Add unit [FLOP/Byte] to all operational intensity metrics (#542)

RRZE-HPC · Oct 20, 2023 · 31fdd93 · 31fdd93
1 parent c001f8c
commit 31fdd93
Show file tree

Hide file tree

Showing 26 changed files with 89 additions and 62 deletions.
diff --git a/groups/CLX/MEM_DP.txt b/groups/CLX/MEM_DP.txt
@@ -42,9 +42,10 @@ Memory write bandwidth [MBytes/s] 1.0E-06*(MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4
 Memory write data volume [GBytes] 1.0E-09*(MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1)*64.0
 Memory bandwidth [MBytes/s] 1.0E-06*(MBOX0C0+MBOX1C0+MBOX2C0+MBOX3C0+MBOX4C0+MBOX5C0+MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1)*64.0/time
 Memory data volume [GBytes] 1.0E-09*(MBOX0C0+MBOX1C0+MBOX2C0+MBOX3C0+MBOX4C0+MBOX5C0+MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1)*64.0
-Operational intensity (PMC0*2.0+PMC1+PMC2*4.0+PMC3*8.0)/((MBOX0C0+MBOX1C0+MBOX2C0+MBOX3C0+MBOX4C0+MBOX5C0+MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1)*64.0)
+Operational intensity [FLOP/Byte] (PMC0*2.0+PMC1+PMC2*4.0+PMC3*8.0)/((MBOX0C0+MBOX1C0+MBOX2C0+MBOX3C0+MBOX4C0+MBOX5C0+MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1)*64.0)
 Vectorization ratio [%] 100*(PMC0+PMC2+PMC3)/(PMC0+PMC1+PMC2+PMC3)
 
+
 LONG
 Formulas:
 Power [W] = PWR_PKG_ENERGY/runtime
@@ -59,7 +60,7 @@ Memory write bandwidth [MBytes/s] = 1.0E-06*(SUM(CAS_COUNT_WR))*64.0/runtime
 Memory write data volume [GBytes] = 1.0E-09*(SUM(CAS_COUNT_WR))*64.0
 Memory bandwidth [MBytes/s] = 1.0E-06*(SUM(CAS_COUNT_RD)+SUM(CAS_COUNT_WR))*64.0/runtime
 Memory data volume [GBytes] = 1.0E-09*(SUM(CAS_COUNT_RD)+SUM(CAS_COUNT_WR))*64.0
-Operational intensity = (FP_ARITH_INST_RETIRED_128B_PACKED_DOUBLE*2+FP_ARITH_INST_RETIRED_SCALAR_DOUBLE+FP_ARITH_INST_RETIRED_256B_PACKED_DOUBLE*4+FP_ARITH_INST_RETIRED_512B_PACKED_DOUBLE*8)/(SUM(CAS_COUNT_RD)+SUM(CAS_COUNT_WR))*64.0)
+Operational intensity [FLOP/Byte] = (FP_ARITH_INST_RETIRED_128B_PACKED_DOUBLE*2+FP_ARITH_INST_RETIRED_SCALAR_DOUBLE+FP_ARITH_INST_RETIRED_256B_PACKED_DOUBLE*4+FP_ARITH_INST_RETIRED_512B_PACKED_DOUBLE*8)/(SUM(CAS_COUNT_RD)+SUM(CAS_COUNT_WR))*64.0)
 Vectorization ratio [%] = 100*(FP_ARITH_INST_RETIRED_128B_PACKED_DOUBLE+FP_ARITH_INST_RETIRED_256B_PACKED_DOUBLE+FP_ARITH_INST_RETIRED_512B_PACKED_DOUBLE)/(FP_ARITH_INST_RETIRED_SCALAR_DOUBLE+FP_ARITH_INST_RETIRED_128B_PACKED_DOUBLE+FP_ARITH_INST_RETIRED_256B_PACKED_DOUBLE+FP_ARITH_INST_RETIRED_512B_PACKED_DOUBLE)
 --
 Profiling group to measure memory bandwidth drawn by all cores of a socket.

