US 12,321,728 B2
Method of rebinding computing unit in heterogeneous computing clouds and apparatus thereof
Hwansoo Han, Suwon-si (KR); and Sungin Hong, Suwon-si (KR)
Assigned to Research & Business Foundation Sungkyunkwan University, Suwon-si (KR)
Filed by Research & Business Foundation SUNGKYUNKWAN UNIVERSITY, Suwon-si (KR)
Filed on Dec. 29, 2022, as Appl. No. 18/091,160.
Claims priority of application No. 10-2021-0192932 (KR), filed on Dec. 30, 2021.
Prior Publication US 2023/0214196 A1, Jul. 6, 2023
Int. Cl. G06F 9/44 (2018.01); G06F 8/41 (2018.01); G06F 9/445 (2018.01)
CPC G06F 8/41 (2013.01) [G06F 9/44521 (2013.01)] 9 Claims
OG exemplary drawing
 
1. A dynamic rebinding method for a computing unit in heterogeneous computing clouds, the method comprising:
receiving a first computing request from a terminal;
generating a static FAT binary by compiling device binary codes for each of all types of heterogeneous accelerators based on the first computing request;
generating and storing global data including the device binary codes and libraries of all types of the heterogeneous accelerators;
generating a structure capable of dynamic binding by separating the device binary codes for each type of the heterogeneous accelerators from the static FAT binary;
allocating a first compute node and first heterogeneous accelerators based on the first computing request;
dynamically binding the computing unit including the device binary codes and the libraries for the allocated first heterogeneous accelerators;
transmitting the computing unit dynamically bound to the first compute node;
operating the allocated first heterogeneous accelerators based on the computing unit;
generating local caching data including the device binary codes and the libraries of all heterogeneous accelerators of the assigned first computer node excepting the assigned first heterogeneous accelerators from the stored global data;
transmitting the local caching data to the assigned first compute node;
receiving a second computing request from the terminal; and
determining an operation of the computing unit based on the second computing request,
wherein the determining of the operation of the computing unit comprises:
allocating a second compute node and second heterogeneous accelerators based on the second computing request, and
determining the operation of the computing unit based on whether the first compute node and the second compute node are identical and whether the first heterogeneous accelerators and the second heterogeneous accelerators are identical.