CMPXCHG8B_LOCK (M64) - Throughput and Uops

With unroll_count=500 and no inner loop

• Code:

     0:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
  

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 20.38
  • Reference cycles: 15.36
  • UOPS_EXECUTED.THREAD: 18.0
  • RETIRE_SLOTS: 20.0
  • UOPS_MITE: 0.0
  • UOPS_MS: 19.96
  • UOPS_PORT_0: 3.71
  • UOPS_PORT_1: 4.44
  • UOPS_PORT_6: 5.74
  • UOPS_PORT_49: 1.0
  • UOPS_PORT_78: 1.0
  • UOPS_PORT_5B: 6.89
  • UOPS_PORT_5B>=2: 1.53
  • UOPS_PORT_23A: 1.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.0

With unroll_count=500, no inner loop, and 1 NOP

• Code:

     0:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     5:	90                   	nop
  

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 20.38
  • Reference cycles: 15.36
  • UOPS_EXECUTED.THREAD: 18.0
  • RETIRE_SLOTS: 21.0
  • UOPS_MITE: 1.0
  • UOPS_MS: 19.97
  • UOPS_PORT_0: 3.96
  • UOPS_PORT_1: 4.0
  • UOPS_PORT_6: 5.91
  • UOPS_PORT_49: 1.0
  • UOPS_PORT_78: 1.0
  • UOPS_PORT_5B: 7.6
  • UOPS_PORT_5B>=2: 1.47
  • UOPS_PORT_23A: 1.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With loop_count=1000 and unroll_count=10

• Code:

     0:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
  

• Show nanoBench command
• Results:
  • Instructions retired: 1.2
  • Core cycles: 20.34
  • Reference cycles: 15.3
  • UOPS_EXECUTED.THREAD: 18.1
  • RETIRE_SLOTS: 20.1
  • UOPS_MITE: 0.1
  • UOPS_MS: 20.01
  • UOPS_PORT_0: 3.64
  • UOPS_PORT_1: 4.38
  • UOPS_PORT_6: 5.79
  • UOPS_PORT_49: 1.0
  • UOPS_PORT_78: 1.0
  • UOPS_PORT_5B: 6.89
  • UOPS_PORT_5B>=2: 1.6
  • UOPS_PORT_23A: 1.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.1

With loop_count=100 and unroll_count=100

• Code:

     0:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
  

• Show nanoBench command
• Results:
  • Instructions retired: 1.02
  • Core cycles: 20.37
  • Reference cycles: 15.33
  • UOPS_EXECUTED.THREAD: 18.01
  • RETIRE_SLOTS: 20.01
  • UOPS_MITE: 0.01
  • UOPS_MS: 20.0
  • UOPS_PORT_0: 3.67
  • UOPS_PORT_1: 4.43
  • UOPS_PORT_6: 5.74
  • UOPS_PORT_49: 1.0
  • UOPS_PORT_78: 1.0
  • UOPS_PORT_5B: 6.87
  • UOPS_PORT_5B>=2: 1.53
  • UOPS_PORT_23A: 1.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.01

With additional dependency-breaking instructions

With unroll_count=500 and no inner loop

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
  

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 20.06
  • Reference cycles: 15.07
  • UOPS_EXECUTED.THREAD: 18.0
  • RETIRE_SLOTS: 22.0
  • UOPS_MITE: 2.0
  • UOPS_MS: 20.0
  • UOPS_PORT_0: 3.96
  • UOPS_PORT_1: 5.39
  • UOPS_PORT_6: 5.57
  • UOPS_PORT_49: 1.0
  • UOPS_PORT_78: 1.0
  • UOPS_PORT_5B: 7.58
  • UOPS_PORT_5B>=2: 1.5
  • UOPS_PORT_23A: 1.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.99

With loop_count=1000 and unroll_count=10

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
  

• Show nanoBench command
• Results:
  • Instructions retired: 3.2
  • Core cycles: 20.08
  • Reference cycles: 15.11
  • UOPS_EXECUTED.THREAD: 18.1
  • RETIRE_SLOTS: 22.1
  • UOPS_MITE: 2.1
  • UOPS_MS: 20.01
  • UOPS_PORT_0: 4.0
  • UOPS_PORT_1: 5.56
  • UOPS_PORT_6: 5.81
  • UOPS_PORT_49: 1.0
  • UOPS_PORT_78: 1.0
  • UOPS_PORT_5B: 7.8
  • UOPS_PORT_5B>=2: 1.56
  • UOPS_PORT_23A: 1.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With loop_count=100 and unroll_count=100

