Research

This research direction aims at developing future computing systems based on emerging hardware. These computing systems promise substantial (orders of magnitude) improvements in throughput and energy-efficiency. The high-level idea of this research direction is to leverage emerging non-volatile memories (NVMs) and perform energy-efficient processing in-memory (PIM).

Relevant publications:

1. M Rashed, S. Thijssen, D. Simon SK Jha, and R Ewetz, “Execution Sequence Optimization for Processing In-Memory using Parallel Data Preparation," in 61st Design Automation Conference (DAC), 2024
2. M Rashed, S. Thijssen, F Yao, SK Jha, and R Ewetz, “STREAM: Towards READ-based In-Memory Computing for Streaming Based Processing for Data-Intensive Applications," in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2023
3. M Rashed, SK Jha, and R Ewetz, “Discovering the In-Memory Kernels of 3D Dot-Product Engines," in 28th Asia and South Pacific Design Automation Conference (ASP-DAC), 2023
4. M Rashed, SK Jha, and R Ewetz, “Logic Synthesis for Digital In-Memory Computing," in 41st International Conference On Computer Aided Design (ICCAD), 2022 (Best Paper Candidate)
5. M Rashed, SK Jha, F Yao and R Ewetz, “Hybrid Digital-Digital In-Memory Computing," in 25th Design Automation and Test in Europe Conference (DATE), 2022
6. M Rashed, S. Thijssen, F Yao, SK Jha, and R Ewetz, “STREAM: Towards READ-based In-Memory Computing for Streaming based Data Processing," in 27th Asia and South Pacific Design Automation Conference (ASP-DAC), 2022
7. M Rashed, SK Jha, and R Ewetz, “Hybrid Anlog-Digital In-Memory Computing," in 40th International Conference On Computer Aided Design (ICCAD), 2021

AI models have surpassed human-level capabilities for several cognitive tasks such as image classification and object detection. However, it is a daunting task to execute large AI models on traditional computing systems. The goal of this research direction is to utilize emerging computing paradigms to accelerate AI applications.

Relevant publications:

1. M Rashed, S. Thijssen, SK Jha, and R Ewetz, “Automated Synthesis for In-Memory Computing," in 42nd International Conference On Computer Aided Design (ICCAD), 2023
2. M Rashed, S. Thijssen, SK Jha, H Zheng, and R Ewetz, “Path-based Processing using In-Memory Systolic Arrays for Accelerating Data-Intensive Applications," in 42nd International Conference On Computer Aided Design (ICCAD), 2023
3. M Rashed, A Awad, SK Jha, and R Ewetz, “Towards Resilient Analog In-Memory Deep Learning via Data Layout Re-Organization," in 59th Design Automation Conference (DAC), 2022 (Selected as a Publicity Paper)