Hsieh Department Of Electrical Engineering






Notebook

Murali Annavaram

Professor
University of Southeren California


PhD Openings


If you are interested in pursuing a PhD in distributed machine learning, security/privacy of machine learning systems, graph analytics you are welcome to apply to USC's PhD program in CS department or CENG (ECE department) and list my name as one of the faculty you are interested in.

Bio


Murali Annavaram has been a faculty member in the Ming-Hsieh Department of Electrical Engineering at the University of Southern California from 2007. He held the Robert G. and Mary G. Lane Early Career Chair until 2017. He is currently a visiting faculty scientist at Facebook. Prior to USC, he was a senior research scientist at the Intel Microprocessor Research Labs from 2001 to 2007, and in 2007 he was a visiting researcher at the Nokia Research Center,





Current Research Interests


ML

Systems for Machine Learning
Security and Privacy of ML
Distributed ML

Comp Arch

Secure hardware
Systems for graph analytics
Near data processing

SFQ Tech

Superconducting CPUs
Superconducting Memory Technologies
Superconducting SoC

Education


Ph.D 2001

Ph.D, Computer Science Engineering
The University of Michigan, Ann Arbor, MI

M.S 1996

M.S, Computer Science Engineering
Colorado State University, Fort Collins, CO

B.Tech 1993

B.Tech, Computer Science Engineering
NIT, Warangal, India



Professional Experience


Present 2012

Professor
University of Southern California, CA

Present 2020

Faculty Scientist
Facebook, CA

2012 2007

Asst. Professor
University of Southern California, CA

2007 2007

Visiting Faculty Researcher
Nokia Research Center

2007 2001

Senior Research Scientist
Intel Corporation

1995 1995

Summer Intern
AT&T Bell Labs

1994 1993

Software Engineer
Wipro Systems



Honors and Awards


HPCA 2021 TPC Chair



ISCA 2018 General Chair



ISCA, Micro and HPCA hall of fames



Keynote speaker Sweedish Multicore symposium, IEEE IOLTS



                                           






Publications


GPUGuard: Mitigating Contention Based Side and Covert Channel Atacks on GPUs

Q. Xu, H. Naghibijouybari, S. Wang, N. Abu-Ghazaleh, M. Annavaram

Distributed Matrix Multiplication Using Speed Adaptive Coding

Krishna Narra, Mehrdad Kiamari, Salman Avestimehr, Murali Annavaram

Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge

Chaoyang He, Murali Annavaram, Salman Avestimehr

Collage Inference: Using Coded Redundancy for Lowering Latency Variation in Distributed Image Classification Systems

K. Narra, Z.Lin, S. Avestimehr, G. Ananthanarayanan, M. Annavaram

GraphSSD: Graph Semantics Aware SSD

Kiran Kumar Matam, Gunjae Koo, Haipeng Zha, Hung-Wei Tseng, Murali Annavaram