Disclosed herein, among other things, are methods and apparatus for providing a time-stamp based controller for synchronization of sink or source sampling rate with external packet rate. A method for wireless communications includes receiving a transmission of a packet using a wireless transceiver of an electronic device, and using a processor of the electronic device to read a first value of a system timer and store the first value as an arrival time-stamp. The packet is decoded and processed by the processor, and sent to an output. When the processed packet is sent, a second value of the system timer is read, adjusted and stored as a departure time-stamp. The arrival time-stamp and the departure time-stamp are used to calculate an adjustment stimulus for a sample rate actuator of the electronic device. The sample rate actuator is configured to maintain synchronization of sampling rate with an external packet rate.

A new processing architecture is described in which a data processing unit (DPU) is utilized within a device. Unlike conventional compute models that are centered around a central processing unit (CPU), example implementations described herein leverage a DPU that is specially designed and optimized for a data-centric computing model in which the data processing tasks are centered around, and the primary responsibility of, the DPU. For example, various data processing tasks, such as networking, security, and storage, as well as related work acceleration, distribution and scheduling, and other such tasks are the domain of the DPU. The DPU may be viewed as a highly programmable, high-performance input/output (I/O) and data-processing hub designed to aggregate and process network and storage I/O to and from multiple other components and/or devices. This frees resources of the CPU, if present, for computing-intensive tasks.

A highly-programmable access node is described that can be configured and optimized to perform input and output (I/O) tasks, such as storage and retrieval of data to and from storage devices (such as solid state drives), networking, data processing, and the like. For example, the access node may be configured to execute a large number of data I/O processing tasks relative to a number of instructions that are processed. The access node may be highly programmable such that the access node may expose hardware primitives for selecting and programmatically configuring data processing operations. As one example, the access node may be used to provide high-speed connectivity and I/O operations between and on behalf of computing devices and storage components of a network, such as for providing interconnectivity between those devices and a switch fabric of a data center.

Technologies for balancing throughput across input ports include a network switch. The network switch is to generate, for an arbiter unit in a first stage of a hierarchy of stages of arbiter units, turn data indicative of a set of turns in which to transfer packet data from devices connected to input ports of the arbiter unit. The network switch is also to transfer, with the arbiter unit, the packet data from the devices in the set of turns. Additionally, the network switch is to determine weight data indicative of the number of turns represented in the set and provide the weight data from the arbiter unit in the first stage to another arbiter unit in a subsequent stage to cause the arbiter unit in the subsequent stage to allocate a number of turns for the transfer of the packet data from the arbiter unit in the first stage.

Examples herein disclose an identification of a set of skew requirements corresponding to a set of data signals. Based on the set of skew requirements, the examples prioritize an order of transmission for the set of data signals. The example queue the set of data signals in accordance with the prioritized order.

Orders received by an electronic trading system are processed in batches based on the instrument to which an order relates. An incoming order is assigned to a queue of a queue set that makes up the batch according to a random process. Where orders are received from related trading parties they are assigned to the same queue set according to their time of receipt. The batch has a random duration within defined minimum and maximum durations and at the end of the batch, the orders held in the queues are transferred to a matching thread of the trading system sequentially with one order being removed from each queue and a number of passes of the queues completed until orders have been removed.

Systems, apparatuses, and methods for implementing asynchronous feedback training sequences are described. A transmitter transmits a training sequence indication to a receiver via a communication channel including a plurality of data lines. The training sequence indication includes a bit sequence to indicate the beginning of a training sequence. The indication includes a transition from a zero to a one at the midpoint of a supercycle of N clock cycles in length, followed by a predetermined number of ones. The training sequence indication is then followed by a test pattern. The beginning of the test pattern occurs at the end of a supercycle. The receiver determines if there are any errors in the received test pattern, and then sends feedback to the transmitter that indicates whether any errors were detected. Responsive to receiving the feedback, the transmitter alters delay settings for one or more of the data lines.

Message prioritization may be provided. First, a message may be received and a priority level may be calculated for the message. If the message is not rejected for having a priority lower than a predetermined threshold, the message may be placed in a first priority queue. Next, the message may be de-queued from the first priority queue based upon the calculated priority level for the message. Distribution group recipients corresponding to the message may then be expanded and the priority level for the message may be re-calculated based upon the expanded distribution group recipients. Next, the message may be placed in a second priority queue. The message may then be de-queued from the second priority queue based upon the re-calculated priority level for the message and delivered.

Technologies for low-latency data streaming include a computing device having a processor that includes a producer and a consumer. The producer generates a data item, and in a local buffer producer mode adds the data item to a local buffer, and in a remote buffer producer mode adds the data item to a remote buffer. When the local buffer is full, the producer switches to the remote buffer producer mode, and when the remote buffer is below a predetermined low threshold, the producer switches to the local buffer producer mode. The consumer reads the data item from the local buffer while operating in a local buffer consumer mode and reads the data item from the remote buffer while operating in a remote buffer consumer mode. When the local buffer is above a predetermined high threshold, the consumer may switch to a catch-up operating mode. Other embodiments are described and claimed.

An apparatus, system, and method are provided for a distributed function-specific buffer arrangement in a communication layer. A first module included in the layered communication architecture reserves a buffer in association with communicating a PDU. The buffer is included in a set of buffers allocated in association with the first module. The first module provides the PDU to a second module included in the layered communication architecture. Providing the PDU to the second module includes storing the PDU to the buffer and transferring ownership of the buffer to the second module. The second module accesses the PDU from a memory space associated with the buffer and releases the ownership of the buffer based on successfully accessing the PDU.