Hi Greg,

the solution that you outlined did not work on my system, probably because the host value of pBufOut remains equal to NULL after the offload, and the offload RTL does not know how to look up this array in the offloaded array table. The only way that I could make it work it is by passing a second array and copying the contents into it on the coprocessor:

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

int main() {

  size_t bufLen;
  char* pBufMIC = NULL;
  char* pBufHost = NULL;

#pragma offload target(mic:0) nocopy(pBufMIC : length(0) alloc_if(0) free_if(0))
  {
    bufLen = 60;
    pBufMIC = (char*) malloc(bufLen);
    for (int i = 0; i < bufLen; i++)
  pBufMIC[i] = (char)(48+i%10);
  }

  printf("On the host, bufLen = %ld\n", bufLen);
  pBufHost = (char*) malloc(bufLen);

#pragma offload target(mic:0) nocopy(pBufMIC : length(0) alloc_if(0) free_if(0)) out(pBufHost : length(bufLen))
  {
    pBufHost[0:bufLen] = pBufMIC[0:bufLen];
  }

  for (int i = 0; i < bufLen; i++) printf("%c", pBufHost[i]);
  printf("\n");
}

$ icpc foo1.cc

$ ./a.out
On the host, bufLen = 60
012345678901234567890123456789012345678901234567890123456789

There is, however, a much more elegant solution in the virtual-shared memory model:

#include <stdlib.h>
#include <iostream>

char* _Cilk_shared pBuf = NULL;
_Cilk_shared size_t bufLen;

_Cilk_shared void MyFunction() {
  bufLen = 60;
  pBuf = (char*) _Offload_shared_malloc(bufLen);
#ifdef __MIC__
  std::cout << "Initialized the array on the coprocessor\n" << std::flush;
#endif
  for (int i = 0; i < bufLen; i++)
    pBuf[i] = (char)(48+i%10);
}

int main() {
  _Cilk_offload MyFunction();
  std::cout << "Back on the host, lOutBufLen = " << bufLen << std::endl;
  for (int i = 0; i < bufLen; i++) std::cout << pBuf[i]; std::cout << std::endl;
}

$ icpc foo2.cc

$ ./a.out

Initialized the array on the coprocessor
Back on the host, lOutBufLen = 60
012345678901234567890123456789012345678901234567890123456789