cc-metric-collector/collectors/likwid/groups/skylake/MEM_DP.txt

60 lines
2.8 KiB
Plaintext
Raw Normal View History

2021-03-25 14:47:10 +01:00
SHORT Overview of arithmetic and main memory performance
EVENTSET
FIXC0 INSTR_RETIRED_ANY
FIXC1 CPU_CLK_UNHALTED_CORE
FIXC2 CPU_CLK_UNHALTED_REF
PWR0 PWR_PKG_ENERGY
PWR3 PWR_DRAM_ENERGY
PMC0 FP_ARITH_INST_RETIRED_128B_PACKED_DOUBLE
PMC1 FP_ARITH_INST_RETIRED_SCALAR_DOUBLE
PMC2 FP_ARITH_INST_RETIRED_256B_PACKED_DOUBLE
MBOX0C1 DRAM_READS
MBOX0C2 DRAM_WRITES
METRICS
Runtime (RDTSC) [s] time
Runtime unhalted [s] FIXC1*inverseClock
Clock [MHz] 1.E-06*(FIXC1/FIXC2)/inverseClock
CPI FIXC1/FIXC0
Energy [J] PWR0
Power [W] PWR0/time
Energy DRAM [J] PWR3
Power DRAM [W] PWR3/time
DP [MFLOP/s] 1.0E-06*(PMC0*2.0+PMC1+PMC2*4.0)/time
AVX DP [MFLOP/s] 1.0E-06*(PMC2*4.0)/time
Packed [MUOPS/s] 1.0E-06*(PMC0+PMC2)/time
Scalar [MUOPS/s] 1.0E-06*PMC1/time
Memory load bandwidth [MBytes/s] 1.0E-06*MBOX0C1*64.0/time
Memory load data volume [GBytes] 1.0E-09*MBOX0C1*64.0
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)/((MBOX0C1+MBOX0C2)*64.0)
LONG
Formulas:
Power [W] = PWR_PKG_ENERGY/runtime
Power DRAM [W] = PWR_DRAM_ENERGY/runtime
DP [MFLOP/s] = 1.0E-06*(FP_ARITH_INST_RETIRED_128B_PACKED_DOUBLE*2+FP_ARITH_INST_RETIRED_SCALAR_DOUBLE+FP_ARITH_INST_RETIRED_256B_PACKED_DOUBLE*4)/runtime
AVX DP [MFLOP/s] = 1.0E-06*(FP_ARITH_INST_RETIRED_256B_PACKED_DOUBLE*4)/runtime
Packed [MUOPS/s] = 1.0E-06*(FP_ARITH_INST_RETIRED_128B_PACKED_DOUBLE+FP_ARITH_INST_RETIRED_256B_PACKED_DOUBLE)/runtime
Scalar [MUOPS/s] = 1.0E-06*FP_ARITH_INST_RETIRED_SCALAR_DOUBLE/runtime
Memory read bandwidth [MBytes/s] = 1.0E-06*DRAM_READS*64.0/runtime
Memory read data volume [GBytes] = 1.0E-09*DRAM_READS*64.0
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)/(DRAM_READS+DRAM_WRITES)*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
a per socket base. Also outputs total data volume transferred from main memory.
SSE scalar and packed double precision FLOP rates. Also reports on packed AVX
32b instructions.
The operational intensity is calculated using the FP values of the cores and the
memory data volume of the whole socket. The actual operational intensity for
multiple CPUs can be found in the statistics table in the Sum column.