公开(公告)号：GB2606600A

公开(公告)日：2022-11-16

申请号：GB202116839

申请日：2021-11-23

Applicant: IBM

Inventor： JUN SAWADA ,  MYRON D FLICKNER ,  ANDREW STEPHEN CASSIDY ,  JOHN VERNON ARTHUR ,  PALLAB DATTA ,  DHARMENDRA S MODHA ,  STEVEN KYLE ESSER ,  BRIAN SEISHO TABA ,  JENNIFER KLAMO ,  RATHINAKUMAR APPUSWAMY ,  FILIPP AKOPYAN ,  CARLOS ORTEGA OTERO

IPC: G06N3/04 ,  G06N3/063

Abstract: A neural inference chip is provided, including at least one neural inference core. The at least one neural inference core is adapted to apply a plurality of synaptic weights to a plurality of input activations to produce a plurality of intermediate outputs. The at least one neural inference core comprises a plurality of activation units configured to receive the plurality of intermediate outputs and produce a plurality of activations. Each of the plurality of activation units is configured to apply a configurable activation function to its input. The configurable activation function has at least a re-ranging term and a scaling term, the re-ranging term determining the range of the activations and the scaling term determining the scale of the activations. Each of the plurality of activations units is configured to obtain the re-ranging term and the scaling term from one or more look up tables.

公开(公告)号：IL295718B1

公开(公告)日：2024-12-01

申请号：IL29571822

申请日：2022-08-17

Applicant: IBM ,  JUN SAWADA ,  DHARMENDRA S MODHA ,  ANDREW STEPHEN CASSIDY ,  JOHN VERNON ARTHUR ,  TAPAN KUMAR NAYAK ,  CARLOS ORTEGA OTERO ,  BRIAN TABA ,  FILIPP A AKOPYAN ,  PALLAB DATTA

Inventor： JUN SAWADA ,  DHARMENDRA S MODHA ,  ANDREW STEPHEN CASSIDY ,  JOHN VERNON ARTHUR ,  TAPAN KUMAR NAYAK ,  CARLOS ORTEGA OTERO ,  BRIAN TABA ,  FILIPP A AKOPYAN ,  PALLAB DATTA

IPC: G06F17/15 ,  G06F17/16

Abstract: Neural inference chips for computing neural activations are provided. In various embodiments, a neural inference chip comprises at least one neural core, a memory array, an instruction buffer, and an instruction memory. The instruction buffer has a position corresponding to each of a plurality of elements of the memory array. The instruction memory provides at least one instruction to the instruction buffer. The instruction buffer advances the at least one instruction between positions in the instruction buffer. The instruction buffer provides the at least one instruction to at least one of the plurality of elements of the memory array from its associated position in the instruction buffer when the memory of the at least one of the plurality of elements contains data associated with the at least one instruction. Each element of the memory array provides a data block from its memory to its horizontal buffer in response to the arrival of an associated instruction from the instruction buffer. The horizontal buffer of each element of the memory array provides a data block to the horizontal buffer of another of the elements of the memory array or to the at least one neural core.

公开(公告)号：GB2586556A

公开(公告)日：2021-02-24

申请号：GB202018026

申请日：2019-03-28

Applicant: IBM

Inventor： DHARMENDRA SHANTILAL MODHA ,  JOHN VERNON` ARTHUR ,  JUN SAWADA ,  STEVEN KYLE ESSER ,  RATHINAKUMAR APPUSWAMY ,  BRIAN SEISHO TABA ,  ANDREW STEPHEN CASSIDY ,  PALLAB DATTA ,  MYRON DALE FLICKNER ,  HARTMUT PENNER ,  JENNIFER KLAMO

IPC: G06N3/063 ,  G06F7/544

Abstract: Neural inference chips and cores adapted to provide time, space, and energy efficient neural inference via parallelism and on-chip memory are provided. In various embodiments, the neural inference chips comprise: a plurality of neural cores interconnected by an on-chip network; a first on-chip memory for storing a neural network model, the first on-chip memory being connected to each of the plurality of cores by the on-chip network; a second on-chip memory for storing input and output data, the second on-chip memory being connected to each of the plurality of cores by the on-chip network.

