TensorRT setMaxWorkspaceSize的含义

NVIDIA的官方入门博客有两段说的比较详细

TensorRT allows you to increase GPU memory footprint during the engine building phase with the setMaxWorkspaceSize function. Increasing the limit may affect the number of applications that could share the GPU at the same time. Setting this limit too low may filter out several algorithms and create a suboptimal engine. TensorRT allocates just the memory required even if the amount set in IBuilder::setMaxWorkspaceSize is much higher. Applications should therefore allow the TensorRT builder as much workspace as they can afford. TensorRT allocates no more than this and typically less.
This example uses 1 GB, which lets TensorRT pick any algorithm available.

Layer algorithms often require temporary workspace. This parameter limits the maximum
size that any layer in the network can use. If an insufficient scratch is provided, it is
possible that TensorRT may not be able to find an implementation for a given layer.

// Allow TensorRT to use up to 1 GB of GPU memory for tactic selectionconstexpr size_t MAX_WORKSPACE_SIZE = 1ULL << 30; // 1 GB worked well for this example
...
// Set the builder flag
builder->setMaxWorkspaceSize(MAX_WORKSPACE_SIZE);