event

Ph.D. Proposal Oral Exam - Narasimha Vasishta Kidambi

Title:  Energy-Efficient Mixed-Signal CIM Architectures for Solving Integer-Constrained Least Squares Problems: Hardware Realization and Next-Generation Analog CIM Design

Committee: 

Dr. Mukhopadhyay, Advisor    

Dr. Datta, Chair

Dr. Yu

Media

No media selected

Summary

The objective of the proposed research is to develop energy-efficient mixed-signal compute-in-memory (CIM) architectures for solving integer-constrained least squares (ICLS) problems. The work demonstrates a 65 nm hardware implementation using 8T-SRAM and a stochastic Hopfield Neural Network solver. It further introduces a next-generation analog CIM design with improved DAC, accumulation, and ADC circuits to enhance computational accuracy and energy efficiency.

Details

Thursday
Oct 9 2025
03:00pm - 05:00pm

Location: Room 3126, Klaus

In campus calendar: No

Sidebar Content

No sidebar content

Groups

Status

  • Workflow status: Published
  • Created by: Daniela Staiculescu
  • Created: 10/07/2025
  • Modified By: Daniela Staiculescu
  • Modified: 10/07/2025

Related Links

Categories

Keywords

Target Audience