Christina Delimitrou is an Assistant Professor in the Electrical and Computer Engineering Department at Cornell University. She is a member of the Computer Systems Laboratory, where she works on improving the design and management of large-scale datacenters. In 2015-2016 she was a postdoctoral researcher and lecturer at Stanford University. Christina graduated from Stanford with a PhD in Electrical Engineering in 2015. As part of her PhD work, she built practical systems for cluster management and scheduling in warehouse-scale computers. She is the recipient of a Facebook Research Fellowship, a Stanford Graduate Fellowship, two ASPLOS best paper runner-up awards, an IISWC 2012 best paper nomination, and a 2014 IEEE Micro Top Picks. She has also earned an MS from Stanford (2011) and a diploma in Electrical and Computer Engineering from the National Technical University of Athens (2009).
Christina's primary interests are in designing resource-efficient datacenters and improving the way their resources are managed. She is also interested in hardware acceleration, applied data mining, performance monitoring and debugging, cloud security, and architecture and distributed systems broadly.
In fall 2016, I created a new graduate (PhD level) course on Datacenter Computing (ECE6960: Topics on Datacenter Computing). The course followed a mixed lecture-paper reading syllabus and covered the entire cloud computing system stack, from hardware architecture and accelerators, to datacenter OS and network systems, scheduling and cluster management, programming frameworks, and emerging cloud application designs. The students had to submit paper summaries for each paper we reviewed and participate in the in-class discussion. The course had a midterm that tested the contest covered in the lectures, and more importantly involved a large semester-long research project that students conducted in groups of 2 or 3. Several of these projects are continuing into the Spring'17 semester and have evolved into long-term research topics. The long-term goal for this course is to become a regular 5xxx level class, beginning in Spring 2018.
In spring 2017, I have taken a teaching leave.
- 2016. "Security Implications of Data Mining in Cloud Scheduling." IEEE Computer Architecture Letters 15 (2): 109-112. .
- 2016. "DRAF: A Low-Power DRAM-Based Reconfigurable Acceleration Fabric." Seoul June. .
- 2016. "Automatic Generation of Efficient Accelerators for Reconfigurable Hardware." Seoul June. .
- 2016. "HCloud: Resource-Efficient Provisioning in Shared Cloud Systems." Atlanta April (2nd Quarter/Spring). .
- 2014. "Quality-of-Service-Aware Scheduling in Heterogeneous Datacenters with Paragon." May. .
Selected Awards and Honors
- IEEE MICRO TOP PICKS AWARD FOR THE BEST PAPERS PUBLISHED IN 2016 IN COMPUTER ARCHITECTURE CONFERENCES, BASED ON NOVELTY AND LONG-TERM IMPACT 2016
- Facebook Research Fellowship (Facebook) 2014
- Best of Computer Architecture Letters (CAL) for 2013 \"The Net ix Challenge: Datacenter Edition" (Computer Architecture Letters) 2014
- IEEE Micro's Top Picks \"Paragon: QoS-Aware Scheduling for Heterogeneous Datacenters" (IEEE Micro's) 2014
- Best Poster Award \ "Improving Efficiency in Cloud Computing" (IAP-Stanford Cloud Workshop) 2013
- Diploma in Electrical and Computer Engineering (Electrical and Computer Engineering), National Technical University of Athens, 2009
- MS (Electrical Engineering), Stanford University, 2011
- Ph D (Electrical Engineering), Stanford University, 2015