Abstract: A network interface controller (NIC) capable of efficient operation management for host accelerators is provided. The NIC can be equipped with a host interface and triggering logic block. During operation, the host interface can couple the NIC to a host device. The triggering logic block can obtain, via the host interface from the host device, an operation associated with an accelerator of the host device. The triggering logic block can determine whether a triggering condition has been satisfied for the operation based on an indicator received from the accelerator. If the triggering condition has been satisfied, the triggering logic block can obtain a piece of data generated from the accelerator from a memory location and execute the operation using the piece of data.

Abstract: A network interface controller (NIC) capable of on-demand paging is provided. The NIC can be equipped with a host interface, an operation logic block, and an address logic block. The host interface can couple the NIC to a host device. The operation logic block can obtain from a remote device, a request for an operation based on a virtual memory address. The address logic block can obtain, from the operation logic block, a request for an address translation for the virtual memory address and issue an address translation request to the host device via the host interface. If the address translation is unsuccessful, the address logic block can send a page request to a processor of the host device via the host interface. The address logic block can then determine that a page has been allocated in response to the page request and reissue the address translation request.

Abstract: A network interface controller (NIC) capable of efficient operation management for host accelerators is provided. The NIC can be equipped with a host interface and triggering logic block. During operation, the host interface can couple the NIC to a host device. The triggering logic block can obtain, via the host interface from the host device, an operation associated with an accelerator of the host device. The triggering logic block can determine whether a triggering condition has been satisfied for the operation based on an indicator received from the accelerator. If the triggering condition has been satisfied, the triggering logic block can obtain a piece of data generated from the accelerator from a memory location and execute the operation using the piece of data.

Abstract: A network interface controller (NIC) capable of on-demand paging is provided. The NIC can be equipped with a host interface, an operation logic block, and an address logic block. The host interface can couple the NIC to a host device. The operation logic block can obtain from a remote device, a request for an operation based on a virtual memory address. The address logic block can obtain, from the operation logic block, a request for an address translation for the virtual memory address and issue an address translation request to the host device via the host interface. If the address translation is unsuccessful, the address logic block can send a page request to a processor of the host device via the host interface. The address logic block can then determine that a page has been allocated in response to the page request and reissue the address translation request.

Abstract: A network interface controller (NIC) capable of efficient memory access is provided. The NIC can be equipped with an operation logic block, a signaling logic block, and a tracking logic block. The operation logic block can maintain an operation group associated with packets requesting an operation on a memory segment of a host device of the NIC. The signaling logic block can determine whether a packet associated with the operation group has arrived at or departed from the NIC. Furthermore, the tracking logic block can determine that a request for releasing the memory segment has been issued. The tracking logic block can then determine whether at least one packet associated with the operation group is under processing in the NIC. If no packet associated with the operation group is under processing in the NIC, tracking logic block can notify the host device that the memory segment can be released.

Abstract: A network interface controller (NIC) capable of hybrid message matching is provided. The NIC can be equipped with a host interface, a hardware endpoint, and an endpoint management logic block. The host interface can couple the NIC to a host device. The hardware endpoint can facilitate a point of communication for an application running on the host device. The endpoint management logic block can maintain a list for storing a message associated with an endpoint represented by the hardware endpoint. The endpoint management logic block can then determine whether the utilization of the list is higher than a threshold. If the utilization is higher than the threshold, the endpoint management logic block can set a state of the endpoint to indicate that the endpoint is software managed. The NIC thus can transfer the control of the endpoint from the hardware endpoint to a software process of the host device.

Abstract: A network interface controller (NIC) capable of efficient memory access is provided. The NIC can be equipped with an operation logic block, a signaling logic block, and a tracking logic block. The operation logic block can maintain an operation group associated with packets requesting an operation on a memory segment of a host device of the NIC. The signaling logic block can determine whether a packet associated with the operation group has arrived at or departed from the NIC. Furthermore, the tracking logic block can determine that a request for releasing the memory segment has been issued. The tracking logic block can then determine whether at least one packet associated with the operation group is under processing in the NIC. If no packet associated with the operation group is under processing in the NIC, tracking logic block can notify the host device that the memory segment can be released.

Abstract: A network interface controller (NIC) capable of hybrid message matching is provided. The NIC can be equipped with a host interface, a hardware endpoint, and an endpoint management logic block. The host interface can couple the NIC to a host device. The hardware endpoint can facilitate a point of communication for an application running on the host device. The endpoint management logic block can maintain a list for storing a message associated with an endpoint represented by the hardware endpoint. The endpoint management logic block can then determine whether the utilization of the list is higher than a threshold. If the utilization is higher than the threshold, the endpoint management logic block can set a state of the endpoint to indicate that the endpoint is software managed. The NIC thus can transfer the control of the endpoint from the hardware endpoint to a software process of the host device.

Abstract: A network interface controller (NIC) capable of on-demand paging is provided. The NIC can be equipped with a host interface, an operation logic block, and an address logic block. The host interface can couple the NIC to a host device. The operation logic block can obtain from a remote device, a request for an operation based on a virtual memory address. The address logic block can obtain, from the operation logic block, a request for an address translation for the virtual memory address and issue an address translation request to the host device via the host interface. If the address translation is unsuccessful, the address logic block can send a page request to a processor of the host device via the host interface. The address logic block can then determine that a page has been allocated in response to the page request and reissue the address translation request.