diff --git a/groups/CLX/MEM_SP.txt b/groups/CLX/MEM_SP.txt
@@ -42,7 +42,7 @@ Memory write bandwidth [MBytes/s] 1.0E-06*(MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4
 Memory write data volume [GBytes] 1.0E-09*(MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1)*64.0
 Memory bandwidth [MBytes/s] 1.0E-06*(MBOX0C0+MBOX1C0+MBOX2C0+MBOX3C0+MBOX4C0+MBOX5C0+MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1)*64.0/time
 Memory data volume [GBytes] 1.0E-09*(MBOX0C0+MBOX1C0+MBOX2C0+MBOX3C0+MBOX4C0+MBOX5C0+MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1)*64.0
-Operational intensity (PMC0*4.0+PMC1+PMC2*8.0+PMC3*16.0)/((MBOX0C0+MBOX1C0+MBOX2C0+MBOX3C0+MBOX4C0+MBOX5C0+MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1)*64.0)
+Operational intensity [FLOP/Byte] (PMC0*4.0+PMC1+PMC2*8.0+PMC3*16.0)/((MBOX0C0+MBOX1C0+MBOX2C0+MBOX3C0+MBOX4C0+MBOX5C0+MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1)*64.0)
 Vectorization ratio [%] 100*(PMC0+PMC2+PMC3)/(PMC0+PMC1+PMC2+PMC3)
 
 LONG
@@ -59,7 +59,7 @@ Memory write bandwidth [MBytes/s] = 1.0E-06*(SUM(CAS_COUNT_WR))*64.0/runtime
 Memory write data volume [GBytes] = 1.0E-09*(SUM(CAS_COUNT_WR))*64.0
 Memory bandwidth [MBytes/s] = 1.0E-06*(SUM(CAS_COUNT_RD)+SUM(CAS_COUNT_WR))*64.0/runtime
 Memory data volume [GBytes] = 1.0E-09*(SUM(CAS_COUNT_RD)+SUM(CAS_COUNT_WR))*64.0
-Operational intensity = (FP_ARITH_INST_RETIRED_128B_PACKED_SINGLE*4+FP_ARITH_INST_RETIRED_SCALAR_SINGLE+FP_ARITH_INST_RETIRED_256B_PACKED_SINGLE*8+FP_ARITH_INST_RETIRED_512B_PACKED_SINGLE*16)/(SUM(CAS_COUNT_RD)+SUM(CAS_COUNT_WR))*64.0)
+Operational intensity [FLOP/Byte] = (FP_ARITH_INST_RETIRED_128B_PACKED_SINGLE*4+FP_ARITH_INST_RETIRED_SCALAR_SINGLE+FP_ARITH_INST_RETIRED_256B_PACKED_SINGLE*8+FP_ARITH_INST_RETIRED_512B_PACKED_SINGLE*16)/(SUM(CAS_COUNT_RD)+SUM(CAS_COUNT_WR))*64.0)
 Vectorization ratio [%] = 100*(FP_ARITH_INST_RETIRED_128B_PACKED_SINGLE+FP_ARITH_INST_RETIRED_256B_PACKED_SINGLE+FP_ARITH_INST_RETIRED_512B_PACKED_SINGLE)/(FP_ARITH_INST_RETIRED_SCALAR_SINGLE+FP_ARITH_INST_RETIRED_128B_PACKED_SINGLE+FP_ARITH_INST_RETIRED_256B_PACKED_SINGLE+FP_ARITH_INST_RETIRED_512B_PACKED_SINGLE)
 --
 Profiling group to measure memory bandwidth drawn by all cores of a socket.

diff --git a/groups/ICL/MEM_DP.txt b/groups/ICL/MEM_DP.txt
@@ -34,7 +34,7 @@ Memory evict bandwidth [MBytes/s]  1.0E-06*MBOX0C2*64.0/time
 Memory evict data volume [GBytes]  1.0E-09*MBOX0C2*64.0
 Memory bandwidth [MBytes/s] 1.0E-06*(MBOX0C1+MBOX0C2)*64.0/time
 Memory data volume [GBytes] 1.0E-09*(MBOX0C1+MBOX0C2)*64.0
-Operational intensity (PMC0*2.0+PMC1+PMC2*4.0+PMC3*8.0)/((MBOX0C1+MBOX0C2)*64.0)
+Operational intensity [FLOP/Byte] (PMC0*2.0+PMC1+PMC2*4.0+PMC3*8.0)/((MBOX0C1+MBOX0C2)*64.0)
 Vectorization ratio [%] 100*(PMC0+PMC2+PMC3)/(PMC0+PMC1+PMC2+PMC3)
 
