Clang offload bundle example

build.sh

#!/bin/sh
/opt/rocm/llvm/bin/clang++ --offload-arch=gfx906:xnack- -L/opt/rocm/hip/lib -lamdhip64 ex.hip

ex.hip

#include <hip/hip_runtime.h>

__global__ void square(int* array, int n) {
    int tid = blockDim.x * blockIdx.x + threadIdx.x;
    if (tid < n)
        array[tid] = array[tid] * array[tid];
}

int main() {
}