Cuda fortran and optimization flags

Accelerated Computing HPC Compilers Legacy PGI Compilers
1

Hi,

I have some Cuda fortran code that makes heavy use of trigonometric functions for complex numbers.

I have noticed that the code produces correct output when I compile without optimization flags, i.e., -Mcuda=maxregcount:32,cc30,cuda5.5

However, as soon as I turn on optimization (e.g., -O2), results are corrupted. It’s difficult for me to find the problem but I am suspicious that optimization breaks some of the device intrinsics that I am using.

Any suggestions why this could happen? I thought that optimization only affect the CPU part of the code, not the device intrinsics.

Thanks, Jan

2

Hi Jan,

Optimization would be applied to your kernels so does have an effect. Though exactly what’s happening I’m not sure. Can you send us a reproducing example (or the whole code) so we can investigate?

Either send a note to PGI Customer Service (trs@pgroup.com) or I can send you a link to NVIDIA’s secure ftp where you can upload the package.

Thanks,
Mat