Computer Scientist
Computer Scientist

Biography

Nicolas Bohm Agostini is a computer scientist at Pacific Northwest National Laboratory (PNNL). He obtained his bachelor’s degree in electrical engineering from the Universidade Federal do Rio Grande do Sul in 2015, followed by a master of science degree in electrical and computer engineering from Northeastern University in 2022 and a PhD in computer engineering from Northeastern University in 2024. With a strong focus on computer architecture and high-performance computing, Agostini has gained extensive expertise in accelerating machine learning and linear algebra applications. As a passionate educator, he has taught courses in compilers, GPU programming, and embedded robotics.

Agostini joined PNNL in 2020 and is the lead developer of the SODA-OPT compiler, which automates system-level partitioning of high-level applications and enables automatic code optimizations for superior outcomes in custom hardware generation. SODA-OPT is part of the SODA toolchain, which seeks to democratize the design and deployment of energy-efficient, domain-specific hardware accelerators by providing open-source, scalable, and compiler-driven tools to generate high-performance designs for field-programmable gate arrays (FPGAs) and application-specific integrated circuits.

His research vision is to empower scientists, engineers, and developers across disciplines with seamless access to next-generation hardware acceleration, enabling transformative breakthroughs in machine learning and scientific computing through software-defined, hardware-optimized solutions.

Disciplines and Skills

  • C
  • C++
  • Compilers
  • Computer architecture
  • Electronic circuit design
  • Electronic instrumentation
  • FPGAs
  • Game design and development
  • GitHub
  • GitLab
  • GPUs
  • High-performance computing
  • Linux system administration
  • Machine learning
  • Natural language processing
  • Python

Education

PhD in computer engineering, Northeastern University

MS in electrical and computer engineering, Northeastern University

BEE in electronic/computer engineering, Universidade Federal do Rio Grande do Sul

Affiliations and Professional Service

Judge, Student Research Competition, International Symposium on Code Generation and Optimization

Reviewer, International Conference for High Performance Computing, Networking, Storage and Analysis

Reviewer, ACM International Conference on Architectural Support for Programming Languages and Operating Systems

Reviewer, International Conference on Parallel Computing

Reviewer, ACM Transactions on Architecture and Code Optimization

Web chair, Computing Frontier conference

Former web chair, IEEE Technical Committee on Computer Architecture website

Presenter, International Symposium on Computer Architecture

Presenter, International Symposium on High-Performance Computer Architecture

Presenter, Design, Automation and Test in Europe Conference

Main organizer, Annual Compiler Frontiers Workshop

Awards and Recognitions

Publications

2025

  • Bohm Agostini N., C.G. Johnson, W.C. Cannon, and A. Tumeo. 2025. "ChemComp: A Compilation Framework for Computing with Chemical Reaction Networks." In Proceedings of the 30th Asia and South Pacific Design Automation Conference (ASPDAC 2025), January 20-23, 2025, Tokyo, Japan, 872 - 878. New York, New York:Association for Computing Machinery. PNNL-SA-205337. doi:10.1145/3658617.3703315
  • Bohm Agostini N., C.G. Johnson, W.R. Cannon, and A. Tumeo. 2025. "ChemComp: Compiling and Computing with Chemical Reaction Networks." In Design, Automation and Test in Europe Conference (DATE 2025), March 31-April 2, 2025, Lyon, France, 1-7. Piscataway, New Jersey:IEEE. PNNL-SA-207722. doi:10.23919/DATE64628.2025.10993207
  • Bohm Agostini N., G. Gozzi, M. Fiorito, C. Barone, S. Curzel, A.M. Limaye, and M. Minutoli, et al. 2025. "Extending High-Level Synthesis with AI/ML Methods." In Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design (ICCAD 2024), October 27-31, 2024, New York, NY, Paper No. 28. New York, New York:Association for Computing Machinery. PNNL-SA-202929. doi:10.1145/3676536.3689923
  • Manjunath D., N. Bohm Agostini, A. Tumeo, J. Zhang, and C. Chackrabarti. 2025. "ML4SODA: A Decision Tree Guided Design Space Exploration for Fast and High Quality MLIR-based HLS." In Great Lakes Symposium on VLSI (GLSVLSI 2025), June 30-July 2, 2025, New Orleans, LA, edited by L. Peng, et al, 758 - 763. New York, New York:Association for Computing Machinery. PNNL-SA-211078. doi:10.1145/3716368.3735223
  • Varshika M.L., J. Hollenbach, N. Bohm Agostini, A.M. Limaye, A. Tumeo, and A. Das. 2025. "Online Learning for Dynamic Structural Characterization in Electron Energy Loss Spectroscopy." In Design, Automation & Test in Europe Conference (DATE 2025), March 31-April 2, 2025, Lyon, France, 1-7. Piscataway, New Jersey:IEEE. PNNL-SA-203900. doi:10.23919/DATE64628.2025.10992865
  • Yin J., Z. Song, N. Bohm Agostini, A. Tumeo, and C. Yu. 2025. "HEC: Equivalence Verification Checking for Code Transformation via Equality Saturation." In Proceedings of the 2025 USENIX Annual Technical Conference (ATC 2025), July 7-9, 2025, Boston, MA, 1181 - 1196. Berkeley, California:USENIX Association. PNNL-SA-211091.

