Limit max channels for ring graph on single node Rome (#347)

* Limit max channels for ring graph on single node Rome
* Partially revert "Use non-temporal access for streaming data (#341)"

tools/rccl-prim-test/rccl_prim_test.cpp

@@ -29,6 +29,7 @@ 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"