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
  

• Show nanoBench command
• Results:
  • Instructions retired: 3.02
  • Core cycles: 20.07
  • Reference cycles: 15.1
  • UOPS_EXECUTED.THREAD: 18.01
  • RETIRE_SLOTS: 22.01
  • UOPS_MITE: 2.01
  • UOPS_MS: 20.0
  • UOPS_PORT_0: 3.94
  • UOPS_PORT_1: 5.42
  • UOPS_PORT_6: 5.6
  • UOPS_PORT_49: 1.0
  • UOPS_PORT_78: 1.0
  • UOPS_PORT_5B: 7.64
  • UOPS_PORT_5B>=2: 1.5
  • UOPS_PORT_23A: 1.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With unroll_count=200 and no inner loop

• Code:

     0:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     5:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
     b:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    11:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
  

• Show nanoBench command
• Results:
  • Instructions retired: 4.0
  • Core cycles: 81.28
  • Reference cycles: 60.96
  • UOPS_EXECUTED.THREAD: 72.0
  • RETIRE_SLOTS: 80.0
  • UOPS_MITE: 0.0
  • UOPS_MS: 79.91
  • UOPS_PORT_0: 13.75
  • UOPS_PORT_1: 18.02
  • UOPS_PORT_6: 22.94
  • UOPS_PORT_49: 4.0
  • UOPS_PORT_78: 4.0
  • UOPS_PORT_5B: 21.28
  • UOPS_PORT_5B>=2: 4.13
  • UOPS_PORT_23A: 4.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.0

With loop_count=1000 and unroll_count=2

• Code:

     0:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     5:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
     b:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    11:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
  

• Show nanoBench command
• Results:
  • Instructions retired: 5.0
  • Core cycles: 81.11
  • Reference cycles: 61.02
  • UOPS_EXECUTED.THREAD: 72.5
  • RETIRE_SLOTS: 80.5
  • UOPS_MITE: 0.5
  • UOPS_MS: 80.04
  • UOPS_PORT_0: 13.57
  • UOPS_PORT_1: 17.26
  • UOPS_PORT_6: 23.35
  • UOPS_PORT_49: 4.0
  • UOPS_PORT_78: 4.0
  • UOPS_PORT_5B: 21.81
  • UOPS_PORT_5B>=2: 4.52
  • UOPS_PORT_23A: 4.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.5

With loop_count=100 and unroll_count=20

• Code:

     0:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     5:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
     b:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    11:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
  

• Show nanoBench command
• Results:
  • Instructions retired: 4.1
  • Core cycles: 81.23
  • Reference cycles: 61.12
  • UOPS_EXECUTED.THREAD: 72.05
  • RETIRE_SLOTS: 80.05
  • UOPS_MITE: 0.05
  • UOPS_MS: 79.99
  • UOPS_PORT_0: 13.82
  • UOPS_PORT_1: 17.95
  • UOPS_PORT_6: 22.79
  • UOPS_PORT_49: 4.0
  • UOPS_PORT_78: 4.0
  • UOPS_PORT_5B: 21.27
  • UOPS_PORT_5B>=2: 4.22
  • UOPS_PORT_23A: 4.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.05

With additional dependency-breaking instructions

With unroll_count=200 and no inner loop

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     b:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
    11:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    17:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
  

• Show nanoBench command
• Results:
  • Instructions retired: 6.0
  • Core cycles: 80.64
  • Reference cycles: 60.56
  • UOPS_EXECUTED.THREAD: 72.0
  • RETIRE_SLOTS: 82.0
  • UOPS_MITE: 1.95
  • UOPS_MS: 79.9
  • UOPS_PORT_0: 15.28
  • UOPS_PORT_1: 18.87
  • UOPS_PORT_6: 23.48
  • UOPS_PORT_49: 4.0
  • UOPS_PORT_78: 4.0
  • UOPS_PORT_5B: 25.96
  • UOPS_PORT_5B>=2: 5.97
  • UOPS_PORT_23A: 4.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.98

With loop_count=1000 and unroll_count=2

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     b:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
    11:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    17:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
  

• Show nanoBench command
• Results:
  • Instructions retired: 7.0
  • Core cycles: 80.67
  • Reference cycles: 60.69
  • UOPS_EXECUTED.THREAD: 72.5
  • RETIRE_SLOTS: 82.5
  • UOPS_MITE: 2.5
  • UOPS_MS: 80.04
  • UOPS_PORT_0: 15.11
  • UOPS_PORT_1: 19.15
  • UOPS_PORT_6: 23.98
  • UOPS_PORT_49: 4.0
  • UOPS_PORT_78: 4.0
  • UOPS_PORT_5B: 25.83
  • UOPS_PORT_5B>=2: 6.32
  • UOPS_PORT_23A: 4.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With loop_count=100 and unroll_count=20

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     b:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
    11:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    17:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
  

• Show nanoBench command
• Results:
  • Instructions retired: 6.1
  • Core cycles: 80.62
  • Reference cycles: 60.65
  • UOPS_EXECUTED.THREAD: 72.05
  • RETIRE_SLOTS: 82.05
  • UOPS_MITE: 2.05
  • UOPS_MS: 79.99
  • UOPS_PORT_0: 15.2
  • UOPS_PORT_1: 19.03
  • UOPS_PORT_6: 23.57
  • UOPS_PORT_49: 4.0
  • UOPS_PORT_78: 4.0
  • UOPS_PORT_5B: 25.86
  • UOPS_PORT_5B>=2: 6.02
  • UOPS_PORT_23A: 4.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With additional dependency-breaking instructions (before each instruction)

