Iraklis Anagnostopoulos

Iraklis Anagnostopoulos

Associate Professor

About me

I am Associate Professor at the School of Electrical, Computer & Biomedical Engineering at Southern Illinois University Carbondale and the director of the Embedded Systems Software Lab, which focuses on:

  • Machine learning: Approximate computing, heterogeneous hardware accelerators, neural network optimizations, and hardware/software co-design.
  • System optimization: Application customization, power-aware scheduling, and memory management.
  • Many-core systems: Application mapping, network-on-chip architectures, run-time resource management, design and exploration of heterogeneous platforms, and resource contention minimization.

See also Curriculum Vitae.

News (Updated December 2023)

  • 12/2023: Our submission, Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantization is accepted at IEEE Transactions on Emerging Topics in Computing.

  • 09/2023: I am very excited to share that our proposal DESC: Type I: Towards Greener AI Computing: Designing and Managing Sustainable Heterogeneous Edge Data Centers was funded by NSF! More exciting research days are coming!

  • 04/2023: And we finally got it!! Our paper, Automated Energy-Efficient DNN Compression under Fine-Grain Accuracy Constraints received the Best Paper Award in the prestigious DATE 2023 conference! The best conference in design automation organized in Europe.


  • 02/2023: Our submission, OmniBoost: Boosting Throughput of Heterogeneous Embedded Devices under Multi-DNN Workload was accepted to IEEE/ACM Design Automation Conference 2023 (DAC) conference!

  • 11/2022: Our submission, Automated Energy-Efficient DNN Compression under Fine-Grain Accuracy Constraints was accepted to DATE 2023 conference! It is also nominated for Best Paper Award.

  • 08/2022: Our proposal, Collaborative Research: CyberTraining: Pilot: Research Workforce Development for Deep Learning Systems in Advanced GPU Cyberinfrastructure was selected for funding by NSF!

  • 07/2022: Our submission, Energy-efficient DNN Inference on Approximate Accelerators Through Formal Property Exploration is accepted at IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (ESWEEK Special issue).

  • 05/2022: Our submission, Targeting DNN Inference via Efficient Utilization of Heterogeneous Precision DNN Accelerators is accepted at IEEE Transactions on Emerging Topics in Computing.

  • 03/2022: Our submission, A Pressure-Aware Policy for Contention Minimization on Multi-core Systems is accepted at ACM Transactions on Architecture and Code Optimization.

  • 01/2022: Our submission, Thermal-Aware Design for Approximate DNN Accelerators is accepted at IEEE Transactions on Computers.

  • 01/2022: Our submission, Fair Scheduling Through Collaborative Filtering on Multicore Systems is accepted at the IEEE International Symposium on Circuits and Systems 2022 (ISCAS).

  • 10/2021: Our submission, Energy Efficient Edge Computing Enabled by Satisfaction Games and Approximate Computing is accepted at IEEE Transactions on Green Communications and Networking.

  • 07/2021: Our submission, Positive/Negative Approximate Multipliers for DNN Accelerators is accepted at IEEE/ACM International Conference On Computer Aided Design (ICCAD).

  • 05/2021: After a long and stressful period, I finally got tenure and promotion to the rank of Associate Professor! I would like to thank my family and my colleagues for their help and their support.

  • 03/2020: Our submission, Impact of NCFET on Neural Network Accelerators is accepted at IEEE Access journal.

  • 02/2020: Our submission, Control Variate Approximation for DNN Accelerators is accepted at the IEEE/ACM Design Automation Conference 2021 (DAC).

  • 01/2020: Our submission, Priority-Aware Scheduling Under Shared-ResourceContention on Chip Multicore Processors is accepted at the IEEE International Symposium on Circuits and Systems 2021 (ISCAS).

  • 12/2020: Our submission, Efficient Deployment of Spiking Neural Networks on SpiNNaker Neuromorphic Platform is accepted at the IEEE Transactions on Circuits and Systems.

  • 12/2020: Our submission, Online Frequency-based Performance and Power Estimation for Clustered Multi-Processor Systems is accepted at the Springer Computers and Electrical Engineering Journal.

  • 11/2020: I am excited to share that two of our papers, Reliability-Aware Quantization for Anti-Aging NPUs, a collaboration with Karlsruhe Institute of Technology and University of Stuttgart, and Efficient Resource Management of Clustered Multi-Processor Systems Through Formal Property Exploration, a collaboration with Arizona State University, were accepted to DATE 2021 conference!

  • 09/2020: Our submission, Prognostics and Health Management Data Handling by Critical Tasks on Multi-Core Platforms was accepted at IEEE International Conference on Electronics Circuits and Systems (ICECS).

  • 08/2020: Our submission, Weight-Oriented Approximation for Energy-Efficient Neural Network Inference Accelerators was accepted at IEEE Transactions on Circuits and Systems I: Regular Papers.