公开(公告)号：GB2585615A

公开(公告)日：2021-01-13

申请号：GB202016300

申请日：2019-03-11

Applicant: IBM

Inventor： JUN SAWADA ,  DHARMENDRA SHANTILAL MODHA ,  JOHN VERNON` ARTHUR ,  STEVEN KYLE ESSER ,  BRIAN SEISHO TABA ,  ANDREW STEPHEN CASSIDY ,  PALLAB DATTA ,  MYRON DALE FLICKNER ,  HARTMUT PENNER ,  JENNIFER KLAMO ,  RATHINAKUMAR APPUSWAMY

IPC: G06N3/063 ,  G06F7/544 ,  G06F17/16

Abstract: Massively parallel neural inference computing elements are provided. A plurality of multipliers is arranged in a plurality of equal-sized groups. Each of the plurality of multipliers is adapted to, in parallel, apply a weight to an input activation to generate an output. A plurality of adders is operatively coupled to one of the groups of multipliers. Each of the plurality of adders is adapted to, in parallel, add the outputs of the multipliers within its associated group to generate a partial sum. A plurality of function blocks is operatively coupled to one of the plurality of adders. Each of the plurality of function blocks is adapted to, in parallel, apply a function to the partial sum of its associated adder to generate an output value.

公开(公告)号：GB2586556B

公开(公告)日：2021-08-11

申请号：GB202018026

申请日：2019-03-28

Applicant: IBM

Inventor： DHARMENDRA SHANTILAL MODHA ,  JOHN VERNON` ARTHUR ,  JUN SAWADA ,  STEVEN KYLE ESSER ,  RATHINAKUMAR APPUSWAMY ,  BRIAN SEISHO TABA ,  ANDREW STEPHEN CASSIDY ,  PALLAB DATTA ,  MYRON DALE FLICKNER ,  HARTMUT PENNER ,  JENNIFER KLAMO

IPC: G06N3/063 ,  G06F7/544

Abstract: Neural inference chips and cores adapted to provide time, space, and energy efficient neural inference via parallelism and on-chip memory are provided. In various embodiments, the neural inference chips comprise: a plurality of neural cores interconnected by an on-chip network; a first on-chip memory for storing a neural network model, the first on-chip memory being connected to each of the plurality of cores by the on-chip network; a second on-chip memory for storing input and output data, the second on-chip memory being connected to each of the plurality of cores by the on-chip network.

公开(公告)号：GB2587175A

公开(公告)日：2021-03-17

申请号：GB202100512

申请日：2019-06-13

Applicant: IBM

Inventor： ANDREW STEPHEN CASSIDY ,  PALLAB DATTA ,  JENNIFER KLAMO ,  JUN SAWADA ,  RATHINAKUMAR APPUSWAMY ,  STEVEN KYLE ESSER ,  DHARMENDRA SHANTILAL MODHA ,  BRIAN SEISHO TABA ,  JOHN VERNON` ARTHUR ,  MYRON DALE FLICKNER ,  HARTMUT PENNER

IPC: G06N3/063 ,  G06N3/04 ,  G06N3/08 ,  G11C11/54

Abstract: Hardware neural network processors, are provided. A neural core includes a weight memory, an activation memory, a vector-matrix multiplier, and a vector processor. The vector-matrix multiplier is adapted to receive a weight matrix from the weight memory, receive an activation vector from the activation memory, and compute a vector-matrix multiplication of the weight matrix and the activation vector. The vector processor is adapted to receive one or more input vector from one or more vector source and perform one or more vector functions on the one or more input vector to yield an output vector. In some embodiments a programmable controller is adapted to configure and operate the neural core.

