mirror of
https://github.com/ClusterCockpit/cc-metric-collector.git
synced 2024-12-28 08:09:06 +01:00
35 lines
1.7 KiB
Plaintext
35 lines
1.7 KiB
Plaintext
|
SHORT Double Precision MFLOP/s
|
||
|
|
||
|
EVENTSET
|
||
|
FIXC0 INSTR_RETIRED_ANY
|
||
|
FIXC1 CPU_CLK_UNHALTED_CORE
|
||
|
FIXC2 CPU_CLK_UNHALTED_REF
|
||
|
PMC0 FP_ARITH_INST_RETIRED_128B_PACKED_DOUBLE
|
||
|
PMC1 FP_ARITH_INST_RETIRED_SCALAR_DOUBLE
|
||
|
PMC2 FP_ARITH_INST_RETIRED_256B_PACKED_DOUBLE
|
||
|
PMC3 FP_ARITH_INST_RETIRED_512B_PACKED_DOUBLE
|
||
|
|
||
|
METRICS
|
||
|
Runtime (RDTSC) [s] time
|
||
|
Runtime unhalted [s] FIXC1*inverseClock
|
||
|
Clock [MHz] 1.E-06*(FIXC1/FIXC2)/inverseClock
|
||
|
CPI FIXC1/FIXC0
|
||
|
DP [MFLOP/s] 1.0E-06*(PMC0*2.0+PMC1+PMC2*4.0+PMC3*8.0)/time
|
||
|
AVX DP [MFLOP/s] 1.0E-06*(PMC2*4.0+PMC3*8.0)/time
|
||
|
AVX512 DP [MFLOP/s] 1.0E-06*(PMC3*8.0)/time
|
||
|
Packed [MUOPS/s] 1.0E-06*(PMC0+PMC2+PMC3)/time
|
||
|
Scalar [MUOPS/s] 1.0E-06*PMC1/time
|
||
|
Vectorization ratio 100*(PMC0+PMC2+PMC3)/(PMC0+PMC1+PMC2+PMC3)
|
||
|
|
||
|
LONG
|
||
|
Formulas:
|
||
|
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+FP_ARITH_INST_RETIRED_512B_PACKED_DOUBLE*8)/runtime
|
||
|
AVX DP [MFLOP/s] = 1.0E-06*(FP_ARITH_INST_RETIRED_256B_PACKED_DOUBLE*4+FP_ARITH_INST_RETIRED_512B_PACKED_DOUBLE*8)/runtime
|
||
|
AVX512 DP [MFLOP/s] = 1.0E-06*(FP_ARITH_INST_RETIRED_512B_PACKED_DOUBLE*8)/runtime
|
||
|
Packed [MUOPS/s] = 1.0E-06*(FP_ARITH_INST_RETIRED_128B_PACKED_DOUBLE+FP_ARITH_INST_RETIRED_256B_PACKED_DOUBLE+FP_ARITH_INST_RETIRED_512B_PACKED_DOUBLE)/runtime
|
||
|
Scalar [MUOPS/s] = 1.0E-06*FP_ARITH_INST_RETIRED_SCALAR_DOUBLE/runtime
|
||
|
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)
|
||
|
-
|
||
|
SSE scalar and packed double precision FLOP rates.
|
||
|
|