Update MEM_SP.txt

RRZE-HPC · Nov 15, 2023 · 2270b9f · 2270b9f
1 parent c2a8dbb
commit 2270b9f
Showing 1 changed file with 5 additions and 5 deletions.
diff --git a/groups/SPR/MEM_SP.txt b/groups/SPR/MEM_SP.txt
@@ -55,7 +55,7 @@ Energy [J]  PWR0
 Power [W] PWR0/time
 Energy DRAM [J]  PWR3
 Power DRAM [W] PWR3/time
-SP [MFLOP/s]  1.0E-06*(PMC0*2.0+PMC1+PMC2*4.0+PMC3*8.0)/time
+SP [MFLOP/s]  1.0E-06*(PMC0*4.0+PMC1+PMC2*8.0+PMC3*16.0)/time
 AVX SP [MFLOP/s] 1.0E-06*(PMC2*8.0+PMC3*16.0)/time
 Packed [MUOPS/s]   1.0E-06*(PMC0+PMC2+PMC3)/time
 Scalar [MUOPS/s] 1.0E-06*PMC1/time
@@ -65,14 +65,14 @@ 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+MBOX8C1+MBOX9C1+MBOX10C1+MBOX11C1+MBOX12C1+MBOX13C1+MBOX14C1+MBOX15C1)*64.0
 Memory bandwidth [MBytes/s] 1.0E-06*(MBOX0C0+MBOX1C0+MBOX2C0+MBOX3C0+MBOX4C0+MBOX5C0+MBOX6C0+MBOX7C0+MBOX8C0+MBOX9C0+MBOX10C0+MBOX11C0+MBOX12C0+MBOX13C0+MBOX14C0+MBOX15C0+MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1+MBOX6C1+MBOX7C1+MBOX8C1+MBOX9C1+MBOX10C1+MBOX11C1+MBOX12C1+MBOX13C1+MBOX14C1+MBOX15C1)*64.0/time
 Memory data volume [GBytes] 1.0E-09*(MBOX0C0+MBOX1C0+MBOX2C0+MBOX3C0+MBOX4C0+MBOX5C0+MBOX6C0+MBOX7C0+MBOX8C0+MBOX9C0+MBOX10C0+MBOX11C0+MBOX12C0+MBOX13C0+MBOX14C0+MBOX15C0+MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1+MBOX6C1+MBOX7C1+MBOX8C1+MBOX9C1+MBOX10C1+MBOX11C1+MBOX12C1+MBOX13C1+MBOX14C1+MBOX15C1)*64.0
-Operational intensity [FLOP/Byte] (PMC0*2.0+PMC1+PMC2*4.0+PMC3*8.0)/((MBOX0C0+MBOX1C0+MBOX2C0+MBOX3C0+MBOX4C0+MBOX5C0+MBOX6C0+MBOX7C0+MBOX8C0+MBOX9C0+MBOX10C0+MBOX11C0+MBOX12C0+MBOX13C0+MBOX14C0+MBOX15C0+MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1+MBOX6C1+MBOX7C1+MBOX8C1+MBOX9C1+MBOX10C1+MBOX11C1+MBOX12C1+MBOX13C1+MBOX14C1+MBOX15C1)*64.0)
+Operational intensity [FLOP/Byte] (PMC0*4.0+PMC1+PMC2*8.0+PMC3*16.0)/((MBOX0C0+MBOX1C0+MBOX2C0+MBOX3C0+MBOX4C0+MBOX5C0+MBOX6C0+MBOX7C0+MBOX8C0+MBOX9C0+MBOX10C0+MBOX11C0+MBOX12C0+MBOX13C0+MBOX14C0+MBOX15C0+MBOX0C1+MBOX1C1+MBOX2C1+MBOX3C1+MBOX4C1+MBOX5C1+MBOX6C1+MBOX7C1+MBOX8C1+MBOX9C1+MBOX10C1+MBOX11C1+MBOX12C1+MBOX13C1+MBOX14C1+MBOX15C1)*64.0)
 
 LONG
 Formulas:
 Power [W] = PWR_PKG_ENERGY/runtime
 Power DRAM [W] = PWR_DRAM_ENERGY/runtime
-SP [MFLOP/s] = 1.0E-06*(FP_ARITH_INST_RETIRED_128B_PACKED_SINGLE*2+FP_ARITH_INST_RETIRED_SCALAR_SINGLE+FP_ARITH_INST_RETIRED_256B_PACKED_SINGLE*4+FP_ARITH_INST_RETIRED_512B_PACKED_SINGLE*8)/runtime
-AVX SP [MFLOP/s] = 1.0E-06*(FP_ARITH_INST_RETIRED_256B_PACKED_SINGLE*4+FP_ARITH_INST_RETIRED_512B_PACKED_SINGLE*8)/runtime
+SP [MFLOP/s] = 1.0E-06*(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)/runtime
+AVX SP [MFLOP/s] = 1.0E-06*(FP_ARITH_INST_RETIRED_256B_PACKED_SINGLE*8+FP_ARITH_INST_RETIRED_512B_PACKED_SINGLE*16)/runtime
 Packed [MUOPS/s] = 1.0E-06*(FP_ARITH_INST_RETIRED_128B_PACKED_SINGLE+FP_ARITH_INST_RETIRED_256B_PACKED_SINGLE+FP_ARITH_INST_RETIRED_512B_PACKED_SINGLE)/runtime
 Scalar [MUOPS/s] = 1.0E-06*FP_ARITH_INST_RETIRED_SCALAR_SINGLE/runtime
 Memory read bandwidth [MBytes/s] = 1.0E-06*(SUM(CAS_COUNT_RD))*64.0/runtime
@@ -81,7 +81,7 @@ 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 [FLOP/Byte] = (FP_ARITH_INST_RETIRED_128B_PACKED_SINGLE*2+FP_ARITH_INST_RETIRED_SCALAR_SINGLE+FP_ARITH_INST_RETIRED_256B_PACKED_SINGLE*4+FP_ARITH_INST_RETIRED_512B_PACKED_SINGLE*8)/(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)
 --
 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