I am a Research Scientist at Facebook.
I was a PhD candidate (ABD status, having completed all requirements but my dissertation) in Electrical and Computer Engineering at Carnegie Mellon University in Pittsburgh Pennsylvania, where I was advised by Onur Mutlu. I was named a Google PhD Fellow in 2015 as well as a John and Claire Bertucci Graduate Fellow in 2013. My research focused on designing reliable, high-performance, and energy-efficient memory architectures.
I received my BS at the University of California at Los Angeles in Computer Science in 2010 and my MS at Carnegie Mellon University in Electrical and Computer Engineering in 2014. I interned at Google during the summer of 2014, where I worked with Partha Ranganathan, Jichuan Chang, Kim Hazelwood, Joel Coburn, and Rama Govindaraju. I interned at Facebook from 2013 to 2014, where I worked with Qiang Wu and Sanjeev Kumar, and again from the fall of 2014, where I worked with Qiang Wu and Yee Jiun Song. I also interned at Hewlett-Packard Labs in Palo Alto, California from 2006 to 2012 under the guidance of Rich Friedrich, Partha Ranganathan, Mehul Shah, and Jichuan Chang.
Carnegie Mellon University
Electrical and Computer Engineering
CIC Building 4th Floor
c/o Olivia Vadnais
4720 Forbes Ave, Ste 410
Pittsburgh, PA 15213 USA
I research reliable, high-performance, and energy-efficient system designs. Below are a selection of my publications.
Tuomas Pelkonen, Scott Franklin, Justin Teller, Paul Cavallaro, Qi Huang, Justin Meza, and Kaushik Veeraraghavan: Gorilla: A Fast, Scalable, In-Memory Time Series Database. VLDB, 2015.
Justin Meza, Qiang Wu, Sanjeev Kumar, and Onur Mutlu: A Large-Scale Study of Flash Memory Errors in the Field. SIGMETRICS, 2015.
Featured on Hacker News — "A Large-Scale Study of Flash Memory Failures in the Field"
Featured on ZDNet — "Facebook's SSD findings: Failure, fatigue and the data center"
— "The case against SSDs"
Featured on The Register — "Facebook SSD failure study pinpoints mid-life burnout rate trough"
Featured on TechSpot — "Researchers publish first large-scale, in-field SSD reliability report"
Featured on The Tech Report — "Facebook SSD reliability study shows early burnouts"
Featured on Digital Trends — "Want your SSD to last? Keep it cool, says new study from Facebook"
Featured on Tech Week Europe — "Facebook Study Into SSDs Finds 'Several Distinct Failure Periods'"
Featured on Silicon.fr — "Au cœur des pannes de SSD des datacenters de Facebook"
Featured on TechNews.bg — "SSD грешат често при интензивен запис"
Featured on HWSW — "Mitől függ egy SSD élettartama?"
Featured on StorageServers — "Facebook confirms that SSDs suffer from fatigue and temperature!"
Featured on TechRevu — "Facebook's SSD Findings: Failure, Fatigue, And The Data Center"
Featured on StorageNewsletter — "Large-Scale Study of SSD Failures"
Tweeted by Symantec
Discussion on Wechat — "Facebook闪存失效大规模研究揭示五大不为人知的现象"
Justin Meza, Qiang Wu, Sanjeev Kumar, and Onur Mutlu: Revisiting Memory Errors in Large-Scale Production Data Centers: Analysis and Modeling of New Trends from the Field. DSN, 2015.
Onur Mutlu, Justin Meza, and Lavanya Subramanian: The Main Memory System: Challenges and Opportunities. Communications of the Korean Institute of Information Scientists and Engineers, 2015.
HanBin Yoon, Justin Meza, Naveen Muralimanohar, Norman P. Jouppi, and Onur Mutlu: Efficient Data Mapping and Buffering Techniques for Multi-Level Cell Phase-Change Memories. ACM Transactions on Architecture and Code Optimizations, 2014.
Best Presentation Award at HiPEAC 2015
Yixin Luo, Sriram Govindan, Bikash Sharma, Mark Santaniello, Justin Meza, Aman Kansal, Jie Liu, Badriddine Khessib, Kushagra Vaid, and Onur Mutlu: Characterizing Application Memory Error Vulnerability to Optimize Data Center Cost via Heterogeneous-Reliability Memory. International Conference on Dependable Systems and Networks, 2014.
Featured on ZDNet — "How good does memory need to be?"
