US 11,853,766 B2
Technology to learn and offload common patterns of memory access and computation
Vy Vo, Portland, OR (US); Dipanjan Sengupta, Hillsboro, OR (US); Mariano Tepper, Portland, OR (US); and Javier Sebastian Turek, Beaverton, OR (US)
Assigned to Intel Corporation, Santa Clara, CA (US)
Filed by Intel Corporation, Santa Clara, CA (US)
Filed on Jul. 25, 2022, as Appl. No. 17/872,927.
Application 17/872,927 is a continuation of application No. 16/914,293, filed on Jun. 27, 2020, granted, now 11,403,102.
Prior Publication US 2022/0357951 A1, Nov. 10, 2022
Int. Cl. G06F 9/38 (2018.01); G06F 9/32 (2018.01); G06F 9/50 (2006.01); G06F 12/0815 (2016.01); G06N 3/063 (2023.01); G06F 11/34 (2006.01); G06F 18/21 (2023.01); G06N 3/045 (2023.01)
CPC G06F 9/3877 (2013.01) [G06F 9/321 (2013.01); G06F 9/5016 (2013.01); G06F 9/5066 (2013.01); G06F 11/3457 (2013.01); G06F 12/0815 (2013.01); G06F 18/217 (2023.01); G06N 3/045 (2023.01); G06N 3/063 (2013.01); G06F 2212/1021 (2013.01)] 24 Claims
OG exemplary drawing
 
1. A system comprising:
memory;
a central processing unit (CPU) to execute first operations;
in-memory execution circuitry in the memory; and
detector software to cause offloading of second operations to the in-memory execution circuitry after detecting a benefit of the offloading based on machine learning, the in-memory execution circuitry to execute the second operations in a first execution path, the CPU to execute the first operations in a second execution path.