apparatus and method are described for asynchronous texel shading. For example, one embodiment of a graphics processing apparatus comprises: a first shader to perform shading operations on a plurality of pixels in a first pass and to submit a request to shade texels; and a texel shader to responsively perform texel shading operations in response to the request from the first shader, the texel shader to write results to a procedural texture stored in a memory subsystem, the procedural texture to be read during a second pass by the first shader or another shader.

    Reducing the number of IO requests to memory when executing a program that iteratively processes contiguous data
    8.
    发明授权
    Reducing the number of IO requests to memory when executing a program that iteratively processes contiguous data 有权
    在执行迭代处理连续数据的程序时,减少对内存的IO请求数

    公开(公告)号:US09483810B2

    公开(公告)日:2016-11-01

    申请号:US13997053

    申请日:2011-12-28

    申请人: Tomasz Janczak

    发明人: Tomasz Janczak

    摘要: Methods and apparatuses to reduce the number of IO requests to memory when executing a program that iteratively processes contiguous data are provided. A first set of data elements may be loaded in a first register and a second set of data elements may be loaded in a second register. The first set of data elements and the second set of data elements can be used during the execution of a program to iteratively process the data elements. For each of a plurality of iterations, a corresponding set of data elements to be used during the execution of an operation for the iteration may be selected from the first set of data elements stored in the first register and the second set of data elements stored in the second register. In this way, the same data elements are not re-loaded from memory during each iteration.

    摘要翻译: 提供了在执行迭代处理连续数据的程序时减少对存储器的IO请求数量的方法和装置。 可以将第一组数据元素加载到第一寄存器中,并且第二组数据元素可以被加载到第二寄存器中。 可以在执行程序期间使用第一组数据元素和第二组数据元素来迭代地处理数据元素。 对于多个迭代中的每一个,可以从存储在第一寄存器中的第一组数据元素和存储在第一寄存器中的第二组数据元素中选择要在执行迭代操作期间使用的相应的数据元素组 第二个登记册。 以这种方式,在每次迭代期间,相同的数据元素都不会从内存中重新加载。

    Reducing the number of sequential operations in an application to be performed on a shared memory cell
    10.
    发明授权
    Reducing the number of sequential operations in an application to be performed on a shared memory cell 有权
    减少要在共享存储器单元上执行的应用程序中的顺序操作的数量

    公开(公告)号:US09449360B2

    公开(公告)日:2016-09-20

    申请号:US13997056

    申请日:2011-12-28

    摘要: Methods and apparatuses to reduce the number of sequential operations such as atomic operations in an application to be performed on a shared memory cell may be provided. A translation unit can detect in the application multiple atomic operations to be performed on the same memory and replaces the multiple atomic operations with an equivalent single atomic operation. In some implementations, the application includes shader code. In some implementations, each of the multiple atomic operations increment a value stored at the same memory by an update amount. The translation unit may calculate the partial prefix sum over all the atomic operations and replace the multiple atomic operations with a single atomic operation to increment the value stored at memory by the sum of the update amounts.

    摘要翻译: 可以提供用于减少在共享存储器单元上执行的应用中的诸如原子操作的顺序操作的数量的方法和装置。 翻译单元可以在应用程序中检测要在同一个存储器上执行的多个原子操作,并用等效的单一原子操作替换多个原子操作。 在一些实现中,应用程序包括着色器代码。 在一些实现中,多个原子操作中的每一个将存储在相同存储器上的值增加更新量。 翻译单元可以在所有原子操作上计算部分前缀和,并用单个原子操作替换多个原子操作,以将存储在存储器中的值增加更新量的总和。