Hello! My name is Michael LeBeane and I’m currently a Senior Staff Engineer at Qualcomm, where I work on modeling and architecture to support emerging graphics programming models. Before that I spent 5 years working at AMD Research, where I focused on research in computer networks, GPUs, and simulation frameworks.

I’m a PhD graduate from The University of Texas at Austin where I worked in the Laboratory for Computer Architecture (LCA). I’m also a graduate from Washington University in St. Louis where I studied computer science and interned with Intel.

Click here to download my CV

Conference Publications

Increasing GPU Translation Reach by Leveraging Under-Utilized On-Chip Resources Jagadish Kotra, Michael LeBeane, Mahmut Kandemir, Gabriel Loh International Symposium on Microarchitecture (MICRO). October 2021

GPU Initiated OpenSHMEM: Correct and Efficient Intra-Kernel Networking for dGPUs
Khaled Hamidouche, Michael LeBeane
Principles and Practice of Parallel Programming (PPoPP). February 2020.
[Paper] [Slides]

Optimizing GPU Cache Policies for MI Workloads
Johnathan Alsop, Matthew D. Sinclair, Anthony Gutierrez, Srikant Bharadwaj, Xianwei Zhang, Bradford Beckmann, Alexandru Dutu, Onur Kayiran, Michael LeBeane, Brandon Potter, Sooraj Puthoor, Tsung Tai Yeh
International Symposium on Workload Characterization (IISWC) (Short Paper). November 2019.
[ArXiV Paper]

ComP-Net: Command Processor Networking for Efficient Intra-kernel Communications on GPUs
Michael LeBeane, Khaled Hamidouche, Mauricio Breternitz, Brad Benton, Steve Reinhardt, Lizy K. John
International Conference on Parallel Architectures and Compilation Techniques (PACT). November 2018.
[Paper] [Slides]

Neighborhood-Aware Address Translation for Irregular GPU Applications
Seunghee Shin, Michael LeBeane, Yan Solihin, Arkaprava Basu
International Symposium on Microarchitecture (MICRO). October 2018.
[Paper] [Slides]

Case Study of Process Variation-Based Domain Partitioning of GPGPUs
Shomit Das, Michael LeBeane, Bradford Beckmann, Greg Sadowski
International Symposium on Asynchronous Circuits and Systems (ASYNC). May 2018.
[Paper]

Lost in Abstraction: Pitfalls of Analyzing GPUs at the Intermediate Language Level
Anthony Gutierrez, Bradford M Beckmann, Alexandru Dutu, Joseph Gross, Michael LeBeane, John Kalamatianos, Onur Kayiran, Matthew Poremba, Brandon Potter, Sooraj Puthoor, Matthew D Sinclair, Mark Wyse, Jieming Yin, Xianwei Zhang, Akshay Jain, Timothy Rogers
International Symposium on High Performance Computer Architecture (HPCA). February 2018.
[Paper] [Slides]

GPU Triggered Networking for Intra-Kernel Communications
Michael LeBeane, Khaled Hamidouche, Brad Benton, Mauricio Breternitz, Steven K. Reinhardt, and Lizy K. John
International Conference for High Performance Computing, Networking, Storage, and Analysis (SC). November 2017.
[Paper] [Slides]

Extended Task Queuing: Active Messages for Heterogeneous Systems
Michael LeBeane, Brandon Potter, Abhisek Pan, Alexandru Dutu, Vinay Agarwala, Wonchan Lee, Deepak Majeti, Bibek Ghimire, Eric Van Tassell, Samuel Wasmundt, Brad Benton, Mauricio Breternitz, Michael L. Chu, Mithuna Thottethodi, Lizy K. John, and Steven K. Reinhardt
International Conference for High Performance Computing, Networking, Storage, and Analysis (SC). November 2016.
[Paper] [Slides]

Proxy-Guided Load Balancing of Graph Processing Workloads on Heterogeneous Clusters
Shuang Song, Meng Li, Xinnian Zheng, Jee Ho Ryoo, Reena Panda, Michael LeBeane, Andreas Gerstlauer, and Lizy K. John
International Conference on Parallel Processing (ICPP). August 2016.
[Paper]

Genesys: Automatically Generating Representative Training-sets
Reena Panda, Xinnian Zheng, Jee Ho Ryoo, Michael LeBeane, Shuang Song, Andreas Gerstlauer, and Lizy K. John
International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation (SAMOS). July 2016.
[Paper]

Data Partitioning Strategies for Graph Workloads on Heterogeneous Clusters
Michael LeBeane, Shuang Song, Reena Panda, Jee Ho Ryoo, and Lizy K. John
International Conference for High Performance Computing, Networking, Storage and Analysis (SC). November 2015.
[Paper] [Slides]

Performance Characterization of Modern Databases on Out-of-order CPUs
Reena Panda, Christopher Erb, Michael LeBeane, Jee Ho Ryoo, and Lizy K. John
International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD). October 2015.
[Paper]

