公开(公告)号：US20190187775A1

公开(公告)日：2019-06-20

申请号：US15846117

申请日：2017-12-18

Applicant: Facebook, Inc.

Inventor： Nadav Rotem ,  Jong Soo Park ,  Mikhail Smelyanskiy ,  Abdulkadir Utku Diril

IPC: G06F1/32 ,  G06N5/02 ,  G06F9/38

Abstract: A computer-implemented method for dynamically managing the power usage and/or performance of an artificial intelligence (AI) hardware accelerator may include (1) receiving an instruction stream that includes one or more instructions for performing at least one AI-specific computing task, (2) identifying a plurality of special-purpose, hardware-based functional units configured to perform AI-specific computing tasks, (3) predicting, based on an analysis of at least a portion of the instruction stream, a power-usage requirement for at least one of the functional units when executing the instruction stream, and then (4) modifying, based on the power-usage requirement, the power supplied to at least one of the functional units. Various other methods and systems are also disclosed.

公开(公告)号：US20190179869A1

公开(公告)日：2019-06-13

申请号：US15839229

申请日：2017-12-12

Applicant: Facebook, Inc.

Inventor： Jong Soo Park ,  Nadav Rotem ,  Mikhail Smelyanskiy ,  Abdulkadir Utku Diril

IPC: G06F17/16 ,  G06F7/523 ,  G06F15/18 ,  G06N3/02 ,  G06F12/0875

CPC classification number: G06F17/16 ,  G06F7/523 ,  G06F12/0875 ,  G06F17/156 ,  G06N3/02 ,  G06N20/00

Abstract: A special-purpose hardware accelerator may include a cache configured to store an input matrix related to performing a convolution operation and a matrix-multiplication subsystem pre-configured with matrix-transform coefficients for performing matrix-transform operations. The matrix-multiplication subsystem may perform the convolution operation by (1) reading the input matrix from the cache, (2) transforming the input matrix via matrix multiplication, (3) transforming, via matrix multiplication, a parameter matrix that includes convolution parameters for performing the convolution operation, (4) applying the transformed parameter matrix to the transformed input matrix via an element-wise multiplication operation, and then (5) performing an inverse-transformation operation on the results of the element-wise multiplication operation to create an output matrix for the convolution operation. Various other systems and methods are also disclosed.

公开(公告)号：US20190171927A1

公开(公告)日：2019-06-06

申请号：US15833985

申请日：2017-12-06

Applicant: Facebook, Inc.

Inventor： Abdulkadir Utku Diril ,  Jong Soo Park ,  Nadav Rotem ,  Mikhail Smelyanskiy

IPC: G06N3/04 ,  G06N5/04 ,  G06N3/08

Abstract: A method for performing layer-level quantization may include (1) performing an inference of an activation layer of a neural network, (2) storing a first limit value of the activation layer in a data storage system, (3) storing a second limit value of the activation layer in the data storage system, (4) determining a scaling factor based on the first and second limit values, and then (5) applying the scaling factor on a subsequent inference. Various other methods, systems, and devices are also disclosed.