SWDEV-491375 - Limit the SW batch size

Applications may submit commands withoout waits
for GPU. That causes a growth of SW unreleased commands.
Make sure runtime flushes SW queue, if it grows over some
threshold, controlled by DEBUG_CLR_MAX_BATCH_SIZE.

Change-Id: Ia4d85c24210ef91c394f638ab6b53b14323a0396

rocclr/utils/flags.hpp

@@ -259,6 +259,8 @@ release(bool, HIP_ALWAYS_USE_NEW_COMGR_UNBUNDLING_ACTION, false,              \
         "Force to always use new comgr unbundling action")                    \
 release(uint, DEBUG_HIP_BLOCK_SYNC, 50,                                       \
         "Blocks synchronization on CPU until the callback processing is done")\
+release(uint, DEBUG_CLR_MAX_BATCH_SIZE, 1000,                                 \
+        "Forces the callback to clean-up CPU submission queue")               \
 release(bool, DEBUG_HIP_KERNARG_COPY_OPT, true,                               \
         "Enable/Disable multiple kern arg copies")                            \
 release(bool, DEBUG_CLR_USE_STDMUTEX_IN_AMD_MONITOR, false,                   \