With unroll_count=200 and no inner loop

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     b:	48 31 d2             	xor    rdx,rdx
     e:	48 31 c0             	xor    rax,rax
    11:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
    17:	48 31 d2             	xor    rdx,rdx
    1a:	48 31 c0             	xor    rax,rax
    1d:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    23:	48 31 d2             	xor    rdx,rdx
    26:	48 31 c0             	xor    rax,rax
    29:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
  

• Show nanoBench command
• Results:
  • Instructions retired: 12.0
  • Core cycles: 80.34
  • Reference cycles: 60.48
  • UOPS_EXECUTED.THREAD: 72.01
  • RETIRE_SLOTS: 88.0
  • UOPS_MITE: 8.0
  • UOPS_MS: 79.91
  • UOPS_PORT_0: 17.1
  • UOPS_PORT_1: 22.07
  • UOPS_PORT_6: 23.12
  • UOPS_PORT_49: 4.0
  • UOPS_PORT_78: 4.0
  • UOPS_PORT_5B: 33.63
  • UOPS_PORT_5B>=2: 8.9
  • UOPS_PORT_23A: 4.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 4.0

With loop_count=1000 and unroll_count=2

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     b:	48 31 d2             	xor    rdx,rdx
     e:	48 31 c0             	xor    rax,rax
    11:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
    17:	48 31 d2             	xor    rdx,rdx
    1a:	48 31 c0             	xor    rax,rax
    1d:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    23:	48 31 d2             	xor    rdx,rdx
    26:	48 31 c0             	xor    rax,rax
    29:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
  

• Show nanoBench command
• Results:
  • Instructions retired: 13.0
  • Core cycles: 80.32
  • Reference cycles: 60.43
  • UOPS_EXECUTED.THREAD: 72.5
  • RETIRE_SLOTS: 88.51
  • UOPS_MITE: 8.52
  • UOPS_MS: 80.03
  • UOPS_PORT_0: 17.29
  • UOPS_PORT_1: 22.88
  • UOPS_PORT_6: 24.26
  • UOPS_PORT_49: 4.0
  • UOPS_PORT_78: 4.0
  • UOPS_PORT_5B: 33.84
  • UOPS_PORT_5B>=2: 8.76
  • UOPS_PORT_23A: 4.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 4.0

With loop_count=100 and unroll_count=20

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     b:	48 31 d2             	xor    rdx,rdx
     e:	48 31 c0             	xor    rax,rax
    11:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
    17:	48 31 d2             	xor    rdx,rdx
    1a:	48 31 c0             	xor    rax,rax
    1d:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    23:	48 31 d2             	xor    rdx,rdx
    26:	48 31 c0             	xor    rax,rax
    29:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
  

• Show nanoBench command
• Results:
  • Instructions retired: 12.1
  • Core cycles: 80.31
  • Reference cycles: 60.43
  • UOPS_EXECUTED.THREAD: 72.05
  • RETIRE_SLOTS: 88.05
  • UOPS_MITE: 8.05
  • UOPS_MS: 79.99
  • UOPS_PORT_0: 17.1
  • UOPS_PORT_1: 22.08
  • UOPS_PORT_6: 23.24
  • UOPS_PORT_49: 4.0
  • UOPS_PORT_78: 4.0
  • UOPS_PORT_5B: 33.53
  • UOPS_PORT_5B>=2: 8.81
  • UOPS_PORT_23A: 4.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 4.0

With unroll_count=100 and no inner loop

• Code:

     0:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     5:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
     b:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    11:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
    17:	f0 41 0f c7 4e 20    	lock cmpxchg8b QWORD PTR [r14+0x20]
    1d:	f0 41 0f c7 4e 28    	lock cmpxchg8b QWORD PTR [r14+0x28]
    23:	f0 41 0f c7 4e 30    	lock cmpxchg8b QWORD PTR [r14+0x30]
    29:	f0 41 0f c7 4e 38    	lock cmpxchg8b QWORD PTR [r14+0x38]
  

• Show nanoBench command
• Results:
  • Instructions retired: 8.0
  • Core cycles: 162.6
  • Reference cycles: 121.92
  • UOPS_EXECUTED.THREAD: 144.02
  • RETIRE_SLOTS: 160.0
  • UOPS_MITE: 0.02
  • UOPS_MS: 159.8
  • UOPS_PORT_0: 31.25
  • UOPS_PORT_1: 38.72
  • UOPS_PORT_6: 50.71
  • UOPS_PORT_49: 8.0
  • UOPS_PORT_78: 8.0
  • UOPS_PORT_5B: 45.76
  • UOPS_PORT_5B>=2: 7.57
  • UOPS_PORT_23A: 8.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.01

