SHORT Single Precision MFlops/s

EVENTSET
FIXC0 INSTR_RETIRED_ANY
FIXC1 CPU_CLK_UNHALTED_CORE
FIXC2 CPU_CLK_UNHALTED_REF
PMC0  SIMD_COMP_INST_RETIRED_PACKED_SINGLE
PMC1  SIMD_COMP_INST_RETIRED_SCALAR_SINGLE

METRICS
Runtime (RDTSC) [s] time
Runtime unhalted [s] FIXC1*inverseClock
Clock [MHz]  1.E-06*(FIXC1/FIXC2)/inverseClock
CPI  FIXC1/FIXC0
SP MFlops/s 1.0E-06*(PMC0*4.0+PMC1)/time

LONG
Formulas:
SP MFlops/s = 1.0E-06*(SIMD_COMP_INST_RETIRED_PACKED_SINGLE*4+SIMD_COMP_INST_RETIRED_SCALAR_SINGLE)/time
-
Profiling group to measure single precision SSE flops. Dont forget that your code might also execute X87 flops.
On the number of SIMD_COMP_INST_RETIRED_PACKED_SINGLE you can see how well your code was vectorized.


