Abstract: A programmable, non-linear (PNL) activation engine for a neural network is capable of receiving input data within a circuit. In response to receiving an instruction corresponding to the input data, the PNL activation engine is capable of selecting a first non-linear activation function from a plurality of non-linear activation functions by decoding the instruction. The PNL activation engine is capable of fetching a first set of coefficients corresponding to the first non-linear activation function from a memory. The PNL activation engine is capable of performing a polynomial approximation of the first non-linear activation function on the input data using the first set of coefficients. The PNL activation engine is capable of outputting a result from the polynomial approximation of the first non-linear activation function.

Abstract: An inference server is capable of receiving a plurality of inference requests from one or more client systems. Each inference request specifies one of a plurality of different endpoints. The inference server can generate a plurality of batches each including one or more of the plurality of inference requests directed to a same endpoint. The inference server also can process the plurality of batches using a plurality of workers executing in an execution layer therein. Each batch is processed by a worker of the plurality of workers indicated by the endpoint of the batch.

Abstract: An inference server is capable of receiving a plurality of inference requests from one or more client systems. Each inference request specifies one of a plurality of different endpoints. The inference server can generate a plurality of batches each including one or more of the plurality of inference requests directed to a same endpoint. The inference server also can process the plurality of batches using a plurality of workers executing in an execution layer therein. Each batch is processed by a worker of the plurality of workers indicated by the endpoint of the batch.

Abstract: Controlling a data processing (DP) array includes creating a replica of a register address space of the DP array based on the design and the DP array. A sequence of instructions, including write instructions and read instructions, is received. The write instructions correspond to buffer descriptors specifying runtime data movements for a design for a DP array. The write instructions are converted into transaction instructions and the read instructions are converted into wait instructions based on the replica of the register address space. The transaction instructions and the wait instructions are included in an instruction buffer. The instruction buffer is provided to a microcontroller configured to execute the transaction instructions and the wait instructions to implement the runtime data movements for the design as implemented in the DP array. In another aspect, the instruction buffer is stored in a file for subsequent execution by the microcontroller.

Abstract: An integrated circuit includes a plurality of kernels and a virtual machine coupled to the plurality of kernels. The virtual machine is configured to interpret instructions directed to different ones of the plurality of kernels. The virtual machine is configured to control operation of the different ones of the plurality of kernels responsive to the instructions.

Abstract: Instruction generation for a data processing array and microcontroller includes generating a tensor-level intermediate representation from a machine learning model using kernel expressions. Statements of the tensor-level intermediate representation are partitioned into a first set of statements and a second set of statements. From the first set of statements, kernel instructions are generated based on a reconfigurable neural engine model. The kernel instructions are executable by a compute tile of a data processing array to implement compute functions of the machine learning model. From the set of second statements, microcontroller instructions are generated based on a super-graph model. The microcontroller instructions are executable by a microcontroller of the data processing array to move data into and out from the data processing array.

Abstract: Controlling a data processing (DP) array includes creating a replica of a register address space of the DP array based on the design and the DP array. A sequence of instructions, including write instructions and read instructions, is received. The write instructions correspond to buffer descriptors specifying runtime data movements for a design for a DP array. The write instructions are converted into transaction instructions and the read instructions are converted into wait instructions based on the replica of the register address space. The transaction instructions and the wait instructions are included in an instruction buffer. The instruction buffer is provided to a microcontroller configured to execute the transaction instructions and the wait instructions to implement the runtime data movements for the design as implemented in the DP array. In another aspect, the instruction buffer is stored in a file for subsequent execution by the microcontroller.

Abstract: An integrated circuit includes a plurality of kernels and a virtual machine coupled to the plurality of kernels. The virtual machine is configured to interpret instructions directed to different ones of the plurality of kernels. The virtual machine is configured to control operation of the different ones of the plurality of kernels responsive to the instructions.

Abstract: A programmable, non-linear (PNL) activation engine for a neural network is capable of receiving input data within a circuit. In response to receiving an instruction corresponding to the input data, the PNL activation engine is capable of selecting a first non-linear activation function from a plurality of non-linear activation functions by decoding the instruction. The PNL activation engine is capable of fetching a first set of coefficients corresponding to the first non-linear activation function from a memory. The PNL activation engine is capable of performing a polynomial approximation of the first non-linear activation function on the input data using the first set of coefficients. The PNL activation engine is capable of outputting a result from the polynomial approximation of the first non-linear activation function.

Abstract: An inference server is capable of receiving a plurality of inference requests from one or more client systems. Each inference request specifies one of a plurality of different endpoints. The inference server can generate a plurality of batches each including one or more of the plurality of inference requests directed to a same endpoint. The inference server also can process the plurality of batches using a plurality of workers executing in an execution layer therein. Each batch is processed by a worker of the plurality of workers indicated by the endpoint of the batch.

Abstract: Embodiments herein describe techniques for interfacing a neural network application with a neural network accelerator using a library. The neural network application may execute on a host computing system while the neural network accelerator executes on a massively parallel hardware system, e.g., a FPGA. The library operates a pipeline for submitting the tasks received from the neural network application to the neural network accelerator. In one embodiment, the pipeline includes a pre-processing stage, an FPGA execution stage, and a post-processing stage which each correspond to different threads. When receiving a task from the neural network application, the library generates a packet that includes the information required for the different stages in the pipeline to perform the tasks. Because the stages correspond to different threads, the library can process multiple packets in parallel which can increase the utilization of the neural network accelerator on the hardware system.

