Seminars

View all Seminars  |  Download ICal for this event

Fast and Accurate Performance Analysis for Emerging Network-on-Chip (NoCs) with Emerging Workloads

Series: CSA Faculty Colloquium

Speaker: Prof. Sumit Kumar Mandal Assistant Professor Dept. of C.S.A IISc.

Date/Time: Sep 04 16:00:00

Location: CSA Auditorium, (Room No. 104, Ground Floor)

Abstract:
Performance analysis of Network-on-Chip (NoC) plays a crucial role in design space exploration of SoCs, but traditional cycle-accurate NoC simulation often limits the ability to explore a large design space efficiently due to their notoriously slow execution. Existing NoC performance analysis techniques assume certain micro-architectural details (e.g., a particular arbitration technique) to be homogeneous across the entire NoC. However, emerging NoC architectures may have hybrid arbitration across the NoC to ensure high throughput. Moreover, existing analytical model-based interconnect performance estimation techniques are not applicable for the interconnects of ML accelerators since they exhibit specific communication patterns due to their data flow accelerator-based compute structure. There exist several lightweight performance analysis techniques to reduce the design-space exploration time for NoCs, but all of them lack flexibility. In this work, we present an end-to-end fast and flexible NoC performance analysis framework based on analytical modeling grounded on queuing theory. Our proposed framework is more than 90% accurate in NoC performance estimation and three orders of magnitude faster than cycle accurate NoC simulation -- offering an efficient platform for rapid design space exploration and early-stage NoC performance optimization. Our proposed end-to-end framework has been consumed by one of the leading silicon industries and helped them to reduce translation time from >2 years to <2 months.

Speaker Bio:
Sumit K. Mandal is currently an assistant professor in Indian Institute of Science, Bangalore. He completed his PhD from University of Wisconsin-Madison. He received best paper award from ACM TODAES in 2020 and ESweek in 2022. He is one of the ACM India eminent speakers. He received INAE Young Engineer award. His research interests include energy efficient communication architecture for machine learning applications with emerging technologies and performance modeling of computer systems.