Justin Meza, Yixin Luo, Samira Khan, Jishen Zhao, Yuan Xie, and Onur Mutlu: A Case for Efficient Hardware/Software Cooperative Management of Storage and Memory. Workshop on Energy-Efficient Design, 2013.
HanBin Yoon, Justin Meza, Rachata Ausavarungnirun, Rachael Harding, and Onur Mutlu: Row Buffer Locality-Aware Caching Policies for Hybrid Memories. International Conference on Computer Design, 2012.
Best Paper Award in Computer Systems and Applications Track
Justin Meza, Jing Li, and Onur Mutlu: A Case for Small Row Buffers in Non-Volatile Main Memories. International Conference on Computer Design, 2012, Poster Session.
Justin Meza, Jing Li, and Onur Mutlu: Evaluating Row Buffer Locality in Future Non-Volatile Main Memories. SAFARI Technical Report, 2012.
Justin Meza, Jichuan Chang, HanBin Yoon, Onur Mutlu, and Parthasarathy Ranganathan: Enabling Efficient and Scalable Hybrid Memories Using Fine-Granularity DRAM Cache Management. Computer Architecture Letters, 2012.
Jichuan Chang, Justin Meza, Parthasarathy Ranganathan, Cullen Bash, and Amip Shah: Totally Green: Evaluating and Designing Servers for Lifecycle Environmental Impact. International Conference on Architectural Support for Programming Languages and Operating Systems, 2012.
Pick of the Month in December 2012 IEEE Sustainable Computing Register
John L. Hennessy and David A. Patterson: Chapter 6 Exercises in Computer Architecture: A Quantitative Approach. Fifth Edition, Elsevier, 2012.
HanBin Yoon, Justin Meza, Rachata Ausavarungnirun, Rachael Harding, and Onur Mutlu: Row Buffer Locality-Aware Data Placement in Hybrid Memories. SAFARI Technical Report, 2011.
Jichuan Chang, Justin Meza, Parthasarathy Ranganathan, Cullen Bash, and Amip Shah: Green Server Design: Beyond Operational Energy to Sustainability. Workshop on Power-Aware Computing and Systems, 2010.
Justin Meza, Rocky Shih, Amip Shah, Parthasarathy Ranganathan, Jichuan Chang, and Cullen Bash: Lifecycle-Based Data Center Design. ASME International Mechanical Engineering Congress and Exposition, 2010.
Justin Meza, Mehul A. Shah, Parthasarathy Ranganathan, Mike Fitzner, and Judson Veazey: Tracking the Power in an Enterprise Decision Support System. International Symposium on Low Power Electronics and Design, 2009.
Stavros Harizopoulos, Mehul A. Shah, Justin Meza, and Parthasarathy Ranganathan. Energy Efficiency: The New Holy Grail of Data Management Systems Research. Conference on Innovative Data Systems, 2009.
Suzanne Rivoire, Mehul A. Shah, Parthasarathy Ranganathan, Christos Kozyrakis, and Justin Meza: Models and Metrics to Enable Energy-Efficiency Optimizations. IEEE Computer, Volume 40, Issue 12, 2007.
Sometimes, when I work at a company, I submit patent applications for my inventions. Below is a list of the patents for which I am an inventor.
I work on a variety of open- and closed-sourced projects (the open source projects I contribute to can be found on my GitHub). Below is a selection of the projects I contribute to.
LOLCODE — I wrote and maintain the most widely-used interpreter for the LOLCODE esoteric programming langugage. I now maintain the LOLCODE specification as well as its website.
inet — inet is a simple TCP/UDP communication library written in C. It abstracts away the icky socket and protocal interfaces into a more declarative host-based model of communication.
triad — triad is an implementation of the Chord peer-to-peer lookup service in C. It maps 64b integers to IP addresses and can be used as the underlying service-discovery layer for a distributed system.
My full name is Justin James Meza (my last name is pronounced "meɪzʌ" in IPA) and I'm of Caucasian and Mexican descent. I grew up near Los Angeles, California, although I'm currently traveling around, working toward completing my PhD at CMU. My Chinese name is 梅杰士.
I’m an avid music fan and when I have free time, I enjoy playing the electric bass guitar and keyboard. I also enjoy art (mainly oil paints and gouache), reading, writing, and, of course, programming. I run on Verve and Philz coffee. I have a personal blog, but I only rarely post on it.
These are some generally useful books that I like to keep within arm's reach:
These are the books that I am currently reading: