Abstract: A method and system for realizing a FPGA server, wherein centralized monitoring and managing all SoC FPGA compute nodes within the server by a motherboard, the motherboard comprising: a plurality of self-defined management interfaces for connecting the SoC FPGA compute nodes to supply power and data switch to the SoC FPGA compute nodes; a management network switch module for interconnecting the SoC FPGA compute nodes and supplying management; and a core control unit for managing the SoC FPGA compute nodes through the self-defined management interfaces and a self-defined management interface protocol, and acquiring operating parameters of the SoC FPGA compute nodes to manage and monitor the SoC FPGA compute nodes based on the management interface protocol.

Abstract: A method and system for realizing a FPGA server, wherein centralized monitoring and managing all SoC FPGA compute nodes within the server by a motherboard, the motherboard comprising: a plurality of self-defined management interfaces for connecting the SoC FPGA compute nodes to supply power and data switch to the SoC FPGA compute nodes; a management network switch module for interconnecting the SoC FPGA compute nodes and supplying management; and a core control unit for managing the SoC FPGA compute nodes through the self-defined management interfaces and a self-defined management interface protocol, and acquiring operating parameters of the SoC FPGA compute nodes to manage and monitor the SoC FPGA compute nodes based on the management interface protocol.

Abstract: A resource access method applied to a computer and the computer, where the resource access method is performed by a resource controller which is used to implement resource virtualization. The method includes receiving a resource access request of a virtual machine (VM) for a resource, where the resource access request carries a resource virtual address and an identifier of the VM, translating the resource virtual address into a resource physical address using the identifier of the VM and based on a preset resource information mapping relationship, updating the resource virtual address in the resource access request using the resource physical address, and sending an updated resource access request to a to-be-accessed resource corresponding to the resource physical address in order to access the to-be-accessed resource.

Abstract: A GPU resource allocation method and system relate to the field of computer technologies. A global logic controller determines a to-be-distributed kernel program in a kernel status register table; searches an SM status register table for an SM capable of running at least one entire thread block; when the SM capable of running at least one entire block is not found, searches the SM status register table for a first SM, where the first SM is an SM capable of running at least one thread warp; and when the first SM is found, distributes a block from the to-be-distributed kernel program to the first SM; or when the first SM is not found, searches for a second SM and then distributes the block from the to-be-distributed kernel program to the second SM. The GPU resource allocation method and system are applicable to GPU resource allocation.

Abstract: The present invention provides a GPU resource allocation method. A to-be-distributed kernel program in a kernel status register table is identified by using a global logic controller (201). The global logic controller searches in an SM status register table for an SM that can run at least one complete block, and the SM status register table is configured to store a quantity of available resources in each SM (202). When the global logic controller does not find the SM that can run at least one complete block, the SM status register table is searched for a first SM, and the first SM is an SM that can run at least one warp (203). When the global logic controller finds the first SM, a block in the to-be-distributed kernel program is distributed to the first SM (204).

Abstract: A control method and a control device are provided. A router receives data sent by a first device, where the data carries an identifier of an input/output (I/O) device, determines, according to the identifier of the I/O device and a correspondence between the I/O device and a controller, a controller corresponding to the identifier of the I/O device, sends the data to the controller corresponding to the identifier of the I/O device such that the controller processes the data according to firmware code stored in the controller, receives the processed data sent by the controller, and sends the processed data to a second device, where the second device or the first device is the I/O device. The firmware code is generally programmable, and therefore a control device applying the foregoing control method can be relatively flexibly implemented.

Abstract: A computer includes a processor and multiple components directly or indirectly connected to the processor. Each component is coupled to a control device, and is configured to provide resources for one or more application programs running in the computer. The processor, when executing an application program, attaches a tag to an application request, and sends the tag-attached application request to a control device coupled with a component to which the tag-attached application request is directed. The control device receives the tag-attached application request, determines, based on the tag and a resource allocation policy, an amount of resources in the component and instructs the component to allocate the amount of resources and process the application request in accordance with the amount of resources allocated for the application request.

