diff --git a/test/input.xml b/test/input.xml
index 884cb0cfb3..1c690c79a0 100644
--- a/test/input.xml
+++ b/test/input.xml
@@ -1,4 +1,4 @@
-<metric name=CPC_ME1_STALL_WAIT_ON_RCIU_READ,SQ_WAVES,SQ_WAVE_READY,SQ_CYCLES,SQ_ITEMS,SQ_INSTS_VMEM_WR,VWRITE_INSTS,SQ_INSTS_SMEM,SFETCH_INSTS ></metric>
+<metric name=SQ_CYCLES,SQ_WAVES,SQ_INSTS_SMEM,SQ_INSTS_VALU,TA_FLAT_WRITE_WAVEFRONTS[0],TA_FLAT_WRITE_WAVEFRONTS[1],CPC_ALWAYS_COUNT,CPC_ME1_STALL_WAIT_ON_RCIU_READ,VWRITE_INSTS,SFETCH_INSTS,VALU_INSTS ></metric>
 <trace name=SQTT copy=true >
   <parameters
     HSA_VEN_AMD_AQLPROFILE_PARAMETER_NAME_MASK=0xf
diff --git a/test/metrics.xml b/test/metrics.xml
index 0272badd1c..992e70913f 100644
--- a/test/metrics.xml
+++ b/test/metrics.xml
@@ -2,9 +2,12 @@
   <metric name=SQ_CYCLES block=SQ event=2 ></metric>
   <metric name=SQ_WAVES block=SQ event=4 ></metric>
   <metric name=SQ_ITEMS block=SQ event=14 ></metric>
+  <metric name=SQ_INSTS_VALU block=SQ event=26 ></metric>
   <metric name=SQ_INSTS_VMEM_WR block=SQ event=27 ></metric>
   <metric name=SQ_INSTS_VMEM_RD block=SQ event=28 ></metric>
   <metric name=SQ_INSTS_SMEM block=SQ event=31 ></metric>
+  <metric name=SQ_INSTS_FLAT_LDS_ONLY block=SQ event=33 ></metric>
+  <metric name=SQ_INSTS_LDS block=SQ event=34 ></metric>
   <metric name=SQ_WAVE_READY block=SQ event=47 ></metric>
 
   <metric name=TA_FLAT_READ_WAVEFRONTS block=TA event=101 ></metric>
@@ -17,22 +20,13 @@
   <metric name=CPC_ALWAYS_COUNT block=CPC event=0 ></metric>
   <metric name=CPC_ME1_STALL_WAIT_ON_RCIU_READ block=CPC event=8 ></metric>
 
-  <metric
-    name=TA_FLAT_READ_WAVEFRONTS_sum
-    expr=TA_FLAT_READ_WAVEFRONTS[0]+TA_FLAT_READ_WAVEFRONTS[1]
-  ></metric>
   <metric
     name=TA_FLAT_WRITE_WAVEFRONTS_sum
-    expr=TA_FLAT_WRITE_WAVEFRONTS[0]+TA_FLAT_WRITE_WAVEFRONTS[1]
+    expr=TA_FLAT_WRITE_WAVEFRONTS[0]+TA_FLAT_WRITE_WAVEFRONTS[1]+TA_FLAT_WRITE_WAVEFRONTS[2]+TA_FLAT_WRITE_WAVEFRONTS[3]
   ></metric>
 </gfx8>
 
 <global>
-  # VFETCH_INSTS
-  # The average number of vector fetch instructions from the video memory executed per work-item (affected by flow control).
-  # Excludes FLAT instructions that fetch from video memory.
-  <metric name=VFETCH_INSTS expr=1000*(SQ_INSTS_VMEM_RD-TA_FLAT_READ_WAVEFRONTS_sum)/SQ_WAVES ></metric>
-
   # VWRITE_INSTS
   # The average number of vector write instructions to the video memory executed per work-item (affected by flow control). Excludes FLAT instructions that write to video memory.
   <metric name=VWRITE_INSTS expr=1000*(SQ_INSTS_VMEM_WR-TA_FLAT_WRITE_WAVEFRONTS_sum)/SQ_WAVES ></metric>
@@ -40,4 +34,9 @@
   # SFETCH_INSTS
   # The average number of scalar fetch instructions from the video memory executed per work-item (affected by flow control).
   <metric name=SFETCH_INSTS expr=1000*SQ_INSTS_SMEM/SQ_WAVES ></metric>
+
+  # VALU_INSTS
+  # The average number of vector ALU instructions executed per work-item (affected by flow control).
+  <metric name=VALU_INSTS expr=SQ_INSTS_VALU/SQ_WAVES ></metric>
+
 </global>