counters dumping optimization

Change-Id: I8c694e5380e15179453148dd9ab3a3e51b6db861

test/tool/pmc_input1.xml

@@ -0,0 +1,14 @@
+# Filter by dispatches range, GPU index and kernel names
+<metric
+  # range format "3:9"
+  range=""
+  # list of gpu indexes "0,1,2,3"
+  gpu_index="0,1,2,3"
+  # list of matched sub-strings "Simple1,Conv1,SimpleConvolution"
+  kernel="Simple1,Conv1,SimpleConvolution"
+></metric>
+
+# List of metrics
+<metric
+  name=SQ:4,SQ_WAVES,SQ_INSTS_SMEM,SQ_INSTS_VALU,TA_FLAT_WRITE_WAVEFRONTS[0],TA_FLAT_WRITE_WAVEFRONTS[1],GPUBusy,VALUBusy,SALUBusy,MemUnitBusy,SFetchInsts,FetchSize,VWriteInsts
+></metric>