SHUFFLE PATTERN GENERATING CIRCUIT, PROCESSOR, SHUFFLE PATTERN GENERATING METHOD, AND INSTRUCTION SEQUENCE
    1.
    发明申请
    SHUFFLE PATTERN GENERATING CIRCUIT, PROCESSOR, SHUFFLE PATTERN GENERATING METHOD, AND INSTRUCTION SEQUENCE 有权
    小型图案生成电路,处理器,SHUFFLE图案生成方法和指令序列

    公开(公告)号:US20130275718A1

    公开(公告)日:2013-10-17

    申请号:US13822213

    申请日:2012-09-13

    IPC分类号: G06F9/30

    摘要: Based on an input index sequence (702) composed of four indices (each having a bit width of 8 bits), a shift-copier generates an index sequence (902) by shifting each index leftward by 1 bit and making two copies of each index, and outputs the generated index sequence (902). An adder generates a shuffle pattern (703) by adding 1, 0, 1, 0, 1, 0, 1 and 0 to the indices in the index sequence (902) from left to right, and outputs the generated shuffle pattern (703).

    摘要翻译: 基于由四个索引(每个具有8位的位宽度)组成的输入索引序列(702),移位复制器通过向左移位1位并将每个索引的两个拷贝移位来生成索引序列(902) ,并输出生成的索引序列(902)。 加法器通过从索引序列(902)中从左到右将0,1,0,1,0,1,0,1和0加到索引序列(902)中的索引来产生混洗图案(703),并输出生成的随机样式(703) 。

    Dedicated crossbar and barrel shifter block on programmable logic resources
    2.
    发明授权
    Dedicated crossbar and barrel shifter block on programmable logic resources 失效
    专用的横杆和桶形移位器块可编程逻辑资源

    公开(公告)号:US07042248B1

    公开(公告)日:2006-05-09

    申请号:US10454728

    申请日:2003-06-03

    IPC分类号: H03K19/177

    摘要: A dedicated hardware block is provided for implementing crossbars and/or barrel shifters in programmable logic resources. Crossbar and/or barrel shifter circuitry may replace one or more rows, one or more columns, one or more rectangles, or any combination thereof of programmable logic regions on a programmable logic resource. The functionality of the crossbar and/or barrel shifter circuitry can further be improved by implementing time-multiplexing.

    摘要翻译: 提供专用硬件块用于在可编程逻辑资源中实现十字路口和/或桶形移位器。 横杆和/或桶形移位器电路可以替代可编程逻辑资源上的可编程逻辑区域的一行或多行,一列或多列,一个或多个矩形或其任意组合。 可以通过实施时间复用来进一步改进交叉开关和/或桶形移位器电路的功能。

    Wide shifting in the vector permute unit
    3.
    发明授权
    Wide shifting in the vector permute unit 有权
    矢量变换单位宽移

    公开(公告)号:US06343337B1

    公开(公告)日:2002-01-29

    申请号:US09572058

    申请日:2000-05-17

    IPC分类号: G06F1300

    CPC分类号: G06F7/766 G06F5/015

    摘要: A crossbar is implemented within multimedia facilities of a processor to perform vector permute operations, in which the bytes of a source operand are reordered in the target output. The crossbar is then reused for other instructions requiring multiplexing or shifting operations, particularly those in which the size of additional multiplexers or the size and delay of a barrel shifter is significant. A wide shift operation, for example, may be performed with one cycle latency by the crossbar and one additional layer of multiplexers or a small barrel shifter. The crossbar facility thus gets reused with improved performance of the instructions now sharing the crossbar and a reduction in the total area required by a multimedia facility within a processor.

    摘要翻译: 在处理器的多媒体设施内实现交叉开关以执行矢量置换操作,其中源操作数的字节在目标输出中重新排序。 然后,交叉开关重新用于需要复用或移位操作的其他指令,特别是其中附加多路复用器的大小或桶形移位器的大小和延迟是显着的那些指令。 例如,可以通过交叉开关和一个附加的多路复用器层或小桶形移位器以一个周期的等待时间来执行宽移位操作。 因此,交叉开关设备被重新使用,现在共享交叉开关的指令的性能得到改善,并且减少处理器内的多媒体设备所需的总面积。

    SYMMETRIC FILTER ARITHMETIC APPARATUS AND SYMMETRIC FILTER ARITHMETIC METHOD
    4.
    发明申请
    SYMMETRIC FILTER ARITHMETIC APPARATUS AND SYMMETRIC FILTER ARITHMETIC METHOD 有权
    对称滤波算法和对称滤波算法

    公开(公告)号:US20140219577A1

    公开(公告)日:2014-08-07

    申请号:US13818198

    申请日:2012-07-25

    申请人: Yoshiteru Hayashi

    发明人: Yoshiteru Hayashi

    IPC分类号: G06T5/10

    摘要: A symmetric filter arithmetic apparatus includes a first data shuffling unit which reads a first data string that is a plurality of consecutive pieces of data from a register file and extract, from the first data string, a left-side data string that is a plurality of consecutive pieces of data to be multiplied by a left-side filter coefficient that is a filter coefficient on a left side of a center of the coefficients, and a second data shuffling unit which reads a second data string that is a plurality of consecutive pieces of data from the register file and extract, from the second data string, a right-side data string that is a plurality of consecutive pieces of data to be multiplied by a right-side filter coefficient that is a filter coefficient on a right side of the center and is the same value as the left-side filter coefficient.

