Use non-temporal access for streaming data (#341)

* Use non-temporal access for streaming data

* Revert to ulong2 after fixing compiling issue

tools/rccl-prim-test/rccl_prim_test.cpp

@@ -29,7 +29,6 @@ THE SOFTWARE.
 #include <iostream> //cerr
 #include <unistd.h> //usleep
 #include <cstring>
-#include <hip/hip_runtime_api.h>
 #include <hip/hip_runtime.h>
 #include "copy_kernel.h"