Home

I am an assistant professor in the Department of Computer Science and Engineering at the University of Michigan. I am affiliated with Advanced Computer Architecture Lab (ACAL). My research focuses on architecture, compiler and runtime systems, especially such systems for warehouse scale datacenters.

Check out my publications and my research group (the Clarity Lab)  to find out more about my research. Contact me at lingjia at eecs.umich.edu.

 

Ph.D. Students
Yunqi Zhang
Michael Laurenzano
Chang-Hong Hsu
Parker Hill
Ram Kannan
Johann Hauswald
Ravi Mukundrajan

News:

Check out the DjiNN video on youtube

Come to the Sirius Tutorial at ASPLOS ’15!

Sirius: An Open End-to-End Voice and Vision Personal Assistant and Its Implications for Future Warehouse Scale Computers” is accepted for ASPLOS ’15!

Mike and Yunqi did a fantastic job presenting at MICRO ’14.

Adrenaline: Pinpointing and Reining in Tail Queries with Quick Voltage Boosting” and “Octopus-Man: QoS-Driven Task Management for Heterogeneous Multicore in Warehouse Scale Computers” are accepted at HPCA ’15!

Protean Code: Achieving Near-Free Online Code Transformations for Warehouse Scale Computers” and “SMiTe: Precise QoS Prediction on Real System SMT Processors to Improve Utilization in Warehouse Scale Computers” are accepted at MICRO ’14!

Check out our short video on Protean Code.

PC co-chair of IISWC ’14.

The Register reports our work published at HPCA ’13 (also covered in ACM tech news): Link

Will join Google Mountain View as visiting faculty this summer!

Both “Bubble-PiPo” and “Heterogeneity in “Homogeneous” Warehouse-Scale Computers” accepted for ISCA ’13!

“ReQoS: Reactive Static/Dynamic Compilation for QoS in Warehouse Scale Computers” accepted for ASPLOS ’13!

CGO’12 paper “Compiling For Niceness: Mitigating Contention for QoS in Warehouse Scale Computers” won best paper award !!

ISCA’11 paper “The Impact of Memory Subsystem Resource Sharing on Datacenter Applications” selected as one of Excellent Papers for 2011 by Google! Check out the Google Research blog post and detailed description .

Bubble-Up paper selected for IEEE MICRO Top Picks 2012!

Recent Paper selected as “Spotlight Feature” of IEEE Computer Architecture Letter! Also selected as HPCA 2012 “Best Papers from Computer Architecture Letters!”

Publications

2015

[ISCA ’15] Djinn: DNN as a Service and Its Implications for Future Warehouse Scale Computers. Johann Hauswald, Yiping Kang, Michael A. Laurenzano, Quan Chen, Cheng Li, Ronald Dreslinski, Trevor Mudge, Jason Mars, and Lingjia Tang. In Proceedings of the 42nd Annual International Symposium on Computer Architecture (ISCA), ISCA ’15, New York, NY, USA, 2015. ACM. Acceptance Rate: 19% 
 pdf slide lightning

[ISCA ’15] Thermal Time Shifting: Leveraging Phase Change Materials to Reduce Cooling Costs in Warehouse-Scale Computers. Matt Skach, Manish Arora, Chang-Hong Hsu, Qi Li, Dean Tullsen, Lingjia Tang, and Jason Mars. In Proceedings of the 42nd Annual International Symposium on Computer Architecture (ISCA), ISCA ’15, New York, NY, USA, 2015. ACM. Acceptance Rate: 19% 
 pdf slide

[ASPLOS ’15] Sirius: An Open End-to-End Voice and Vision Personal Assistant and Its Implications for Future Warehouse Scale Computers. Johann Hauswald, Yunqi Zhang, Michael A. Laurenzano, Cheng Li, Austin Rovinski, Arjun Khurana, Ron Dreslinski, Vinicius Petrucci, Trevor Mudge, Lingjia Tang, and Jason Mars. In Proceedings of the Twentieth International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), New York, NY, USA, 2015. ACM. Acceptance Rate: 17% pdf slide

[HPCA’15] Adrenaline: Pinpointing and Reining in Tail Queries with Quick Voltage Boosting. Chang-Hong Hsu, Yunqi Zhang, Michael A. Laurenzano, David Meisner, Thomas Wenisch, Lingjia Tang, Jason Mars, and Ron Dreslinski. In Proceedings of the 2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA), Washington, DC, USA, 2015. IEEE Computer Society. Acceptance Rate: 22% pdf slide

