公开(公告)号：US20210295139A1

公开(公告)日：2021-09-23

申请号：US16826552

申请日：2020-03-23

Applicant: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP

Inventor： Jitendra Onkar Kolhe ,  Gustavo Knuppe ,  Shyam Sankar Gopalakrishnan ,  Vaithyalingam Nagendran ,  Shounak Bandopadhyay

IPC: G06N3/063 ,  G06N3/04 ,  G06F9/50

Abstract: In some examples, a system generates a neural network comprising logical identifiers of compute resources. For executing the neural network, the system maps the logical identifiers to physical addresses of physical resources, and loads instructions of the neural network onto the physical resources, wherein the loading comprises converting the logical identifiers in the neural network to the physical addresses.

公开(公告)号：US12254416B2

公开(公告)日：2025-03-18

申请号：US17229497

申请日：2021-04-13

Applicant: Hewlett Packard Enterprise Development LP

Inventor： Jitendra Onkar Kolhe ,  Soumitra Chatterjee ,  Vaithyalingam Nagendran ,  Shounak Bandopadhyay

IPC: G06F9/44 ,  G06N3/063 ,  G06N3/10

Abstract: Examples disclosed herein relate to using a compiler for implementing tensor operations in a neural network base computing system. A compiler defines the tensor operations to be implemented. The compiler identifies a binary tensor operation receiving input operands from a first output tensor of a first tensor operation and a second output tensor of a second tensor operation from two different paths of the convolution neural network. For the binary tensor operation, the compiler allocates a buffer space for a first input operand in the binary tensor operation based on a difference between a count of instances of the first output tensor and a count of instances of the second output tensor.

公开(公告)号：US11556766B2

公开(公告)日：2023-01-17

申请号：US16826552

申请日：2020-03-23

Applicant: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP

Inventor： Jitendra Onkar Kolhe ,  Gustavo Knuppe ,  Shyam Sankar Gopalakrishnan ,  Vaithyalingam Nagendran ,  Shounak Bandopadhyay

IPC: G06F9/50 ,  G06N3/063 ,  G06N3/04

Abstract: In some examples, a system generates a neural network comprising logical identifiers of compute resources. For executing the neural network, the system maps the logical identifiers to physical addresses of physical resources, and loads instructions of the neural network onto the physical resources, wherein the loading comprises converting the logical identifiers in the neural network to the physical addresses.