With loop_count=1000 and unroll_count=1

• Code:

     0:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     5:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
     b:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    11:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
    17:	f0 41 0f c7 4e 20    	lock cmpxchg8b QWORD PTR [r14+0x20]
    1d:	f0 41 0f c7 4e 28    	lock cmpxchg8b QWORD PTR [r14+0x28]
    23:	f0 41 0f c7 4e 30    	lock cmpxchg8b QWORD PTR [r14+0x30]
    29:	f0 41 0f c7 4e 38    	lock cmpxchg8b QWORD PTR [r14+0x38]
  

• Show nanoBench command
• Results:
  • Instructions retired: 10.0
  • Core cycles: 162.19
  • Reference cycles: 122.03
  • UOPS_EXECUTED.THREAD: 145.0
  • RETIRE_SLOTS: 161.0
  • UOPS_MITE: 1.0
  • UOPS_MS: 160.11
  • UOPS_PORT_0: 30.69
  • UOPS_PORT_1: 37.26
  • UOPS_PORT_6: 51.71
  • UOPS_PORT_49: 8.0
  • UOPS_PORT_78: 8.0
  • UOPS_PORT_5B: 47.51
  • UOPS_PORT_5B>=2: 8.28
  • UOPS_PORT_23A: 8.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With loop_count=100 and unroll_count=10

• Code:

     0:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     5:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
     b:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    11:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
    17:	f0 41 0f c7 4e 20    	lock cmpxchg8b QWORD PTR [r14+0x20]
    1d:	f0 41 0f c7 4e 28    	lock cmpxchg8b QWORD PTR [r14+0x28]
    23:	f0 41 0f c7 4e 30    	lock cmpxchg8b QWORD PTR [r14+0x30]
    29:	f0 41 0f c7 4e 38    	lock cmpxchg8b QWORD PTR [r14+0x38]
  

• Show nanoBench command
• Results:
  • Instructions retired: 8.2
  • Core cycles: 162.46
  • Reference cycles: 122.22
  • UOPS_EXECUTED.THREAD: 144.1
  • RETIRE_SLOTS: 160.1
  • UOPS_MITE: 0.09
  • UOPS_MS: 159.98
  • UOPS_PORT_0: 31.25
  • UOPS_PORT_1: 38.67
  • UOPS_PORT_6: 50.71
  • UOPS_PORT_49: 8.0
  • UOPS_PORT_78: 8.0
  • UOPS_PORT_5B: 45.77
  • UOPS_PORT_5B>=2: 7.63
  • UOPS_PORT_23A: 8.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.1

With additional dependency-breaking instructions

With unroll_count=100 and no inner loop

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     b:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
    11:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    17:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
    1d:	f0 41 0f c7 4e 20    	lock cmpxchg8b QWORD PTR [r14+0x20]
    23:	f0 41 0f c7 4e 28    	lock cmpxchg8b QWORD PTR [r14+0x28]
    29:	f0 41 0f c7 4e 30    	lock cmpxchg8b QWORD PTR [r14+0x30]
    2f:	f0 41 0f c7 4e 38    	lock cmpxchg8b QWORD PTR [r14+0x38]
  

• Show nanoBench command
• Results:
  • Instructions retired: 10.0
  • Core cycles: 161.98
  • Reference cycles: 121.76
  • UOPS_EXECUTED.THREAD: 143.98
  • RETIRE_SLOTS: 162.01
  • UOPS_MITE: 1.84
  • UOPS_MS: 160.0
  • UOPS_PORT_0: 32.5
  • UOPS_PORT_1: 39.95
  • UOPS_PORT_6: 50.82
  • UOPS_PORT_49: 8.0
  • UOPS_PORT_78: 8.0
  • UOPS_PORT_5B: 52.85
  • UOPS_PORT_5B>=2: 10.87
  • UOPS_PORT_23A: 8.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.97

With loop_count=1000 and unroll_count=1

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     b:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
    11:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    17:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
    1d:	f0 41 0f c7 4e 20    	lock cmpxchg8b QWORD PTR [r14+0x20]
    23:	f0 41 0f c7 4e 28    	lock cmpxchg8b QWORD PTR [r14+0x28]
    29:	f0 41 0f c7 4e 30    	lock cmpxchg8b QWORD PTR [r14+0x30]
    2f:	f0 41 0f c7 4e 38    	lock cmpxchg8b QWORD PTR [r14+0x38]
  

• Show nanoBench command
• Results:
  • Instructions retired: 12.0
  • Core cycles: 162.06
  • Reference cycles: 121.97
  • UOPS_EXECUTED.THREAD: 145.0
  • RETIRE_SLOTS: 163.0
  • UOPS_MITE: 3.0
  • UOPS_MS: 160.09
  • UOPS_PORT_0: 32.57
  • UOPS_PORT_1: 40.23
  • UOPS_PORT_6: 53.39
  • UOPS_PORT_49: 8.0
  • UOPS_PORT_78: 8.0
  • UOPS_PORT_5B: 52.72
  • UOPS_PORT_5B>=2: 10.91
  • UOPS_PORT_23A: 8.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With loop_count=100 and unroll_count=10

