Matrix multiplication acceleration of sparse matrices using column folding and squeezing
O Azizi, G Boudoukh, T Werner, A Yang… - US Patent …, 2020 - Google Patents
Disclosed embodiments relate to sparse matrix multiplica tion (SMM) acceleration using
column folding and squeez ing. In one example, a processor, in response to a SMM …
column folding and squeez ing. In one example, a processor, in response to a SMM …
Method for matrix by vector multiplication for use in artificial neural network
PW Hsieh, CC Hsu, TL Chen - US Patent 10,534,839, 2020 - Google Patents
US10534839B2 - Method for matrix by vector multiplication for use in artificial neural
network - Google Patents US10534839B2 - Method for matrix by vector multiplication for …
network - Google Patents US10534839B2 - Method for matrix by vector multiplication for …
Architecture for sparse neural network acceleration
A method, a computer-readable medium, and an apparatus for a sparse neural network are
provided. The apparatus may include a hardware accelerator. The apparatus may deter …
provided. The apparatus may include a hardware accelerator. The apparatus may deter …
Systems and devices for formatting neural network parameters
US11275996B2 - Systems and devices for formatting neural network parameters - Google
Patents US11275996B2 - Systems and devices for formatting neural network parameters …
Patents US11275996B2 - Systems and devices for formatting neural network parameters …
Configuring sparse neuronal networks
A method for selecting a reduced number of model neurons in a neural network includes
generating a first sparse set of non-zero decoding vectors. Each of the decoding vector is …
generating a first sparse set of non-zero decoding vectors. Each of the decoding vector is …
Sparse matrix storage in a database
Z Zhao, JA Cox, R Albright - US Patent 10,275,479, 2019 - Google Patents
Methods, processes and computer-program products are disclosed for use in a parallelized
computing system in which representations of large sparse matrices are efficiently encoded …
computing system in which representations of large sparse matrices are efficiently encoded …
Memory-to-memory instructions to accelerate sparse-matrix by dense-vector and sparse-vector by dense-vector multiplication
AK Mishra, DT Marr, ET Grochowski - US Patent 10,489,063, 2019 - Google Patents
First elements of a dense vector to be multiplied with first elements of a first row of a sparse
array may be determined. The determined first elements of the dense vector may be written …
array may be determined. The determined first elements of the dense vector may be written …
Matrix processing apparatus
Methods, systems, and apparatus, including a system for transforming sparse elements to a
dense matrix. The system is configured to receive a request for an output matrix based on …
dense matrix. The system is configured to receive a request for an output matrix based on …
Systems and methods for providing vector-wise sparsity in a neural network
The present disclosure relates to systems and methods for providing vector-wise sparsity in
neural networks. In some embodiments, an exemplary method for providing vector-wise …
neural networks. In some embodiments, an exemplary method for providing vector-wise …
Systems and methods for generation of sparse code for convolutional neural networks
(57) ABSTRACT A system and method may generate code to be used when executing
neural networks (NNs), for example convolu tional neural networks (CNNs) which may …
neural networks (NNs), for example convolu tional neural networks (CNNs) which may …