公开(公告)号：US20230244525A1

公开(公告)日：2023-08-03

申请号：US18160209

申请日：2023-01-26

Applicant: Intel Corporation

Inventor： Ningxin Hu ,  Feng Dai ,  Junyong Ding ,  Junwei Fu ,  Mohammad Haghighat ,  Mousumi Hazra ,  Mingming Xu ,  Min Zhang

IPC: G06F9/48 ,  G06N5/022

CPC classification number: G06F9/4881 ,  G06N5/022

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed for an XPU-aware dynamic compute scheduling framework. These improve processing of cloud client application pipelines across XPU devices by incorporating memory, machine readable instructions and processor circuitry to execute the functions of: trace an execution of an input model by a graph tracer; build a compute graph based on the trace of the input model; communicate an operational parameter; create a first XPU device assignment to recommend an XPU device to use based on at least one provisioned policy of a system-wide XPU selection policy provider; update the compute graph based on the first XPU device assignment; and send the first XPU device assignment to the devices through a dispatch command.