Abstract: Techniques to reduce the latency in notifying that space in a memory has been freed up are described. For example, when moving data from on-chip memory of a computing engine to system memory, the computing engine can be notified that its on-chip memory is free before an acknowledgment is provided by the system memory that the data being moved has been written into the system memory. The computing engine can be given access to the on-chip memory sooner by generating an early semaphore update based on a determination that the set of data being moved to system memory has been read out from the on-chip memory. The early semaphore update need not wait for the acknowledgement from the system memory, thus reducing the latency of notifying the computing engine that the on-chip memory is free.

Abstract: On-chip software-based activity monitoring is implemented to configure hardware-based activity throttling. A software-based activity monitor implemented on an integrated circuit obtains data from on-chip components to determine throttling modifications for a processing engine of the integrated circuit. The throttling modifications are applied to throttling criteria that is used by a hardware-based activity monitor on the integrated circuit which is responsible for directly evaluating and throttling processing at the processing engine of the integrated circuit.

Abstract: Simulated network packets may be processed via a network processing pipeline. A packet processor may implement packet processing stages to process network packets received via physical network interface at the packet processor. A controller for the packet processor may provide simulated network packets to the packet processor for processing at the different packet processing stages, bypassing the physical network interface. Dummy simulated packets may be provided to or generated at the packet processor on behalf of the controller to be parsed, processed, and returned to the controller. Metadata simulated packets may be injected into the packet processing stages and recaptured in storage locations that are accessible to the controller.

Abstract: Systems and methods are provided to perform multiply-accumulate operations of reduced precision numbers in a systolic array. Each row of the systolic array can receive reduced inputs from a respective reducer. The reduced input can include a reduced input data element and/or a reduced weight. The systolic array may lack support for inputs with a first bit-length and the reducers may reduce the bit-length of a given input from the first bit-length to a second shorter bit-length and provide the reduced input to the array. In order to reduce the bit-length, the reducer may reduce the number of trailing bits of the input. Further, the systolic array can receive a reduced and rounded input. The systolic array can propagate the reduced input through the processing elements in the systolic array. Each processing element may include a multiplier and/or an adder to perform arithmetical operations based on the reduced input.

Abstract: Disclosed are techniques for implementing features within a network device. The network device can function to forward sequences of data packets received by the network device as well as concurrently generate or check test type of data packets.

Abstract: Systems and methods are provided to enable parallelized multiply-accumulate operations in a systolic array. Each column of the systolic array can include multiple busses enabling independent transmission of input partial sums along the respective bus. Each processing element of a given columnar bus can receive an input partial sum from a prior element of the given columnar bus, and perform arithmetic operations on the input partial sum. Each processing element can generate an output partial sum based on the arithmetic operations, provide the output partial sum to a next processing element of the given columnar bus, without the output partial sum being processed by a processing element of the column located between the two processing elements that uses a different columnar bus. Use of columnar busses can enable parallelization to increase speed or enable increased latency at individual processing elements.

Abstract: Systems and methods are provided to perform multiply-accumulate operations of multiple data types in a systolic array. One or more processing elements in the systolic array can include a shared multiplier and one or more adders. The shared multiplier can include a separate and/or a shared circuitry where the shared circuitry can perform at least a part of integer multiplication and at least a part of non-integer multiplication. The one or more adders can include one or more shared adders or one or more separate adders. The shared adder can include a separate and/or a shared circuitry where the shared circuitry can perform at least a part of integer addition and at least a part of non-integer addition.

Abstract: Disclosed herein are techniques for performing multi-layer neural network processing for multiple contexts. In one embodiment, a computing engine is set in a first configuration to implement a second layer of a neural network and to process first data related to a first context to generate first context second layer output. The computing engine can be switched from the first configuration to a second configuration to implement a first layer of the neural network. The computing engine can be used to process second data related to a second context to generate second context first layer output. The computing engine can be set to a third configuration to implement a third layer of the neural network to process the first context second layer output and the second context first layer output to generate a first processing result of the first context and a second processing result of the second context.

Abstract: Disclosed herein are techniques for performing multi-layer neural network processing for multiple contexts. In one embodiment, a computing engine is set in a first configuration to implement a second layer of a neural network and to process first data related to a first context to generate first context second layer output. The computing engine can be switched from the first configuration to a second configuration to implement a first layer of the neural network. The computing engine can be used to process second data related to a second context to generate second context first layer output. The computing engine can be set to a third configuration to implement a third layer of the neural network to process the first context second layer output and the second context first layer output to generate a first processing result of the first context and a second processing result of the second context.

Abstract: A semiconductor package can include a capacitance die. The package can have multiple dice (e.g., logic die, memory die) mounted on a substrate. Each die can include a power domain. The dice can be distributed on the substrate such that an extra space is present on the substrate between at least some of the dice. For example, an extra space may be present between two dice, at a corner of the substrate, or other locations. The extra space can disrupt a coplanarity of the semiconductor package. The capacitance die can be located in the extra space so as to establish the coplanarity with the other dice. The capacitance die can include a capacitor array electrically coupled to multiple power domains of the plurality of dice.

