RDTSCP - Throughput and Uops
With unroll_count=500 and no inner loop
Code:
0: 0f 01 f9 rdtscp
Show nanoBench command
Results:
Instructions retired: 1.0
Core cycles: 36.17
Reference cycles: 18.03
UOPS_EXECUTED.THREAD: 17.0
RETIRE_SLOTS: 20.0
UOPS_MITE: 2.0
UOPS_MS: 18.0
UOPS_PORT_0: 3.0
UOPS_PORT_1: 5.0
UOPS_PORT_5: 3.0
UOPS_PORT_6: 6.0
UOPS_PORT_23: 0.0
UOPS_PORT_49: 0.0
UOPS_PORT_78: 0.0
DIV_CYCLES: 0.0
ILD_STALL.LCP: 0.0
UOPS_MITE>=1: 1.0
With unroll_count=500, no inner loop, and 1 NOP
Code:
0: 0f 01 f9 rdtscp 3: 90 nop
Show nanoBench command
Results:
Instructions retired: 2.0
Core cycles: 35.75
Reference cycles: 17.82
UOPS_EXECUTED.THREAD: 17.0
RETIRE_SLOTS: 21.0
UOPS_MITE: 3.0
UOPS_MS: 18.0
UOPS_PORT_0: 4.5
UOPS_PORT_1: 5.0
UOPS_PORT_5: 3.0
UOPS_PORT_6: 4.5
UOPS_PORT_23: 0.0
UOPS_PORT_49: 0.0
UOPS_PORT_78: 0.0
DIV_CYCLES: 0.0
ILD_STALL.LCP: 0.0
UOPS_MITE>=1: 2.0
With loop_count=1000 and unroll_count=10
Code:
0: 0f 01 f9 rdtscp
Show nanoBench command
Results:
Instructions retired: 1.2
Core cycles: 35.0
Reference cycles: 17.48
UOPS_EXECUTED.THREAD: 17.1
RETIRE_SLOTS: 20.1
UOPS_MITE: 2.1
UOPS_MS: 18.01
UOPS_PORT_0: 3.1
UOPS_PORT_1: 5.1
UOPS_PORT_5: 3.0
UOPS_PORT_6: 5.9
UOPS_PORT_23: 0.0
UOPS_PORT_49: 0.0
UOPS_PORT_78: 0.0
DIV_CYCLES: 0.0
ILD_STALL.LCP: 0.0
UOPS_MITE>=1: 1.1
With loop_count=100 and unroll_count=100
Code:
0: 0f 01 f9 rdtscp
Show nanoBench command
Results:
Instructions retired: 1.02
Core cycles: 35.33
Reference cycles: 17.63
UOPS_EXECUTED.THREAD: 17.01
RETIRE_SLOTS: 20.01
UOPS_MITE: 2.01
UOPS_MS: 18.0
UOPS_PORT_0: 3.01
UOPS_PORT_1: 5.01
UOPS_PORT_5: 3.0
UOPS_PORT_6: 5.99
UOPS_PORT_23: 0.0
UOPS_PORT_49: 0.0
UOPS_PORT_78: 0.0
DIV_CYCLES: 0.0
ILD_STALL.LCP: 0.0
UOPS_MITE>=1: 1.01