US 11,704,562 B1
Architecture for virtual instructions
Harshit Khaitan, San Jose, CA (US); Miguel Angel Guerrero, Palo Alto, CA (US); Liangzhen Lai, Fremont, CA (US); and Simon James Hollis, Redmond, WA (US)
Assigned to Meta Platforms, Inc., Menlo Park, CA (US)
Filed by Meta Platforms, Inc., Menlo Park, CA (US)
Filed on Nov. 4, 2020, as Appl. No. 17/88,947.
Int. Cl. G06N 3/08 (2023.01); G06N 3/04 (2023.01); G06F 8/41 (2018.01)
CPC G06N 3/08 (2013.01) [G06F 8/433 (2013.01); G06F 8/458 (2013.01); G06N 3/04 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
a machine learning accelerator (MLA) hardware configured to perform machine-learning operations according to native instructions;
an interpreter computing module configured to:
generate, based on virtual instructions, machine language instructions configured to be processed by a processing hardware implementing the interpreter computing module; and
cause the processing hardware to perform machine-learning operations according to the machine language instructions; and
a compiler computing module associated with the MLA hardware, the compiler computing module configured to:
receive instructions for performing an inference using a machine-learning model;
based on the received instructions:
generate the native instructions configured to be processed by the MLA hardware, the native instructions specifying first machine-learning operations associated with performing the inference; and
generate the virtual instructions configured to be processed by the interpreter computing module, the virtual instructions specifying second machine-learning operations associated with performing the inference.