Samsung Electronics Co., Ltd.

Sync Computing Corp.

Titash Rakshit

Borna Josip Obradovic

Ryan M Hatcher

Jorge A Kittl

Mark Stephen Rodder

Joon Goo Hong

Rwik Sengupta

Dharmendar Reddy Palle

Wei-E Wang

Chris Bowen

Daniel Nelson Carothers

Malik Aqeel Anwar

Vladimir Nikitin

Dmytro Apalkov

Jeffrey G Bernstein

Robert Christopher Bowen

Suraj Deepak Bramhavar

Engin Ipek

Jeffrey Chou

Erica Lin

Palle Dharmendar

A method of pipelining inference of a neural network, which includes an i-th layer (i being an integer greater than zero), an (i+1)-th layer, and an (i+2)-th layer, includes processing a first set of i-th values of the i-th layer to generate (i+1)-th values for the (i+1)-th layer, determining a quantity of the (i+1)-th values as being sufficient for processing, and in response to the determining, processing the (i+1)-th values to generate an output value for the (i+2)-th layer while concurrently processing a second set of i-th values of the i-th layer.

Ultra pipelined accelerator for machine learning inference

A neuromorphic device for the analog computation of a linear combination of input signals, for use, for example, in an artificial neuron. The neuromorphic device provides non-volatile programming of the weights, and fast evaluation and programming, and is suitable for fabrication at high density as part of a plurality of neuromorphic devices. The neuromorphic device is implemented as a vertical stack of flash-like cells with a common control gate contact and individually contacted source-drain (SD) regions. The vertical stacking of the cells enables efficient use of layout resources.

High-density neuromorphic computing element

A neuromorphic weight cell (NWC) including a resistor ladder including a plurality of resistors connected in series, and a plurality of shunting nonvolatile memory (NVM) elements, each of the shunting NVM elements being coupled in parallel to a corresponding one of the resistors.

Monolithic multi-bit weight cell for neuromorphic computing

A method of assigning processing resources is described. The method includes receiving an application and analyzing the application to determine an expected run time use of the processing resources. At least a portion of the processing resources are assigned to the application based on the expected run time use of the processing resources. A computing system architecture including a processing resource pool, an interface, and a special purpose optimization coprocessor is also described. The interface receives an application to be executed. The special purpose optimization coprocessor receives information about the application and the processing resource pool and outputs an allocation scheme for allocating tasks of the application to the processing resource pool.

Real time scheduling using expected application resource usage

A method of storing a sparse weight matrix for a trained artificial neural network in a circuit including a series of clusters. The method includes partitioning the sparse weight matrix into at least one first sub-block and at least one second sub-block. The first sub-block includes only zero-value weights and the second sub-block includes non-zero value weights. The method also includes assigning the non-zero value weights in the at least one second sub-block to at least one cluster of the series of clusters of the circuit. The circuit is configured to perform matrix-vector-multiplication (MVM) between the non-zero value weights of the at least one second sub-block and an input vector during an inference process utilizing the artificial neural network. The sub-blocks containing all zero elements are power gated, thereby reducing overall energy consumption for inference.

Method of enabling sparse neural networks on memresistive accelerators

A method of pipelining inference of a neural network, which includes an i-th layer (i being an integer greater than zero) and an (i+1)-th layer, includes processing, for a first input image, first i-th values of the i-th layer to generate first (i+1)-th values for the (i+1)-th layer, processing, for the first input image, the first (i+1)-th values of the (i+1)-th layer to generate output values, and concurrently with processing, for the first image, the (i+1)-th values, processing, for a second input image, second i-th values of the i-th layer to generate second (i+1)-th values.

Batch size pipelined PIM accelerator for vision inference on multiple images

A non-volatile data retention circuit includes a complementary latch configured to generate and store complementary non-volatile spin states corresponding to an input signal when in a write mode, and to concurrently generate a first charge current signal and a second charge current corresponding to the complementary non-volatile spin states when in read mode, and a differential amplifier coupled to the complementary latch and configured to generate an output signal based on the first and second charge current signals.

Giant spin hall-based compact neuromorphic cell optimized for differential read inference

A neuromorphic multi-bit digital weight cell configured to store a series of potential weights for a neuron in an artificial neural network. The neuromorphic multi-bit digital weight cell includes a parallel cell including a series of passive resistors in parallel and a series of gating transistors. Each gating transistor of the series of gating transistors is in series with one passive resistor of the series of passive resistors. The neuromorphic cell also includes a series of programming input lines connected to the series of gating transistors, an input terminal connected to the parallel cell, and an output terminal connected to the parallel cell.

Multi-bit, SoC-compatible neuromorphic weight cell using ferroelectric FETs

A method and system for training a neural network are described. The method includes providing at least one continuously differentiable model of the neural network. The at least one continuously differentiable model is specific to hardware of the neural network. The method also includes iteratively training the neural network using the at least one continuously differentiable model to provide at least one output for the neural network. Each iteration uses at least one output of a previous iteration and a current continuously differentiable model of the at least one continuously differentiable model.

Method and system for training of neural networks using continuously differentiable models

A method and system are provided. The method includes mapping a binary matrix to an undirected graph form, applying a two-way graph partition algorithm to the mapped binary matrix that minimizes edge cuts between partitions in the mapped binary matrix, applying a greedy algorithm recursively to find a set of row or column permutations that maximizes a transfer of non-zeros from sparse blocks to nonsparse blocks, and sparsifying or densifying the binary matrix according to the applied greedy algorithm.

Optimization of sparsified neural network layers for semi-digital crossbar architectures

A method, system and electronic device for mitigating variance in a two transistor two resistive memory element (2T2R) circuit is provided. The method includes calculating a sum of a number of logical 1's in a column of bitcells in the 2T2R circuit, N, of an input vector, sensing output current values from each current line in the column of bitcells and calculating an inner product, M, of the input vector and the bitcells in the column in the 2T2R circuit based on the sensed output current values.

Variation mitigation scheme for semi-digital mac array with a 2T-2 resistive memory element bitcell

A semiconductor device includes a series of metal routing layers and a complementary pair of planar field-effect transistors (FETs) on an upper metal routing layer of the metal routing layers. The upper metal routing layer is M3 or higher. Each of the FETs includes a channel region of a crystalline material. The crystalline material may include polycrystalline silicon. The upper metal routing layer M3 or higher may include cobalt.

Growing community of inventors

Austin, TX, United States of America

Titash Rakshit