Abstract: A computing system including an application processor and a direct dataflow compute-in-memory accelerator. The direct dataflow compute-in-memory accelerator executes is configured to an execute accelerator task on accelerator data to generate an accelerator task result. An accelerator driver is configured to stream the accelerator task data from the application processor to the direct dataflow compute-in-memory architecture without placing a load on the application processor. The accelerator drive can also return the accelerator task result to the application processor.

Abstract: A multi-accumulator multiply-and-accumulate (MAC) unit can include a multiplier and a plurality of accumulators. The multiplier can be configured to multiply a given element of a corresponding column of a first matrix and a plurality of elements of a corresponding row of a second matrix to generate a plurality of corresponding partial product elements that can be accumulated by corresponding ones of the plurality of accumulators.

Abstract: A memory processing unit (MPU) can include a first memory, a second memory, a plurality of processing regions and control logic. The first memory can include a plurality of memory regions. The plurality of memory regions can be organized in a plurality of memory blocks. The plurality of memory regions can be configured to store integer, B-float, and/or Group B-float encode data. The plurality of processing regions can be interleaved between the plurality of processing regions of the first memory. The plurality of processing regions can be organized in a plurality of core groups include a plurality of compute cores. The compute groups in the processing regions can be coupled to a plurality of adjacent memory blocks in the adjacent memory regions. The second memory can be coupled to the plurality of processing regions.

Abstract: A memory processing unit (MPU) can include a first memory, a second memory, a plurality of processing regions and control logic. The first memory can include a plurality of memory regions. The plurality of memory regions can be organized in a plurality of memory blocks. The plurality of processing regions can be interleaved between the plurality of processing regions of the first memory. The plurality of processing regions can be organized in a plurality of core groups include a plurality of compute cores. The compute groups in the processing regions can be coupled to a plurality of adjacent memory blocks in the adjacent memory regions. The second memory can be coupled to the plurality of processing regions.

Abstract: A memory processing unit (MPU) can include a first memory, a second memory, a plurality of processing regions and control logic. The first memory can include a plurality of regions. The plurality of processing regions can be interleaved between the plurality of regions of the first memory. The processing regions can include a plurality of compute cores. The second memory can be coupled to the plurality of processing regions. The control logic can configure data flow between compute cores of one or more of the processing regions and corresponding adjacent regions of the first memory. The control logic can also configure data flow between the second memory and the compute cores of one or more of the processing regions. The control logic can also configure data flow between compute cores within one or more respective ones of the processing regions.

Abstract: A memory processing unit (MPU) can include a first memory, a second memory, a plurality of processing regions and control logic. The first memory can include a plurality of regions. The plurality of processing regions can be interleaved between the plurality of regions of the first memory. The processing regions can include a plurality of compute cores. The second memory can be coupled to the plurality of processing regions. The control logic can configure data flow between compute cores of one or more of the processing regions and corresponding adjacent regions of the first memory. The control logic can also configure data flow between the second memory and the compute cores of one or more of the processing regions. The control logic can also configure data flow between compute cores within one or more respective ones of the processing regions. The control logic can also configure array data for storage memory of the MPU.

Abstract: A memory processing unit (MPU) configuration method can include mapping operations of one or more neural network models to sets of cores in a plurality of processing regions. In addition, dataflow of the one or more neural network models can be mapped to the sets of cores in the plurality of processing regions. Furthermore, configuration information can be generated based on the mapping of the operations of the one or more neural network models to the set of cores in the plurality of processing regions and the mapping of dataflow of the one or more neural network models to the sets of cores in the plurality of processing regions. The method can be implemented by generating an initial graph from a neural network model. A mapping graph can then be generated from the final graph. One or more configuration files can then be generated from the mapping graph.

Abstract: A memory processing unit (MPU) can include a first memory, a second memory, a plurality of processing regions and control logic. The first memory can include a plurality of regions. The plurality of processing regions can be interleaved between the plurality of regions of the first memory. The processing regions can include a plurality of compute cores. The second memory can be coupled to the plurality of processing regions. The control logic can configure data flow between compute cores of one or more of the processing regions and corresponding adjacent regions of the first memory. The control logic can also configure data flow between the second memory and the compute cores of one or more of the processing regions. The control logic can also configure data flow between compute cores within one or more respective ones of the processing regions.

Abstract: A monolithic integrated circuit (IC) including one or more compute circuitry, one or more non-volatile memory circuits, one or more communication channels and one or more communication interface. The one or more communication channels can communicatively couple the one or more compute circuitry, the one or more non-volatile memory circuits and the one or more communication interface together. The one or more communication interfaces can communicatively couple one or more circuits of the monolithic integrated circuit to one or more circuits external to the monolithic integrated circuit.

Abstract: A memory processing unit architecture can include a plurality of memory regions and a plurality of processing regions interleaved between the plurality of memory regions. The plurality of processing regions can be configured to perform computation functions of a model such as an artificial neural network. Data can be transferred between the computation functions in respective memory processing regions. In addition, the memory regions can be utilized to transfer data between a computation function in one processing region and a computation function in another processing region adjacent to the given memory region.