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     b:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
    11:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    17:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
    1d:	f0 41 0f c7 4e 20    	lock cmpxchg8b QWORD PTR [r14+0x20]
    23:	f0 41 0f c7 4e 28    	lock cmpxchg8b QWORD PTR [r14+0x28]
    29:	f0 41 0f c7 4e 30    	lock cmpxchg8b QWORD PTR [r14+0x30]
    2f:	f0 41 0f c7 4e 38    	lock cmpxchg8b QWORD PTR [r14+0x38]
  

• Show nanoBench command
• Results:
  • Instructions retired: 10.2
  • Core cycles: 161.88
  • Reference cycles: 121.82
  • UOPS_EXECUTED.THREAD: 144.1
  • RETIRE_SLOTS: 162.1
  • UOPS_MITE: 2.09
  • UOPS_MS: 159.98
  • UOPS_PORT_0: 32.34
  • UOPS_PORT_1: 40.07
  • UOPS_PORT_6: 51.3
  • UOPS_PORT_49: 8.0
  • UOPS_PORT_78: 8.0
  • UOPS_PORT_5B: 52.66
  • UOPS_PORT_5B>=2: 10.98
  • UOPS_PORT_23A: 8.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With additional dependency-breaking instructions (before each instruction)

With unroll_count=100 and no inner loop

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     b:	48 31 d2             	xor    rdx,rdx
     e:	48 31 c0             	xor    rax,rax
    11:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
    17:	48 31 d2             	xor    rdx,rdx
    1a:	48 31 c0             	xor    rax,rax
    1d:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    23:	48 31 d2             	xor    rdx,rdx
    26:	48 31 c0             	xor    rax,rax
    29:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
    2f:	48 31 d2             	xor    rdx,rdx
    32:	48 31 c0             	xor    rax,rax
    35:	f0 41 0f c7 4e 20    	lock cmpxchg8b QWORD PTR [r14+0x20]
    3b:	48 31 d2             	xor    rdx,rdx
    3e:	48 31 c0             	xor    rax,rax
    41:	f0 41 0f c7 4e 28    	lock cmpxchg8b QWORD PTR [r14+0x28]
    47:	48 31 d2             	xor    rdx,rdx
    4a:	48 31 c0             	xor    rax,rax
    4d:	f0 41 0f c7 4e 30    	lock cmpxchg8b QWORD PTR [r14+0x30]
    53:	48 31 d2             	xor    rdx,rdx
    56:	48 31 c0             	xor    rax,rax
    59:	f0 41 0f c7 4e 38    	lock cmpxchg8b QWORD PTR [r14+0x38]
  

• Show nanoBench command
• Results:
  • Instructions retired: 24.0
  • Core cycles: 160.64
  • Reference cycles: 120.96
  • UOPS_EXECUTED.THREAD: 144.0
  • RETIRE_SLOTS: 176.0
  • UOPS_MITE: 15.98
  • UOPS_MS: 159.93
  • UOPS_PORT_0: 40.35
  • UOPS_PORT_1: 50.18
  • UOPS_PORT_6: 50.94
  • UOPS_PORT_49: 8.0
  • UOPS_PORT_78: 8.0
  • UOPS_PORT_5B: 82.72
  • UOPS_PORT_5B>=2: 21.2
  • UOPS_PORT_23A: 8.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 8.0

With loop_count=1000 and unroll_count=1

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     b:	48 31 d2             	xor    rdx,rdx
     e:	48 31 c0             	xor    rax,rax
    11:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
    17:	48 31 d2             	xor    rdx,rdx
    1a:	48 31 c0             	xor    rax,rax
    1d:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    23:	48 31 d2             	xor    rdx,rdx
    26:	48 31 c0             	xor    rax,rax
    29:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
    2f:	48 31 d2             	xor    rdx,rdx
    32:	48 31 c0             	xor    rax,rax
    35:	f0 41 0f c7 4e 20    	lock cmpxchg8b QWORD PTR [r14+0x20]
    3b:	48 31 d2             	xor    rdx,rdx
    3e:	48 31 c0             	xor    rax,rax
    41:	f0 41 0f c7 4e 28    	lock cmpxchg8b QWORD PTR [r14+0x28]
    47:	48 31 d2             	xor    rdx,rdx
    4a:	48 31 c0             	xor    rax,rax
    4d:	f0 41 0f c7 4e 30    	lock cmpxchg8b QWORD PTR [r14+0x30]
    53:	48 31 d2             	xor    rdx,rdx
    56:	48 31 c0             	xor    rax,rax
    59:	f0 41 0f c7 4e 38    	lock cmpxchg8b QWORD PTR [r14+0x38]
  

