-
公开(公告)号:US20200250003A1
公开(公告)日:2020-08-06
申请号:US16652038
申请日:2018-06-29
申请人: Intel Corporation
发明人: Shao-Wen Yang , Yen-Kuang Chen , Ragaad Mohammed Irsehid Altarawneh , Juan Pablo Munoz Chiabrando , Siew Wen Chin , Kushal Datta , Subramanya R. Dulloor , Julio C. Zamora Esquivel , Omar Ulises Florez Choque , Vishakha Gupta , Scott D. Hahn , Rameshkumar Illikkal , Nilesh Kumar Jain , Siti Khairuni Amalina Kamarol , Anil S. Keshavamurthy , Heng Kar Lau , Jonathan A. Lefman , Yiting Liao , Michael G. Millsap , Ibrahima J. Ndiour , Luis Carlos Maria Remis , Addicam V. Sanjay , Usman Sarwar , Eve M. Schooler , Ned M. Smith , Vallabhajosyula S. Somayazulu , Christina R. Strong , Omesh Tickoo , Srenivas Varadarajan , Jesús A. Cruz Vargas , Hassnaa Moustafa , Arun Raghunath , Katalin Klara Bartfai-Walcott , Maruti Gupta Hyde , Deepak S. Vembar , Jessica McCarthy
摘要: In one embodiment, an apparatus comprises a processor to: identify a workload comprising a plurality of tasks; generate a workload graph based on the workload, wherein the workload graph comprises information associated with the plurality of tasks; identify a device connectivity graph, wherein the device connectivity graph comprises device connectivity information associated with a plurality of processing devices; identify a privacy policy associated with the workload; identify privacy level information associated with the plurality of processing devices; identify a privacy constraint based on the privacy policy and the privacy level information; and determine a workload schedule, wherein the workload schedule comprises a mapping of the workload onto the plurality of processing devices, and wherein the workload schedule is determined based on the privacy constraint, the workload graph, and the device connectivity graph. The apparatus further comprises a communication interface to send the workload schedule to the plurality of processing devices.
-
公开(公告)号:US20220108054A1
公开(公告)日:2022-04-07
申请号:US17552955
申请日:2021-12-16
申请人: Intel Corporation
IPC分类号: G06F30/27
摘要: An architecture search system evaluates a search space of neural network and hardware architectures with a plurality of candidate controllers. Each controller attempts to identify an optimized architecture using a different optimization algorithm. To identify a controller for the search space, the architecture search system samples subspaces of the search space having a portion of the neural network search space and a portion of the hardware search space. For each subspace, candidate controllers are scored with respect to the optimized design determined by the respective candidate controllers. Using the scores for the various candidate controllers across the sampled subspaces, a controller is selected to optimize the overall network architecture search space.
-