Carnegie Mellon University

Diana Marculescu

Diana Marculescu

David Edward Schramm Professor, Electrical and Computer Engineering

  • 2124 Hamerschlag Hall
  • 412-268-1167
Address 5000 Forbes Avenue
Pittsburgh, PA 15213


Diana Marculescu received the Dipl.Ing. degree in computer science from the Polytechnic University of Bucharest, Bucharest, Romania, and the Ph.D. degree in computer engineering from the University of Southern California, Los Angeles, CA, in 1991 and 1998, respectively. She is the David Edward Schramm Professor in the Department of Electrical and Computer Engineering, Carnegie Mellon University. Dr. Marculescu has served as Associate Department Head for Academic Affairs (2014-2018) and is the Founding Director for the College of Engineering Center for Faculty Success at CMU. Her current research interests include energy- and reliability-aware computing, hardware aware machine learning applications, and computing for sustainability and life science applications. 

Dr. Marculescu was a recipient of the National Science Foundation Faculty Career Award from 2000 to 2004, the ACM SIGDA Technical Leadership Award in 2003, the Carnegie Institute of Technology George Tallman Ladd Research Award in 2004, and Best Paper Awards at the IEEE Asia and South Pacific Design Automation Conference (2005), IEEE International Conference on Computer Design (2008), International Symposium on Quality Electronic Design (2009), ACM Great Lakes Symposium on VLSI (2017), and IEEE Trans. on Very Large Scale Integrated (VLSI) Systems (2011, 2018). She was an IEEE Circuits and Systems Society Distinguished Lecturer from 2004 to 2005 and the Chair of the Association for Computing Machinery (ACM) Special Interest Group on Design Automation from 2005 to 2009. She is an IEEE Fellow and an ACM Distinguished Scientist. 

Dr. Marculescu served as chair for several conferences and symposia, and as editor for multiple journals. She was the Technical Program Chair of the ACM/IEEE International Workshop on Logic and Synthesis in 2004, the ACM/IEEE International Symposium on Low Power Electronics and Design in 2006, and the General Chair of the same symposia in 2003 and 2007, respectively. Dr. Marculescu also served as the Technical Program Chair of the IEEE/ACM International Symposium on Networks-on-Chip in 2012, the IEEE/ACM International Conference on Computer-Aided Design in 2013, and as the General Chair for the same conferences in 2015. She has served as an Associate Editor for the IEEE Transactions on VLSI Systems, the IEEE Transactions on Computers, the IEEE Computer Architecture Letters, and the ACM Transactions on Design Automation of Electronic Systems. Dr. Marculescu was an ELATE Fellow (2013-2014), and the recipient of an Australian Research Council Future Fellowship (2013-2017) and the Marie R. Pistilli Women in EDA Achievement Award (2014).


Ph.D., 1998 
Computer Engineering 
University of Southern California

MS, 1991
Computer Science 
Polytechnic Institute of Bucharest, Romania


Hardware-Aware Machine Learning

While the holy grail for judging the quality of a Machine Learning (ML) model is its serving accuracy, and only recently its resource usage, neither of these metrics translate directly to energy efficiency, runtime, or mobile device battery lifetime. Our research focuses on developing accurate, platform‐specific power and runtime models for ML models and new hardware-aware ML model (co-)design methodologies that allow machine learners and hardware designers to identify the most accurate model configuration that satisfies given hardware constraints.

Machine Learning for Efficient Computing

Power dissipation is a critical design concern for systems spanning the edge to cloud continuum, driven by increased levels of system complexity and wide spread use of mobile applications. Our work relies on statistical learning approaches for managing power and other resources in large scale computing systems and implementing computational kernels for on-chip learning in an energy efficient manner. For edge and mobile devices, our research looks into lightweight on-chip implementation of statistical learning approaches.

Computing for Social and Life Science Applications

We live in a world governed by highly complex interconnected systems, spanning different dynamics and timescales. Our research develops models and computing systems that enable running these models in an efficient manner to produce meaningful analyses. Examples of applications include scalable and efficient approaches for modeling and analysis of river networks in the context of small footprint power generation and distribution. In the field of systems biology, we have demonstrated the effectiveness of hardware emulation for accelerating analysis of large cell signaling networks.


  • Sustainability- and energy-aware modeling and optimization
  • Energy-aware machine learning
  • Fast and accurate power modeling, estimation, optimization for multi-core systems
  • Modeling and optimization for sustainability in computing and renewable energy
  • Discrete modeling and analysis of non-silicon networks
  • Logical models and hardware emulation for efficient nonlinear system analysis
  • Electronic textiles and smart fabrics
  • Reliability- and variability-aware system design
  • Modeling, analysis, and optimization of soft-error rate in large digital circuits
  • Microarchitecture to system level design variability modeling and mitigation
  • 3D integration and impact of process variations

Related news

Tuesday, May 29, 2018

“Circling the block” may soon be circling the drain

A team of ECE Ph.D. students placed third in the Siemens FutureMakers Challenge, and plan to continue development of their app which could forever change the parking landscape.
Wednesday, May 16, 2018

ECE Team wins IEEE Transactions on Very Large Scale Integration Systems Best Paper Award

Professors Radu Marculescu and Diana Marculescu, post-doctoral researcher Ryan Kim, and Ph.D. student Zhuo Chen have been awarded the 2018 IEEE Transactions on Very Large Scale Integration Systems Prize Paper Award from the Circuits and Systems Society (CAS) of the Institute of Electrical and Electronics Engineers (IEEE).
Monday, April 16, 2018

Marculescu receives Celebration of Education Award

Barbara Lazarus advocated for graduate students and young faculty, a quality that Electrical and Computer Engineering Professor Diana Marculescu boldly displays. She has advised and mentored 61 graduate students. Through mentoring, she hopes to empower her mentees to define their path as professionals and researchers.
Monday, June 05, 2017

Marculescu and O’Hallaron receive faculty awards

Two ECE professors have received College of Engineering Faculty Awards, which are given to faculty in recognition of their academic and research achievements. Each award has different criteria and requirements.
Thursday, May 18, 2017

ECE team wins Best Paper Award at Great Lakes Symposium

ECE’s Ruizhou Ding, Zeye (Dexter) Liu, Rongye Shi, Diana Marculescu, and Shawn Blanton recently received the Best Paper Award at the 27th edition of the Association for Computing Machinery’s (ACM) Great Lakes Symposium on Very Large Scale Integration (GLSVLSI).
Friday, September 09, 2016


Diana Marculescu and Radu Marculescu have been awarded an NSF grant to develop a new paradigm for Big Data computing.
Thursday, August 18, 2016

Kovačević and Marculescu receive professorships

As the highest academic award a university can bestow on a faculty member, professorships are reserved for those who show continued contributions in their field.
Friday, April 01, 2016

CMU joins national network for manufacturing innovation to support research on functional fabrics

The U.S. Department of Defense has tapped Carnegie Mellon University as a partner in a $75 million national research institute that will support American textile manufacturers in bringing sophisticated new materials and textiles to the marketplace.
Tuesday, March 29, 2016

Internet on a chip: researchers step towards energy-efficient multicore chips

In their recent paper, Wireless NoC for VFI-enabled multicore chip design: performance evaluation and design trade-offs, researchers from Carnegie Mellon’s Department of Electrical and Computer Engineering and Washington State University identify a new approach for enabling energy-efficient multicore systems.