 LONG
@@ -52,8 +52,9 @@ Memory write bandwidth [MBytes/s] = 1.0E-06*DRAM_WRITES*64.0/runtime
 Memory write data volume [GBytes] = 1.0E-09*DRAM_WRITES*64.0
 Memory bandwidth [MBytes/s] = 1.0E-06*(DRAM_READS+DRAM_WRITES)*64.0/runtime
 Memory data volume [GBytes] = 1.0E-09*(DRAM_READS+DRAM_WRITES)*64.0
-Operational intensity = (FP_ARITH_INST_RETIRED_128B_PACKED_DOUBLE*2+FP_ARITH_INST_RETIRED_SCALAR_DOUBLE+FP_ARITH_INST_RETIRED_256B_PACKED_DOUBLE*4+FP_ARITH_INST_RETIRED_512B_PACKED_DOUBLE*8)/(DRAM_READS+DRAM_WRITES)*64.0)
+Operational intensity [FLOP/Byte] = (FP_ARITH_INST_RETIRED_128B_PACKED_DOUBLE*2+FP_ARITH_INST_RETIRED_SCALAR_DOUBLE+FP_ARITH_INST_RETIRED_256B_PACKED_DOUBLE*4+FP_ARITH_INST_RETIRED_512B_PACKED_DOUBLE*8)/(DRAM_READS+DRAM_WRITES)*64.0)
 Vectorization ratio [%] = 100*(FP_ARITH_INST_RETIRED_128B_PACKED_DOUBLE+FP_ARITH_INST_RETIRED_256B_PACKED_DOUBLE+FP_ARITH_INST_RETIRED_512B_PACKED_DOUBLE)/(FP_ARITH_INST_RETIRED_SCALAR_DOUBLE+FP_ARITH_INST_RETIRED_128B_PACKED_DOUBLE+FP_ARITH_INST_RETIRED_256B_PACKED_DOUBLE+FP_ARITH_INST_RETIRED_512B_PACKED_DOUBLE)
+
 --
 Profiling group to measure memory bandwidth drawn by all cores of a socket.
 Since this group is based on Uncore events it is only possible to measure on

diff --git a/groups/ICL/MEM_SP.txt b/groups/ICL/MEM_SP.txt
@@ -34,7 +34,7 @@ Memory evict bandwidth [MBytes/s]  1.0E-06*MBOX0C2*64.0/time
 Memory evict data volume [GBytes]  1.0E-09*MBOX0C2*64.0
 Memory bandwidth [MBytes/s] 1.0E-06*(MBOX0C1+MBOX0C2)*64.0/time
 Memory data volume [GBytes] 1.0E-09*(MBOX0C1+MBOX0C2)*64.0
-Operational intensity (PMC0*4.0+PMC1+PMC2*8.0+PMC3*16.0)/((MBOX0C1+MBOX0C2)*64.0)
+Operational intensity [FLOP/Byte] (PMC0*4.0+PMC1+PMC2*8.0+PMC3*16.0)/((MBOX0C1+MBOX0C2)*64.0)
 Vectorization ratio [%] 100*(PMC0+PMC2+PMC3)/(PMC0+PMC1+PMC2+PMC3)
 
