Why dla need so much workspace size?

i want to transfrom my models from onnx to tensorrt and work in dla instead of gpu.
but it was always print

[TensorRT] ERROR: Try increasing the workspace size with IBuilderConfig::setMaxWorkspaceSize() if using IBuilder::buildEngineWithConfig, or IBuilder::setMaxWorkspaceSize() if using IBuilder::buildCudaEngine.

even if the max workspace size had been set to 5 GiB.
there was no more memory to increase.

i work with nvidia nx

nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2019 NVIDIA Corporation
Built on Wed_Oct_23_21:14:42_PDT_2019
Cuda compilation tools, release 10.2, V10.2.89

Hi,
Please check the below links, as they might answer your concerns.
https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#dla_topic
https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#dla_layers
Thanks!

Hi @fanyj233,

We request you to use following thread.

Thank you.