kfdtest: A+A: CP writes to NC mem need flush

Refer to commit "Mark buffers accessed by CP as UC"

A+A buffers are mapped as NC. CP (PM4Writes) need ReleaseMem function to
ensure the write go through to the memory

Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Change-Id: I4ee55a6e40fba078f5950d95c8fee7ee076260bf


[ROCm/ROCR-Runtime commit: 57f46b53ec]

projects/rocr-runtime/tests/kfdtest/src/KFDLocalMemoryTest.cpp

@@ -58,6 +58,8 @@ TEST_F(KFDLocalMemoryTest, AccessLocalMem) {
 
     //local memory
     HsaMemoryBuffer destBuf(PAGE_SIZE, defaultGPUNode, false, true);
+    HsaEvent *event;
+    ASSERT_SUCCESS(CreateQueueTypeEvent(false, false, defaultGPUNode, &event));
 
     PM4Queue queue;
 
@@ -65,10 +67,12 @@ TEST_F(KFDLocalMemoryTest, AccessLocalMem) {
 
     queue.PlaceAndSubmitPacket(PM4WriteDataPacket(destBuf.As<unsigned int*>(), 0, 0));
 
-    queue.Wait4PacketConsumption();
+    queue.Wait4PacketConsumption(event);
 
+    hsaKmtDestroyEvent(event);
     EXPECT_SUCCESS(queue.Destroy());
 
+
     TEST_END
 }