WattWatcher: Fine-Grained Power Estimation For Emerging Workloads
Michael LeBeane, Jee Ho Ryoo, Reena Panda, and Lizy K. John
International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD). October 2015.
[Paper] [Slides]

GPGPU Benchmark Suites: How Well Do They Sample the Performance Spectrum? (Best Paper Runner-Up)
Jee Ho Ryoo, Saddam Quirem, Michael LeBeane, Reena Panda, Shuang Song, and Lizy K. John
The IEEE International Conference on Parallel Processing (ICPP). September 2015.
[Paper]

WattWatcher: Fine-Grained Power Estimation on Live Multicore Systems Using Configurable Models (Best in Session)
Michael LeBeane, Jee Ho Ryoo, Reena Panda, and Lizy K. John
SRC TECHCON. September 2015.
[Paper]

Control Flow Behavior of Cloud Workloads (Poster Paper)
Jee Ho Ryoo, Michael LeBeane, Muhammad Faisal Iqbal, and Lizy K. John
The IEEE International Symposium on Workload Characterization (IISWC). October 2014.
[Paper]

Technical Reports

Containment Domains Semantics version 0.2
Michael Sullivan, Ikhwan Lee, Jinsuk Chung, Song Zhang, Seong-Lyong Gong, Derong Liu, Michael LeBeane, Kyushick Lee, and Mattan Erez.
Technical report Tr-LPH-2014–001, LPH Group, Department of Electrical and Computer Engineering, The University of Texas at Austin, February, 2014.
[Report]

Containment Domains Semantics version 0.1
Michael Sullivan, Ikhwan Lee, Jinsuk Chung, Song Zhang, Seong-Lyong Gong, Derong Liu, Michael LeBeane, and Mattan Erez
Technical report Tr-LPH-2013–001, LPH Group, Department of Electrical and Computer Engineering, The University of Texas at Austin. October 2013.
[Report]

Dissertation

Optimizing Communication for Clusters of GPUs
Michael LeBeane
[Dissertation] [Slides]

Patents

Systems and methods for reducing instruction code memory footprint for multiple processes executed at a coprocessor Khaled Hamidouche, Michael LeBeane, Hari Thangirala. Advanced Micro Devices Incorporated, assignee. Application Number 16/719076.
[Link]

Efficient memory-semantic networking using scoped memory models Michael LeBeane, Khaled Hamidouche, Hari Thangirala, Brandon Potter. Advanced Micro Devices Incorporated, assignee. Patent Number 11714559. [Link]

Techniques to improve translation lookaside buffer reach by leveraging idle resources Jagadish Kotra, Michael LeBeane. Advanced Micro Devices Incorporated, assignee. Patent Number 11321241. [Link]

Network Command Coalescing on GPUs Michael LeBeane, Khaled Hamidouche, Brandon Potter. Advanced Micro Devices Incorporated, assignee. Patent Number 11922207. [Link]

Apparatus and method for neighborhood-aware virtual to physical address translations
Michael LeBeane, Seunghee Shin. Advanced Micro Devices Incorporated, assignee. Patent Number 10684957.
[Link]

Network-related performance for gpus
Michael LeBeane, Khaled Hamidouche, Brad Beckmann. Advanced Micro Devices Incorporated, assignee. Application Number 16/049216.
[Link]

Optimized and scalable sparse triangular linear systems on networks of accelerators
Khaled Hamidouche, Michael LeBeane, Nicholas Malaya, Joseph Greathouse. Advanced Micro Devices Incorporated, assignee. Patent Number 10936697.
[Link]

Network packet templating for gpu-initiated communication
Khaled Hamidouche, Michael LeBeane, Brad Benton. Advanced Micro Devices Incorporated, assignee. Patent Number 10740163.
[Link]

Quality of service for input/output memory management unit
Arkaprava Basu, Michael LeBeane, Eric Van Tassell. Advanced Micro Devices Incorporated, assignee. Patent Number 111444732. [Link]

Optimized asynchronous training of neural networks using a distributed parameter server with eager updates
Khaled Hamidouche, Michael LeBeane, Brad Benton, Michael Chu. Advanced Micro Devices Incorporated, assignee. Patent Number 11630994. [Link]

Gpu networking using an integrated command processor
Michael LeBeane, Khaled Hamidoouche, Brad Benton. Advanced Micro Devices Incorporated, assignee. Patent Number 11544121. [Link]

Network cache injection for coherent gpus
Michael LeBeane, Brad Benton, Vinay Agarwala. Advanced Micro Devices Incorporated, assignee. Patent Number 11687460. [Link]

GPU remote communication with triggered operations
Michael LeBeane and Steve Reinhardt. Advanced Micro Devices Incorporated, assignee. Patent Number 10936533.
[Link]

Network interface controller-based scheduling of processing tasks in a distributed computing system
Michael LeBeane, Abhisek Pan, and Steve Reinhardt. Advanced Micro Devices Incorporated, assignee. Patent Number 10963309.
[Link]

Power-aware Work Stealing
Mauricio Breternitz, Deepak Majeti, and Michael LeBeane. Advanced Micro Devices Incorporated, assignee. Patent Number 10089155. [Link]