New laptop with GTX 1060. Just installed Ubuntu 16.04 and Cuda Toolkit 8.0. I start with creating a new project: Cuda C/C++ Project-> CUDA Runtime Projekt -> give name etc.
Then we get to the Generate PTX/GPU Code Setting. If i choose standard 3.5 and create project and run the generated example everything works as expected.
But if i choose only 6.0 on PTX and GPU code generation the example project will still run, but i will not have any cuda syntax highlights or auto completes in the file. Adding certain header files like cuda_runtime etc does not fix it.
I thought this setting is somewhat like "set compute capability to X.X" to get all the new cuda features with the higher version (like shfl, dynamic parallelism and so on). That's why i thought it should work like everything else if i select 6.0 instead of 3.5.
Am i missing something or am i just wrong about the expected behaviour?