 LONG
@@ -52,8 +52,9 @@ Memory write bandwidth [MBytes/s] = 1.0E-06*DRAM_WRITES*64.0/runtime
 Memory write data volume [GBytes] = 1.0E-09*DRAM_WRITES*64.0
 Memory bandwidth [MBytes/s] = 1.0E-06*(DRAM_READS+DRAM_WRITES)*64.0/runtime
 Memory data volume [GBytes] = 1.0E-09*(DRAM_READS+DRAM_WRITES)*64.0
-Operational intensity = (FP_ARITH_INST_RETIRED_128B_PACKED_SINGLE*4+FP_ARITH_INST_RETIRED_SCALAR_SINGLE+FP_ARITH_INST_RETIRED_256B_PACKED_SINGLE*8+FP_ARITH_INST_RETIRED_512B_PACKED_SINGLE*16)/(DRAM_READS+DRAM_WRITES)*64.0)
+Operational intensity [FLOP/Byte] = (FP_ARITH_INST_RETIRED_128B_PACKED_SINGLE*4+FP_ARITH_INST_RETIRED_SCALAR_SINGLE+FP_ARITH_INST_RETIRED_256B_PACKED_SINGLE*8+FP_ARITH_INST_RETIRED_512B_PACKED_SINGLE*16)/(DRAM_READS+DRAM_WRITES)*64.0)
 Vectorization ratio [%] = 100*(FP_ARITH_INST_RETIRED_128B_PACKED_SINGLE+FP_ARITH_INST_RETIRED_256B_PACKED_SINGLE+FP_ARITH_INST_RETIRED_512B_PACKED_SINGLE)/(FP_ARITH_INST_RETIRED_SCALAR_SINGLE+FP_ARITH_INST_RETIRED_128B_PACKED_SINGLE+FP_ARITH_INST_RETIRED_256B_PACKED_SINGLE+FP_ARITH_INST_RETIRED_512B_PACKED_SINGLE)
+
 -
 Profiling group to measure memory bandwidth drawn by all cores of a socket.
 Since this group is based on Uncore events it is only possible to measure on

diff --git a/groups/ICX/MEM_DP.txt b/groups/ICX/MEM_DP.txt
@@ -47,9 +47,10 @@ Memory write bandwidth [MBytes/s] 1.0E-06*(MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4
 Memory write data volume [GBytes] 1.0E-09*(MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1+MBOX6C1+MBOX7C1)*64.0
 Memory bandwidth [MBytes/s] 1.0E-06*(MBOX0C0+MBOX1C0+MBOX2C0+MBOX3C0+MBOX4C0+MBOX5C0+MBOX6C0+MBOX7C0+MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1+MBOX6C1+MBOX7C1)*64.0/time
 Memory data volume [GBytes] 1.0E-09*(MBOX0C0+MBOX1C0+MBOX2C0+MBOX3C0+MBOX4C0+MBOX5C0+MBOX6C0+MBOX7C0+MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1+MBOX6C1+MBOX7C1)*64.0
-Operational intensity (PMC0*2.0+PMC1+PMC2*4.0+PMC3*8.0)/((MBOX0C0+MBOX1C0+MBOX2C0+MBOX3C0+MBOX4C0+MBOX5C0+MBOX6C0+MBOX7C0+MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1+MBOX6C1+MBOX7C1)*64.0)
+Operational intensity [FLOP/Byte] (PMC0*2.0+PMC1+PMC2*4.0+PMC3*8.0)/((MBOX0C0+MBOX1C0+MBOX2C0+MBOX3C0+MBOX4C0+MBOX5C0+MBOX6C0+MBOX7C0+MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1+MBOX6C1+MBOX7C1)*64.0)
 Vectorization ratio [%] 100*(PMC0+PMC2+PMC3)/(PMC0+PMC1+PMC2+PMC3)
 
