143 results about "Network interface controller" patented technology

A coherent, intelligent, packet-switched memory fabric enables predictive, cache-coherent access across distributed compute, accelerator, and memory resources using a Memory-Fabric Transaction Layer Protocol (MF-TLP). MF-TLP defines routable packet formats for read, write, vectorized, atomic, reduction, collective, and predictive-prefetch transactions executed by memory-centric network interface controllers (MC-NICs). Each MC-NIC performs packet parsing, address translation, coherence management, and near-memory arithmetic or tensor operations while coordinating with MF-TLP-aware switches providing hierarchical directory control, multi-path routing, and in-network aggregation. Vectorized and multimodal packets encode multiple addresses or tensor offsets to reduce scatter / gather overhead, and programmable caching and quality-of-service modules manage tiered memory and tenant fairness. MF-TLP supports extension headers for predictive prefetch, collective coordination, and tenant governance, operating across hierarchical leaf-spine topologies using Ultra-Ethernet Transport, InfiniBand, or CXL fabrics. The system delivers scalable, low-latency, memory-centric orchestration for large-language-model training, multimodal AI, and data-intensive analytics.

A network interface controller (NIC) capable of facilitating efficient data request management is provided. The NIC can be equipped with a command queue, a message chopping unit (MCU), and a traffic management logic block. During operation, the command queue can store a command issued via a host interface. The MCU can then determine a type of the command and a length of a response of the command. If the command is a data request, the traffic management logic block can determine whether the length of the response is within a threshold. If the length exceeds the threshold, the traffic management logic block can pace the command such that the response is within the threshold.

Assemblies and methods of manufacturing are provided for a liquid cooled network-interface controller (NIC) assembly configured to receive and operably engage a transceiver module. An example liquid cooled NIC assembly includes a PCB, a first thermally conductive member supported by the PCB, and a second thermally conductive member supported by the first thermally conductive member. The first thermally conductive member is thermally isolated from the second thermally conductive member. A liquid cooling unit may thermally engage the first thermally conductive member and the second thermally conductive member. The first thermally conductive member and the second thermally conductive member are configured to conduct heat toward the liquid cooling unit, such that the liquid cooling unit may dissipate heat from the first thermally conductive member and the second thermally conductive member.

Devices, systems, methods, and processes for flow entropy management using network address translation (NAT) scheme are described herein. Typically, due to fewer flows and high bandwidth demands in backend data center networks, hash distribution algorithms may exhibit bias, leading to congestion on certain network paths while others remain underutilized, a phenomenon known as low flow entropy. To address the low flow entropy problem, a network interface controller (NIC) decomposes a traffic flow into multiple flowlets and applies a NAT operation on each flowlet. In the NAT operation, an actual source port value of a flowlet is replaced with a unique unused source port value to make the flowlet look like a different traffic flow to a switch. Thus, the switch processes each flowlet as a different traffic flow and uses load balancing schemes to distribute the flowlets across various network paths. Thus, improving the flow entropy of the network.

A network resiliency controller may monitor a port status for a network interface controller. A software defined datapath may be used to virtualize different ports of the network interface controller and direct traffic to a given port. If it is determined that a port failure is imminent or has occurred, one or more selectors may modify a port associated with the network interface controller. The network resiliency controller may identify the port switching, determine a new connection has been established with a new port, and then modify one or more traffic rules for routing traffic along the new port.

Systems and methods are directed toward migration operations, such as live migration operations, associated with confidential computing environments. Responsive to a request to migrate data, a secure hypervisor may establish a secure communication channel to a network interface controller to pass one or more keys for accessing securely stored data. The secure hypervisor may generate a descriptor associated with a memory location of the data and then pass the descriptor to the network interface controller. As a result, encryption / decryption operations may be offloaded to the network interface controller, which may use the descriptor and key to migrate the data from a source location to a destination location.

The invention discloses a data path structure suitable for cross-domain interaction of high-performance PCIe non-transparent bridge equipment. The data path structure comprises external equipment, an upstream endpoint, a downstream endpoint, a network interface controller connection network, a first bypass module group and a second bypass module group, the external equipment, the upstream endpoint, the network interface controller connection network and the downstream endpoint are sequentially in communication connection, the upstream endpoint and the downstream endpoint are the same in structure, the upstream endpoint is in communication connection with the first bypass module group, and the downstream endpoint is in communication connection with the second bypass module group; and the first bypass module group and the second bypass module group have the same structure. According to the data path structure provided by the invention, through mutual cooperation of the new path and the old path, the overall performance of the non-transparent bridge can be improved, and then the data path structure adapts to high-performance PCIe cross-domain transmission under high load and large flow.

