test: add tests to validate cache/mem blocks

To validate cache and memory blocks profiling, this patch prepares
tests to profile dedicated kernels using specified counters, to
compare the profiled results against expected ones, and further
show the test is a fail or pass.  Tests here are focusing on cache
hit/miss, memory fetch/write size.

Change-Id: Icbc8096a6e15256dec66297597a57c7665a533b8

test/tool/metrics.xml

@@ -32,6 +32,7 @@
   <metric name="TCC_EA_WRREQ_64B_sum" expr=sum(TCC_EA_WRREQ_64B,16) descr="Number of 64-byte transactions going (64-byte write or CMPSWAP) over the TC_EA_wrreq interface. Sum over TCC instances."></metric>
   <metric name="TCC_WRREQ_STALL_max" expr=max(TCC_EA_WRREQ_STALL,16) descr="Number of cycles a write request was stalled. Max over TCC instances."></metric>
 
+  <metric name="TCC_MC_WRREQ_sum" expr=TCC_EA_WRREQ_64B_sum*2+(TCC_EA_WRREQ_sum-TCC_EA_WRREQ_64B_sum) descr="Number of 32-byte effective writes. Sum over TCC instaces."></metric>
   <metric name="FETCH_SIZE" expr=(TCC_EA_RDREQ_32B_sum*32+(TCC_EA_RDREQ_sum-TCC_EA_RDREQ_32B_sum)*64)/1024 descr="The total kilobytes fetched from the video memory. This is measured with all extra fetches and any cache or memory effects taken into account."></metric>
   <metric name="WRITE_SIZE" expr=((TCC_EA_WRREQ_sum-TCC_EA_WRREQ_64B_sum)*32+TCC_EA_WRREQ_64B_sum*64)/1024 descr="The total kilobytes written to the video memory. This is measured with all extra fetches and any cache or memory effects taken into account."></metric>
 </gfx9>
@@ -137,6 +138,13 @@
     expr=100*SQ_INST_CYCLES_SALU*4/SIMD_NUM/GRBM_GUI_ACTIVE
   ></metric>
 
+  # Mem32Bwrites    The number of effective 32B write transactions into memory
+  <metric
+    name="Mem32Bwrites"
+    descr=""
+    expr=TCC_MC_WRREQ_sum
+  ></metric>
+
   # FetchSize       The total kilobytes fetched from the video memory. This is measured with all extra fetches and any cache or memory effects taken into account.
   <metric
     name="FetchSize"