[HPCA’15] Octopus-Man: QoS-Driven Task Management for Heterogeneous Multicore in Warehouse Scale Computers. Vinicius Petrucci, Michael A. Laurenzano, Yunqi Zhang, John Doherty, Daniel Mosse, Jason Mars, and Lingjia Tang. In Proceedings of the 2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA), Washington, DC, USA, 2015. IEEE Computer Society. Acceptance Rate: 22% pdf slide

2014

[MICRO ’14] Protean Code: Achieving Near-Free Online Code Transformations for Warehouse Scale Computers.  Michael Laurenzano, Yunqi Zhang, Lingjia Tang, and Jason Mars. In Proceedings of the 47th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO-47, New York, NY, USA, 2014. ACM. Acceptance Rate: 19% pdf slides

[MICRO ’14] SMiTe: Precise QoS Prediction on Real System SMT Processors to Improve Utilization in Warehouse Scale Computers. Yunqi Zhang, Michael Laurenzano, Jason Mars, and Lingjia Tang. In Proceedings of the 47th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO-47, New York, NY, USA, 2014. ACM. Acceptance Rate: 19% pdf slides lightening

[USENIX ATC ’14] HaPPy: Hyperthread-aware Power Profiling Dynamically   Yan Zhai, Xiao Zhang, Stephane Eranian, Lingjia Tang, and Jason Mars. In Proceedings of the 2014 USENIX Conference on USENIX Annual Technical Conference (Usenix ATC), USENIX ATC’14, pages 211-218, Berkeley, CA, USA, 2014. USENIX Association. Acceptance Rate: 15% 
 pdf

[Scientific Computing] Enabling fair pricing on high performance computer systems with node sharing   Alex D. Breslow, Ananta Tiwari, Martin Schulz, Laura Carrington, Lingjia Tang, and Jason Mars. Scientific Programming, 22(2):59-74, 2014. 
 
 .

2013

[ISCA ’13] Bubble-Flux: Precise Online QoS Management for Increased Utilization in Warehouse Scale Computers Hailong Yang, Alex Breslow, Jason Mars and Lingjia Tang. International Symposium on Computer Architecture 2013. pdf slides

[ISCA ’13]  Heterogeneity in “Homogeneous” Warehouse-Scale Computers: A Production Scale Investigation and Design  Jason Mars, Lingjia Tang.  International Symposium on Computer Architecture 2013. pdf

[ASPLOS ’13]  ReQoS: Reactive Static/Dynamic Compilation for QoS in Warehouse Scale Computers  Lingjia Tang, Jason Mars, Wei Wang, Tanima Dey and Mary Lou Soffa. International Conference on Architectural Support for Programming Languages and Operating Systems 2013. pdf slides

[HPCA ’13]  Optimizing Google’s Warehouse Scale Computers: The NUMA Experience                Lingjia Tang, Jason Mars, Xiao Zhang, Robert Hagmann, Robert Hundt and Eric Tune. IEEE International Symposium on High Performance Computer Architecture 2013. pdf slides

[SC ’13] Enabling Fair Pricing on HPC Systems with Node Sharing  Alex Breslow, Ananta Tiwari, Laura Carrington, Lingjia Tang and Jason Mars. Super Computing 2013. pdf

2012

[IEEE MICRO ’12] Increasing Utilization in Warehouse Scale Computers Using Bubble-Up!            Jason Mars, Lingjia Tang, Robert Hundt, Kevin Skadron, Mary Lou Soffa. Special Issue: IEEE Micro’s Top Picks from 2011 Computer Architecture Conferences (MICRO TOP PICKS) 2012. pdf

[CGO ’12] Compiling For Niceness: Mitigating Contention for QoS in Warehouse Scale Computers Lingjia Tang, Jason Mars, Mary Lou Soffa. International Symposium on Code Generation and Optimization 2012. Best paper award. pdf

[ISPASS ’12] Performance Analysis of Thread Mappings with a Holistic View of the Hardware Resources  Wei Wang, Tanima Dey, Jason Mars, Lingjia Tang, Jack Davidson, Mary Lou Soffa.IEEE International Symposium on Performance Analysis of Systems and Software 2012. pdf

2011

[ISCA ’11] The Impact of Memory Subsystem Resource Sharing on Datacenter Applications     Lingjia Tang, Jason Mars, Neil Vachharajani, Robert Hundt, Mary Lou Soffa. International Symposium on Computer Architecture 2011. Acceptance Rate: (40/208) 19% selected as one of Excellent Papers for 2011 by Google pdf slides

