5

After persistently getting error : identifier "atomicAdd" is undefined, I've found the solution to be to compile with -arch sm_20 flag. But how to pass this compiler flag in VS 2010? I have tried like so under Project > Properties:

enter image description here

But this apparently has had no effect and the error persists - what am I doing wrong?

Many thanks.

mchen
  • 9,808
  • 17
  • 72
  • 125

3 Answers3

15

You can select the options for the GPU Code Generation in this dialog:

GPU Code Generation

In this case "compute_20" means that i am compiling for the virtual compute architecture 2.0 - virtual architecture influences the PTX generation stage.

The second part that comes after the coma is "sm_21".This influences the CUBIN generation stage. It defines the real GPU architecture i want to compile the PTX to.

You can find detailed description of the nvcc command line parameters that control the code generation here.

RoBiK
  • 1,740
  • 12
  • 15
2

Go to the "Device" section under "CUDA C/C++". There, within "Code Generation" you can specify your sm_20. No need for the -arch.

Bart
  • 19,692
  • 7
  • 68
  • 77
2

Be aware that there's separate properties for both the project and .cu files. Apparently they get merged before compilation.

I'd gotten caught by this trying to specify GPUs for compute 3.0 & greater, but .cu properties had some leftover specifications for 1.0 & 2.0

DoctorBonzo
  • 41
  • 5