  • 07/2020: Our submission, NPU Thermal Management was accepted at IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (ESWEEK 2020 Special Issue).

  • 05/2020: Our submission, Edge-First Resource Management for Video-based Applications: A Face Detection Use-case was accepted at IEEE Embedded Systems Letters.

  • 05/2020: Our submission, Inference and Energy Efficient Design of Deep Neural Networks for Embedded Devices was accepted at IEEE Computer Society Annual Symposium on VLSI (ISVLSI 2020).

  • 05/2020: I am honored to be invited as member of the TPC for ASP-DAC 2020.

  • 02/2020: Our submission, Frequency-based Power Efficiency Improvement of CNNs on Heterogeneous IoT Computing Systems was accepted at IEEE World Forum on The Internet of Things (WF-IoT 2020).

  • 02/2020: Our submission, Adaptive Approximate Computing on Hardware Accelerators Targeting Internet-of-Things was accepted at IEEE World Forum on The Internet of Things (WF-IoT 2020).

  • 01/2020: Our submission, ARIAN: A scalable method for Adding aRbItrAry Numbers on modern processors was accepted at IEEE International Symposium on Circuits and Systems 2020 (ISCAS).

  • 01/2020: Our submission, A Machine Learning Approach For Improving Power Efficiency on Clustered Multi-Processor System was accepted at IEEE International Symposium on Circuits and Systems 2020 (ISCAS).

  • 11/2019: I am honored to be invited as member of the TPC for DAC 2020.

  • 11/2019: Our submission, Meeting Power Constraints while Mitigating Contention on Clustered Multi-Processor Systems was accepted at IEEE Embedded Systems Letters.

  • 11/2019: Our suoverbmission, Improving GPU Performance with a Power-Aware SM Allocation Methodology was accepted at MDPI Electronics Journal.

  • 09/2019: Our submission, Performance and Fairness Improvement on CMPs Considering Bandwidth and Cache Utilization was accepted at IEEE Computer Architectures Letters.

  • 07/2019: Our submission, Kernel-based Resource Allocation for Improving GPU Throughput while Minimizing the Activity Divergence of SMs was accepted at IEEE Transactions on Circuits and Systems–I: Regular Papers.

  • 07/2019: Our submission, Performance and Aging Aware Resource Allocation for Concurrent GPU Applications under Process Variation was accepted at IEEE Transactions on Nanotechnology.

  • 07/2019: Our lab did a great job informing and creating enjoyable demos for the students involved in the SMASH Illinois program



  • 06/2019 Our proposal Modular and scalable infrastructure for the SIUC campus was accepted for funding by the Illinois Environmental Protection Agency through the US Department of Energy.

  • 04/2019: Our lab did a great job presenting two very impressive demos at SIU Open DAY 2019! Many thanks to my students Ioannis Galanis, Shivam Kundan, and Linclon Kinley for their help and their support.


  • 04/2019: I am deeply honored to receive the Outstanding Teacher award for 2018 for the Electrical & Computer Engineering department.

  • 03/2019: Our submission, Environmental-Based Speed Recommendation for Future Smart Cars was accepted at the journal Future Internet.

  • 02/2019: Our submission, Workload-aware Management Targetting Multi-Gateway Internet-of-Things was accepted at IEEE International Conference on Omni-layer Intelligent systems (COINS).

  • 09/2018: Two papers accepted at IEEE International Conference on Electronics Circuits and Systems. Optimizing Performance of GPU Applications with SM Activity Divergence Minimization and Drop: Distributed Run-Time and Power Constraint Mapping for Many-Core Systems.

  • 09/2018: I am pleased to read that our demo was one of the most requested activities during SIU Open day (Article in Southern Illinoisan).

  • 08/2018: I am very happy to announce that today our lab received the 48-node SpiNNaker based board for our research on modern neuromorphic platforms.

  • 07/2018: Our submission, Performance-based and Aging-aware Resource Allocation for Concurrent GPU Applications was accepted at IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT).

  • 04/2018: Our submission, A Message-Passing Microcoded Synchronization for Distributed Shared Memory Architectures was accepted at IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

  • 01/2018: Our submission, Hierarchical Distributed Run-time Resource Management scheme for NoC based Many-Cores was accepted at ACM Transactions on Embedded Computing Systems.

  • 01/2018: Two papers accepted at International IEEE Symposium on Circuits and Systems.

  • 11/2017: Two papers accepted at Conference on Design, Automation and Test in Europe (DATE) 2018. Congratulations to all hard-working students!

  • 02/2017: Our paper was accepted at ACM Great Lakes Symposium on VLSI 2017 (GLSVLSI).

  • 01/2017: Three papers accepted at International IEEE Symposium on Circuits and Systems. Congratulations to all hard-working students!