Abstract: A processing unit can include a plurality of chiplets coupled in a cascade topology by a plurality of interfaces. A set of the plurality of cascade coupled chiplets can be configured to execute a plurality of layers or blocks of layers of an artificial intelligence model. The set of cascade coupled chiplets can also be configured with parameter data of corresponding ones of the plurality of layers or blocks of layers of the artificial intelligence model.

Abstract: A sparse video inference chip is designed to extract spatio-temporal features from videos for action classification and motion tracking. The core is a sparse video inference processor that implements recurrent neural network in three layers of processing. High sparsity is enforced in each layer of processing, reducing the complexity by two orders of magnitude and allowing all multiply-accumulates (MAC) to be replaced by select-accumulates (SA). The design is demonstrated in a 3.98 mm2 40 nm CMOS chip with an Open-RISC processor providing software-defined control and classification.

Abstract: An information processor is provided that includes an inference module configured to extract a subset of data from information in an input and a classification module configured to classify the information in the input based on the extracted data. The inference module includes a first plurality of convolvers acting in parallel to apply each of N1 convolution kernels to each of N2 portions of the input image in order to generate an interim sparse representation of the input and a second plurality of convolvers acting in parallel to apply each of N3 convolution kernels to each of N4 portions of the interim sparse representation to generate a final sparse representation containing the extracted data. In order to take advantage of sparsity in the interim sparse representation, N3 is greater than N4 to parallelize processing in a non-sparse dimension and/or the second plurality of convolvers comprise sparse convolvers.

Abstract: A memory processing unit can be configured to compute partial products between one or more elements of a first matrix stored in a given row of a memory cell array and sequential bits of one or more elements of a second matrix. The partial products can be calculated first sequentially across the set of rows and second sequentially across the bit positions of the elements of the second matrix. Alternatively, the partial products can be calculated first sequentially across the bit positions of the elements of the second matrix first and second sequentially across the set of rows. The partial products for each column of elements can be accumulated and bit shifted to compute the dot product of the first and second matrix.

Abstract: Techniques for computing matrix convolutions in a plurality of multiply and accumulate units including data reuse of adjacent values. The data reuse can include reading a current value of the first matrix in from memory for concurrent use by the plurality of multiply and accumulate units. The data reuse can also include reading a current value of the second matrix in from memory to a serial shift buffer coupled to the plurality of multiply and accumulate units. The data reuse can also include reading a current value of the second matrix in from memory for concurrent use by the plurality of multiply and accumulate units.

Abstract: A monolithic integrated circuit (IC) including one or more compute circuitry, one or more non-volatile memory circuits, one or more communication channels and one or more communication interface. The one or more communication channels can communicatively couple the one or more compute circuitry, the one or more non-volatile memory circuits and the one or more communication interface together. The one or more communication interfaces can communicatively couple one or more circuits of the monolithic integrated circuit to one or more circuits external to the monolithic integrated circuit.

Abstract: A memory processing unit can be configured to compute partial products between one or more elements of a first matrix stored in a first storage location and sequential bits of one or more elements of a second matrix stored in a second storage location. The partial products can be calculated utilizing zero bit skipping to increase throughput and or reduce energy consumption. The partial products for each column of elements can be accumulated and bit shifted to compute the dot product of the first and second matrix.

Abstract: A memory processing unit can be configured to compute partial products between one or more elements of a first matrix stored in a first storage location and sequential bits of one or more elements of a second matrix stored in a second storage location. The partial products can be calculated utilizing zero bit skipping to increase throughput and or reduce energy consumption. The partial products for each column of elements can be accumulated and bit shifted to compute the dot product of the first and second matrix.

Abstract: A memory processing unit can be configured to compute partial products between one or more elements of a first matrix stored in a given row of a memory cell array and sequential bits of one or more elements of a second matrix. The partial products can be calculated first sequentially across the set of rows and second sequentially across the bit positions of the elements of the second matrix. Alternatively, the partial products can be calculated first sequentially across the bit positions of the elements of the second matrix first and second sequentially across the set of rows. The partial products for each column of elements can be accumulated and bit shifted to compute the dot product of the first and second matrix.

Abstract: A configurable neuro-inspired convolution processor is designed as an array of neurons each operating in an independent clock domain. The processor implements a recurrent network using efficient sparse convolutions with zero-patch skipping for feedforward operations, and sparse spike-driven reconstruction for feedback operations. A globally asynchronous locally synchronous structure enables scalable design and load balancing to achieve 22% reduction in power. Fabricated in 40 nm CMOS, the 2.56 mm2 inference processor integrates 48 neurons, a hub and an Open RISC processor. The chip achieves 718 GOPS at 380 MHz, and demonstrates applications in feature extraction from images and depth extraction from stereo images.