Mohammadamin Ajdari

Mohammadamin Ajdari is highly interested in doing novel research in all aspects of computer architecture and system software, with special focus on designing scalable infrastructures (processing & data storage) for emerging data-intensive applications (including machine learning use cases). He has 11+ years of experience in doing system architecture research in academia, 5+ years of industry experience mostly as Research Team Lead and Research Director, and a history of authoring 14+ research papers in top-tier international venues (ASPLOS, MICRO, HPCA, SIGMETRICS, etc.). Mohammadamin has had a number of prestigious awards including the Best BSc Project Awardee at Department of Electrical Engineering at Sharif University of Technology (2012), Winner of POSCO Asia Fellowship in South Korea (2013), Best Paper Nominee for part of his PhD thesis at the top conference of HPCA (2019), Receiving Honorable Mention in IEEE MICRO Top Picks for his first-authored paper as an influential computer architecture paper (2019). In addition to academic aspects of research that Mohammadamin pursues, he has been always interested in practical research which addresses industry requirements. In this regard, some of his first-authored/co-authored work (e.g., MICRO’15, ISCA’2018, HPCA’19, MICRO’19) have been the foundation of a startup in South Korea (MangoBoost), worth 300M dollars in 2023. His later 6-year research work in HPDS Corp (in Iran) also resulted in next-generation storage system products.

We have a number of openings for Master and PhD students to join our team.

If you are interested in practical research (useful for both industry and academia), and would like to MOVE the BOUNDARIES of knowledge and technology in the domains related to computer architecture HW/SW, then you should join us!

For more information, please visit my homepage:

https://mohammadamin-ajdari.github.io/

2013/09 - 2019/08, Pohang University of Science and Technology (South Korea), Computer Science and Engineering (Focus: Computer System Architecture), PhD

2008/09 - 2013/07, Sharif University of Technology (Iran), Electrical Engineering (Focus: Electronics), Bachelor

2026/4 – Present: Tsinghua Shenzhen International Graduate School, Tsinghua University, Assistant Professor

2022/10 – 2025/11: High Performance Data Storage and Processing (HPDS) Corp (in Iran), Director of System Research & Technology

2021/5 – 2022/10:  High Performance Data Storage and Processing (HPDS) Corp (in Iran), Research Team Lead

2019/12 – 2021/5: High Performance Data Storage and Processing (HPDS) Corp (in Iran), Senior R&D Engineer/Researcher

My main research interests are the following:

Designing Scalable Storage Systems:  Architecting for next generation storage systems by redesigning or enhancing from the bottom hardware layer to the system software and application layer. Our enhancements are in performance, reliability, capacity, and power-consumption.

Machine Learning Infrastructure and Workloads: Analysis and design of next generation infrastructures for emerging workloads, HPC architectures and schedulers, customization for emerging workloads to maximize performance, performance per cost, etc.

Characterization and System Modeling: Characterization of real system hardware/software, modeling their behavior, designing simulators and exploring architectural design choices are common tracks of our research projects.

[1] A. Sedaghatgoo*, M.Ajdari*, E. Teymouri, H. Asadi, “Do Not Get Fooled: Use True Utilization on High-Performance Storage Devices”, IEEE International Symposium on Performance Analysis of System and Software (ISPASS), 2026

[2] A. Dezhban*, M.Ajdari*, H. Asadi, “Characterization and Performance Analysis of Aging Effect on Enterprise HDDs”, IEEE International Symposium on Performance Analysis of System and Software (ISPASS), 2026

[3] MM. Gharaguzlu*, M.Ajdari*, H. Asadi, “Smart Prediction of I/O Accesses in Enterprise Workloads to Accelerate Data Serving During Array Reconstruction”, IEEE Computer Architecture Letters (CAL), 2026

[4] E. Adibi, M.Ajdari, P. Arefijamal, A. Ahmadi-Tonekaboni, H. Asadi, “I/O-ETEM: an I/O-Aware Approach for Estimating Execution Time of Machine Learning Workloads”, IEEE Computer Architecture Letters (CAL), 2025

[5] M. Ajdari*, B. Montazerzohour*, K. Abdi, H. Asadi, “Empirical Architectural Analysis on Performance Scalability of Petascale All-Flash Storage Systems”, IEEE Computer Architecture Letters (CAL), 2024  

[6] M.Ajdari, P. Peykani Sani, A. Moradi, M. Khanalizadeh Imani, A.H. Bazkhanei, H.Asadi, “Re-architecting I/O Caches for Emerging Fast Storage Devices”, ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2023, Vancouver, Canada

[7] M. Ajdari, P. Raaf, M. Kishani, R. Salkhordeh, H. Asadi, A. Brinkmann, “An Enterprise Open-Source Data Reduction Architecture for All-Flash Storage Systems”, ACM SIGMETRICS, 2022, India  

 [8] M. Ajdari, W. Lee, P. Park, J. Kim, J. Kim, “FIDR: A Scalable Storage System for Fine-Grain Inline Data Reduction With Efficient Memory Handling”, International Symposium on Microarchitecture (MICRO) 2019, Oct 2019, Ohio, USA  

[9] M. Ajdari, P. Park, J. Kim, D. Kwon, J. Kim, “CIDR: Cost-effective In-Line Data Reduction System for Terabit-per-Second Scale SSD Arrays”, International Symposium on High Performance Computer Architecture (HPCA) 2019, Feb 2019, Washington DC, USA <Best Paper Nominee> <IEEE MICRO TOP Picks Honorable Mention>

[10] D. Kwon*, J. Ahn*, D. Chae, M. Ajdari, J. Lee, S. Bae, Y.Kim, J. Kim, “DCS-Ctrl: A fast and flexible device-control mechanism for device centric server architecture”, International Symposium on Computer Architecture (ISCA) 2018, June 2018, Los Angeles, California, USA

[11] J. Joe, G. Lee, H. Jang, J. Lee, M. Ajdari , J. Kim, “DiagSim: Systematically diagnosing simulators for healthy simulations”, ACM Transactions on Architecture and Code Optimization (TACO), 2018   

[12] M. Ajdari*, P. Park*, D. Kwon, J. Kim, J. Kim, “A scalable HW-based inline deduplication for SSD arrays”, IEEE Computer Architecture Letters (CAL), Sep 2017   

 [13] J. Ahn*, D. Kwon*, Y.Kim, M.Ajdari, J. Lee, J. Kim, “DCS:A fast and scalable device-centric server architecture”, International Symposium on Microarchitecture (MICRO) 2015, Dec 2015, Waikiki, USA  

      *: Co-first author

·  As the technical representative of HPDS Corp,presenting HPDS latest data storage products/solutions to ICT ministers from Economic Corporation Organization (ECO) countries (note: ~10 fast growing countries in western part of Asia constitute ECO group), Tehran, Iran, [July 2023]

· Introducing HPDS Flagship storage product (SANGold) on Iran’s National TV,[ Aug. 2023]

· “Honorable Mention” of one my first-authored papers as a top architectural paper in IEEE MICRO Top Picks 2019

· “Best Paper Nomination”for part of my PhD thesis published in HPCA 2019

· Winner of POSCO Asia Fellowship from POSCO TJ Park Foundation (2013- 2015)

· Ranked 1^st in the B.Sc. project competition held among all students who defended their B.Sc.  projects in 2012 in Department of Electrical Engineering, Sharif University of Technology