Compiler for optimizing number of cores used to implement neural network
US12165069B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 29, 2019 |
| Grant date | Dec 10, 2024 |
| Priority date | — |
| Expiry date | Oct 4, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N7/08
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Some embodiments provide a compiler for optimizing the implementation of a machine-trained network (e.g., a neural network) on an integrated circuit (IC). The compiler of some embodiments receives a specification of a machine-trained network including multiple layers of computation nodes and generates a graph representing options for implementing the machine-trained network in the IC. In some embodiments, the graph includes nodes representing options for implementing each layer of the machine-trained network and edges between nodes for different layers representing different implementations that are compatible. In some embodiments, the graph is populated according to rules relating to memory use and the numbers of cores necessary to implement a particular layer of the machine trained network such that nodes for a particular layer, in some embodiments, represent fewer than all the possible groupings of sets of clusters.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.