2024

  • Bohm Agostini N., P. Gibson, J. Haris, M. Jayaweera, N. Rubin, A. Tumeo, and J.L. Abell�n, et al. 2024. "AXI4MLIR: User-Driven Automatic Host Code Generation for Custom AXI-Based Accelerators." In IEEE/ACM International Symposium on Code Generation and Optimization (CGO 2024), March 2-6, 2024, Edinburgh, UK, 143-157. Piscataway, New Jersey:IEEE. PNNL-SA-184683. doi:10.1109/CGO57630.2024.10444801
  • Johnson C.G., N. Bohm Agostini, W.R. Cannon, and A. Tumeo. 2024. "Computing with a Chemical Reservoir." In IEEE International Conference on Rebooting Computing (ICRC 2024), December 16-17, 2024, San Diego, CA, 1-7. Piscataway, New Jersey:IEEE. PNNL-SA-204902. doi:10.1109/ICRC64395.2024.10937022
  • Limaye A.M., C. Barone, N. Bohm Agostini, M. Minutoli, J.B. Manzano Franco, V.G. Castellana, and G. Gozzi, et al. 2024. "Towards Automated Generation of Chiplet-Based Systems." In Proceedings of the 29th Asia and South Pacific Design Automation Conference (ASPDAC 2024), January 22-25, 2024, Incheon, South Korea, 771-776. Piscataway, New Jersey:IEEE. PNNL-SA-192586. doi:10.1109/ASP-DAC58780.2024.10473980

2023

  • Castellana V.G., N. Bohm Agostini, A.M. Limaye, V.C. Amatya, M. Minutoli, J.B. Manzano Franco, and A. Tumeo, et al. 2023. "Towards On-Chip Learning for Low Latency Reasoning with End-to-End Synthesis." In Proceedings of the 28th Asia and South Pacific Design Automation Conference (ASPDAC 2023), January 16-19, 2023, Tokyo, Japan, 632-638. New York, New York:Association for Computing Machinery. PNNL-SA-179740. doi:10.1145/3566097.3568360
  • Luo Y., C. Tan, N. Bohm Agostini, A. Li, A. Tumeo, N. Dave, and T. Geng. 2023. "ML-CGRA: An Integrated Compilation Framework to Enable Efficient Machine Learning Acceleration on CGRAs." In Proceedings of the 60th ACM/IEEE Design Automation Conference (DAC 2023), July 9-13, 2023, San Franciso, CA, 1-6. Piscataway, New Jersey:IEEE. PNNL-SA-180015. doi:10.1109/DAC56929.2023.10247873