• Show nanoBench command
• Results:
  • Instructions retired: 26.0
  • Core cycles: 160.62
  • Reference cycles: 120.86
  • UOPS_EXECUTED.THREAD: 145.0
  • RETIRE_SLOTS: 177.01
  • UOPS_MITE: 17.0
  • UOPS_MS: 160.07
  • UOPS_PORT_0: 40.22
  • UOPS_PORT_1: 51.71
  • UOPS_PORT_6: 53.27
  • UOPS_PORT_49: 8.0
  • UOPS_PORT_78: 8.0
  • UOPS_PORT_5B: 82.87
  • UOPS_PORT_5B>=2: 20.77
  • UOPS_PORT_23A: 8.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 8.0

With loop_count=100 and unroll_count=10

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     b:	48 31 d2             	xor    rdx,rdx
     e:	48 31 c0             	xor    rax,rax
    11:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
    17:	48 31 d2             	xor    rdx,rdx
    1a:	48 31 c0             	xor    rax,rax
    1d:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    23:	48 31 d2             	xor    rdx,rdx
    26:	48 31 c0             	xor    rax,rax
    29:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
    2f:	48 31 d2             	xor    rdx,rdx
    32:	48 31 c0             	xor    rax,rax
    35:	f0 41 0f c7 4e 20    	lock cmpxchg8b QWORD PTR [r14+0x20]
    3b:	48 31 d2             	xor    rdx,rdx
    3e:	48 31 c0             	xor    rax,rax
    41:	f0 41 0f c7 4e 28    	lock cmpxchg8b QWORD PTR [r14+0x28]
    47:	48 31 d2             	xor    rdx,rdx
    4a:	48 31 c0             	xor    rax,rax
    4d:	f0 41 0f c7 4e 30    	lock cmpxchg8b QWORD PTR [r14+0x30]
    53:	48 31 d2             	xor    rdx,rdx
    56:	48 31 c0             	xor    rax,rax
    59:	f0 41 0f c7 4e 38    	lock cmpxchg8b QWORD PTR [r14+0x38]
  

• Show nanoBench command
• Results:
  • Instructions retired: 24.2
  • Core cycles: 160.61
  • Reference cycles: 120.85
  • UOPS_EXECUTED.THREAD: 144.1
  • RETIRE_SLOTS: 176.1
  • UOPS_MITE: 16.1
  • UOPS_MS: 159.98
  • UOPS_PORT_0: 40.38
  • UOPS_PORT_1: 50.52
  • UOPS_PORT_6: 51.22
  • UOPS_PORT_49: 8.0
  • UOPS_PORT_78: 8.0
  • UOPS_PORT_5B: 82.92
  • UOPS_PORT_5B>=2: 21.17
  • UOPS_PORT_23A: 8.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 8.0

With unroll_count=100 and no inner loop

• Code:

     0:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     5:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
     b:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    11:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
    17:	f0 41 0f c7 4e 20    	lock cmpxchg8b QWORD PTR [r14+0x20]
    1d:	f0 41 0f c7 4e 28    	lock cmpxchg8b QWORD PTR [r14+0x28]
    23:	f0 41 0f c7 4e 30    	lock cmpxchg8b QWORD PTR [r14+0x30]
    29:	f0 41 0f c7 4e 38    	lock cmpxchg8b QWORD PTR [r14+0x38]
    2f:	f0 41 0f c7 4e 40    	lock cmpxchg8b QWORD PTR [r14+0x40]
    35:	f0 41 0f c7 4e 48    	lock cmpxchg8b QWORD PTR [r14+0x48]
    3b:	f0 41 0f c7 4e 50    	lock cmpxchg8b QWORD PTR [r14+0x50]
    41:	f0 41 0f c7 4e 58    	lock cmpxchg8b QWORD PTR [r14+0x58]
    47:	f0 41 0f c7 4e 60    	lock cmpxchg8b QWORD PTR [r14+0x60]
    4d:	f0 41 0f c7 4e 68    	lock cmpxchg8b QWORD PTR [r14+0x68]
    53:	f0 41 0f c7 4e 70    	lock cmpxchg8b QWORD PTR [r14+0x70]
    59:	f0 41 0f c7 4e 78    	lock cmpxchg8b QWORD PTR [r14+0x78]
  

• Show nanoBench command
• Results:
  • Instructions retired: 16.0
  • Core cycles: 325.13
  • Reference cycles: 245.6
  • UOPS_EXECUTED.THREAD: 288.02
  • RETIRE_SLOTS: 320.0
  • UOPS_MITE: -0.11
  • UOPS_MS: 319.8
  • UOPS_PORT_0: 43.18
  • UOPS_PORT_1: 52.26
  • UOPS_PORT_6: 73.97
  • UOPS_PORT_49: 16.0
  • UOPS_PORT_78: 16.0
  • UOPS_PORT_5B: 76.14
  • UOPS_PORT_5B>=2: 13.95
  • UOPS_PORT_23A: 16.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: -0.01