+
 LONG
 Formulas:
 Power [W] = PWR_PKG_ENERGY/runtime
@@ -64,8 +65,9 @@ Memory write bandwidth [MBytes/s] = 1.0E-06*(SUM(CAS_COUNT_WR))*64.0/runtime
 Memory write data volume [GBytes] = 1.0E-09*(SUM(CAS_COUNT_WR))*64.0
 Memory bandwidth [MBytes/s] = 1.0E-06*(SUM(CAS_COUNT_RD)+SUM(CAS_COUNT_WR))*64.0/runtime
 Memory data volume [GBytes] = 1.0E-09*(SUM(CAS_COUNT_RD)+SUM(CAS_COUNT_WR))*64.0
-Operational intensity = (FP_ARITH_INST_RETIRED_128B_PACKED_DOUBLE*2+FP_ARITH_INST_RETIRED_SCALAR_DOUBLE+FP_ARITH_INST_RETIRED_256B_PACKED_DOUBLE*4+FP_ARITH_INST_RETIRED_512B_PACKED_DOUBLE*8)/(SUM(CAS_COUNT_RD)+SUM(CAS_COUNT_WR))*64.0)
+Operational intensity [FLOP/Byte] = (FP_ARITH_INST_RETIRED_128B_PACKED_DOUBLE*2+FP_ARITH_INST_RETIRED_SCALAR_DOUBLE+FP_ARITH_INST_RETIRED_256B_PACKED_DOUBLE*4+FP_ARITH_INST_RETIRED_512B_PACKED_DOUBLE*8)/(SUM(CAS_COUNT_RD)+SUM(CAS_COUNT_WR))*64.0)
 Vectorization ratio [%] = 100*(FP_ARITH_INST_RETIRED_128B_PACKED_DOUBLE+FP_ARITH_INST_RETIRED_256B_PACKED_DOUBLE+FP_ARITH_INST_RETIRED_512B_PACKED_DOUBLE)/(FP_ARITH_INST_RETIRED_SCALAR_DOUBLE+FP_ARITH_INST_RETIRED_128B_PACKED_DOUBLE+FP_ARITH_INST_RETIRED_256B_PACKED_DOUBLE+FP_ARITH_INST_RETIRED_512B_PACKED_DOUBLE)
+
 --
 Profiling group to measure memory bandwidth drawn by all cores of a socket.
 Since this group is based on Uncore events it is only possible to measure on

diff --git a/groups/ICX/MEM_SP.txt b/groups/ICX/MEM_SP.txt
@@ -47,9 +47,10 @@ Memory write bandwidth [MBytes/s] 1.0E-06*(MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4
 Memory write data volume [GBytes] 1.0E-09*(MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1+MBOX6C1+MBOX7C1)*64.0
 Memory bandwidth [MBytes/s] 1.0E-06*(MBOX0C0+MBOX1C0+MBOX2C0+MBOX3C0+MBOX4C0+MBOX5C0+MBOX6C0+MBOX7C0+MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1+MBOX6C1+MBOX7C1)*64.0/time
 Memory data volume [GBytes] 1.0E-09*(MBOX0C0+MBOX1C0+MBOX2C0+MBOX3C0+MBOX4C0+MBOX5C0+MBOX6C0+MBOX7C0+MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1+MBOX6C1+MBOX7C1)*64.0
-Operational intensity (PMC0*4.0+PMC1+PMC2*8.0+PMC3*16.0)/((MBOX0C0+MBOX1C0+MBOX2C0+MBOX3C0+MBOX4C0+MBOX5C0+MBOX6C0+MBOX7C0+MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1+MBOX6C1+MBOX7C1)*64.0)
+Operational intensity [FLOP/Byte] (PMC0*4.0+PMC1+PMC2*8.0+PMC3*16.0)/((MBOX0C0+MBOX1C0+MBOX2C0+MBOX3C0+MBOX4C0+MBOX5C0+MBOX6C0+MBOX7C0+MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1+MBOX6C1+MBOX7C1)*64.0)
 Vectorization ratio [%] 100*(PMC0+PMC2+PMC3)/(PMC0+PMC1+PMC2+PMC3)
 
