A method and device for memory access in processors is provided. A processor, comprising a plurality of computational units, is capable of executing a single instruction on multiple pieces of data simultaneously (SIMD). A read operation is initiated to load data from memory into the plurality of computational units (CUs) arranged into a plurality of CU groups. The memory is arranged into a plurality of memory macro-blocks each associated with a respective CU group of the plurality of CU groups. For each CU group a respective first memory address is determined and for each CU group, the data in the associated memory macro-block is accessed at the respective first memory address.

Instructions and logic provide vector scatter-op and/or gather-op functionality. In some embodiments, responsive to an instruction specifying: a gather and a second operation, a destination register, an operand register, and a memory address; execution units read values in a mask register, wherein fields in the mask register correspond to offset indices in the indices register for data elements in memory. A first mask value indicates the element has not been gathered from memory and a second value indicates that the element does not need to be, or has already been gathered. For each having the first value, the data element is gathered from memory into the corresponding destination register location, and the corresponding value in the mask register is changed to the second value. When all mask register fields have the second value, the second operation is performed using corresponding data in the destination and operand registers to generate results.

Embodiments may be generally direct to apparatuses, systems, method, and techniques to determine a configuration for a plurality of connectors, the configuration to associate a first interconnect protocol with a first subset of the plurality of connectors and a second interconnect protocol with a second subset of the plurality of connectors, the first interconnect protocol and the second interconnect protocol are different interconnect protocols and each comprising one of a serial link protocol, a coherent link protocol, and an accelerator link protocol, cause processing of data for communication via the first subset of the plurality of connectors in accordance with the first interconnect protocol, and cause processing of data for communication via the second subset of the plurality of connector in accordance with the second interconnect protocol.

A method of processing partitions of a tensor in a target order includes receiving, by a reorder unit and from two or more producer units, a plurality of partitions of a tensor in a first order that is different from the target order, storing the plurality of partitions in the reorder unit, and providing, from the reorder unit, the plurality of partitions in the target order to one or more consumer units. In an example, the one or more consumer units process the plurality of partitions in the target order.

Methods, systems, and apparatus, including computer-readable media, are described for an integrated circuit that accelerates machine-learning computations. The circuit includes processor cores that each include: multiple channel controllers; an interface controller for coupling each channel controller to any memory channel of a system memory; and a fetch unit in each channel controller. Each fetch is configured to: receive channel data that encodes addressing information; obtain, based on the addressing information, data from any memory channel of the system memory using the interface controller; and write the obtained data to a vector memory of the processor core via the corresponding channel controller that includes the respective fetch unit.

The present application discloses a computing device that can provide a low-power, highly capable computing platform for computational imaging. The computing device can include one or more processing units, for example one or more vector processors and one or more hardware accelerators, an intelligent memory fabric, a peripheral device, and a power management module. The computing device can communicate with external devices, such as one or more image sensors, an accelerometer, a gyroscope, or any other suitable sensor devices.

A method of processing partitions of a tensor in a target order includes receiving, by a reorder unit and from two or more producer units, a plurality of partitions of a tensor in a first order that is different from the target order, storing the plurality of partitions in the reorder unit, and providing, from the reorder unit, the plurality of partitions in the target order to one or more consumer units. In an example, the one or more consumer units process the plurality of partitions in the target order.

Processors, systems and methods are provided for thread level parallel processing. A processor may comprise a plurality of processing elements (PEs) that each may comprise a configuration buffer, a sequencer coupled to the configuration buffer of each of the plurality of PEs and configured to distribute one or more PE configurations to the plurality of PEs, and a gasket memory coupled to the plurality of PEs and being configured to store at least one PE execution result to be used by at least one of the plurality of PEs during a next PE configuration.

Technologies for switching network traffic include a network switch. The network switch includes one or more processors and communication circuitry coupled to the one or more processors. The communication circuity is capable of switching network traffic of multiple link layer protocols. Additionally, the network switch includes one or more memory devices storing instructions that, when executed, cause the network switch to receive, with the communication circuitry through an optical connection, network traffic to be forwarded, and determine a link layer protocol of the received network traffic. The instructions additionally cause the network switch to forward the network traffic as a function of the determined link layer protocol. Other embodiments are also described and claimed.

An example data processing engine (DPE) for a DPE array in an integrated circuit (IC) includes: a core; a memory including a data memory and a program memory, the program memory coupled to the core, the data memory coupled to the core and including at least one connection to a respective at least one additional core external to the DPE; support circuitry including hardware synchronization circuitry and direct memory access (DMA) circuitry each coupled to the data memory; streaming interconnect coupled to the DMA circuitry and the core; and memory-mapped interconnect coupled to the core, the memory, and the support circuitry.