US 11,941,440 B2
System and method for queuing commands in a deep learning processor
Mohamed Shahim, Thrissur (IN); Sreenivas Aerra Reddy, Hyderabad (IN); Raju Datla, Hyderabad (IN); Lava Kumar Bokam, Vizianagaram (IN); Suresh Kumar Vennam, Hyderabad (IN); and Sameek Banerjee, Hyderabad (IN)
Assigned to Deep Vision Inc., Los Altos, CA (US)
Filed by Deep Vision Inc., Los Altos, CA (US)
Filed on Oct. 25, 2022, as Appl. No. 17/973,290.
Application 17/973,290 is a continuation of application No. 17/211,707, filed on Mar. 24, 2021, granted, now 11,513,847.
Claims priority of provisional application 62/994,108, filed on Mar. 24, 2020.
Prior Publication US 2023/0052277 A1, Feb. 16, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 9/46 (2006.01); G06F 9/48 (2006.01); G06F 9/52 (2006.01); G06N 3/063 (2023.01)
CPC G06F 9/4881 (2013.01) [G06F 9/485 (2013.01); G06F 9/52 (2013.01); G06N 3/063 (2013.01)] 8 Claims
OG exemplary drawing
 
1. A method for maintaining dependencies between command streams for a multicore processor comprising, at a queue processor comprising a set of command queues and a signal-wait counter matrix:
dequeuing a first wait primitive from a first waiting command queue in the set of command queues, the first wait primitive pointing to a first signaling command queue in the set of command queues;
accessing a first register in the signal-wait counter matrix, the first register storing a first number of pending signal primitives; and
in response to detecting the first number of pending signal primitives representing at least one pending signal primitive:
dequeuing a first instruction from the first waiting command queue; and
dispatching a first control signal representing the first instruction.