+
 LONG
 Formulas:
 Power [W] = PWR_PKG_ENERGY/runtime
@@ -64,8 +65,9 @@ Memory write bandwidth [MBytes/s] = 1.0E-06*(SUM(CAS_COUNT_WR))*64.0/runtime
 Memory write data volume [GBytes] = 1.0E-09*(SUM(CAS_COUNT_WR))*64.0
 Memory bandwidth [MBytes/s] = 1.0E-06*(SUM(CAS_COUNT_RD)+SUM(CAS_COUNT_WR))*64.0/runtime
 Memory data volume [GBytes] = 1.0E-09*(SUM(CAS_COUNT_RD)+SUM(CAS_COUNT_WR))*64.0
-Operational intensity = (FP_ARITH_INST_RETIRED_128B_PACKED_SINGLE*4+FP_ARITH_INST_RETIRED_SCALAR_SINGLE+FP_ARITH_INST_RETIRED_256B_PACKED_SINGLE*8+FP_ARITH_INST_RETIRED_512B_PACKED_SINGLE*16)/(SUM(CAS_COUNT_RD)+SUM(CAS_COUNT_WR))*64.0)
+Operational intensity [FLOP/Byte] = (FP_ARITH_INST_RETIRED_128B_PACKED_SINGLE*4+FP_ARITH_INST_RETIRED_SCALAR_SINGLE+FP_ARITH_INST_RETIRED_256B_PACKED_SINGLE*8+FP_ARITH_INST_RETIRED_512B_PACKED_SINGLE*16)/(SUM(CAS_COUNT_RD)+SUM(CAS_COUNT_WR))*64.0)
 Vectorization ratio [%] = 100*(FP_ARITH_INST_RETIRED_128B_PACKED_SINGLE+FP_ARITH_INST_RETIRED_256B_PACKED_SINGLE+FP_ARITH_INST_RETIRED_512B_PACKED_SINGLE)/(FP_ARITH_INST_RETIRED_SCALAR_SINGLE+FP_ARITH_INST_RETIRED_128B_PACKED_SINGLE+FP_ARITH_INST_RETIRED_256B_PACKED_SINGLE+FP_ARITH_INST_RETIRED_512B_PACKED_SINGLE)
+
 --
 Profiling group to measure memory bandwidth drawn by all cores of a socket.
 Since this group is based on Uncore events it is only possible to measure on

diff --git a/groups/arm64fx/MEM_DP.txt b/groups/arm64fx/MEM_DP.txt
@@ -21,10 +21,10 @@ Memory write bandwidth [MBytes/s] 1.0E-06*(PMC3)*256.0/time
 Memory write data volume [GBytes] 1.0E-09*(PMC3)*256.0
 Memory bandwidth [MBytes/s] 1.0E-06*((PMC2-(PMC4+PMC5))+PMC3)*256.0/time
 Memory data volume [GBytes] 1.0E-09*((PMC2-(PMC4+PMC5))+PMC3)*256.0
-Operational intensity (FP) PMC0/(((PMC2-(PMC4+PMC5))+PMC3)*256.0)
-Operational intensity (FP+SVE128) (((PMC1*128.0)/128.0)+PMC0)/(((PMC2-(PMC4+PMC5))+PMC3)*256.0)
-Operational intensity (FP+SVE256) (((PMC1*256.0)/128.0)+PMC0)/(((PMC2-(PMC4+PMC5))+PMC3)*256.0)
-Operational intensity (FP+SVE512) (((PMC1*512.0)/128.0)+PMC0)/(((PMC2-(PMC4+PMC5))+PMC3)*256.0)
+Operational intensity (FP) [FLOP/Byte] PMC0/(((PMC2-(PMC4+PMC5))+PMC3)*256.0)
+Operational intensity (FP+SVE128) [FLOP/Byte] (((PMC1*128.0)/128.0)+PMC0)/(((PMC2-(PMC4+PMC5))+PMC3)*256.0)
+Operational intensity (FP+SVE256) [FLOP/Byte] (((PMC1*256.0)/128.0)+PMC0)/(((PMC2-(PMC4+PMC5))+PMC3)*256.0)
+Operational intensity (FP+SVE512) [FLOP/Byte] (((PMC1*512.0)/128.0)+PMC0)/(((PMC2-(PMC4+PMC5))+PMC3)*256.0)
 
