Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of neural network layers, the circuit comprising: a matrix computation unit configured to, for each of the plurality of neural network layers: receive a plurality of weight inputs and a plurality of activation inputs for the neural network layer, and generate a plurality of accumulated values based on the plurality of weight inputs and the plurality of activation inputs; and a vector computation unit communicatively coupled to the matrix computation unit and configured to, for each of the plurality of neural network layers: apply an activation function to each accumulated value generated by the matrix computation unit to generate a plurality of activated values for the neural network layer.

Abstract: A pneumatic compression garment for treating lymphedema in the head, neck and torso of a patient is disclosed, which includes a first garment portion configured and adapted to be worn on a patient's head and including a plurality of separate and independently inflatable air chambers, and a second garment portion attached to the first garment portion and configured and adapted to be worn of the patient's torso and including a plurality of separate and independently inflatable air chambers.

Abstract: Methods, systems, and apparatus for efficiently performing a computation of a convolutional neural network layer. One of the methods includes transforming a X by Y by Z input tensor into a X? by Y? by Z? input tensor, wherein X? is smaller than or equal to X, Y? is smaller than or equal to Y, and Z? is larger than or equal to Z; obtaining one or more modified weight matrices, wherein the modified weight matrices operate on the X? by Y? by Z? input tensor to generate a U? by V? by W? output tensor, and the U? by V? by W? output tensor is a transformed U by V by W output tensor; and processing the X? by Y? by Z? input tensor using the modified weight matrices to generate the U? by V? by W? output tensor.

Abstract: A method for allocating resources for a machine learning model is disclosed. A machine learning model to be executed on a special purpose machine learning model processor is received. A computational data graph is generated from the machine learning model. The computational dataflow graph represents the machine learning model which includes nodes, connector directed edges, and parameter directed edges. The operations of the computational dataflow graph is scheduled and then compiled using a deterministic instruction set architecture that specifies functionality of a special purpose machine learning model processor. An amount of resources required to execute the computational dataflow graph is determined. Resources are allocated based on the determined amounts of resources required to execute the machine learning model represented by the computational dataflow graph.

Abstract: A system contains a network of processors arranged in a plurality of nodes. Each node comprises a respective plurality of processors connected via local links, and different nodes are connected via global links. The processors of the network communicate with each other to establish a global counter for the network, enabling deterministic communication between the processors of the network. A compiler is configured to explicitly schedule communication traffic across the global and local links of the network of processors based upon the deterministic links between the processors, which enable software-scheduled networking with explicit send or receive instructions executed by functional units of the processors at specific times, to establish a specific ordering of operations performed by the network of processors. In some embodiments, the processors of the network of processors are tensor streaming processors (TSPs).

Abstract: A circuit comprises an input register configured to receive an input vector of elements, a control register configured to receive a control vector of elements, wherein each element of the control vector corresponds to a respective element of the input vector, and wherein each element specifies a permutation of a corresponding element of the input vector, and a permute execution circuit configured to generate an output vector of elements corresponding to a permutation of the input vector. Generating each element of the output vector comprises accessing, at the input register, a particular element of the input vector, accessing, at the control register, a particular element of the control vector corresponding to the particular element of the input vector, and outputting the particular element of the input vector as an element at a particular position of the output vector that is selected based on the particular element of the control vector.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for computing a layer output for a convolutional neural network layer, the method comprising: receiving a plurality of activation inputs; forming a plurality of vector inputs from the plurality of activation inputs, each vector input comprising values from a distinct region within the multi-dimensional matrix; sending the plurality of vector inputs to one or more cells along a first dimension of the systolic array; generating a plurality of rotated kernel structures from each of the plurality of kernel; sending each kernel structure and each rotated kernel structure to one or more cells along a second dimension of the systolic array; causing the systolic array to generate an accumulated output based on the plurality of value inputs and the plurality of kernels; and generating the layer output from the accumulated output.

