MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202541133555 A) filed by Nitte Meenakshi Institute Of Technology, Nitte; Dr Sowmya Madhavan; and Dr Rekha Phadke, Bangalore, Karnataka, on Dec. 30, 2025, for 'an ai-enabled system-on-chip architecture with policy-driven control of compute, memory, and power.'
Inventor(s) include Nitte Meenakshi Institute Technology, Nitte; Dr Sowmya Madhavan; and Dr Rekha Phadke.
The application for the patent was published on Jan. 9, under issue no. 02/2026.
According to the abstract released by the Intellectual Property India: "The invention relates to an AI-enabled System-on-Chip architecture incorporating intelligent resource management for dynamic control of computational, memory, and power resources across heterogeneous processing elements. The system comprises a plurality of heterogeneous processing elements including central processing unit cores, digital signal processors, and artificial intelligence accelerators interconnected through a high-performance interconnect fabric and supported by a hierarchical memory subsystem. A dedicated AI resource management and policy engine continuously monitors workload characteristics, system constraints, and performance metrics to dynamically orchestrate resource allocation, task scheduling, memory access patterns, data movement operations, and power management across the system. The present invention ensures improved resource utilization, enhanced power and energy efficiency, reduced memory bottlenecks, adaptability to diverse AI workloads, and reduced dependence on rigid reference design flows, making it suitable for edge, embedded, and high-performance computing platforms requiring intelligent and autonomous system-level optimization."
Disclaimer: Curated by HT Syndication.