Abstract: A resource access method applied to a computer and the computer, where the resource access method is performed by a resource controller which is used to implement resource virtualization. The method includes receiving a resource access request of a virtual machine (VM) for a resource, where the resource access request carries a resource virtual address and an identifier of the VM, translating the resource virtual address into a resource physical address using the identifier of the VM and based on a preset resource information mapping relationship, updating the resource virtual address in the resource access request using the resource physical address, and sending an updated resource access request to a to-be-accessed resource corresponding to the resource physical address in order to access the to-be-accessed resource.

Abstract: A data processing method for an NOC without buffer and an NOC electronic element are provided. The method includes: receiving multiple packets by a routing node in one processing period, where the plurality of packets need to be transmitted to a same forwarding port; acquiring priority information of the multiple packets and determining priority levels of the packets based on the priority information, where for each packet, the priority information includes time length information of the packet and program priority information of a program corresponding to the packet, and the time length information of the packet represents a time period during which the packet is remained in the NOC; and forwarding a packet having a highest priority through the forwarding port. The method and the NOC electronic element are applied to data processing for the NOC without buffer.

Abstract: The present invention provides a GPU resource allocation method. A to-be-distributed kernel program in a kernel status register table is identified by using a global logic controller (201). The global logic controller searches in an SM status register table for an SM that can run at least one complete block, and the SM status register table is configured to store a quantity of available resources in each SM (202). When the global logic controller does not find the SM that can run at least one complete block, the SM status register table is searched for a first SM, and the first SM is an SM that can run at least one warp (203). When the global logic controller finds the first SM, a block in the to-be-distributed kernel program is distributed to the first SM (204).

Abstract: A GPU resource allocation method and system relate to the field of computer technologies. A global logic controller determines a to-be-distributed kernel program in a kernel status register table; searches an SM status register table for an SM capable of running at least one entire thread block; when the SM capable of running at least one entire block is not found, searches the SM status register table for a first SM, where the first SM is an SM capable of running at least one thread warp; and when the first SM is found, distributes a block from the to-be-distributed kernel program to the first SM; or when the first SM is not found, searches for a second SM and then distributes the block from the to-be-distributed kernel program to the second SM. The GPU resource allocation method and system are applicable to GPU resource allocation.

Abstract: A control method and a control device are provided. A router receives data sent by a first device, where the data carries an identifier of an input/output (I/O) device, determines, according to the identifier of the I/O device and a correspondence between the I/O device and a controller, a controller corresponding to the identifier of the I/O device, sends the data to the controller corresponding to the identifier of the I/O device such that the controller processes the data according to firmware code stored in the controller, receives the processed data sent by the controller, and sends the processed data to a second device, where the second device or the first device is the I/O device. The firmware code is generally programmable, and therefore a control device applying the foregoing control method can be relatively flexibly implemented.

Abstract: A computer includes a processor and multiple components directly or indirectly connected to the processor. Each component is coupled to a control device, and is configured to provide resources for one or more application programs running in the computer. The processor, when executing an application program, attaches a tag to an application request, and sends the tag-attached application request to a control device coupled with a component to which the tag-attached application request is directed. The control device receives the tag-attached application request, determines, based on the tag and a resource allocation policy, an amount of resources in the component and instructs the component to allocate the amount of resources and process the application request in accordance with the amount of resources allocated for the application request.

Abstract: A data processing method for an NOC without buffer and an NOC electronic element are provided. The method includes: receiving multiple packets by a routing node in one processing period, where the plurality of packets need to be transmitted to a same forwarding port; acquiring priority information of the multiple packets and determining priority levels of the packets based on the priority information, where for each packet, the priority information includes time length information of the packet and program priority information of a program corresponding to the packet, and the time length information of the packet represents a time period during which the packet is remained in the NOC; and forwarding a packet having a highest priority through the forwarding port. The method and the NOC electronic element are applied to data processing for the NOC without buffer.