Allocating computations of a machine learning network in a machine learning accelerator
US11734605B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 29, 2020 |
| Grant date | Aug 22, 2023 |
| Priority date | — |
| Expiry date | Aug 9, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/082
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A compiler receives a description of a machine learning network and generates a computer program that implements the machine learning network. The compiler allocates instructions of the computer program to different groups of processing elements (Tiles) for execution such that different groups of Tiles implement different layers of the machine learning network. The compiler may determine the size of the different groups based on a partial computation metric associated with the computations performed to implement the corresponding layer. Furthermore, the compiler may assign specific Tiles to each group based on a set of predefined layout constraints. The compiler may statically schedule at least a portion of the instructions into one or more deterministic phases for execution by the groups of Tiles.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.