Error: "'bin2c' is not recognized as an internal or external command, operable program or batch file."

I’m trying to setup the latest PGI Community Edition (https://www.pgroup.com/products/community.htm) for Windows, on a non-NVIDIA GPU computer.

I understand that this is possible, based on this page https://developer.nvidia.com/pgi-cuda-cc-x86 (who’s download redirects me to the PGI Community Edition),

The PGI CUDA C compiler for x86 platforms allows developers using CUDA to compile and optimize their CUDA applications to run on x86-based workstations, servers and clusters with or without an NVIDIA GPU accelerator.

However after installing Visual Studio with appropriate components like the instructions asked, and installing PGI Community Edition, I get the following error when I run

nvcc hello_world.cu

,

Error: “‘bin2c’ is not recognized as an internal or external command, operable program or batch file.”

Anybody know what the error is?

The hello_world.cu program,

#include <stdio.h>
#include <stdlib.h>

// CUDA runtime
#include <cuda_runtime.h>

__global__ void cuda_hello(){
    printf("Hello World from GPU!\n");
}

int main() {
    cuda_hello<<<1,1>>>(); 
    return 0;
}

I suggest asking questions about this product on the userforums for PGI:

http://pgroup.com/userforum

I’m reasonably sure the cuda-x86 product is no longer supported:

https://www.pgroup.com/resources/docs/18.10/x86/pgi-release-notes/index.htm

“Dropped support for CUDA x86. The -⁠Mcudax86 compiler option is no longer supported.”

(and I believe the end of support for that capability on windows actually predated that announcement)

Also this:

nvcc hello_world.cu

was never the method to invoke the CUDA-x86 capability. When it was still supported by PGI, you had to do something like:

pgcc -Mcudax86 …