Mehmet E Belviranli

Mehmet Esat Belviranli

Assistant Professor

Computer Science Department

Colorado School of Mines

  • Mail:
  • 1500 Illinois St.
  • Golden, CO 80401
  • E-Mail:
  • belviranli@mines.edu
  • CV:

About

I am an assistant professor and the director of the High Performance Systems and Software Lab in the Computer Science Department of Colorado School of Mines. My research group focuses creating ecosystems to increase performance and utilization of heterogeneous systems.

My research interests span:

  • Diversely heterogeneous architectures
  • Analytical performance & resource modeling
  • Autonomous computing
  • Cyber-physical systems
  • Deep learning acceleration
  • Parallel programming paradigms
  • Runtime systems
  • Edge-cloud platforms

Please check 𝕙𝘆𝕡𝗲𝕤𝘆𝕤 (High Performance Systems and Software Lab) web page, to learn more about our team, projects and publications.


Prospective students for research: I am always interested in doing research with self-motivated Ph.D., M.S., and U.G. students. If you are interested in doing research please fill out the research interest form to contact me.

Recent

  • [Publication] -- Nov'24 -- Our paper is accepted to appear in DATE'25. The paper unveils a novel memory-contention based covert communication attack which targets the shared system memory in mobile SoCs.
  • [Funding] -- Jun'24 -- I and my colleagues (Selcuk Kose from University of Rochester and Yuanchao Xu from UC Santa Cruz) are awarded an NSF-SaTC grant , titled "Exploration of Shared Memory Related Security Challenges in Mobile Computing Platforms". This project unveils a new critical side-channel leakage when multiple applications execute together in a shared memory multi-processor system.
  • [Award] -- May'24 -- My Ph.D. student Ismet Dagli has been selected for the prestigious MLCommons ML and Systems Rising Stars 2024 Cohort.
  • [Publication] -- Apr'24 -- Our paper is accepted to appear in ICS'24. The paper proposes a novel scheduling technique for cyber-physical systems with heterogeneous processing units under real-world constraints
  • [Award] -- Mar'24 -- My Ph.D. student Justin Davis has won the outstanding paper award at DATE'24 Autonomous Systems Desigin Initiative.
  • [Award] -- Mar'24 -- My Ph.D. student Ismet Dagli was a finalist in CGO'24 SRC (student research competition).
  • [Publication] -- Dec'23 -- Our paper is accepted to appear in DATE'24. The paper proposes multi network and multi accelerator object detection for aerial drones.
  • [Publication] -- Nov'23 -- Our paper is accepted to appear in PPoPP'24. The paper proposes to increase throughput of concurrently running DNNs on resource-limited SoCs.
  • [Funding] -- Aug'23 -- I and my colleagues (Selcuk Kose and Eby Friedman from University of Rochester, and Adwait Jog from University of Virginia) are awared a DoE grant, titled "Modeling the Memory-Compute Gap in Large-scale Superconductive Systems". This project aims to model the performance of DoE applications on future's large-scale SFQ-based compute systems with CMOS based memory .
  • [Funding] -- Apr'23 -- I and my colleagues (Zafer Mutlu from University of Arizona, Selcuk Kose from University of Rochester, Mike Chrommie from UC Berkeley and Ulya Karpuzcu from University of Minnesota) are awared an NSF Future of Semiconductors (FuSe) Program teaming grant (TG) . This project aims to assemble a multidisciplinary team of experts from different institutions to identify and investigate the challenges facing graphene nanoribbon-based field effect transistor (GNRFET) computing system at the material, device, circuit, and system levels.
  • [Donation] -- Feb'23 -- Google Coral.ai equipment donation. Thanks Google!
  • [Funding] -- Jan'23 -- I and my colleagues (Zafer Mutlu from University of Arizona, Selcuk Kose from University of Rochester and Mike Chrommie from UC Berkeley) are awared a Semiconductor Research Cooperation (SRC) grant on "Smarter Nanoelectronics with Atomically Precise Graphene Nanoribbons". In this project we will be exploring the promising potential of Graphene Nanoribbons as tomorrow's leading transistor technology.
  • [Award] -- Oct'22 -- My Ph.D. student Ismet Dagli has won the third place in MICRO'22 SRC (student research competition).
  • [Publication] -- Jul'22 -- Our paper is accepted to appear in PACT'22. The paper proposes an approach to optimize regular expressions via rewrite-guided synthesis.
  • [Award] -- Mar'22 -- I have been granted U.S. Air Force Research Lab Summer Faculty Fellowship Award for Summer'22.
  • [Publication] -- Feb'22 -- Our paper is accepted to appear in DAC'22. The paper proposes an energy-aware neural network inference execution scheme on multi-accelerator heterogeneous SoCs.
  • [Funding] -- Aug'21 -- I and my colleagues, Jedidiah McClurg and Neil Dantam, at Colorado School of Mines were awarded an NSF grant. We will be developing synthesis based solutions to enable resource-aware execution on diversely heterogeneous architectures.
  • [Publication] -- Jul'21 -- Our paper is accepted to appear in MICRO'21. The paper builds a shared memory contention slowdown model for diversely heterogeneous SoCs.
  • [Publication] -- May'21 -- Our paper is accepted to appear in PARCO. The paper proposes an automatic, generic, and non-intrusive partitioning strategy for DNNs that are represented as computational graphs.
  • [Organization] -- Apr'21 -- Our workshop is accepted for the SC'21 program: RSDHA: Redefining Scalability for Diversely Heterogeneous Architectures.
  • [Award] -- Mar'21 -- I have been granted U.S. Air Force Research Lab Summer Faculty Fellowship Award for Summer'21.
  • [Donation] -- Sep'20 -- Xilinx equipment and license donation. Thanks Xilinx! .
  • [Publication] -- Jul'20 -- Our paper is accepted to appear in PACT'20. The paper is authored by my former mentee, Mohammad Monil, and develops a smart dial for energy/performance tradeoff for diversely heterogeneous systems.
  • [Award] -- Oct'19 -- I was honored with Oak Ridge National Laboratory (ORNL) Significant Event Award for my contributions on the renovation of the ExCL laboratory
  • Organization Committees:
    • ICS'25 - Workshops and Tutorials Chair
    • RSDHA'23 @ SC'23 - Workshop Organizer/General Co-Chair
    • RSDHA'22 @ SC'22 - Workshop Organizer/General Co-Chair
    • RSDHA'21 @ SC'21 - Workshop Organizer/General Co-Chair
    • ISES'21 - Track Chair for ardware/Software for Vehicular Intelligent Systems
    • PPoPP'20 - PC meeting local arrangement Co-Chair
  • Program Committees:
    • ISCA'25
    • IPDPS'25
    • SC'24
    • IPDPS'24
    • SC'23
    • ISC'23
    • DAC'23
    • IPDPS'23
    • DAC'22
    • ISC'22
    • IPDPS'22
    • SC'21 - BoF
    • SC'21 - Grad. Poster
    • NAS'21
    • ICPP'21
    • IPDPS'21
    • EuroPar'21 - PhD Sym.
    • ICPP'20
    • SC'20 - Workshops
    • PACT'20 - SRC
    • PPoPP'20

