Learning Objectives
- Implement provided simulation stubs (heat diffusion, traffic flow, or population models).
- Profile runtime and interpret performance dashboards.
- Reflect on trade-offs between accuracy, speed, and hardware constraints.
A one-week intensive where teams implement simplified physics or environmental models and compare CPU versus GPU performance.
Perfect for advanced programming electives or HPC clubs that want a sprint-style experience with hardware profiling.
Day 1
Teams select a model, run baseline CPU code, and log assumptions.
Day 2–3
Students implement GPU or parallel extensions with mentor support.
Day 4–5
Teams present results, compare benchmarks, and complete retrospectives.
CPU baseline, GPU scaffolding, and test datasets.
Python + C options
Step-by-step log for capturing runtime, memory, and bottlenecks.
Printable + digital formats
Optional remote GPU environment with pre-configured logins.
Limited seats · request early
Artifacts
Evaluation
Complete lab materials are available via GitHub + shared drive access.
Sandbox onboarding steps, acceptable use policy, and troubleshooting tips.