 
 LONG
@@ -39,10 +39,10 @@ Memory write bandwidth [MBytes/s] = 1.0E-06*(L2D_CACHE_WB)*256.0/runtime
 Memory write data volume [GBytes] = 1.0E-09*(L2D_CACHE_WB)*256.0
 Memory bandwidth [MBytes/s] = 1.0E-06*((L2D_CACHE_REFILL-(L2D_SWAP_DM+L2D_CACHE_MIBMCH_PRF))+L2D_CACHE_WB)*256.0/runtime
 Memory data volume [GBytes] = 1.0E-09*((L2D_CACHE_REFILL-(L2D_SWAP_DM+L2D_CACHE_MIBMCH_PRF))+L2D_CACHE_WB)*256.0
-Operational intensity (FP) = FP_DP_FIXED_OPS_SPEC/(((L2D_CACHE_REFILL-(L2D_SWAP_DM+L2D_CACHE_MIBMCH_PRF))+L2D_CACHE_WB)*256.0)
-Operational intensity (FP+SVE128) = (FP_DP_FIXED_OPS_SPEC+((FP_DP_SCALE_OPS_SPEC*128)/128)/(((L2D_CACHE_REFILL-(L2D_SWAP_DM+L2D_CACHE_MIBMCH_PRF))+L2D_CACHE_WB)*256.0)
-Operational intensity (FP+SVE256) = (FP_DP_FIXED_OPS_SPEC+((FP_DP_SCALE_OPS_SPEC*256)/128)/(((L2D_CACHE_REFILL-(L2D_SWAP_DM+L2D_CACHE_MIBMCH_PRF))+L2D_CACHE_WB)*256.0)
-Operational intensity (FP+SVE512) = (FP_DP_FIXED_OPS_SPEC+((FP_DP_SCALE_OPS_SPEC*512)/128)/(((L2D_CACHE_REFILL-(L2D_SWAP_DM+L2D_CACHE_MIBMCH_PRF))+L2D_CACHE_WB)*256.0)
+Operational intensity (FP) [FLOP/Byte] = FP_DP_FIXED_OPS_SPEC/(((L2D_CACHE_REFILL-(L2D_SWAP_DM+L2D_CACHE_MIBMCH_PRF))+L2D_CACHE_WB)*256.0)
+Operational intensity (FP+SVE128) [FLOP/Byte] = (FP_DP_FIXED_OPS_SPEC+((FP_DP_SCALE_OPS_SPEC*128)/128)/(((L2D_CACHE_REFILL-(L2D_SWAP_DM+L2D_CACHE_MIBMCH_PRF))+L2D_CACHE_WB)*256.0)
+Operational intensity (FP+SVE256) [FLOP/Byte] = (FP_DP_FIXED_OPS_SPEC+((FP_DP_SCALE_OPS_SPEC*256)/128)/(((L2D_CACHE_REFILL-(L2D_SWAP_DM+L2D_CACHE_MIBMCH_PRF))+L2D_CACHE_WB)*256.0)
+Operational intensity (FP+SVE512) [FLOP/Byte] = (FP_DP_FIXED_OPS_SPEC+((FP_DP_SCALE_OPS_SPEC*512)/128)/(((L2D_CACHE_REFILL-(L2D_SWAP_DM+L2D_CACHE_MIBMCH_PRF))+L2D_CACHE_WB)*256.0)
 -
 Profiling group to measure memory bandwidth and double-precision FP rate for scalar and SVE vector
 operations with different widths. The events for the SVE metrics assumes that all vector elements

diff --git a/groups/arm64fx/MEM_SP.txt b/groups/arm64fx/MEM_SP.txt
@@ -21,10 +21,10 @@ Memory write bandwidth [MBytes/s] 1.0E-06*(PMC3)*256.0/time
 Memory write data volume [GBytes] 1.0E-09*(PMC3)*256.0
 Memory bandwidth [MBytes/s] 1.0E-06*((PMC2-(PMC4+PMC5))+PMC3)*256.0/time
 Memory data volume [GBytes] 1.0E-09*((PMC2-(PMC4+PMC5))+PMC3)*256.0
-Operational intensity (FP) PMC0/(((PMC2-(PMC4+PMC5))+PMC3)*256.0)
-Operational intensity (FP+SVE128) (((PMC1*128.0)/128.0)+PMC0)/(((PMC2-(PMC4+PMC5))+PMC3)*256.0)
-Operational intensity (FP+SVE256) (((PMC1*256.0)/128.0)+PMC0)/(((PMC2-(PMC4+PMC5))+PMC3)*256.0)
-Operational intensity (FP+SVE512) (((PMC1*512.0)/128.0)+PMC0)/(((PMC2-(PMC4+PMC5))+PMC3)*256.0)
+Operational intensity (FP) [FLOP/Byte] PMC0/(((PMC2-(PMC4+PMC5))+PMC3)*256.0)
+Operational intensity (FP+SVE128) [FLOP/Byte] (((PMC1*128.0)/128.0)+PMC0)/(((PMC2-(PMC4+PMC5))+PMC3)*256.0)
+Operational intensity (FP+SVE256) [FLOP/Byte] (((PMC1*256.0)/128.0)+PMC0)/(((PMC2-(PMC4+PMC5))+PMC3)*256.0)
+Operational intensity (FP+SVE512) [FLOP/Byte] (((PMC1*512.0)/128.0)+PMC0)/(((PMC2-(PMC4+PMC5))+PMC3)*256.0)
 
