Multiply-sum dot product instruction with mask and splat
    11.
    发明申请
    Multiply-sum dot product instruction with mask and splat 审中-公开
    带有掩码和拼接的乘积点积积指令

    公开(公告)号:US20060149804A1

    公开(公告)日:2006-07-06

    申请号:US11000437

    申请日:2004-11-30

    IPC分类号: G06F7/52

    CPC分类号: G06F7/5443

    摘要: An instruction, corresponding methods, and circuitry for efficiently performing partial dot sum products are provided. The instruction may include a source select field for specifying one or more source word elements to participate in the dot sum operation. The instruction may also include a target select field for specifying one or more (or none) target word elements for storing the result of the dot sum operation.

    摘要翻译: 提供了用于有效执行部分点和积的指令,相应方法和电路。 指令可以包括用于指定一个或多个源字元素以参与点和运算的源选择字段。 指令还可以包括用于指定用于存储点和操作的结果的一个或多个(或无)目标字元素的目标选择字段。

    Method and apparatus of supporting cacheable registers
    12.
    发明申请
    Method and apparatus of supporting cacheable registers 有权
    支持可缓存寄存器的方法和装置

    公开(公告)号:US20060026358A1

    公开(公告)日:2006-02-02

    申请号:US10901600

    申请日:2004-07-29

    IPC分类号: G06F12/00

    CPC分类号: G06F12/0888

    摘要: Computer systems with direct updating of cache (e.g., primary L1 cache) memories of a processor, such as a central processing unit (CPU) or graphics processing unit (GPU). Special addresses are reserved for high speed memory. Memory access requests involving these reserved addresses are routed directly to the high speed memory. Memory access requests not involving these reserved addresses are routed to memory external to the processor.

    摘要翻译: 具有直接更新诸如中央处理单元(CPU)或图形处理单元(GPU)的处理器的高速缓存(例如,主要L1高速缓存)存储器的计算机系统。 专用地址保留给高速存储器。 涉及这些保留地址的存储器访问请求直接路由到高速存储器。 不涉及这些保留地址的存储器访问请求被路由到处理器外部的存储器。