Abstract: An assembly, has: a rotor of a rotary internal combustion engine, the rotor having two end faces and a peripheral face between the two end faces, the peripheral face defining apex portions circumferentially-spaced from one another, the rotor having seals, the seals including: apex seals extending between the two end faces and each located at a respective one of the apex portions, end seals engaging ends of the apex seals, and arc seals located on the two end faces and extending between the apex portions; and a tool engaged to the rotor and abutting the seals, the tool having: two cover plates, the rotor located between the two cover plates, the two cover plates abutting the end seals and the arc seals; and posts secured to one or more of the two cover plates and extending between the two cover plates, the posts abutting the apex seals.

Abstract: A system contains a network of processors arranged in a plurality of nodes. Each node comprises a respective plurality of processors connected via local links, and different nodes are connected via global links. The processors of the network communicate with each other to establish a global counter for the network, enabling deterministic communication between the processors of the network. A compiler is configured to explicitly schedule communication traffic across the global and local links of the network of processors based upon the deterministic links between the processors, which enable software-scheduled networking with explicit send or receive instructions executed by functional units of the processors at specific times, to establish a specific ordering of operations performed by the network of processors. In some embodiments, the processors of the network of processors are tensor streaming processors (TSPs).

Abstract: A circuit for transposing a matrix comprising reversal circuitry configured, for each of one or more diagonals of the matrix, to receive elements of the matrix in a first vector and generate a second vector that includes the elements of the matrix in an order that is a reverse of an order of the elements of the matrix in the first vector, and rotation circuitry configured, for each of the one or more diagonals of the matrix, to determine a number of positions by which to rotate the elements of the matrix in the second vector, receive the second vector of elements of the matrix, and generate a third vector that includes the elements of the matrix in the second vector in an order that is a rotation of the elements of the matrix in the second vector by the determined number of positions.

Abstract: A polymer masonry unit is disclosed that can include a polymer added to a quarry byproduct to manufacture a quality brick unit. The present disclosure solves the technological problem of providing a structurally sound brick or concrete alternative without the need for kiln firing, using traditionally unusable waste material. By combining quarry byproduct and a polymer, a polymer masonry unit can be fabricated having compressive strength and architectural utility. In one exemplary embodiment, fiber elements can be added to the byproduct and polymer mixture to increase structural stability. The present disclosure improves the performance of the system itself by providing a basic block or brick unit using an environmentally responsible manufacturing process that reduces cost and waste. The manufacturing process includes a polymer/base material that can be poured into molds that cures over a predetermined period, without the need for kiln firing.

Abstract: A circuit comprises an input register configured to receive an input vector of elements, a control register configured to receive a control vector of elements, wherein each element of the control vector corresponds to a respective element of the input vector, and wherein each element specifies a permutation of a corresponding element of the input vector, and a permute execution circuit configured to generate an output vector of elements corresponding to a permutation of the input vector. Generating each element of the output vector comprises accessing, at the input register, a particular element of the input vector, accessing, at the control register, a particular element of the control vector corresponding to the particular element of the input vector, and outputting the particular element of the input vector as an element at a particular position of the output vector that is selected based on the particular element of the control vector.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for computing a layer output for a convolutional neural network layer, the method comprising: receiving a plurality of activation inputs; forming a plurality of vector inputs from the plurality of activation inputs, each vector input comprising values from a distinct region within the multi-dimensional matrix; sending the plurality of vector inputs to one or more cells along a first dimension of the systolic array; generating a plurality of rotated kernel structures from each of the plurality of kernel; sending each kernel structure and each rotated kernel structure to one or more cells along a second dimension of the systolic array; causing the systolic array to generate an accumulated output based on the plurality of value inputs and the plurality of kernels; and generating the layer output from the accumulated output.

Abstract: A circuit for performing neural network computations for a neural network, the circuit comprising: a systolic array comprising a plurality of cells; a weight fetcher unit configured to, for each of the plurality of neural network layers: send, for the neural network layer, a plurality of weight inputs to cells along a first dimension of the systolic array; and a plurality of weight sequencer units, each weight sequencer unit coupled to a distinct cell along the first dimension of the systolic array, the plurality of weight sequencer units configured to, for each of the plurality of neural network layers: shift, for the neural network layer, the plurality of weight inputs to cells along the second dimension of the systolic array over a plurality of clock cycles and where each cell is configured to compute a product of an activation input and a respective weight input using multiplication circuitry.