Abstract: Systems and methods are provided to enable parallelized multiply-accumulate operations in a systolic array. Each column of the systolic array can include multiple busses enabling independent transmission of input partial sums along the respective bus. Each processing element of a given columnar bus can receive an input partial sum from a prior element of the given columnar bus, and perform arithmetic operations on the input partial sum. Each processing element can generate an output partial sum based on the arithmetic operations, provide the output partial sum to a next processing element of the given columnar bus, without the output partial sum being processed by a processing element of the column located between the two processing elements that uses a different columnar bus. Use of columnar busses can enable parallelization to increase speed or enable increased latency at individual processing elements.

Abstract: Programmatically defined fields of metadata for a network packet may be generated. Instructions indicating different portions of data from different headers of a network packet may be stored at a packet processor. When a network packet is received, the different portions of the data may be extracted from the different headers of the packet according to the instructions and provided to other stages of the packet processor for processing. Different portions of the same programmatically defined field may be utilized at different stages in the packet processor. The programmatically defined field may be used to generate a hash value that selects an entry in a lookup table describing a forwarding decision for a network packet.

Abstract: Disclosed herein are techniques for performing multi-layer neural network processing for multiple contexts. In one embodiment, a computing engine is set in a first configuration to implement a second layer of a neural network and to process first data related to a first context to generate first context second layer output. The computing engine can be switched from the first configuration to a second configuration to implement a first layer of the neural network. The computing engine can be used to process second data related to a second context to generate second context first layer output. The computing engine can be set to a third configuration to implement a third layer of the neural network to process the first context second layer output and the second context first layer output to generate a first processing result of the first context and a second processing result of the second context.

Abstract: Systems and methods are provided to perform multiply-accumulate operations of reduced precision numbers in a systolic array. Each row of the systolic array can receive reduced inputs from a respective reducer. The reducer can receive a particular input and generate multiple reduced inputs from the input. The reduced inputs can include reduced input data elements and/or a reduced weights. The systolic array may lack support for inputs with a first bit-length and the reducers may reduce the bit-length of a given input from the first bit-length to a second shorter bit-length and provide multiple reduced inputs with second shorter bit-length to the array. The systolic array may perform multiply-accumulate operations on each unique combination of the multiple reduced input data elements and the reduced weights to generate multiple partial outputs. The systolic array may sum the partial outputs to generate the output.

Abstract: Systems and methods are provided to perform multiply-accumulate operations of reduced precision numbers in a systolic array. Each row of the systolic array can receive reduced inputs from a respective reducer. The reduced input can include a reduced input data element and/or a reduced weight. The systolic array may lack support for inputs with a first bit-length and the reducers may reduce the bit-length of a given input from the first bit-length to a second shorter bit-length and provide the reduced input to the array. In order to reduce the bit-length, the reducer may reduce the number of trailing bits of the input. Further, the systolic array can receive a reduced and rounded input. The systolic array can propagate the reduced input through the processing elements in the systolic array. Each processing element may include a multiplier and/or an adder to perform arithmetical operations based on the reduced input.

Abstract: Access control lookups may be implemented that support user-configurable and host-configurable processing stages. A request may be received and evaluated to determine whether bypass of user-configured access request processing stages should be bypassed. A lookup may be determined for user-configured access controlled decisions, and the access control decisions can be applied, if not bypassed. A lookup may be determined for a host-configured access control decisions and the access control decisions applied.

Abstract: Directional capacity of interfaces for networking devices are dynamically modified. Network traffic utilization of one direction of a network interface may be determined. A modification to a capacity of the networking device to process network traffic in the one direction of the network may be determined. The modification may then be applied to the networking device so that subsequent network traffic is processed according to the modified capacity in the one direction of the interface.

Abstract: Throttling recommendations for a systolic array may be arbitrated. Throttling recommendations may be received at an arbiter for a systolic array from different sources, such as one or more monitors implemented in an integrated circuit along with the systolic array or sources external to the integrated circuit with the systolic array. A strongest throttling recommendation may be selected. The rate at which data enters the systolic array may be modified according to the strongest throttling recommendation.

Abstract: Systems and methods are provided to enable parallelized multiply-accumulate operations in a systolic array. Each column of the systolic array can include multiple busses enabling independent transmission of input partial sums along the respective bus. Each processing element of a given columnar bus can receive an input partial sum from a prior element of the given columnar bus, and perform arithmetic operations on the input partial sum. Each processing element can generate an output partial sum based on the arithmetic operations, provide the output partial sum to a next processing element of the given columnar bus, without the output partial sum being processed by a processing element of the column located between the two processing elements that uses a different columnar bus. Use of columnar busses can enable parallelization to increase speed or enable increased latency at individual processing elements.

Abstract: Disclosed herein are techniques for management of a non-volatile memory device. In one example, an integrated circuit comprises a cache device and a management controller. The cache device is configured to store a first mapping between logical addresses and physical addresses of a first memory, the first mapping being a subset of mapping between logical addresses and physical addresses of the first memory stored in a second memory, and an access count associated with each of the physical addresses of the first mapping. The management controller is configured to: maintain access statistics of the first memory based on the access counts stored in the cache device; and determine the mapping between logical addresses and physical addresses stored in the second memory based on the access statistics and predicted likelihoods of at least some of the logical addresses receiving an access operation.