An integrated circuit device having separate dies for programmable logic fabric and circuitry to operate the programmable logic fabric are provided. A first integrated circuit die may include field programmable gate array fabric. A second integrated circuit die may be coupled to the first integrated circuit die. The second integrated circuit die may include fabric support circuitry that operates the field programmable gate array fabric of the first integrated circuit die.

An integrated circuit device having separate dies for programmable logic fabric and circuitry to operate the programmable logic fabric are provided. A first integrated circuit die may include field programmable gate array fabric. A second integrated circuit die may be coupled to the first integrated circuit die. The second integrated circuit die may include fabric support circuitry that operates the field programmable gate array fabric of the first integrated circuit die.

Examples described herein generally relate to communication between integrated circuit (IC) dies in a wafer-level fan-out package. In an example, an electronic device includes a wafer-level fan-out package. The wafer-level fan-out package includes a first integrated circuit (IC) die, a second IC die, and a redistribution structure. The first IC die includes a transmitter circuit. The second IC die includes a receiver circuit. The redistribution structure includes physical channels electrically connected to and between the transmitter circuit and the receiver circuit. The transmitter circuit is configured to transmit multiple single-ended data signals and a differential clock signal through the physical channels to the receiver circuit. The receiver circuit is configured to capture data from the multiple single-ended data signals using a first single-ended clock signal based on the differential clock signal.

Systems or methods of the present disclosure may improve scalability (e.g., component scalability, product variation scalability) of integrated circuit systems by disaggregating periphery intellectual property (IP) circuitry into modular periphery IP tiles that can be installed as modules. Such an integrated circuit system may include a first die that includes programmable fabric circuitry and a second die that includes a periphery IP tile. The periphery IP tile may be disaggregated from the programmable fabric die and may be communicatively coupled to the first die via a modular interface.

Systems or methods of the present disclosure may improve scalability (e.g., component scalability, product variation scalability) of integrated circuit systems by disaggregating periphery intellectual property (IP) circuitry into modular periphery IP tiles that can be installed as modules. Such an integrated circuit system may include a first die that includes programmable fabric circuitry and a second die that includes a periphery IP tile. The periphery IP tile may be disaggregated from the programmable fabric die and may be communicatively coupled to the first die via a modular interface.

Systems and methods for neural network processing are provided. A method in a system comprising a plurality of nodes interconnected via a network, where each node includes a plurality of on-chip memory blocks and a plurality of compute units, is provided. The method includes upon service activation receiving an N by M matrix of coefficients corresponding to the neural network model. The method includes loading the coefficients corresponding to the neural network model into the plurality of the on-chip memory blocks for processing by the plurality of compute units. The method includes regardless of a utilization of the plurality of the on-chip memory blocks as part of an evaluation of the neural network model, maintaining the coefficients corresponding to the neural network model in the plurality of the on-chip memory blocks until the service is interrupted or the neural network model is modified or replaced.

Hardware and methods for neural network processing are provided. A method in a hardware node including a pipeline having a matrix vector unit (MVU), a first multifunction unit connected to receive an input from the matrix vector unit, a second multifunction unit connected to receive an output from the first multifunction unit, and a third multifunction unit connected to receive an output from the second multifunction unit is provided. The method includes performing using the MVU a first type of instruction that can only be performed by the MVU to generate a first result. The method further includes performing a second type of instruction that can only be performed by one of the multifunction units and generating a second result and without storing the any of the two results in a global register, passing the second result to the second multifunction and the third multifunction unit.

Techniques described herein may relate to providing a programmable interconnect network (e.g., a programmable network-on-chip (NOC)). A method may include determining a transmission parameter, bonding one or more channels of an interconnect network based at least in part on the transmission parameter, and power-gating any unused channels after the bonding.

Techniques described herein may relate to providing a programmable interconnect network (e.g., a programmable network-on-chip (NOC)). A method may include determining a transmission parameter, bonding one or more channels of an interconnect network based at least in part on the transmission parameter, and power-gating any unused channels after the bonding.

An integrated circuit device may include programmable logic fabric disposed on a first integrated circuit die, such that the programmable logic fabric may include a first region of programmable logic fabric and a second region of programmable logic fabric. The first region of programmable logic fabric is configured to be programmed with a circuit design that operates on a first set of data. The integrated circuit may also include network on chip (NOC) circuitry disposed on a second integrated circuit die, such that the NOC circuitry is configured to communicate data between the first integrated circuit die and the second integrated circuit die.