Selected Publications (Full list)

[ICS'24] Scheduling for Cyber-Physical Systems with Heterogeneous Processing Units under Real-World Constraints
McGowen, Justin; Dagli, Ismet; Dantam, Neil T.; Belviranli, Mehmet E
Proceedings of the 2016 International Conference on Supercomputing

[PPoPP'24] Shared Memory-contention-aware Concurrent DNN Execution for Diversely Heterogeneous SoCs
Dagli, Ismet;Belviranli, Mehmet E
Proceedings of ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming.

[DATE'24] Context-aware Multi-Model Object Detection for Diversely Heterogeneous Compute Systems
Davis, Justin; Belviranli, Mehmet E; (Outstanding Paper Award in Autonomous Systems Design)
2024 Design, Automation & Test in Europe Conference & Exhibition

[PACT'22] Optimizing Regular Expressions via Rewrite-Guided Synthesis
Jedidiah McClurg; Miles Claver; Jackson Garner; Jake Vossen; Jordan Schmerge; Belviranli, Mehmet E
31st International Conference on Parallel Architectures and Compilation Techniques

[DAC'22] AxoNN: Energy-Aware Execution of Neural Network Inference on Multi-Accelerator Heterogeneous SoCs
Ismet Dagli; Alexander Cieslewicz; Jedidiah McClurg; Belviranli, Mehmet E
59th ACM/IEEE Design Automation Conference