    摘要翻译: 对称滤波器运算装置包括:第一数据混洗单元,从第一数据串中读取作为来自寄存器文件的多个连续数据的第一数据串,并从第二数据串中提取多个 要被乘以作为系数中心左侧的滤波器系数的左侧滤波器系数的连续数据块,以及第二数据混洗单元,其读取作为多个连续片段的第二数据串 来自寄存器文件的数据,并从第二数据串中提取右侧数据串,该右侧数据串是要乘以作为右侧的滤波器系数的右侧滤波器系数的多个连续数据块 中心,与左侧滤波器系数相同。

    Method and system for a wiring-efficient permute unit
    5.
    发明授权
    Method and system for a wiring-efficient permute unit 失效
    布线效率置换单元的方法和系统

    公开(公告)号:US08069195B2

    公开(公告)日:2011-11-29

    申请号:US11968692

    申请日:2008-01-03

    IPC分类号: G06F7/00

    摘要: A method of providing wiring efficiency in a permute unit. Multiple selectors receive input data and shared control signals from multiple register files. The permute unit includes multiple multiplexors (MUXs) coupled to multiple logical AND gates. The multiple logical AND gates are coupled to multiple logical OR gates. The logical AND gates are physically separated from the logical OR gates. The logical AND gates receive input from one or more output data signals from the selectors. The logical OR gates combine the one or more output signals from the logical AND gates and provide output data from the permute unit.

    摘要翻译: 一种在置换单元中提供布线效率的方法。 多个选择器从多个寄存器文件接收输入数据和共享控制信号。 置换单元包括耦合到多个逻辑与门的多个多路复用器(MUX)。 多个逻辑与门被耦合到多个逻辑或门。 逻辑“与”门与逻辑或门物理分离。 逻辑与门接收来自选择器的一个或多个输出数据信号的输入。 逻辑或门组合来自逻辑与门的一个或多个输出信号,并提供来自置换单元的输出数据。

    Electronic circuit for implementing a permutation operation
    7.
    发明申请
    Electronic circuit for implementing a permutation operation 失效
    用于实现置换操作的电子电路

    公开(公告)号:US20070011220A1

    公开(公告)日:2007-01-11

    申请号:US11390791

    申请日:2006-03-28

    IPC分类号: G06F17/15

    CPC分类号: G06F7/766

    摘要: A crossbar (20) circuit with multiplexer (22A, 22B) circuits implemented in a polygonal form on a chip. The crossbar can be used for implementing a permutation of input bits (24A, 24B) controlled by a bit vector (25). Horizontal and vertical wiring lengths in the crossbar (20) are reduced by stacking the operand latches (24A, 24B, 25) and horizontal or vertical multiplexers (22A, 22B). This implementation decreases the latency of the crossbar and avoids latches to store intermediated results, thus reducing area and power consumption.

    摘要翻译: 具有以多边形形式在芯片上实现的多路复用器(22A,22B)电路的交叉开关(20)电路。 交叉开关可用于实现由位向量(25)控制的输入位(24A,24B)的置换。 通过堆叠操作数锁存器(24A,24B,25)和水平或垂直多路复用器(22A,22B)来减小横杆(20)中的水平和垂直布线长度。 该实现降低了交叉开关的延迟,并避免了锁存器来存储中间结果,从而减少了面积和功耗。

    Wide shifting in the vector permute unit
    8.
    发明授权
    Wide shifting in the vector permute unit 有权
    矢量变换单位宽移

    公开(公告)号:US06327651B1

    公开(公告)日:2001-12-04

    申请号:US09149466

    申请日:1998-09-08

    IPC分类号: G06F1500

    CPC分类号: G06F7/766 G06F5/015

    摘要: A crossbar is implemented within multimedia facilities of a processor to perform vector permute operations, in which the bytes of a source operand are reordered in the target output. The crossbar is then reused for other instructions requiring multiplexing or shifting operations, particularly those in which the size of additional multiplexers or the size and delay of a barrel shifter is significant. A wide shift operation, for example, may be performed with one cycle latency by the crossbar and one additional layer of multiplexers or a small barrel shifter. The crossbar facility thus gets reused with improved performance of the instructions now sharing the crossbar and a reduction in the total area required by a multimedia facility within a processor.

    摘要翻译: 在处理器的多媒体设施内实现交叉开关以执行矢量置换操作,其中源操作数的字节在目标输出中重新排序。 然后,交叉开关重新用于需要复用或移位操作的其他指令,特别是其中附加多路复用器的大小或桶形移位器的大小和延迟是显着的那些指令。 例如,可以通过交叉开关和一个附加的多路复用器层或小桶形移位器以一个周期的等待时间来执行宽移位操作。 因此,交叉开关设备被重新使用,现在共享交叉开关的指令的性能得到改善,并且减少处理器内的多媒体设备所需的总面积。