公开(公告)号：GB2586763A

公开(公告)日：2021-03-03

申请号：GB202018196

申请日：2019-03-28

Applicant: IBM

Inventor： ANDREW STEPHEN CASSIDY ,  MYRON DALE FLICKNER ,  PALLAB DATTA ,  HARTMUT PENNER ,  RATHINAKUMAR APPUSWAMY ,  JUN SAWADA ,  JOHN VERNON` ARTHUR ,  DHARMENDRA SHANTILAL MODHA ,  STEVEN KYLE ESSER ,  BRIAN SEISHO TABA ,  JENNIFER KLAMO

IPC: G06N3/063

Abstract: Neural inference processors are provided. In various embodiments, a processor includes a plurality of cores. Each core includes a neural computation unit, an activation memory, and a local controller. The neural computation unit is adapted to apply a plurality of synaptic weights to a plurality of input activations to produce a plurality of output activations. The activation memory is adapted to store the input activations and the output activations. The local controller is adapted to load the input activations from the activation memory to the neural computation unit and to store the plurality of output activations from the neural computation unit to the activation memory. The processor includes a neural network model memory adapted to store network parameters, including the plurality of synaptic weights. The processor includes a global scheduler operatively coupled to the plurality of cores, adapted to provide the synaptic weights from the neural network model memory to each core.

公开(公告)号：GB2590888B

公开(公告)日：2021-10-27

申请号：GB202106472

申请日：2019-09-25

Applicant: IBM

Inventor： JOHN VERNON` ARTHUR ,  ANDREW STEPHEN CASSIDY ,  MYRON FLICKNER ,  PALLAB DATTA ,  HARTMUT PENNER ,  RATHINAKUMAR APPUSWAMY ,  JUN SAWADA ,  DHARMENDRA MODHA ,  STEVEN KYLE ESSER ,  BRIAN SEISHO TABA ,  JENNIFER KLAMO

IPC: G06N3/063 ,  G06N3/02

Abstract: Systems for neural network computation are provided. A neural network processor comprises a plurality of neural cores. The neural network processor has one or more processor precisions per activation. The processor is configured to accept data having a processor feature dimension. A transformation circuit is coupled to the neural network processor, and is adapted to: receive an input data tensor having an input precision per channel at one or more features; transform the input data tensor from the input precision to the processor precision; divide the input data into a plurality of blocks, each block conforming to one of the processor feature dimensions; provide each of the plurality of blocks to one of the plurality of neural cores. The neural network processor is adapted to compute, by the plurality of neural cores, output of one or more neural network layers.

公开(公告)号：GB2585615B

公开(公告)日：2021-05-19

申请号：GB202016300

申请日：2019-03-11

Applicant: IBM

Inventor： JUN SAWADA ,  DHARMENDRA SHANTILAL MODHA ,  JOHN VERNON` ARTHUR ,  STEVEN KYLE ESSER ,  BRIAN SEISHO TABA ,  ANDREW STEPHEN CASSIDY ,  PALLAB DATTA ,  MYRON DALE FLICKNER ,  HARTMUT PENNER ,  JENNIFER KLAMO ,  RATHINAKUMAR APPUSWAMY

IPC: G06N3/063 ,  G06F7/544 ,  G06F17/16

Abstract: Massively parallel neural inference computing elements are provided. A plurality of multipliers is arranged in a plurality of equal-sized groups. Each of the plurality of multipliers is adapted to, in parallel, apply a weight to an input activation to generate an output. A plurality of adders is operatively coupled to one of the groups of multipliers. Each of the plurality of adders is adapted to, in parallel, add the outputs of the multipliers within its associated group to generate a partial sum. A plurality of function blocks is operatively coupled to one of the plurality of adders. Each of the plurality of function blocks is adapted to, in parallel, apply a function to the partial sum of its associated adder to generate an output value.

公开(公告)号：GB2553451A

公开(公告)日：2018-03-07

申请号：GB201716188

申请日：2016-01-22

Applicant: IBM

Inventor： ARNON AMIR ,  RATHINAKUMAR APPUSWAMY ,  PALLAB DATTA ,  BENJAMIN GORDON SHAW ,  MYRON DALE FLICKNER ,  PAUL MEROLLA ,  DHARMENDRA SHANTILAL MODHA

IPC: G06N3/04 ,  G06N3/10

Abstract: One embodiment of the invention provides a system for mapping a neural network onto a neurosynaptic substrate. The system comprises a metadata analysis unit for analyzing metadata information associated with one or more portions of an adjacency matrix representation of the neural network, and a mapping unit for mapping the one or more portions of the matrix representation onto the neurosynaptic substrate based on the metadata information.