Relaxed memory consistency model
    11.
    发明授权
    Relaxed memory consistency model 有权
    轻松记忆一致性模型

    公开(公告)号:US08307194B1

    公开(公告)日:2012-11-06

    申请号:US10643754

    申请日:2003-08-18

    IPC分类号: G06F9/30

    摘要: A method and apparatus to provide specifiable ordering between and among vector and scalar operations within a single streaming processor (SSP) via a local synchronization (Lsync) instruction that operates within a relaxed memory consistency model. Various aspects of that relaxed memory consistency model are described. Further, a combined memory synchronization and barrier synchronization (Msync) for a multistreaming processor (MSP) system is described. Also, a global synchronization (Gsync) instruction provides synchronization even outside a single MSP system is described. Advantageously, the pipeline or queue of pending memory requests does not need to be drained before the synchronization operation, nor is it required to refrain from determining addresses for and inserting subsequent memory accesses into the pipeline.

    摘要翻译: 一种通过在松弛存储器一致性模型中操作的本地同步(Lsync)指令在单个流处理器(SSP)内的向量和标量运算之间和之间提供可指定排序的方法和装置。 描述了该松弛记忆一致性模型的各个方面。 此外,描述了用于多流处理器(MSP)系统的组合的存储器同步和屏障同步(Msync)。 而且,描述了全局同步(Gsync)指令,即使在单个MSP系统外也提供同步。 有利的是,在同步操作之前不需要排出未完成的存储器请求的流水线或队列,也不需要避免为后续存储器访问确定地址并将其插入流水线。

    Decoupling of write address from its associated write data in a store to a shared memory in a multiprocessor system
    12.
    发明授权
    Decoupling of write address from its associated write data in a store to a shared memory in a multiprocessor system 有权
    将写入地址从存储中的相关写入数据解耦到多处理器系统中的共享存储器

    公开(公告)号:US07743223B2

    公开(公告)日:2010-06-22

    申请号:US10643742

    申请日:2003-08-18

    IPC分类号: G06F13/00

    CPC分类号: G06F13/1621 G06F12/084

    摘要: In a computer system having a plurality of processors connected to a shared memory, a system and method of decoupling an address from write data in a store to the shared memory. A write request address is generated for a memory write, wherein the write request address points to a memory location in shared memory. A write request is issued to the shared memory, wherein the write request includes the write request address. The write request address is noted in the shared memory and addresses in subsequent load and store requests are compared in share memory to the write request address. The write data is transferred to the shared memory and matched, within the shared memory, to the write request address. The write data is then stored into the shared memory as a function of the write request address.

    摘要翻译: 在具有连接到共享存储器的多个处理器的计算机系统中,将地址与存储器中的写入数据分离到共享存储器的系统和方法。 为存储器写入生成写请求地址,其中写请求地址指向共享存储器中的存储器位置。 向共享存储器发出写请求,其中写请求包括写请求地址。 在共享存储器中记录写入请求地址,并将后续加载和存储请求中的地址在共享存储器中与写入请求地址进行比较。 写入数据被传送到共享存储器,并在共享存储器内匹配写入请求地址。 写入数据随着写请求地址的存储而被存储到共享存储器中。

    VECTOR ATOMIC MEMORY OPERATIONS
    13.
    发明申请
    VECTOR ATOMIC MEMORY OPERATIONS 审中-公开
    矢量原子记忆操作

    公开(公告)号:US20090138680A1

    公开(公告)日:2009-05-28

    申请号:US11946490

    申请日:2007-11-28

    IPC分类号: G06F9/30

    摘要: A processor is operable to execute one or more vector atomic memory operations. A further embodiment provides support for atomic memory operations in a memory manger, which is operable to process atomic memory operations and to return a completion notification or a result.

    摘要翻译: 处理器可操作以执行一个或多个向量原子存储器操作。 另一实施例提供对存储器管理器中的原子存储器操作的支持,其可操作以处理原子存储器操作并返回完成通知或结果。

    Multistream processing memory-and barrier-synchronization method and apparatus
    16.
    发明授权
    Multistream processing memory-and barrier-synchronization method and apparatus 有权
    多流处理存储器和屏障同步方法和装置

    公开(公告)号:US07437521B1

    公开(公告)日:2008-10-14

    申请号:US10643741

    申请日:2003-08-18

    IPC分类号: G06F12/00 G06F9/52

    摘要: A method and apparatus to provide specifiable ordering between and among vector and scalar operations within a single streaming processor (SSP) via a local synchronization (Lsync) instruction that operates within a relaxed memory consistency model. Various aspects of that relaxed memory consistency model are described. Further, a combined memory synchronization and barrier synchronization (Msync) for a multistreaming processor (MSP) system is described. Also, a global synchronization (Gsync) instruction provides synchronization even outside a single MSP system is described. Advantageously, the pipeline or queue of pending memory requests does not need to be drained before the synchronization operation, nor is it required to refrain from determining addresses for and inserting subsequent memory accesses into the pipeline.

    摘要翻译: 一种通过在松弛存储器一致性模型中操作的本地同步(Lsync)指令在单个流处理器(SSP)内的向量和标量运算之间和之间提供可指定排序的方法和装置。 描述了该松弛记忆一致性模型的各个方面。 此外,描述了用于多流处理器(MSP)系统的组合的存储器同步和屏障同步(Msync)。 而且,描述了全局同步(Gsync)指令,即使在单个MSP系统外也提供同步。 有利的是,在同步操作之前不需要排出未完成的存储器请求的流水线或队列,也不需要避免为后续存储器访问确定地址并将其插入流水线。