GPU Acceleration in Optimization and Optimal Control

Pre-congress workshop WS-12 at the 23rd IFAC World Congress — BEXCO Room 103, Busan, Sunday 23 August 2026, 08:30–12:00 KST.
Organizer: Sungho Shin, Massachusetts Institute of Technology · sushin@mit.edu

Lecture slides (PDF)
Hands-on notebooks
- GPU computing in the Julia language
- Optimal control and parameter estimation on GPUs
- The notebook server link for the live session is provided during the workshop.
- To run them locally on an NVIDIA GPU: notebooks and Julia environment

The lecture covers nonlinear optimization, optimal control as a structured nonlinear program, and GPU acceleration; the hands-on session works through the two notebooks above, using ExaModels.jl and MadNLP.jl on a hosted GPU environment. No GPU programming experience is required; bring a laptop with a web browser.

Schedule

All times KST (UTC+9).

08:30–08:35	Logistics
08:35–09:25	Lecture: nonlinear optimization; optimal control as a structured NLP
09:25–09:30	Short break
09:30–10:20	Lecture: GPU acceleration
10:20–10:40	Coffee break
10:40–11:15	Hands-on: GPU computing in Julia
11:15–11:55	Hands-on: optimal control and parameter estimation on GPUs
11:55–12:00	Closing

Registration and contact

Registration is through the IFAC 2026 pre-congress workshops program, available to congress registrants. Participants are expected to follow the IFAC Code of Ethics and Conduct. Questions: sushin@mit.edu.

Organizer

Sungho Shin, Department of Chemical Engineering, Massachusetts Institute of Technology. He works on GPU-accelerated nonlinear optimization for large-scale optimal control, and leads the development of MadNLP.jl and ExaModels.jl.
shin.mit.edu · Google Scholar · GitHub

Papers

The lectures draw on the following papers; a complete list is on the organizer's publications page.

F. Pacaud, S. Shin, A. Montoison, M. Schanen, M. Anitescu. Condensed interior-point methods for scalable nonlinear programming on GPUs. Mathematical Programming Computation, to appear. [arXiv:2405.14236]
S. Shin, M. Schanen, F. Pacaud, A. Montoison, M. Anitescu. ExaModels.jl: an algebraic modeling system for nonlinear programming on GPUs. 2026. [arXiv:2608.16265]
S. Shin, F. Pacaud, M. Anitescu. Accelerating optimal power flow with GPUs: SIMD abstraction of nonlinear programs and condensed-space interior-point methods. Electric Power Systems Research, 2024. [arXiv:2307.16830] [doi]
F. Pacaud, M. Schanen, S. Shin, D. A. Maldonado, M. Anitescu. Parallel interior-point solver for block-structured nonlinear programs on SIMD/GPU architectures. Optimization Methods and Software, 2024. [arXiv:2301.04869] [doi]
F. Pacaud, S. Shin. GPU-accelerated dynamic nonlinear optimization with ExaModels and MadNLP. 63rd IEEE Conference on Decision and Control (CDC), 2024. [arXiv:2403.15913] [doi]
F. Pacaud, S. Shin, M. Schanen, D. A. Maldonado, M. Anitescu. Accelerating condensed interior-point methods on SIMD/GPU architectures. Journal of Optimization Theory and Applications, 2023. [arXiv:2203.11875] [doi]
A. Montoison, F. Pacaud, S. Shin. GPU implementation of second-order linear and nonlinear programming solvers. NeurIPS Workshop on GPU-Accelerated and Scalable Optimization, 2025. [arXiv:2508.16094]