Analog Compute-In-Memory (ACIM) using Non-Volatile Memory arrays can accelerate large language model (LLM) inference, combining large weight capacity with efficient compute and achieving energy and performance benefits. I will review IBM’s work on ACIM demos, addressing its unique device, circuit and architectural challenges and discussing future opportunities for LLM workloads.
This event is part of the Joint MIT AI Hardware Program and Microsystems Technology Laboratories Seminar Series.
Speaker
Pritish Narayanan
Dr. Pritish Narayanan is Principal Research Scientist at IBM Research, Almaden where he leads Analog AI Accelerator design and test efforts. He has worked across the hardware ecosystem from semiconductor fabrication to system software, and given several keynote, invited and tutorial talks.
Explore
Discovery helps explain why solid-state batteries often fail
Zach Winn | MIT News
New research could help prevent the formation of tiny seeds of lithium metal within the electrolyte, enabling batteries that charge faster and last longer.
Graphene can hold multiple states of superconductivity, a new study finds
Jennifer Chu | MIT News
What’s more, the superconducting states get stronger under conditions expected to kill them.
Improving the performance of high-power electronics
Adam Zewe | MIT News
By using a thin layer of diamond to manage excessive heat, researchers can boost the speed and energy-efficiency of next-generation wireless devices.