RDSEED (R64) - Throughput and Uops
With 1 independent instruction
With unroll_count=10 and no inner loop
Code:
0: 49 0f c7 f8 rdseed r8
Show nanoBench command
Results:
Instructions retired: 1.0
Core cycles: 878.2
Reference cycles: 627.13
UOPS_EXECUTED.THREAD: 12.0
RETIRE_SLOTS: 14.0
UOPS_MITE: 0.0
UOPS_MS: 14.0
UOPS_PORT_0: 2.4
UOPS_PORT_1: 3.1
UOPS_PORT_2: 0.5
UOPS_PORT_3: 0.5
UOPS_PORT_4: 0.0
UOPS_PORT_5: 1.8
UOPS_PORT_6: 3.2
UOPS_PORT_7: 0.0
DIV_CYCLES: 0.0
ILD_STALL.LCP: 0.0
UOPS_MITE>=1: 0.0
With unroll_count=10, no inner loop, and 1 NOP
Code:
0: 49 0f c7 f8 rdseed r8 4: 90 nop
Show nanoBench command
Results:
Instructions retired: 2.0
Core cycles: 883.37
Reference cycles: 630.2
UOPS_EXECUTED.THREAD: 12.0
RETIRE_SLOTS: 15.0
UOPS_MITE: 1.0
UOPS_MS: 14.0
UOPS_PORT_0: 2.3
UOPS_PORT_1: 3.2
UOPS_PORT_2: 0.5
UOPS_PORT_3: 0.5
UOPS_PORT_4: 0.0
UOPS_PORT_5: 1.5
UOPS_PORT_6: 3.5
UOPS_PORT_7: 0.0
DIV_CYCLES: 0.0
ILD_STALL.LCP: 0.0
UOPS_MITE>=1: 1.0
With loop_count=10 and unroll_count=1
Code:
0: 49 0f c7 f8 rdseed r8
Show nanoBench command
Results:
Instructions retired: 3.0
Core cycles: 881.2
Reference cycles: 625.6
UOPS_EXECUTED.THREAD: 13.0
RETIRE_SLOTS: 16.6
UOPS_MITE: 0.6
UOPS_MS: 14.0
UOPS_PORT_0: 2.47
UOPS_PORT_1: 3.1
UOPS_PORT_2: 0.5
UOPS_PORT_3: 0.5
UOPS_PORT_4: 0.0
UOPS_PORT_5: 1.55
UOPS_PORT_6: 4.5
UOPS_PORT_7: 0.0
DIV_CYCLES: 0.0
ILD_STALL.LCP: 0.0
UOPS_MITE>=1: 0.6