US 12,189,527 B2
Method and apparatus for managing unified virtual memory by preventing migration of deep learning model's weight from processor memory to coprocessor memory
Wonik Seo, Suwon-si (KR); Dong-uk Ryu, Suwon-si (KR); and Sungduk Cho, Suwon-si (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed on Jun. 28, 2023, as Appl. No. 18/343,099.
Claims priority of application No. 10-2022-0186915 (KR), filed on Dec. 28, 2022.
Prior Publication US 2024/0220407 A1, Jul. 4, 2024
Int. Cl. G06F 12/08 (2016.01)
CPC G06F 12/08 (2013.01) 20 Claims
OG exemplary drawing
 
1. A method of managing a unified virtual memory (UVM) that is backed by a main processor memory and a coprocessor memory, the method comprising:
checking properties of data blocks of the UVM used to execute a deep learning model;
based on a first of the data blocks storing weight data of the deep learning model, storing the first data block in the main processor memory among the main processor memory and the coprocessor memory; and
performing an operation of the deep learning model based on the first data block using a coprocessor while directly loading at least a portion of the first data block from the main processor memory into a cache memory of the coprocessor without migration of the first data block from the main processor memory to the coprocessor memory.