PROCESSOR WITH EFFICIENT MEMORY ACCESS
    2.
    发明公开
    PROCESSOR WITH EFFICIENT MEMORY ACCESS 审中-公开
    具有高效存储器访问的处理器

    公开(公告)号:EP3320428A1

    公开(公告)日:2018-05-16

    申请号:EP16820923.7

    申请日:2016-07-04

    IPC分类号: G06F9/38 G06F9/34

    摘要: A method includes, in a processor (20), processing program code that includes memory- access instructions, wherein at least some of the memory-access instructions include symbolic expressions that specify memory addresses in an external memory (41) in terms of one or more register names. A relationship between the memory addresses accessed by two or more of the memory-access instructions is identified, based on respective formats of the memory addresses specified in the symbolic expressions. An outcome of at least one of the memory-access instructions is assigned to be served from an internal memory (50) in the processor, based on the identified relationship.

    TRACE BUFFER BASED REPLAY FOR CONTEXT SWITCHING
    3.
    发明公开
    TRACE BUFFER BASED REPLAY FOR CONTEXT SWITCHING 审中-公开
    基于TRACE BUFFER的上下文切换

    公开(公告)号:EP3234769A1

    公开(公告)日:2017-10-25

    申请号:EP15816988.8

    申请日:2015-12-02

    IPC分类号: G06F9/38

    摘要: A command processor may process a command stream for execution by at least one processor, including storing data associated with a first set of one or more operations in the command stream in a trace buffer, wherein the first set of one or more operations accesses one or more memory locations in memory, and wherein the data include an indication of contents of the one or more memory locations associated with the first set of one or more operations. The command processor may interrupt the processing of the command stream. The command processor may, in response to resuming processing of the command stream subsequent to the interrupting of the processing of the command stream, replay at least a portion of the command stream, including processing a second set of one or more operations of the command stream based at least in part on the data stored in the trace buffer.

    摘要翻译: 命令处理器可处理用于由至少一个处理器执行的命令流,包括将与命令流中的第一组一个或多个操作相关联的数据存储在跟踪缓冲器中,其中第一组一个或多个操作访问一个或多个操作 存储器中更多的存储器位置,并且其中数据包括与第一组一个或多个操作相关联的一个或多个存储器位置的内容的指示。 命令处理器可能中断命令流的处理。 命令处理器可以响应于在中断命令流的处理之后恢复命令流的处理,重放命令流的至少一部分,包括处理命令流的一个或多个操作的第二集合 至少部分基于存储在跟踪缓冲器中的数据。

    Processor with architecturally-visible programmable on-die storage to store data that is accessible by instruction
    4.
    发明公开
    Processor with architecturally-visible programmable on-die storage to store data that is accessible by instruction 审中-公开
    在一个芯片上与可编程存储器架构可见处理器以存储在指令访问数据

    公开(公告)号:EP2889759A8

    公开(公告)日:2016-02-24

    申请号:EP14193268.1

    申请日:2014-11-14

    申请人: Intel Corporation

    发明人: Lee, Victor W.

    IPC分类号: G06F9/38

    摘要: A processor of an aspect includes an on-die programmable architecturally-visible storage. The processor also includes a decode unit to receive a data access instruction of an instruction set of the processor. The data access instruction to indicate a data address that is to be associated with data to be stored in the on-die programmable architecturally-visible storage, to indicate a data size associated with the data to be stored in the on-die programmable architecturally-visible storage, and to indicate a destination storage location of the processor. An execution unit is coupled with the decode unit and the on-die programmable architecturally-visible storage. The execution unit is on-die with the on-die programmable storage. The execution unit is operable, in response to the data access instruction, to store the data, which is associated with the data address and the data size, in the destination storage location that is to be indicated by the instruction.

    摘要翻译: 一个形态的处理器包括接通可编程架构可见存储。 因此处理器包括解码单元,用于接收设置处理器的指令的一个数据访问指令。 该数据访问指令,以指示没有数据地址将要关联的与将要存储在片上的可编程架构可见存储的数据,以指示与所述数据相关联的数据的大小将被存储在片上的可编程architecturally- 可见的存储,并指示所述处理器的目的地存储位置。 的执行单元与所述解码单元和所述接通可编程架构可见存储。 所述执行单元是在与上最可编程存储。 所述执行单元是可操作的,响应于数据访问指令,来存储数据,这一切都与数据地址,并在目的地存储位置中的数据相关联的大小做是由指令来指示。

    LOAD STORE UNIT WITH REPLAY MECHANISM
    9.
    发明授权
    LOAD STORE UNIT WITH REPLAY MECHANISM 有权
    带有重复机制负载存储单元

    公开(公告)号:EP1644823B1

    公开(公告)日:2007-11-21

    申请号:EP04753838.4

    申请日:2004-06-02

    IPC分类号: G06F9/38

    摘要: A microprocessor (100) may include a scheduler (118) configured to issue operations and a load store unit (126C) configured to execute memory operations issued by the scheduler (118). The load store unit (126C) is configured to store information identifying memory operations issued to the load store unit (126C). In response to detection of incorrect data speculation for one of the issued memory operations, the load store unit (126C) is configured to replay at least one of the issued memory operations by providing an indication to the scheduler (118). The scheduler (118) is configured to responsively reissue the memory operations identified by the load store unit (126C).

    LOAD STORE UNIT WITH REPLAY MECHANISM
    10.
    发明公开
    LOAD STORE UNIT WITH REPLAY MECHANISM 有权
    带有重复机制负载存储单元

    公开(公告)号:EP1644823A1

    公开(公告)日:2006-04-12

    申请号:EP04753838.4

    申请日:2004-06-02

    IPC分类号: G06F9/38

    摘要: A microprocessor (100) may include a scheduler (118) configured to issue operations and a load store unit (126C) configured to execute memory operations issued by the scheduler (118). The load store unit (126C) is configured to store information identifying memory operations issued to the load store unit (126C). In response to detection of incorrect data speculation for one of the issued memory operations, the load store unit (126C) is configured to replay at least one of the issued memory operations by providing an indication to the scheduler (118). The scheduler (118) is configured to responsively reissue the memory operations identified by the load store unit (126C).