Abstract: A circuit for performing neural network computations for a neural network, the circuit comprising: a systolic array comprising a plurality of cells; a weight fetcher unit configured to, for each of the plurality of neural network layers: send, for the neural network layer, a plurality of weight inputs to cells along a first dimension of the systolic array; and a plurality of weight sequencer units, each weight sequencer unit coupled to a distinct cell along the first dimension of the systolic array, the plurality of weight sequencer units configured to, for each of the plurality of neural network layers: shift, for the neural network layer, the plurality of weight inputs to cells along the second dimension of the systolic array over a plurality of clock cycles and where each cell is configured to compute a product of an activation input and a respective weight input using multiplication circuitry.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for computing a layer output for a convolutional neural network layer, the method comprising: receiving a plurality of activation inputs; forming a plurality of vector inputs from the plurality of activation inputs, each vector input comprising values from a distinct region within the multi-dimensional matrix; sending the plurality of vector inputs to one or more cells along a first dimension of the systolic array; generating a plurality of rotated kernel structures from each of the plurality of kernel; sending each kernel structure and each rotated kernel structure to one or more cells along a second dimension of the systolic array; causing the systolic array to generate an accumulated output based on the plurality of value inputs and the plurality of kernels; and generating the layer output from the accumulated output.

Abstract: A circuit comprises an input register configured to receive an input vector of elements, a control register configured to receive a control vector of elements, wherein each element of the control vector corresponds to a respective element of the input vector, and wherein each element specifies a permutation of a corresponding element of the input vector, and a permute execution circuit configured to generate an output vector of elements corresponding to a permutation of the input vector. Generating each element of the output vector comprises accessing, at the input register, a particular element of the input vector, accessing, at the control register, a particular element of the control vector corresponding to the particular element of the input vector, and outputting the particular element of the input vector as an element at a particular position of the output vector that is selected based on the particular element of the control vector.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for computing a layer output for a convolutional neural network layer, the method comprising: receiving the layer input, the layer input comprising a plurality of activation inputs, the plurality of activation inputs represented as a multi-dimensional matrix comprising a plurality of depth levels, each depth level being a respective matrix of distinct activation inputs from the plurality of activation inputs; sending each respective kernel matrix structure to a distinct cell along a first dimension of the systolic array; for each depth level, sending the respective matrix of distinct activation inputs to a distinct cell along a second dimension of the systolic array; causing the systolic array to generate an accumulated output from the respective matrices sent to the cells; and generating the layer output from the accumulated output.

Abstract: A polymer-based compound, useful as a polymer masonry unit is disclosed that can include a polymer added to a quarry byproduct to manufacture a quality brick unit. The present disclosure solves the technological problem of providing a structurally sound brick or concrete alternative without the need for kiln firing, using traditionally unusable waste material. By combining quarry byproduct and a polymer, a polymer masonry unit can be fabricated having compressive strength and architectural utility. In one exemplary embodiment, fiber elements can be added to the byproduct and polymer mixture to increase structural stability. The present disclosure improves the performance of the system itself by providing a basic block or brick unit using an environmentally responsible manufacturing process that reduces cost and waste. The manufacturing process includes a polymer/base material that can be poured into molds that cures over a predetermined period, without the need for kiln firing.

Abstract: A polymer-based compound, useful as a polymer masonry unit is disclosed that can include a polymer added to a quarry byproduct to manufacture a quality brick unit. The present disclosure solves the technological problem of providing a structurally sound brick or concrete alternative without the need for kiln firing, using traditionally unusable waste material. By combining quarry byproduct and a polymer, a polymer masonry unit can be fabricated having compressive strength and architectural utility. In one exemplary embodiment, fiber elements can be added to the byproduct and polymer mixture to increase structural stability. The present disclosure improves the performance of the system itself by providing a basic block or brick unit using an environmentally responsible manufacturing process that reduces cost and waste. The manufacturing process includes a polymer/base material that can be poured into molds that cures over a predetermined period, without the need for kiln firing.