2022

  • Bohm Agostini N., A.M. Limaye, M. Minutoli, V.G. Castellana, J.B. Manzano Franco, A. Tumeo, and S. Curzel, et al. 2022. "SODA Synthesizer: an Open-source, Multi-level, Modular, Extensible Compiler from High-level Frameworks to Silicon." In Proceedings of the 41st IEEE/ACM International Conference on Computer-Aided Design (ICCAD 2022), October 30-November 3, 2022, San Diego, CA, Art. No. 18. New York, New York:Association for Computing Machinery. PNNL-SA-176485. doi:10.1145/3508352.3561101
  • Bohm Agostini N., S. Curzel, A.M. Limaye, V.C. Amatya, M. Minutoli, V.G. Castellana, and J.B. Manzano Franco, et al. 2022. "The SODA Approach: Leveraging High-Level Synthesis for Hardware/Software Co-design and Hardware Specialization: Invited." In Proceedings of the 59th ACM/IEEE Design Automation Conference (DAC 2022), July 10-14, 2022, San Francisco, CA, 1359-1362. New York, New York:Association for Computing Machinery. PNNL-SA-172445. doi:10.1145/3489517.3530628
  • Bohm Agostini N., S. Curzel, J. Zhang, A.M. Limaye, C. Tan, V.C. Amatya, and M. Minutoli, et al. 2022. "Bridging Python to Silicon: The SODA Toolchain." IEEE Micro 42, no. 5:78 - 88. PNNL-SA-169276. doi:10.1109/MM.2022.3178580
  • Bohm Agostini N., S. Curzel, V.C. Amatya, C. Tan, M. Minutoli, V.G. Castellana, and J.B. Manzano Franco, et al. 2022. "An MLIR-based Compiler Flow for System-Level Design and Hardware Acceleration." In Proceedings of the 41st IEEE/ACM International Conference on Computer-Aided Design (ICCAD 2022), October 30-November 3, 2022, San Diego, CA, Art. No. 6. New York, New York:Association for Computing Machinery. PNNL-SA-173501. doi:10.1145/3508352.3549424
  • Tan C., N. Bohm Agostini, T. Geng, C. Xie, J. Li, A. Li, and K.J. Barker, et al. 2022. "DRIPS: Dynamic Rebalancing of Pipelined Streaming Applications on CGRAs." In IEEE International Symposium on High-Performance Computer Architecture (HPCA 2022), April 2-6, 2022, Seoul, Korea, 304-316. Piscataway, New Jersey:IEEE. PNNL-SA-165149. doi:10.1109/HPCA53966.2022.00030

2021

  • Curzel S., N. Bohm Agostini, S. Song, I. Dagli, A.M. Limaye, C. Tan, and M. Minutoli, et al. 2021. "Automated Generation of Integrated Digital and Spiking Neuromorphic Machine Learning Accelerators." In IEEE/ACM International Conference On Computer Aided Design (ICCAD 2021), November 1-4, 2021, Munich, Germany, 1-7. Piscataway, New Jersey:IEEE. PNNL-SA-166239. doi:10.1109/ICCAD51958.2021.9643474
  • Tan C., T. Geng, C. Xie, N. Bohm Agostini, J. Li, A. Li, and K.J. Barker, et al. 2021. "DynPaC: Coarse-Grained, Dynamic, and Partially Reconfigurable Array for Streaming Applications." In IEEE 39th International Conference on Computer Design (ICCD 2021), October 24-27, 2021, Virtual, Online, 33-40. Piscataway, New Jersey:IEEE. PNNL-SA-163151. doi:10.1109/ICCD53106.2021.00018
  • Zhang J., N. Bohm Agostini, S. Song, C. Tan, A.M. Limaye, V.C. Amatya, and J.B. Manzano Franco, et al. 2021. "Towards Automatic and Agile AI/ML Accelerator Design with End-to-End Synthesis." In IEEE 32nd International Conference on Application-specific Systems, Architectures and Processors (ASAP 2021), July 7-9, 2021, Virtual, 218-225. Piscataway, New Jersey:IEEE. PNNL-SA-163507. doi:10.1109/ASAP52443.2021.00040