Hi, my name is Saturnino ("Sat") Garcia and I'm a Ph.D. candidate in the CSE department at UC San Diego where I am advised by Michael Taylor. My research is in the area of program analysis, compilers, and parallel computing. I will graduate in June 2012 and am currently searching for academic positions.

Outside of research, I have been active in many service activities. I previously served as the coordinator for the CSE Graduate Student Association and was a founding member of the Jacobs Graduate Student Council. I also enjoy mentoring. I am proud to have mentored a CRA Outstanding Undergraduate Researcher honorable mention recipient and have served as a CSE teaching assistant mentor on numerous occasions.

I received my M.S. in Computer Science in 2007 (from UCSD). Before that, I graduated from Drexel University in 2005 with a B.S. in Computer Engineering. While there, I worked with Drs. Moshe Kam and Kapil Dandekar. Going even further back, I was born and raised in the small town of Willard, Ohio. People often inquire into the origin of my name. I shared my name with my father, a 1st generation Mexican-American whose purchase of a Tandy computer set me on my path to computer science.

My current research revolves around using dynamic program analyses to aid in the design and programming of multicore processors. The following list is a sample of the projects I have been involved with.

• Kremlin: Kremlin aims to answer the question, "What parts of this program should I spent time parallelizing?". In this sense, it is like gprof, but for parallelization. Kremlin profiles a serial program and tells the programmer not only what regions should be parallelized, but also the order in which they should be parallelized to maximize the return on their effort.
• Kismet: Kismet helps mitigate the risk of parallel software engineering by answering the question, "What is the best performance I can expect if I parallelize this program?" Kismet profiles serial programs and reports the upperbound on parallel speedup based on the program's inherent parallelism and the system it will be running on.
• GreenDroid: GreenDroid is a mobile applications processor designed to dramatically reduce the energy comsumption in smartphones. It employs specialized processing cores that target key portions of the Android platform.

I previously worked in the area of nanoelectronic architectures and DNA self-assembly with Alex Orailoglu.

Selected Publications

• [New]S. Garcia, D. Jeon, C. Louie, M.B. Taylor: Kremlin: Rethinking and Rebooting gprof for the Multicore Age. Proceedings of ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI) 2011. [pdf]
• S. Garcia, D. Jeon, C. Louie, S. Kota Venkata, M.B. Taylor: Bridging the Parallelization Gap: Automating Parallelism Discovery and Planning. USENIX Workshop on Hot Topics in Parallelism (HotPar) 2010. [pdf]
• S. Garcia and A. Orailoglu: Making DNA Self-Assembly Error Proof: Attaining Small Growth Error Rates Through Embedded Information Redundancy. Proceedings of Design, Automation, and Test in Europe (DATE) 2009. pp. 898-901 [pdf]
• S. Garcia and A. Orailoglu: Online Test and Fault-Tolerance for Nanoelectronic Programmable Logic Arrays. Proceedings of the International Symposium on Nanoelectronic Architectures (NANOARCH) 2008. pp. 8-15 [pdf]

Other Publications

• [New] D. Jeon, S. Garcia, C. Louie, M.B. Taylor: Kismet: Parallel Speedup Estimates for Serial Programs. To appear in Proceedings of ACM Conference on Object Oriented Programming Systems Languages and Applications (OOPSLA) 2011. [pdf]
• [New] D. Jeon, S. Garcia, C. Louie, M.B. Taylor: Parkour: Parallel Speedup Estimates for Serial Programs. USENIX Workshop on Hot Topics in Parallelism (HotPar) 2011. [pdf]
• [New] N. Goulding-Hotta, J. Sampson, G. Venkatesh, S. Garcia, J. Auricchio, P.C. Huang, M. Arora, S. Nath, V. Bhatt, J. Babb, S. Swanson, M.B. Taylor: The GreenDroid Mobile Application Processor: An Architecture for Silicon's Dark Future. IEEE Micro Magazine, March/April 2011.
• D. Jeon, S. Garcia, C. Louie, S. Kota Venkata, M.B. Taylor: Kremlin: Like gprof, but for Parallelization. Proceedings of ACM Symposium on Principles and Practice of Parallel Programming (PPoPP) 2011. [paper pdf, poster pdf]. Winner of "Best Student Poster" Award!
• J. Sampson, G. Venkatesh, N. Goulding-Hotta, S. Garcia, S. Swanson, M.B. Taylor: Efficient Complex Operators for Irregular Codes. Proceedings of Int'l Symposium on High-Performance Computer Architecture (HPCA) 2011. [pdf]
• G. Venkatesh, J. Sampson, N. Goulding, S. Garcia, V. Bryksin, J. Lugo-Martinez, S. Swanson, M.B. Taylor: Conservation cores: reducing the energy of mature computations. Proceedings on Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2010. pp. 205-218 [pdf]
• S. Kota Venkata, I. Ahn, D. Jeon, A. Gupta, C. Louie, S. Garcia, S. Belongie, M.B. Taylor: SD-VBS: The San Diego Vision Benchmark Suite. Proceedings on IEEE Int'l Symposium on Workload Characteristics (IISWC) 2009. pp. 55-64 [pdf]
• G. Anderson, L. Urbano, G. Naik, D. Dorsey, A. Mroczkowski, D. Artz, N. Morizio, A. Burnheimer, K. Malfettone, D. Lapadat, E. Sultanik, S. Garcia, M. Peysakhov, W.C. Regli, M. Kam: A Secure Wireless Agent-based Testbed. Proceedings for IEEE Int'l Information Assurance Workshop (IWIA) 2004. pp. 19-32

Teaching Experience

• Intro to Computer Architecture (CSE 141): Su11
• Project in Computer Architecture (CSE 141L): Su11

• Graduate Computer Architecture (CSE 240A): Fa06, Fa07
• Intro to Computer Architecture (CSE 141): Wi07, Sp07, Su07, Wi08
• Project in Computer Architecture (CSE 141L): Sp08, Fa08, Sp11
• Operating Systems (CSE 120): Su08
• Discrete Math (CSE 20): Su08
• Components and Design Techniques for Digital Systems (CSE 140): Su07
• Systems II (TDEC 222 at Drexel University)