System and method to implement a matrix multiply unit of a broadband processor
    64.
    发明授权
    System and method to implement a matrix multiply unit of a broadband processor 失效
    实现宽带处理器的矩阵乘法单元的系统和方法

    公开(公告)号:US08195735B2

    公开(公告)日:2012-06-05

    申请号:US12330962

    申请日:2008-12-09

    IPC分类号: G06F7/52 G06F7/38

    摘要: The present invention provides a system and method for improving the performance of general-purpose processors by implementing a functional unit that computes the product of a matrix operand with a vector operand, producing a vector result. The functional unit fully utilizes the entire resources of a 128b by 128b multiplier regardless of the operand size, as the number of elements of the matrix and vector operands increase as operand size is reduced. The unit performs both fixed-point and floating-point multiplications and additions with the highest-possible intermediate accuracy with modest resources.

    摘要翻译: 本发明提供了一种用于通过实现一个功能单元来提高通用处理器的性能的系统和方法,所述功能单元使用向量操作数来计算矩阵操作数的乘积,产生向量结果。 功能单元完全利用128b乘128b乘法器的全部资源,无论操作数大小如何,因为矩阵和向量操作数的元素数量随着操作数大小的减小而增加。 该单元通过适度的资源执行具有最高可能的中间精度的定点和浮点乘法和补充。

    Method and software for group data operations
    67.
    发明授权
    Method and software for group data operations 有权
    组数据操作的方法和软件

    公开(公告)号:US07818548B2

    公开(公告)日:2010-10-19

    申请号:US11878804

    申请日:2007-07-27

    IPC分类号: G06F9/315

    摘要: Methods and software are presented for processing data in a programmable processor, involving (a) decoding instructions for execution using an execution unit operable to execute instructions by partitioning data stored in registers in a register file into multiple data elements, the instructions selected from an instruction set that includes group arithmetic instructions and group data handling instructions, (b) in response to decoding different group arithmetic instructions, executing a plurality of different group floating-point and group integer arithmetic operations that each arithmetically operates on multiple data elements stored in registers in the register file to produce a catenated result that is returned to a register in the register file, wherein the catenated result comprises a plurality of individual results, and (c) in response to decoding different group data handling instructions, executing group data handling operations that re-arrange data elements in different ways.

    摘要翻译: 提出了用于处理可编程处理器中的数据的方法和软件,其涉及(a)使用执行单元来解码执行指令,所述执行单元可操作以通过将存储在寄存器文件中的寄存器中的数据分割成多个数据元素来执行指令,所述指令从指令中选择 设置为包括组算术指令和组数据处理指令,(b)响应于解码不同组算术指令,执行对存储在寄存器中的多个数据元素进行算术运算的多个不同的组浮点和组整数运算 所述寄存器文件产生返回到所述寄存器文件中的寄存器的接合结果,其中所述接合结果包括多个单独的结果,以及(c)响应于解码不同的组数据处理指令,执行组数据处理操作, 以不同的方式重新排列数据元素。

    Method and software for group floating-point arithmetic operations
    68.
    发明授权
    Method and software for group floating-point arithmetic operations 有权
    组浮点运算的方法和软件

    公开(公告)号:US07730287B2

    公开(公告)日:2010-06-01

    申请号:US11878814

    申请日:2007-07-27

    IPC分类号: G06F9/30

    摘要: Methods and software are presented for processing data in a programmable processor, involving (a) decoding instructions for execution using an execution unit operable to execute instructions by partitioning data stored in registers in a register file into multiple data elements, the instructions selected from an instruction set that includes group arithmetic instructions and group data handling instructions, (b) in response to decoding different group data handling instructions, executing group data handling operations that re-arrange data elements in different ways, and (c) in response to decoding different group arithmetic instructions, executing a plurality of different group floating-point and group integer arithmetic operations that each arithmetically operates on the multiple data elements stored in registers in the register file to produce a catenated result that is returned to a register in the register file, wherein the catenated result comprises a plurality of individual results.

    摘要翻译: 提出了用于处理可编程处理器中的数据的方法和软件,其涉及(a)使用执行单元来解码执行指令,所述执行单元可操作以通过将存储在寄存器文件中的寄存器中的数据分割成多个数据元素来执行指令,所述指令从指令中选择 设置为包括组算术指令和组数据处理指令,(b)响应于解码不同组数据处理指令,执行以不同方式重新排列数据元素的组数据处理操作,以及(c)响应于解码不同组 算术指令,执行对存储在寄存器文件中的寄存器中的多个数据元素进行算术运算的多个不同的组浮点和组整数算术运算,以产生返回到寄存器堆中的寄存器的联结结果,其中 连带结果包括多个单独的结果 lts。

    SYSTEM AND METHOD TO IMPLEMENT A MATRIX MULTIPLY UNIT OF A BROADBAND PROCESSOR
    70.
    发明申请
    SYSTEM AND METHOD TO IMPLEMENT A MATRIX MULTIPLY UNIT OF A BROADBAND PROCESSOR 失效
    用于实现宽带处理器的矩阵多项式单元的系统和方法

    公开(公告)号:US20090094309A1

    公开(公告)日:2009-04-09

    申请号:US12330962

    申请日:2008-12-09

    IPC分类号: G06F7/38 G06F7/52

    摘要: The present invention provides a system and method for improving the performance of general-purpose processors by implementing a functional unit that computes the product of a matrix operand with a vector operand, producing a vector result. The functional unit fully utilizes the entire resources of a 128b by 128b multiplier regardless of the operand size, as the number of elements of the matrix and vector operands increase as operand size is reduced. The unit performs both fixed-point and floating-point multiplications and additions with the highest-possible intermediate accuracy with modest resources.

    摘要翻译: 本发明提供了一种用于通过实现一个功能单元来提高通用处理器的性能的系统和方法,所述功能单元使用向量操作数来计算矩阵操作数的乘积,产生向量结果。 功能单元完全利用128b乘128b乘法器的全部资源,无论操作数大小如何,因为矩阵和向量操作数的元素数量随着操作数大小的减小而增加。 该单元通过适度的资源执行具有最高可能的中间精度的定点和浮点乘法和补充。