GpuPINNTrainingOptions
Options & Configuration · AiDotNet.PhysicsInformed
Configuration options for GPU-accelerated PINN training.
How It Works
For Beginners: These options control how GPU acceleration is used during physics-informed training. GPU acceleration can significantly speed up training by parallelizing operations across thousands of collocation points simultaneously.
Key settings:
- EnableGpu: Master switch for GPU acceleration
- BatchSizeGpu: Larger batches benefit more from GPU parallelism
- ParallelDerivativeComputation: Compute derivatives for multiple points at once
- AsyncTransfers: Overlap CPU/GPU data transfers with computation
Constructors
| Constructor | Summary |
|---|---|
GpuPINNTrainingOptions() |
Properties
| Property | Summary |
|---|---|
GpuAccelerationConfig GpuConfig { get; set; } |
Gets or sets the GPU acceleration configuration. |
GpuPINNTrainingOptions CpuOnly { get; } |
Creates options that disable GPU entirely (CPU-only mode). |
GpuPINNTrainingOptions Default { get; } |
Creates default options suitable for most GPUs. |
GpuPINNTrainingOptions HighEnd { get; } |
Creates options optimized for high-end GPUs (RTX 4090, A100, H100). |
GpuPINNTrainingOptions LowMemory { get; } |
Creates options optimized for memory-constrained GPUs. |
bool AsyncTransfers { get; set; } |
Gets or sets whether to use asynchronous GPU transfers. |
bool EnableGpu { get; set; } |
Gets or sets whether to enable GPU acceleration (default: true if GPU available). |
bool ParallelDerivativeComputation { get; set; } |
Gets or sets whether to compute derivatives in parallel across the batch. |
bool UseMixedPrecision { get; set; } |
Gets or sets whether to use mixed precision (FP16) for forward/backward passes. |
bool UsePinnedMemory { get; set; } |
Gets or sets whether to pin memory for faster GPU transfers. |
bool VerboseLogging { get; set; } |
Gets or sets whether to enable verbose GPU logging for debugging. |
int BatchSizeGpu { get; set; } |
Gets or sets the batch size for GPU operations. |
int MinPointsForGpu { get; set; } |
Gets or sets the minimum number of collocation points to trigger GPU usage. |
int NumStreams { get; set; } |
Gets or sets the number of CUDA streams for parallel operations. |