[MICRO'21] PCCS: Processor-Centric Contention-aware Slowdown Model for Heterogeneous SoCs
Yuanchao Xu; Belviranli, Mehmet E; Xipeng Shen; Vetter, Jeffrey S;
54th Annual IEEE/ACM International Symposium on Microarchitecture

[PARCO] A computational-graph partitioning method for training memory-constrained DNNs
Fareed Qararyah, Mohamed Wahib, Doğa Dikbayır, Mehmet Esat Belviranli , Didem Unat
Parallel Computing, 2021, 102792, ISSN 0167-8191

[PACT'20] MEPHESTO: Modeling Energy-Performance in Heterogeneous SoCs and Their Trade-Offs
Monil, Mohammad; Belviranli, Mehmet E; Lee, Seyong; Vetter, Jeffrey S; Malony, Allen;
2020 International Conference on Parallel Architectures and Compilation Techniques

[DATE'19] FLAME: Graph-based Hardware Representations for Rapid and Precise Performance Modeling
Belviranli, Mehmet E; Vetter, Jeffrey S;
2019 Design, Automation & Test in Europe Conference & Exhibition

[SC'18] DRAGON: Breaking GPU Memory Capacity Limits with Direct NVM Access
Markthub, Pak; Belviranli, Mehmet E; Lee, Seyong; Vetter, Jeffrey S; Matsuoka, Satoshi;
Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis

[HPEC'18] Designing Algorithms for the EMU Migrating-threads-based Architecture
Belviranli, Mehmet E; Lee, Seyong; Vetter, Jeffrey S; (Best Paper Finalist)
2018 IEEE High Performance Extreme Computing Conference

[PPoPP'18] Juggler: A Dependency-Aware Task Based Execution Framework for GPUs
Belviranli, Mehmet E; Lee, Seyong; Vetter, Jeffrey S; Bhuyan, Laxmi N;
Proceedings of ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming.

[MICRO'17] Wireframe: supporting data-dependent parallelism through dependency graph execution in GPUs.
Abdolrashidi, Amir A; Tripathy, Devashree; Belviranli, Mehmet E; Bhuyan, Laxmi N;
Proceedings of the 50th Annual IEEE/ACM International Symposium on Microarchitecture

[ICS'16] CuMAS: Data transfer aware multi-application scheduling for shared GPUs
Belviranli, Mehmet E; Khorasani, Farzad; Bhuyan, Laxmi N; Gupta, Rajiv;
Proceedings of the 2016 International Conference on Supercomputing

[ICS'15] Peerwave: Exploiting wavefront parallelism on GPUs with peer-sm synchronization
Belviranli, Mehmet E; Deng, Peng; Bhuyan, Laxmi N; Gupta, Rajiv; Zhu, Qi;
Proceedings of the 2015 International Conference on Supercomputing

[PACT'15] Stadium hashing: Scalable and flexible hashing on GPUs
Khorasani, Farzad; Belviranli, Mehmet E; Gupta, Rajiv; Bhuyan, Laxmi N;
International Conference on Parallel Architecture and Compilation

[TACO'13] A dynamic self-scheduling scheme for heterogeneous multiprocessor architectures
Belviranli, Mehmet E; Bhuyan, Laxmi N; Gupta, Rajiv;
ACM Transactions on Architecture and Code Optimization 2013

Work Experience

Colorado School of Mines, Golden, CO            August 2019 - Present
Assistant Professor, Computer Science Department

Oak Ridge National Laboratory, Oak Ridge, TN            December 2018 - August 2019
Computer Scientist, Future Technologies Group

Oak Ridge National Laboratory, Oak Ridge, TN            November 2016 - November 2018
PostDoctoral Research Associate, Future Technologies Group

University of California, Riverside, CA            September 2010 - September 2016
Research Assistant, Computer Science and Engineering Department

Samsung Information Systems America, San Jose, CA            June 2013 - September 2013
Processor Architect Intern, Advanced Processor Lab

Tom Sawyer Software, Oakland, CA            August 2007 - July 2008
Software Engineer

Education

B.S. in Computer Science. Bilkent University, Ankara, Turkey
Sep. 2001 - Jun. 2006