US 12,360,818 B1
System and method for multi-vendor artificial intelligence workload optimization and resource allocation in cloud environments
Rajesh Chainani, Singapore (SG); Simon Rizkallah, Singapore (SG); and Ramesh R, Singapore (SG)
Assigned to HybridAI Pte Ltd., Singapore (SG)
Filed by HybridAI Pte Ltd., Singapore (SG)
Filed on Aug. 14, 2024, as Appl. No. 18/804,529.
Int. Cl. G06F 9/50 (2006.01)
CPC G06F 9/5044 (2013.01) [G06F 9/505 (2013.01); G06F 2209/501 (2013.01); G06F 2209/5019 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for recommending and optimizing artificial intelligence (AI) workload placement in a multi-vendor cloud environment, the system comprising:
a server comprising at least one processor configured to:
access input datasets stored in a datacentre associated with an AI workload;
determine one or more type of processing units associated with one or more manufacturers for the input datasets based on a set of predefined criteria;
determine a count of processing units required for processing the input datasets based on the determined one or more types of processing units;
access a multi-vendor processing unit performance database storing performance data for the determined one or more types of processing units from the one or more manufacturers;
utilize a deep learning model to predict infrastructure requirements for the AI workload;
generate recommendations for an optimal processing unit configuration based on the multi-vendor processing unit performance database and the predicted infrastructure requirements;
automatically allocate processing unit resources from the one or more manufacturers based on the recommended optimal processing unit configuration; and
generate data for display on a user interface dashboard presenting information about the one or more manufacturers, the determined one or more types of processing units, the recommended optimal processing unit configuration, and real-time performance metrics of allocated processing unit resources.