会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 1. 发明申请
    • USING PROCESS LOCATION TO BIND IO RESOURCES ON NUMA ARCHITECTURES
    • 使用过程位置对NUMA体系结构进行IO资源分配
    • US20120072622A1
    • 2012-03-22
    • US13076735
    • 2011-03-31
    • Nicolas G. DrouxRajagopal KunhappanSherman Pun
    • Nicolas G. DrouxRajagopal KunhappanSherman Pun
    • G06F3/00
    • G06F13/4022G06F9/505
    • In general, in one aspect, the invention relates to a method for binding input/output (I/O) objects to nodes. The method includes receiving a request to use an I/O device from a process, determining a resource to service the request, generating a first I/O object corresponding to the resource, wherein the first I/O object is unbound, and generating a proc object, wherein the proc object comprises a reference to the process requesting to use the I/O device. The method also includes sending the first I/O object and the proc object to a Non-Uniform Memory Access (NUMA) I/O Framework, determining that the process is executing on a first NUMA node, selecting the first NUMA, binding the first I/O object to the first NUMA node, and servicing the request by processing, on the first NUMA node, the resource corresponding to the first I/O object.
    • 通常,一方面,本发明涉及用于将输入/输出(I / O)对象绑定到节点的方法。 该方法包括从进程接收使用I / O设备的请求,确定用于服务该请求的资源,生成与资源相对应的第一I / O对象,其中第一I / O对象是未绑定的,并且生成 proc对象,其中proc对象包括对请求使用I / O设备的处理的引用。 该方法还包括将第一个I / O对象和proc对象发送到非均匀内存访问(NUMA)I / O框架,确定该进程正在第一个NUMA节点上执行,选择第一个NUMA,绑定第一个 I / O对象到第一NUMA节点,并且通过在第一NUMA节点上处理对应于第一I / O对象的资源来处理该请求。
    • 2. 发明授权
    • Using process location to bind IO resources on NUMA architectures
    • 使用进程位置绑定NUMA架构上的IO资源
    • US08996756B2
    • 2015-03-31
    • US13076735
    • 2011-03-31
    • Nicolas G. DrouxRajagopal KunhappanSherman Pun
    • Nicolas G. DrouxRajagopal KunhappanSherman Pun
    • G06F13/12G06F9/46G06F13/40G06F9/50
    • G06F13/4022G06F9/505
    • In general, in one aspect, the invention relates to a method for binding input/output (I/O) objects to nodes. The method includes receiving a request to use an I/O device from a process, determining a resource to service the request, generating a first I/O object corresponding to the resource, wherein the first I/O object is unbound, and generating a proc object, wherein the proc object comprises a reference to the process requesting to use the I/O device. The method also includes sending the first I/O object and the proc object to a Non-Uniform Memory Access (NUMA) I/O Framework, determining that the process is executing on a first NUMA node, selecting the first NUMA, binding the first I/O object to the first NUMA node, and servicing the request by processing, on the first NUMA node, the resource corresponding to the first I/O object.
    • 通常,一方面,本发明涉及用于将输入/输出(I / O)对象绑定到节点的方法。 该方法包括从进程接收使用I / O设备的请求,确定用于服务该请求的资源,生成与资源相对应的第一I / O对象,其中第一I / O对象是未绑定的,并且生成 proc对象,其中proc对象包括对请求使用I / O设备的处理的引用。 该方法还包括将第一I / O对象和proc对象发送到非均匀存储器访问(NUMA)I / O框架,确定该进程正在第一NUMA节点上执行,选择第一个NUMA,绑定第一个 I / O对象到第一NUMA节点,并且通过在第一NUMA节点上处理对应于第一I / O对象的资源来处理该请求。
    • 3. 发明授权
    • Transfer of arbitrary size messages over memory based interconnects
    • 通过基于内存的互连传输任意大小的消息
    • US07506032B1
    • 2009-03-17
    • US10810171
    • 2004-03-25
    • Prashant RamaraoSherman PunManish Verma
    • Prashant RamaraoSherman PunManish Verma
    • G06F15/16
    • H04L67/1097
    • In accordance with one embodiment of the present invention, there is provided a mechanism for implementing transfer of arbitrary length messages between one or more machines in a computing environment comprised of a plurality of machines. With this mechanism, it is possible to send and receive messages of arbitrary length across memory-based or other interconnects using a single operation. In one embodiment, the machines are interconnected by a memory-mapped link. The memory-mapped link includes processes for mapping an image of a buffer allocated in the storage of the receiving machine into the addressing space of the sending machine. The sending machine may transfer the message to the memory of the receiving machine using a single write operation to the memory mapped image in the sending machine's own address space.
    • 根据本发明的一个实施例,提供了一种用于在由多个机器组成的计算环境中的一个或多个机器之间实现任意长度消息传送的机制。 利用这种机制,可以使用单个操作在基于存储器或其他互连的情况下发送和接收任意长度的消息。 在一个实施例中,机器通过存储器映射链路互连。 存储器映射链路包括将分配在接收机的存储器中的缓冲器的映像映射到发送机的寻址空间的处理。 发送机可以使用对发送机自己的地址空间中的存储器映射图像的单个写入操作将消息传送到接收机的存储器。