[MICRO ’11] Bubble-Up: Increasing Sensible Co-locations for Improved Utilization in Modern Warehouse Scale Computers Jason Mars, Lingjia Tang, Robert Hundt, Kevin Skadron, Mary Lou Soffa. The 44th Annual IEEE/ACM International Symposium on Microarchitecture. Acceptance Rate: (44/209) 21% pdf

[HiPEAC ’11] Directly Characterizing Cross Core Interference Through Contention Synthesis   Jason Mars, Lingjia Tang, Mary Lou Soffa. In Proceedings of the International Conference on High Performance Embedded Architectures & Compilers 2011. Acceptance Rate: 23% pdf

[CAL ’11] Heterogeneity in “Homogeneous” Warehouse-Scale Computers: A Performance Opportunity Jason Mars, Lingjia Tang, Robert Hundt. In IEEE Computer Architecture Letters 2011. Acceptance Rate: 24% pdf

[EXADAPT ’11] Contentiousness vs. Sensitivity: Improving Contention Aware Runtime Systems on Multicore Architectures Lingjia Tang, Jason Mars, Mary Lou Soffa. In ACM SIGPLAN 1st International Workshop on Adaptive Self-Tuning Computing Systems for the Exaflop Era (EXADAPT) @ PLDI 2011

2010 and before

Simulation/Numerical Optimization

Agile Optimization for Coercion. Lingjia Tang, Paul F. Reynolds. In Proceedings of the Winter Simulation Conferences 2007 (WSC ’07)

Explanation Exploration: Explore Emergent Behavior. Ross Gore, Paul Reynolds, Lingjia Tang, David Brogan. In Proceedings of the International Workshop on Principles of Advanced and Distributed Simulation (PADS’07).

Exploit User Insights for Efficient Simulation Adaptation. Lingjia Tang, Paul Reynolds. 2008 VMASC Capstone Conference.


Research

Performant and Energy Efficient Warehouse-Scale Datacenters

Improving datacenter efficiency including performance and energy efficiency is very important for data centers. In addition, increasing performance predictability and reining in the tail latency has been identified as one of the most important challenges in modern datacenter system design. To this end, we have several projects and publications that focus on this theme. We have looked at how to use fine-grained DVFS, heterogeneous architecture, design smart performance prediction capabilities to rein in the tail latency and improve datacenter efficiency.

Related Publications:
[ISCA ’15] “Thermal Time Shifting: Leveraging Phase Change Materials to Reduce Cooling Costs in Warehouse-Scale Computers”
[HPCA’15] “Adrenaline: Pinpointing and Reining in Tail Queries with Quick Voltage Boosting.”
[HPCA’15] Octopus-Man: QoS-Driven Task Management for Heterogeneous Multicore in
[MICRO ’14] SMiTe: Precise QoS Prediction on Real System SMT Processors to Improve Utilization in Warehouse Scale Computers
[USENIX ATC ’14] HaPPy: Hyperthread-aware Power Profiling Dynamically

 

Sirius and Djinn: Open-Source Intelligent Personal assistants and their implications on future datacenter design

If you are interested, check out the preview video on YouTube: DjiNN and Sirius

Sirius – We have designed an open-source Intelligent Personal Assistant (IPA) software, Sirius, that provides functionalities similar to Apple’s Siri, Google’s Google Now and Microsoft Cortana. We have released this software. The release has attracted much attention from the press and open-source community, including Wired, PCWorld, VentureBeat and Hacker News. The Sirius was number 1 trending project on Github for a few weeks. Using Sirius, we have conducted a study for future designs of warehouse-scale computer using various accelerators. The results are summarized in our publication at ASPLOS ’15.

Djinn – We have looked at how to provide deep learning as a general service for various IPA applications in datacenter and how that impacts future WSC designs.

Related Publications:

[ISCA ’15] “Djinn: DNN as a Service and Its Implications for Future Warehouse Scale Computers.”
[ASPLOS ’15] “Sirius: An Open End-to-End Voice and Vision Personal Assistant and Its Implications for Future Warehouse Scale Computers”

 

Near-free Dynamic Compiler 

System adaptability for the dynamic execution environment is critical for quality of service and efficiency in data centers . To this end,we have designed and implemented a dynamic compiler that can recompile and reroute execution to code regions with very small overhead. This allows us to customize code for different execution environment to significantly increase the utilization of datacenters.

Related Publications:

[MICRO ’14] “Protean Code: Achieving Near-Free Online Code Transformations for Warehouse Scale Computers. ” Acceptance Rate: 19%