A system for autonomous compliance with legal regulations in smart contracts; the system includes: a regulatory data collection unit comprising a network interface controller physically connected to an external communications port, a hardware-based public key infrastructure circuit configured to validate digital certificates of regulatory servers, and a direct memory access controller configured to transfer authenticated regulatory update packets from the network interface controller to a volatile buffer memory without processor intervention; a Compliance Code Conversion Unit with a hardware lexicon scanner implemented as a finite state machine and embedded in reconfigurable FPGA logic blocks, a microcontroller executing a hardware-based lexical analysis pipeline stored in firmware registers, and a translation cache memory configured to temporarily store tokenized compliance rules before writing them to a non-volatile instruction memory; a policy evaluation and enforcement unit comprising a transaction verification processor connected to a secure enclave memory, a hardware comparator circuit configured to compare transaction parameters with compliance thresholds stored in the secure enclave memory, and a logic gate circuit configured to generate execution gate signals that selectively allow, block, or modify smart contract execution signals transmitted to a blockchain execution processor; and an audit logging unit with a cryptographic hashing circuit configured to generate block hashes of enforcement records, a timestamp oscillator configured to generate temporal signatures of compliance enforcement actions, and a Merkle tree generation circuit configured to create tamper-proof hierarchical hash structures, with the enforcement records being passed to a decentralized storage interface for anchoring in the chain or distributed ledger.

An example apparatus includes a hardware platform having arithmetic circuits and a memory, the memory configured to store, at a first precision, first compressed parameters of a machine learning (ML) model; a network interface controller; and a controller, supported by the hardware platform, configured to: decompress, from the memory through an increase in precision to a second precision, the first compressed parameters to obtain decompressed parameters; control the arithmetic circuits to train, using arithmetic operations, the ML model and update the decompressed parameters; compress, using quantization and reduction in precision to the first precision, the decompressed parameters as updated to obtain second compressed parameters; send, using the network interface controller, the second compressed parameters over a network to a server; and update the first compressed parameters in the memory in response to data received, through the network interface controller, from the server over the network.

The invention relates to thermal migration for confidential computing environments. The system and method are directed to migration operations associated with a confidential computing environment, such as thermal migration operations. In response to a request to migrate data, the security hypervisor may establish a secure communication channel to the network interface controller to communicate one or more keys for accessing the securely stored data. The security hypervisor may generate a descriptor associated with the memory location of the data and then communicate the descriptor to the network interface controller. Thus, encryption / decryption operations may be offloaded to the network interface controller, which may use the descriptor and the key to migrate data from the source location to the destination location.

A computing device includes a system-on-a-chip. The computing device comprises a network interface controller (NIC) that hosts a plurality of virtual functions and physical functions. Two or more compute nodes are coupled to the NIC. Each compute node is configured to operate a plurality of Virtual Machines (VMs). Each VM is configured to operate in conjunction with a virtual function via a virtual function driver. A dedicated VM operates in conjunction with a virtual NIC using a physical function hosted by the NIC via a physical function driver hosted by the compute node. The computing device further comprises a fabric manager configured to own a physical function of the NIC, to bind virtual functions hosted by the NIC to individual compute nodes, and to pool I / O devices across the two or more compute nodes.

A method processes data requests from a requester to a responder over a network by using remote direct memory access. The method includes the requester issuing two or more requests into a work queue of a network interface controller. The method further includes the network interface controller executing the queued requests by sending them to the responder, and receiving responses to the sent request from the responder. One or more given requests each includes dependency information related to the response from the responder to one or more previous requests in the work queue, the method further includes, before executing the given request by the network interface controller, evaluating the dependency information and executing the given request depending on the result of the evaluation.

Described herein are systems, methods, and other techniques for processing data packets at a compute infrastructure. An application running on the compute infrastructure allocates a region of a memory for a network interface controller to write or read inbound or outbound data packets. A data packet is received at the network interface controller. The data packet is directly written to the region of the memory. A section of the region of the memory adjacent to the data packet is reserved as headroom such that a memory address occupied by the data packet is adjacent to a memory address occupied by the headroom. The application processes the data packet at the region of the memory by adding data to the data packet, wherein adding the data to the data packet causes the data packet to use at least a portion of the headroom.

A computing device includes a system-on-a-chip. The computing device comprises a network interface controller (NIC) that hosts a plurality of virtual functions and physical functions. Two or more compute nodes are coupled to the NIC. Each compute node is configured to operate a plurality of Virtual Machines (VMs). Each VM is configured to operate in conjunction with a virtual function via a virtual function driver. A dedicated VM operates in conjunction with a virtual NIC using a physical function hosted by the NIC via a physical function driver hosted by the compute node. The computing device further comprises a fabric manager configured to own a physical function of the NIC, to bind virtual functions hosted by the NIC to individual compute nodes, and to pool I / O devices across the two or more compute nodes.