With loop_count=1000 and unroll_count=1

• Code:

     0:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     5:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
     b:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    11:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
    17:	f0 41 0f c7 4e 20    	lock cmpxchg8b QWORD PTR [r14+0x20]
    1d:	f0 41 0f c7 4e 28    	lock cmpxchg8b QWORD PTR [r14+0x28]
    23:	f0 41 0f c7 4e 30    	lock cmpxchg8b QWORD PTR [r14+0x30]
    29:	f0 41 0f c7 4e 38    	lock cmpxchg8b QWORD PTR [r14+0x38]
    2f:	f0 41 0f c7 4e 40    	lock cmpxchg8b QWORD PTR [r14+0x40]
    35:	f0 41 0f c7 4e 48    	lock cmpxchg8b QWORD PTR [r14+0x48]
    3b:	f0 41 0f c7 4e 50    	lock cmpxchg8b QWORD PTR [r14+0x50]
    41:	f0 41 0f c7 4e 58    	lock cmpxchg8b QWORD PTR [r14+0x58]
    47:	f0 41 0f c7 4e 60    	lock cmpxchg8b QWORD PTR [r14+0x60]
    4d:	f0 41 0f c7 4e 68    	lock cmpxchg8b QWORD PTR [r14+0x68]
    53:	f0 41 0f c7 4e 70    	lock cmpxchg8b QWORD PTR [r14+0x70]
    59:	f0 41 0f c7 4e 78    	lock cmpxchg8b QWORD PTR [r14+0x78]
  

• Show nanoBench command
• Results:
  • Instructions retired: 18.0
  • Core cycles: 324.54
  • Reference cycles: 244.19
  • UOPS_EXECUTED.THREAD: 289.0
  • RETIRE_SLOTS: 321.01
  • UOPS_MITE: 1.0
  • UOPS_MS: 320.07
  • UOPS_PORT_0: 42.97
  • UOPS_PORT_1: 51.88
  • UOPS_PORT_6: 74.46
  • UOPS_PORT_49: 16.0
  • UOPS_PORT_78: 16.0
  • UOPS_PORT_5B: 76.31
  • UOPS_PORT_5B>=2: 14.42
  • UOPS_PORT_23A: 16.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With loop_count=100 and unroll_count=10

• Code:

     0:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     5:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
     b:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    11:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
    17:	f0 41 0f c7 4e 20    	lock cmpxchg8b QWORD PTR [r14+0x20]
    1d:	f0 41 0f c7 4e 28    	lock cmpxchg8b QWORD PTR [r14+0x28]
    23:	f0 41 0f c7 4e 30    	lock cmpxchg8b QWORD PTR [r14+0x30]
    29:	f0 41 0f c7 4e 38    	lock cmpxchg8b QWORD PTR [r14+0x38]
    2f:	f0 41 0f c7 4e 40    	lock cmpxchg8b QWORD PTR [r14+0x40]
    35:	f0 41 0f c7 4e 48    	lock cmpxchg8b QWORD PTR [r14+0x48]
    3b:	f0 41 0f c7 4e 50    	lock cmpxchg8b QWORD PTR [r14+0x50]
    41:	f0 41 0f c7 4e 58    	lock cmpxchg8b QWORD PTR [r14+0x58]
    47:	f0 41 0f c7 4e 60    	lock cmpxchg8b QWORD PTR [r14+0x60]
    4d:	f0 41 0f c7 4e 68    	lock cmpxchg8b QWORD PTR [r14+0x68]
    53:	f0 41 0f c7 4e 70    	lock cmpxchg8b QWORD PTR [r14+0x70]
    59:	f0 41 0f c7 4e 78    	lock cmpxchg8b QWORD PTR [r14+0x78]
  

• Show nanoBench command
• Results:
  • Instructions retired: 16.2
  • Core cycles: 324.99
  • Reference cycles: 244.58
  • UOPS_EXECUTED.THREAD: 288.1
  • RETIRE_SLOTS: 320.1
  • UOPS_MITE: 0.1
  • UOPS_MS: 319.98
  • UOPS_PORT_0: 43.03
  • UOPS_PORT_1: 52.23
  • UOPS_PORT_6: 73.97
  • UOPS_PORT_49: 16.0
  • UOPS_PORT_78: 16.0
  • UOPS_PORT_5B: 76.1
  • UOPS_PORT_5B>=2: 13.88
  • UOPS_PORT_23A: 16.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.1