Abstract: A network interface controller (NIC) capable of efficient operation management for host accelerators is provided. The NIC can be equipped with a host interface and triggering logic block. During operation, the host interface can couple the NIC to a host device. The triggering logic block can obtain, via the host interface from the host device, an operation associated with an accelerator of the host device. The triggering logic block can determine whether a triggering condition has been satisfied for the operation based on an indicator received from the accelerator. If the triggering condition has been satisfied, the triggering logic block can obtain a piece of data generated from the accelerator from a memory location and execute the operation using the piece of data.

Abstract: A network interface controller (NIC) capable of efficient memory access is provided. The NIC can be equipped with an operation logic block, a signaling logic block, and a tracking logic block. The operation logic block can maintain an operation group associated with packets requesting an operation on a memory segment of a host device of the NIC. The signaling logic block can determine whether a packet associated with the operation group has arrived at or departed from the NIC. Furthermore, the tracking logic block can determine that a request for releasing the memory segment has been issued. The tracking logic block can then determine whether at least one packet associated with the operation group is under processing in the NIC. If no packet associated with the operation group is under processing in the NIC, tracking logic block can notify the host device that the memory segment can be released.

Abstract: An improved method for the prevention of deadlock in a massively parallel processor (MPP) system wherein, prior to a process sending messages to another process running on a remote processor, the process allocates space in a deadlock-avoidance FIFO. The allocated space provides a “landing zone” for requests that the software process (the application software) will subsequently issue using a remote-memory-access function. In some embodiments, the deadlock-avoidance (DLA) function provides two different deadlock-avoidance schemes: controlled discard and persistent reservation. In some embodiments, the software process determines which scheme will be used at the time the space is allocated.

Abstract: An improved method for the prevention of deadlock in a massively parallel processor (MPP) system wherein, prior to a process sending messages to another process running on a remote processor, the process allocates space in a deadlock-avoidance FIFO. The allocated space provides a “landing zone” for requests that the software process (the application software) will subsequently issue using a remote-memory-access function. In some embodiments, the deadlock-avoidance (DLA) function provides two different deadlock-avoidance schemes: controlled discard and persistent reservation. In some embodiments, the software process determines which scheme will be used at the time the space is allocated.

Abstract: A high performance computer system has compute nodes interconnected by an inter-node communication network. The compute nodes include local packetized interconnects. Shared memory between compute nodes is emulated by tunneling packetized interconnect packets between the compute nodes. A memory region on one of the compute nodes is used as a window into a memory region in another compute node. Special registers may be provided to expedite remote operations on small amounts of data.

Abstract: An improved method for the prevention of deadlock in a massively parallel processor (MPP) system wherein, prior to a process sending messages to another process running on a remote processor, the process allocates space in a deadlock-avoidance FIFO. The allocated space provides a “landing zone” for requests that the software process (the application software) will subsequently issue using a remote-memory-access function. In some embodiments, the deadlock-avoidance (DLA) function provides two different deadlock-avoidance schemes: controlled discard and persistent reservation. In some embodiments, the software process determines which scheme will be used at the time the space is allocated.

Abstract: A high performance computer system has compute nodes interconnected by an inter-node communication network. The compute nodes include local packetized interconnects. Shared memory between compute nodes is emulated by tunneling packetized interconnect packets between the compute nodes. A memory region on one of the compute nodes is used as a window into a memory region in another compute node. Special registers may be provided to expedite remote operations on small amounts of data.

Abstract: A high performance computer system has compute nodes interconnected by an inter-node communication network. The compute nodes include local packetized interconnects. Shared memory between compute nodes is emulated by tunneling packetized interconnect packets between the compute nodes. A memory region on one of the compute nodes is used as a window into a memory region in another compute node. Special registers may be provided to expedite remote operations on small amounts of data.

Abstract: A high performance computer system has compute nodes interconnected by an inter-node communication network. The compute nodes include local packetized interconnects. Shared memory between compute nodes is emulated by tunneling packetized interconnect packets between the compute nodes. A memory region on one of the compute nodes is used as a window into a memory region in another compute node. Special registers may be provided to expedite remote operations on small amounts of data.

Abstract: A high performance computer system has compute nodes interconnected by an inter-node communication network. The compute nodes include local packetized interconnects. Shared memory between compute nodes is emulated by tunneling packetized interconnect packets between the compute nodes. A memory region on one of the compute nodes is used as a window into a memory region in another compute node. Special registers may be provided to expedite remote operations on small amounts of data.

Abstract: A high performance computer system has compute nodes interconnected by an inter-node communication network. The compute nodes include local packetized interconnects. Shared memory between compute nodes is emulated by tunneling packetized interconnect packets between the compute nodes. A memory region on one of the compute nodes is used as a window into a memory region in another compute node. Special registers may be provided to expedite remote operations on small amounts of data.