Message Boards Message Boards

Using CUDA Function Load and C compiler error Red Hat RHEL 6.5

I am using CUDA under Red Hat Linux  RHEL  6.5  86_64 . ; I am using the NVIDIA driver and a GeoForce 630 Card.

entered this code
doubleFun = CUDAFunctionLoad["
  __global__ void doubleVec(mint * in,  mint length) {
      mint index = threadIdx.x + blockIdx.x * blockDim.x;
 
   if (index < length)
     in[index] = 2*in[index];
    }", "doubleVec", {{_Integer}, _Integer}, 256,
  ShellOutputFunction -> Print]

Then I got the followng error

CUDAFunctionLoad::cmpf: The kernel compilation failed. Consider setting the option "ShellOutputFunction"->Print to display the compiler error message. >>

The shelloutPrint options returns the following eror
gcc: error trying to exec 'cc1plus': execvp: No such file or directory


Need your help.   I code was extracted from Wolfram CUDALink documentation.  As you may see, confusing because the cc1plus:execvp is not part of my writen code.
POSTED BY: Jose Calderon
Reply to this discussion
Community posts can be styled and formatted using the Markdown syntax.
Reply Preview
Attachments
Remove
or Discard

Group Abstract Group Abstract