Predicting Accurate Hot Spots in a More Than Ten-Thousand-Core GPU with a Million-Time Speedup over FEM Enabled by a Physics-based Learning Algorithm

Documenti analoghi

• PyPOD-GP: Using PyTorch for Accelerated Chip-Level Thermal Simulation of the GPU
  di: He, Neil, et al.
  Pubblicazione: (2024)
• Revisiting the Canonicalization for Fast and Accurate Crystal Tensor Property Prediction
  di: Hua, Haowei, et al.
  Pubblicazione: (2024)
• Bridging Computational Fluid Dynamics Algorithm and Physics-Informed Learning: SIMPLE-PINN for Incompressible Navier-Stokes Equations
  di: Wei, Chang, et al.
  Pubblicazione: (2026)
• A Memory Efficient Adjoint Method to Enable Billion Parameter Optimization on a Single GPU in Dynamic Problems
  di: Herrmann, Leon, et al.
  Pubblicazione: (2025)
• MsFEM-Inspired CNNs with Transfer Learning for Multiscale Model Reduction
  di: Zhang, Xuehan, et al.
  Pubblicazione: (2026)