How to run Cuda with cub

I am trying wrap thrust and cub in different enclosing namespaces follow [RFE] Support linking multiple Thrust versions: Add hooks that wrap the `thrust::` namespace in a custom namespace · Issue #1401 · NVIDIA/thrust · GitHub but i can’t run it in jetson xavier nx. Please help me a tutorial to run both together.

Hi,

Did you meet any errors when doing so?
If yes, could you share a sample and the error log with us?

Thanks.

error: name followed by “::” must be a class or namespace name when I use DeviceScan::InclusiveSum() and thrust together.

Hi,

Could you share the sample with us so we can check how to modify it directly?

Thanks.

I try to reinit TLD GPU with example htld/heterogenous_tld_lib at e431720d9a7cc129cd847f54881199916e35043f · ShawnHuang/htld · GitHub

But I can’t build hetld_cu library.

Hi,

Thanks for the feedback.
We are checking this internally and will share more information with you later.

Thanks.

Hi,

Could you share the error when you build the hetld_cu library?
The library looks designed for a desktop user rather than Jetson.

Thanks

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.