Enhance HIP trace debug functions.

- Control with HIP_DB=mask (env var).  See src/hip_hcc.cpp for mask
  values:
    #define DB_API    0 /* 0x01 - shortcut to enable HIP_TRACE_API on single switch */
    #define DB_SYNC   1 /* 0x02 - trace synchronization pieces */
    #define DB_MEM    2 /* 0x04 - trace memory allocation / deallocation */
    #define DB_COPY1  3 /* 0x08 - trace memory copy commands. . */
    #define DB_SIGNAL 4 /* 0x10 - trace signal pool commands */
- Combine with HIP_TRACE to see debug with API trace.
- Use colors to distinguish different flows of debug.
- Add define COMPILE_DB_TRACE to allow removing all debug at compile-time

include/hcc_detail/hip_runtime.h

@@ -500,7 +500,7 @@ do {\
   lp.cf = &cf;  \
   hipStream_t trueStream = (ihipPreLaunchKernel(_stream, &lp.av)); \
     if (HIP_TRACE_API) {\
-        fprintf(stderr, "hiptrace1: launch '%s' gridDim:[%d.%d.%d] groupDim:[%d.%d.%d] groupMem:+%d stream=%p\n", \
+        fprintf(stderr, "==hip-api: launch '%s' gridDim:[%d.%d.%d] groupDim:[%d.%d.%d] groupMem:+%d stream=%p\n", \
                 #_kernelName, lp.gridDim.z, lp.gridDim.y, lp.gridDim.x, lp.groupDim.z, lp.groupDim.y, lp.groupDim.x, lp.groupMemBytes, (void*)(_stream));\
     }\
   _kernelName (lp, __VA_ARGS__);\