US 12,093,801 B1
Neural network processing based on subgraph recognition
Richard John Heaton, San Jose, CA (US); Randy Renfu Huang, Morgan Hill, CA (US); and Ron Diamant, Albany, CA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on May 3, 2023, as Appl. No. 18/142,952.
Application 18/142,952 is a continuation of application No. 16/219,760, filed on Dec. 13, 2018, granted, now 11,714,992.
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/00 (2019.01); G06F 9/30 (2018.01); G06F 9/48 (2006.01); G06F 16/901 (2019.01); G06N 3/04 (2023.01)
CPC G06N 3/04 (2013.01) [G06F 9/30003 (2013.01); G06F 9/4881 (2013.01); G06F 16/9024 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
a database that stores subsets of executable instructions, wherein each subset of the subsets of executable instructions is associated with one of a plurality of subgraph identifiers and one of a plurality of processor identifiers; and
one or more processors; and
a non-transitory computer-readable medium storing a compiler that, when executed by the one or more processors, causes the compiler to:
receive a computational graph to be executed on a processor;
determine a subgraph identifier of a computational subgraph from the computational graph;
determine a processor identifier of the processor;
retrieve, from the database, instructions from one of the subsets of executable instructions associated with both the subgraph identifier and the processor identifier, the instructions having been stored in the database prior to the compiler receiving the computational graph; and
provide the instructions for execution by the processor.