System and method for efficient processing of instructions using control unit to select operations
    117.
    发明授权
    System and method for efficient processing of instructions using control unit to select operations 有权
    使用控制单元有效处理指令的系统和方法来选择操作

    公开(公告)号:US06308262B1

    公开(公告)日:2001-10-23

    申请号:US09163521

    申请日:1998-09-30

    Applicant: Millind Mittal

    Inventor: Millind Mittal

    CPC classification number: G06F9/30189 G06F9/3836 G06F9/3842 G06F9/3885

    Abstract: An apparatus and method for performing efficient processing of instructions is described. In one embodiment, a processor comprises a storage area to store a data operand and a control unit that is coupled to the storage area. A first circuit is coupled to the storage area and the control unit, which performs a first operation under a first condition. A second circuit is coupled to the storage area and the control unit, which performs a second operation under a second condition. The control unit operates on data elements in the data operand to process an instruction, and determines if processing of the instruction is to be performed under the second condition. If so, the second circuit is selected to process the instruction, otherwise the first circuit is selected to process the instruction. Various embodiments are disclosed.

    Abstract translation: 描述用于执行指令的有效处理的装置和方法。 在一个实施例中,处理器包括用于存储数据操作数的存储区域和耦合到存储区域的控制单元。 第一电路耦合到存储区域和控制单元,其在第一条件下执行第一操作。 第二电路耦合到存储区域和控制单元,其在第二条件下执行第二操作。 控制单元对数据操作数中的数据单元进行操作以处理指令,并且确定在第二条件下是否执行指令的处理。 如果是这样,则选择第二个电路来处理指令,否则选择第一个电路来处理指令。 公开了各种实施例。

    Method and apparatus for decoding one or more instructions after renaming destination registers
    118.
    发明授权
    Method and apparatus for decoding one or more instructions after renaming destination registers 失效
    用于在重命名目的地寄存器之后对一个或多个指令进行解码的方法和装置

    公开(公告)号:US06192464B1

    公开(公告)日:2001-02-20

    申请号:US09001255

    申请日:1997-12-31

    Applicant: Millind Mittal

    Inventor: Millind Mittal

    CPC classification number: G06F9/3017 G06F9/384 G06F9/3875

    Abstract: In one aspect the present invention provides for a method for executing a sequence of instructions in a processor. The method comprises decoding a first the instructions into one or more first micro-ops, renaming destination registers identified in a first portion of the first micro-ops by reassigning available additional physical registers for the destination registers, and decoding a second portion of the first micro-ops into one or more second micro-ops. The act of renaming has renamed a destination register of at least one micro-op of the second portion of the first micro-ops. The method executes a third portion of the first and the second micro-ops.

    Abstract translation: 在一个方面,本发明提供了一种用于在处理器中执行指令序列的方法。 该方法包括首先将指令解码为一个或多个第一微操作,通过重新分配用于目的地寄存器的可用附加物理寄存器来重命名在第一微操作的第一部分中识别的目的地寄存器,以及对第一微操作的第二部分进行解码 微操作成一个或多个第二个微操作。 重命名的行为已经重命名了第一微操作的第二部分的至少一个微操作的目的地寄存器。 该方法执行第一和第二微操作的第三部分。

    Method of sorting numbers to obtain maxima/minima values with ordering
    119.
    发明授权
    Method of sorting numbers to obtain maxima/minima values with ordering 有权
    排序数字获得最大/最小值的方法

    公开(公告)号:US6128614A

    公开(公告)日:2000-10-03

    申请号:US246575

    申请日:1999-02-08

    Abstract: A technique for sorting packed numbers of two operands into minima or maxima operand with their indices to identify the origin of those selected values. After packing two source operands with a plurality of data elements containing numerical values, greater-than comparison operation is performed on the two operands to generate a mask. The mask is used to identify those corresponding pair of data elements of the first and second operands which need to be passed through the subsequent stages in order to generate a sorted minima or maxima. The operands are AND'ed with the mask or the complement of the mask to generate the required minima/maxima result. The same AND'ing technique is used with two other operands containing indices of the values in the first two operands. The indices identify the originating location of the sorted maxima/minima.

    Abstract translation: 一种用于将两个操作数的打包数分成最小值或最大值操作数的技术,其索引用于标识这些选定值的起始点。 在使用包含数值的多个数据元素打包两个源操作数之后,对两个操作数进行大于比较的操作以生成掩码。 掩模用于识别需要通过后续阶段的第一和第二操作数的相应数据元素对,以便生成排序的最小值或最大值。 操作数与掩码或掩码的补码进行“和”生成所需的最小/最大值结果。 使用与前两个操作数中包含值的两个其他操作数相同的AND'ing技术。 这些索引标识了排序最大值/最小值的起始位置。

    Computer implemented method for providing a two dimensional rotation of
packed data
    120.
    发明授权
    Computer implemented method for providing a two dimensional rotation of packed data 失效
    用于提供打包数据的二维旋转的计算机实现的方法

    公开(公告)号:US5984515A

    公开(公告)日:1999-11-16

    申请号:US917671

    申请日:1997-08-21

    CPC classification number: G06F9/30014 G06F9/30036 G06T3/60

    Abstract: In a computer system having stored therein a first and a second packed data having corresponding data elements, a method for generating a two dimensional rotation of said packed data. The method includes the steps of generating a first set of intermediate results in response to a first instruction by multiplying the data elements of the first packed data with corresponding elements of a third packed data. The elements of said third packed data represent either a sine or cosine function. A second step of generating a second set of intermediate results in response to a second instruction by multiplying the data elements of the second packed data with corresponding elements of a fourth packed data. The elements of the fourth packed data represent either a sine or cosine function. A third and final step of generating a set of final results in response to a third instruction by performing an arithmetic operation between corresponding elements of the first and second sets of intermediate results. The final results represent a two dimensional rotation of the elements of the first set of packed data.

    Abstract translation: 在其中存储有具有相应数据元素的第一和第二打包数据的计算机系统中,一种用于产生所述打包数据的二维旋转的方法。 该方法包括以下步骤:通过将第一打包数据的数据元素与第三打包数据的相应元素相乘来响应于第一指令来生成第一组中间结果。 所述第三打包数据的元素表示正弦或余弦函数。 第二步骤,通过将第二打包数据的数据元素与第四打包数据的对应元素相乘来响应于第二指令来生成第二组中间结果。 第四打包数据的元素表示正弦或余弦函数。 通过在第一和第二组中间结果的相应元素之间执行算术运算来产生响应于第三指令的一组最终结果的第三和最后一步骤。 最终结果表示第一组打包数据的元素的二维旋转。

Patent Agency Ranking