2018-02-12 Assigned to INTEL CORPORATION reassignment INTEL CORPORATION
ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors …

Abstract Systems and methods may make exchanging data in a neural network (NN) during
training more efficient. Exchanging weights among a number of processors training a NN …

One or more examples include an apparatus having a hardware barrier logic to detect
thread groups relating to machine learning operations and facilitate barrier synchronization …

Source code of a graph analysis program expressed in a platform-independent language
which supports linear algebra primitives is obtained. An executable version of the program is …

A method and system for computing one or more outputs of a neural network having a
plurality of layers is provided. The method and system can include determining a plurality of …

A method and system for performing general matrix-matrix multiplication (GEMM) operations
on a graphics processor unit (GPU) using Smart kernels. During operation, the system may …

(57) ABSTRACT A system and method of executing a convolution layer of a neural network
may include:(a) selecting an output spatial position (OSP) of an output matrix data element …

Techniques facilitating generation of a fused kernel that can approximate a full kernel of a
convolutional neural network are provided. In one example, a computer-implemented …

A system and method for machine learning, with a processing circuit executing an operating
system, the processing circuit being connected to a first memory and to a second memory. In …

A method and system performing a general matrix-matrix multiplication (GEMM) operation
using a kernel compiled with optimal maximum register count (MRC). During operation, the …