SWDEV-292525 - [vdi] Path to streamOps shaders

Implementation to use a blit kernel to perform
a hipStreamWait/write instead of an AQL packet.

Change-Id: I462671ed5cec37144dfe97ff66439249196117c1

rocclr/utils/flags.hpp

@@ -263,7 +263,9 @@ release(size_t, PAL_PREPINNED_MEMORY_SIZE, 64,                                \
 release(bool, AMD_CPU_AFFINITY, false,                                        \
         "Reset CPU affinity of any runtime threads")                          \
 release(bool, ROC_USE_FGS_KERNARG, true,                                      \
-        "Use fine grain kernel args segment for supported asics")
+        "Use fine grain kernel args segment for supported asics")             \
+release(bool, GPU_STREAMOPS_CP_WAIT, false,                                   \
+        "Force the stream wait memory operation to wait on CP.")
 
 namespace amd {