Software-defined tensor streaming multiprocessor for large-scale machine learning
US12277444B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 23, 2022 |
| Grant date | Apr 15, 2025 |
| Priority date | — |
| Expiry date | Jul 21, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F15/7867
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A system contains a network of processors arranged in a plurality of nodes. Each node comprises a respective plurality of processors connected via local links, and different nodes are connected via global links. The processors of the network communicate with each other to establish a global counter for the network, enabling deterministic communication between the processors of the network. A compiler is configured to explicitly schedule communication traffic across the global and local links of the network of processors based upon the deterministic links between the processors, which enable software-scheduled networking with explicit send or receive instructions executed by functional units of the processors at specific times, to establish a specific ordering of operations performed by the network of processors. In some embodiments, the processors of the network of processors are tensor streaming processors (TSPs).
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.