When are kernels loaded on to the device mem? Any CUDA Guru knows this

[Noel_Lopes]

Did this behavior change since CUDA 1.1?

My experiments with renouveau at that time where suggesting that it was only loaded after the cuLaunchGrid call.

Anyway, this means that if I use only one kernel in a module containing a few hundred kernels (typical of libraries using templates like CUBLAS, CUDPP…), all kernels will be loaded to device memory?

(I don’t say it’s a bad thing, just asking…)

I sure hope kernels are loaded only when they are called (in runtime). This is what makes sense for me.

However I would like to know this for sure.

Anyway, thank you Sylvain Collange and tmurray