Abstract: In the disclosed methods and systems for processing in a neural network system, a host computer system writes a plurality of weight matrices associated with a plurality of layers of a neural network to a memory shared with a neural network accelerator. The host computer system further assembles a plurality of per-layer instructions into an instruction package. Each per-layer instruction specifies processing of a respective layer of the plurality of layers of the neural network, and respective offsets of weight matrices in a shared memory. The host computer system writes input data and the instruction package to the shared memory. The neural network accelerator reads the instruction package from the shared memory and processes the plurality of per-layer instructions of the instruction package.

Abstract: A disclosed neural network processing system includes a host computer system, a RAMs coupled to the host computer system, and neural network accelerators coupled to the RAMs, respectively. The host computer system is configured with software that when executed causes the host computer system to write input data and work requests to the RAMS. Each work request specifies a subset of neural network operations to perform and memory locations in a RAM of the input data and parameters. A graph of dependencies among neural network operations is built and additional dependencies added. The operations are partitioned into coarse grain tasks and fine grain subtasks for optimal scheduling for parallel execution. The subtasks are scheduled to accelerator kernels of matching capabilities. Each neural network accelerator is configured to read a work request from the respective RAM and perform the subset of neural network operations on the input data using the parameters.

Abstract: In disclosed approaches of neural network processing, a host computer system copies an input data matrix from host memory to a shared memory for performing neural network operations of a first layer of a neural network by a neural network accelerator. The host instructs the neural network accelerator to perform neural network operations of each layer of the neural network beginning with the input data matrix. The neural network accelerator performs neural network operations of each layer in response to the instruction from the host. The host waits until the neural network accelerator signals completion of performing neural network operations of layer i before instructing the neural network accelerator to commence performing neural network operations of layer i+1, for i?1. The host instructs the neural network accelerator to use a results data matrix in the shared memory from layer i as an input data matrix for layer i+1 for i?1.

Abstract: An example preprocessor circuit includes: a first buffer configured to store rows of image data and output a row thereof; a second buffer, coupled to the first buffer, including storage locations to store respective image samples of the row output by the first buffer; shift registers; an interconnect network including connections, each connection coupling a respective one of the shift registers to more than one of the storage locations, one or more of the storage locations being coupled to more than one of the connections; and a control circuit configured to load the shift registers with the image samples based on the connections and shift the shift registers to output streams of image samples.

Abstract: At least one neural network accelerator performs operations of a first subset of layers of a neural network on an input data set, generates an intermediate data set, and stores the intermediate data set in a shared memory queue in a shared memory. A first processor element of a host computer system provides input data to the neural network accelerator and signals the neural network accelerator to perform the operations of the first subset of layers of the neural network on the input data set. A second processor element of the host computer system reads the intermediate data set from the shared memory queue, performs operations of a second subset of layers of the neural network on the intermediate data set, and generates an output data set while the neural network accelerator is performing the operations of the first subset of layers of the neural network on another input data set.

Abstract: Embodiments herein describe techniques for interfacing a neural network application with a neural network accelerator that operate on two heterogeneous computing systems. For example, the neural network application may execute on a central processing unit (CPU) in a computing system while the neural network accelerator executes on a FPGA. As a result, when moving a software-hardware boundary between the two heterogeneous systems, changes may be made to both the neural network application (using software code) and to the accelerator (using RTL). The embodiments herein describe a software defined approach where shared interface code is used to express both sides of the interface between the two heterogeneous systems in a single abstraction (e.g., a software class).

Abstract: Methods and apparatus are described for simultaneously buffering and reformatting (e.g., transposing) a matrix for high-speed data streaming in general matrix multiplication (GEMM), which may be implemented by a programmable integrated circuit (IC). Examples of the present disclosure increase the effective double data rate (DDR) memory throughput for streaming data into GEMM digital signal processing (DSP) engine multifold, as well as eliminate slow data reformatting on a host central processing unit (CPU). This may be accomplished through software-defined (e.g., C++) data structures and access patterns that result in hardware logic that simultaneously buffers and reorganizes the data to achieve linear DDR addressing.

Abstract: An example preprocessor circuit for formatting image data into a plurality of streams of image samples includes: a plurality of memory banks configured to store the image data; multiplexer circuitry coupled to the memory banks; a first plurality of registers coupled to the multiplexer circuitry; a second plurality of registers coupled to the first plurality of registers, outputs of the second plurality of registers configured to provide the plurality of streams of image samples; bank address and control circuitry coupled to control inputs of the plurality of memory banks, the multiplexer circuitry, and the first plurality of registers; output control circuitry coupled to control inputs of the second plurality of registers; and a control state machine coupled to the bank address and control circuitry and the output control circuitry.

Abstract: An example multiply accumulate (MACC) circuit includes: a multiply-accumulator having an accumulator output register; a quantizer, coupled to the multiply accumulator; and a control circuit coupled to the multiply-accumulator and the quantizer, the control circuit configured to provide control data to the quantizer, the control data indicative of a most-significant bit (MSB) to least significant bit (LSB) range for selecting bit indices from the accumulator output register.