 
 LONG
@@ -39,10 +39,10 @@ Memory write bandwidth [MBytes/s] = 1.0E-06*(L2D_CACHE_WB)*256.0/runtime
 Memory write data volume [GBytes] = 1.0E-09*(L2D_CACHE_WB)*256.0
 Memory bandwidth [MBytes/s] = 1.0E-06*((L2D_CACHE_REFILL-(L2D_SWAP_DM+L2D_CACHE_MIBMCH_PRF))+L2D_CACHE_WB)*256.0/runtime
 Memory data volume [GBytes] = 1.0E-09*((L2D_CACHE_REFILL-(L2D_SWAP_DM+L2D_CACHE_MIBMCH_PRF))+L2D_CACHE_WB)*256.0
-Operational intensity (FP) = FP_DP_FIXED_OPS_SPEC/(((L2D_CACHE_REFILL-(L2D_SWAP_DM+L2D_CACHE_MIBMCH_PRF))+L2D_CACHE_WB)*256.0)
-Operational intensity (FP+SVE128) = (FP_DP_FIXED_OPS_SPEC+((FP_DP_SCALE_OPS_SPEC*128)/128)/(((L2D_CACHE_REFILL-(L2D_SWAP_DM+L2D_CACHE_MIBMCH_PRF))+L2D_CACHE_WB)*256.0)
-Operational intensity (FP+SVE256) = (FP_DP_FIXED_OPS_SPEC+((FP_DP_SCALE_OPS_SPEC*256)/128)/(((L2D_CACHE_REFILL-(L2D_SWAP_DM+L2D_CACHE_MIBMCH_PRF))+L2D_CACHE_WB)*256.0)
-Operational intensity (FP+SVE512) = (FP_DP_FIXED_OPS_SPEC+((FP_DP_SCALE_OPS_SPEC*512)/128)/(((L2D_CACHE_REFILL-(L2D_SWAP_DM+L2D_CACHE_MIBMCH_PRF))+L2D_CACHE_WB)*256.0)
+Operational intensity (FP) [FLOP/Byte] = FP_DP_FIXED_OPS_SPEC/(((L2D_CACHE_REFILL-(L2D_SWAP_DM+L2D_CACHE_MIBMCH_PRF))+L2D_CACHE_WB)*256.0)
+Operational intensity (FP+SVE128) [FLOP/Byte] = (FP_DP_FIXED_OPS_SPEC+((FP_DP_SCALE_OPS_SPEC*128)/128)/(((L2D_CACHE_REFILL-(L2D_SWAP_DM+L2D_CACHE_MIBMCH_PRF))+L2D_CACHE_WB)*256.0)
+Operational intensity (FP+SVE256) [FLOP/Byte] = (FP_DP_FIXED_OPS_SPEC+((FP_DP_SCALE_OPS_SPEC*256)/128)/(((L2D_CACHE_REFILL-(L2D_SWAP_DM+L2D_CACHE_MIBMCH_PRF))+L2D_CACHE_WB)*256.0)
+Operational intensity (FP+SVE512) [FLOP/Byte] = (FP_DP_FIXED_OPS_SPEC+((FP_DP_SCALE_OPS_SPEC*512)/128)/(((L2D_CACHE_REFILL-(L2D_SWAP_DM+L2D_CACHE_MIBMCH_PRF))+L2D_CACHE_WB)*256.0)
 -
 Profiling group to measure memory bandwidth and single-precision FP rate for scalar and SVE vector
 operations with different widths. The events for the SVE metrics assumes that all vector elements