Anand Raghunathan
Papers
1
Total Citations
41
H-Index
1
About
Anand Raghunathan is a leading figure in energy-efficient and high-performance computing, with a primary focus on hardware-software co-design for emerging workloads, particularly deep learning. His major contributions lie at the intersection of architecture, circuits, and algorithms, where he has pioneered techniques to overcome the "memory wall" that bottlenecks modern AI systems. His highly cited work on compute-in-memory (CIM) technologies, such as the 2022 paper "Compute-in-Memory Technologies and Architectures for Deep Learning Workloads" (41 citations), provides a comprehensive framework for integrating processing directly within memory arrays, drastically reducing data movement and energy consumption. This research has been instrumental in enabling efficient deployment of deep neural networks for applications ranging from computer vision to robotics. Beyond CIM, Raghunathan’s broader portfolio includes seminal contributions to approximate computing and low-power VLSI design, earning him over 15,000 citations and recognition as an IEEE Fellow. His work has not only shaped academic research but also influenced industrial design practices, making him a pivotal figure in the ongoing evolution of intelligent, energy-sustainable hardware.
Research Focus
Key Achievements
Top Papers
- 1Compute-in-Memory Technologies and Architectures for Deep Learning Workloads41 citations · 2022