A system for automated, middleware-based intelligent data mapping between heterogeneous enterprise resource planning (ERP) systems and cloud platforms, the system comprising the following: an ERP data acquisition unit with a variety of physical communication ports, selected from Ethernet and serial ports, a network interface controller physically connected to the communication ports, and a DMA (Direct Memory Access) controller configured to transfer raw ERP data packets into a volatile buffer memory without processor intervention; a Semantic Mapping Unit consisting of a Field Programmable Gate Array (FPGA) configured as a lexical analyzer to analyze ERP schema definitions and extract entity descriptors, and a Tensor Processing Unit (TPU) configured to evaluate the semantic similarity between heterogeneous schema elements based on ontological models stored in a non-volatile memory repository; a transformation logic unit comprising a parallelized vector processor configured to perform matrix-based transformations, field normalizations and structural reorganization of ERP data into a harmonized format, and a rule application circuit configured to perform compliance-based anonymization, unit conversions and value scaling prior to cloud distribution; a cloud interface unit comprising a protocol adapter bank with encoders, translators, and message queue writers, wherein the cloud interface unit is coupled with a cryptographic controller configured with a hardware public key infrastructure (PKI) circuit to generate digital signatures and verify integrity codes for all outgoing payloads; and a Feedback Learning Control Unit implemented in the firmware, wherein the engine is electrically coupled to the Semantic Mapping Unit and the Transformation Logic Unit and is configured to monitor error logs, success rates and acknowledgment codes received from the cloud platforms and to update the semantic and transformation rules stored in the non-volatile memory repository accordingly.

The present invention provides a system of trademark surveillance system with image understanding for multi-country and the method thereof, which is implemented by providing a user-operated user electronic device. The user electronic device comprises a second processor and a second network interface controller. A server comprises a second application program. The second processor is connected to the server through the second network interface controller and executes the second application program to perform trademark monitoring, particularly to monitor trademark images by inputting a text description.

An example network interface controller (NIC) includes: first resources configured to supply first traffic; second resources configured to supply second traffic; a load balancer, coupled to the first and second resources, configured to balance the first traffic and the second traffic between first and second port circuits of a link aggregation group (LAG) using a hash function; and remote direct memory access (RDMA) logic configured to, using the hash function, divide work requests into a first set of work requests for first packets that hash to the first port circuit and a second set of work requests for second packets that hash to the second port circuit, the RDMA logic configured to supply the first set of work requests to the first resources and the second set of work requests to the second resources.

Systems, methods, and apparatuses, including network interface controllers and computer-readable media, for traffic shaping offload. A network computing device can receive data packets for transmission and implement a traffic policy that includes transmitting at least some data packets without delay to their intended destination. Confirmation tokens for non-delayed packets can be queued in a time-indexed data structure and dequeued according to a traffic shaping policy. Confirmation tokens can be generated and stored independent of the time at which corresponding packets for the tokens are transmitted. Dequeued confirmation tokens can cause the network computing device to receive additional packets for transmission. The device can flag at least some packets for transmission without delay according to aspects of the disclosure, while un-flagged packets can be shaped according to a different traffic shaping policy.

The invention relates to one-to-many TCP connection splicing. A computing device includes at least one network interface controller (NIC), a memory, and at least one processor including one or more cores. The NIC (s) receive inbound transmission control protocol (TCP) data packets and transmit outbound TCP data packets. The memory stores a program of instructions that the processor executes to divide a data path within the computing device that includes both a receiving endpoint and a transmitting endpoint into a first path and a second path. In response to determining that the first inbound TCP data packet is associated with the established TCP connection and the data stitching group, the processor assigns the first inbound TCP data packet to the first path and assigns a second inbound TCP data packet that is not assigned to the first path to the second path. The processor performs a one-to-many data stitching of payload data from the first inbound TCP data packet to the outbound TCP data packet using the first path.

Encryption operations are securely offloaded to a network interface controller (NIC). Encryption keys are securely transferred from a virtual machine (VM) to the NIC and data is securely transferred from encrypted VM memory to secure buffers in the NIC. The NIC handles the encryption and decryption operations in hardware, greatly increasing encryption performance while not reducing security. This is especially useful in cloud server environments, so the cloud service provider does not have access to the encryption keys or the unencrypted data. The offloaded operations are performed with numerous different communication protocols, including RDMA, QUIC, IPsec underlay and WireGuard.

In one embodiment, a method is disclosed, comprising: receiving a packet; processing the packet in a Control Unit–User Plane (CU-UP) as a user-space application with kernel-bypass networking; performing packet Input / Output (I / O) by the CU-UP user-space application, wherein the CU-UP performs Internet Protocol (IP) validation on received user-plane packets before processing Packet Data Convergence Protocol (PDCP), Service Data Adaptation Protocol (SDAP) and General Packet Radio Service Tunnelling Protocol (GTPU) protocol stack and performing direct I / O to a Network Interface Controller (NIC) for sending the packet over a network to a Distributed Unit (DU). The method may further comprise using a containerized CU-UP. The method may further comprise using a plurality of worker threads. The method may further comprise using a polling user space networking accelerator framework.

The present disclosure relates to DPU infrastructure management. In one embodiment, a system includes a plurality of host computers, a plurality of data processing units (DPUs), each DPU including a network interface controller (NIC) and a processing core, each DPU connected to a respective host computer, and at least one management node to provision software on the processing core of each DPU and to synchronize a lifecycle of each DPU with a lifecycle of the respective host computer during provisioning of the software.

Disclosed is a camera adapter having a case with a first side used for mounting a camera, a second side with a surface mount for mounting the camera adapter to a surface such as a wall or a ceiling and a circuit board mounted within the case. The circuit board includes at least a network interface controller for connecting to a network with a Power over Ethernet (POE) capability, a relay controller for a light, an amplifier, and a microphone bridge. A third side of the case is configured to house the light to be visible to a user. The circuit board can handled all of the video and audio processing of the camera and connect to the surface only via a single CAT5 / 6 connection for network and power connectivity.

An avionics data communication network includes a computing device configured to asynchronously transmit data packets in parallel via three or more redundant network interface controllers (NICs). The data packets offered to the avionics data communication network are bound using a token bucket filter (TBF). Three or more redundant network switches are configured to receive and relay the data packets from a different NIC of the three or more redundant NICs of the computing device. An avionics device is configured to receive the data packets from the computing device within a deterministic end-to-end transmission delay bound, the avionics device receiving the data packets via at least one of the three or more redundant network switches.

The application provides a gradient compression and communication optimization method for large model distributed training, which is applied to a distributed synchronous training cluster equipped with a GPU and an RDMA network interface controller. The method generates a communication feature vector by collecting gradient tensor statistical features and real-time state of an RDMA link; the gradient tensor is cut into gradient blocks matching the transmission granularity of the NIC and is allocated independent compression strategy slots; a deterministic state machine is used to match the compression strategy and communication route for each block, and the decision process and back propagation calculation are executed in overlap; the hardware decompression at the receiving end is performed through an error feedback compensation mechanism to inhibit the compression precision loss. The application realizes the collaborative optimization of compression and routing, improves the calculation and communication parallelism, effectively reduces the gradient communication delay, and improves the efficiency of large model distributed training.

A network interface controller (NIC) facilitating incast management at a computing system is provided. During operation, the NIC can receive, via a network, a request to send data from a remote computing system. The NIC can determine that the request is among a plurality of requests from a plurality of remote computing systems accessible via the network. Based on a descriptor in the request, the NIC can determine a storage location of the data at the remote computing system. The NIC can then determine a level of congestion associated with the plurality of requests at the computing system. The NIC can schedule a data retrieval in response to the request based on the level of congestion and with respect to the plurality of requests. The NIC can then retrieve the data from the storage location based on remote access.

An internet end-user device includes a processor, a network interface controller; and a memory including instructions that, when executed by the one or more processors cause the end-user device to configure the end-user device to use a red network and perform dependency verification of the end-user device. A method includes configuring an end-user device to use a red network; and verify one or more operational dependencies associated with the configuration of the end-user device. A non-transitory computer readable medium includes program instructions that when executed, cause an internet end-user device for use by end users to configure the end-user device to use a red network and verify one or more operational dependencies associated with of the end-user device.

An electronic device may include a communication module for exchanging data with an external device, and at least one processor for controlling the electronic device, wherein the processor may: receive first information regarding the state of a network interface controller (NIC) driver for the communication module; receive, as second information, at least a part of simple network management protocol (SNMP) information regarding a network stack; receive third information regarding the state of sockets; determine a target problem state of the electronic device on the basis of the first information, the second information, and the third information; and perform a preconfigured target recovery operation corresponding to the determined target problem state.

Encryption operations are securely offloaded to a network interface controller (NIC). Encryption keys are securely transferred from a virtual machine (VM) to the NIC and data is securely transferred from encrypted VM memory to secure buffers in the NIC. The NIC handles the encryption and decryption operations in hardware, greatly increasing encryption performance while not reducing security. This is especially useful in cloud server environments, so the cloud service provider does not have access to the encryption keys or the unencrypted data. The offloaded operations are performed with numerous different communication protocols, including RDMA, QUIC, IPsec underlay and WireGuard.

A stacked memory such as a high bandwidth memory (HBM) with a wide data path is used by a streaming pipeline in a network interface controller to buffer segments of a data packet to allow the network interface controller to perform operations on the packet payload. The headers and packet payload can be scanned and classified concurrently with the buffered payload parsed in parallel.