With additional dependency-breaking instructions

With unroll_count=100 and no inner loop

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     b:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
    11:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    17:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
    1d:	f0 41 0f c7 4e 20    	lock cmpxchg8b QWORD PTR [r14+0x20]
    23:	f0 41 0f c7 4e 28    	lock cmpxchg8b QWORD PTR [r14+0x28]
    29:	f0 41 0f c7 4e 30    	lock cmpxchg8b QWORD PTR [r14+0x30]
    2f:	f0 41 0f c7 4e 38    	lock cmpxchg8b QWORD PTR [r14+0x38]
    35:	f0 41 0f c7 4e 40    	lock cmpxchg8b QWORD PTR [r14+0x40]
    3b:	f0 41 0f c7 4e 48    	lock cmpxchg8b QWORD PTR [r14+0x48]
    41:	f0 41 0f c7 4e 50    	lock cmpxchg8b QWORD PTR [r14+0x50]
    47:	f0 41 0f c7 4e 58    	lock cmpxchg8b QWORD PTR [r14+0x58]
    4d:	f0 41 0f c7 4e 60    	lock cmpxchg8b QWORD PTR [r14+0x60]
    53:	f0 41 0f c7 4e 68    	lock cmpxchg8b QWORD PTR [r14+0x68]
    59:	f0 41 0f c7 4e 70    	lock cmpxchg8b QWORD PTR [r14+0x70]
    5f:	f0 41 0f c7 4e 78    	lock cmpxchg8b QWORD PTR [r14+0x78]
  

• Show nanoBench command
• Results:
  • Instructions retired: 18.0
  • Core cycles: 324.45
  • Reference cycles: 244.0
  • UOPS_EXECUTED.THREAD: 288.0
  • RETIRE_SLOTS: 322.0
  • UOPS_MITE: 1.96
  • UOPS_MS: 319.8
  • UOPS_PORT_0: 43.11
  • UOPS_PORT_1: 53.31
  • UOPS_PORT_6: 73.24
  • UOPS_PORT_49: 16.0
  • UOPS_PORT_78: 16.0
  • UOPS_PORT_5B: 76.63
  • UOPS_PORT_5B>=2: 14.57
  • UOPS_PORT_23A: 16.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With loop_count=1000 and unroll_count=1

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     b:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
    11:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    17:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
    1d:	f0 41 0f c7 4e 20    	lock cmpxchg8b QWORD PTR [r14+0x20]
    23:	f0 41 0f c7 4e 28    	lock cmpxchg8b QWORD PTR [r14+0x28]
    29:	f0 41 0f c7 4e 30    	lock cmpxchg8b QWORD PTR [r14+0x30]
    2f:	f0 41 0f c7 4e 38    	lock cmpxchg8b QWORD PTR [r14+0x38]
    35:	f0 41 0f c7 4e 40    	lock cmpxchg8b QWORD PTR [r14+0x40]
    3b:	f0 41 0f c7 4e 48    	lock cmpxchg8b QWORD PTR [r14+0x48]
    41:	f0 41 0f c7 4e 50    	lock cmpxchg8b QWORD PTR [r14+0x50]
    47:	f0 41 0f c7 4e 58    	lock cmpxchg8b QWORD PTR [r14+0x58]
    4d:	f0 41 0f c7 4e 60    	lock cmpxchg8b QWORD PTR [r14+0x60]
    53:	f0 41 0f c7 4e 68    	lock cmpxchg8b QWORD PTR [r14+0x68]
    59:	f0 41 0f c7 4e 70    	lock cmpxchg8b QWORD PTR [r14+0x70]
    5f:	f0 41 0f c7 4e 78    	lock cmpxchg8b QWORD PTR [r14+0x78]
  

• Show nanoBench command
• Results:
  • Instructions retired: 20.0
  • Core cycles: 324.49
  • Reference cycles: 244.21
  • UOPS_EXECUTED.THREAD: 289.0
  • RETIRE_SLOTS: 323.0
  • UOPS_MITE: 3.0
  • UOPS_MS: 320.09
  • UOPS_PORT_0: 43.96
  • UOPS_PORT_1: 53.77
  • UOPS_PORT_6: 75.27
  • UOPS_PORT_49: 16.0
  • UOPS_PORT_78: 16.0
  • UOPS_PORT_5B: 77.78
  • UOPS_PORT_5B>=2: 14.7
  • UOPS_PORT_23A: 16.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With loop_count=100 and unroll_count=10

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     b:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
    11:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    17:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
    1d:	f0 41 0f c7 4e 20    	lock cmpxchg8b QWORD PTR [r14+0x20]
    23:	f0 41 0f c7 4e 28    	lock cmpxchg8b QWORD PTR [r14+0x28]
    29:	f0 41 0f c7 4e 30    	lock cmpxchg8b QWORD PTR [r14+0x30]
    2f:	f0 41 0f c7 4e 38    	lock cmpxchg8b QWORD PTR [r14+0x38]
    35:	f0 41 0f c7 4e 40    	lock cmpxchg8b QWORD PTR [r14+0x40]
    3b:	f0 41 0f c7 4e 48    	lock cmpxchg8b QWORD PTR [r14+0x48]
    41:	f0 41 0f c7 4e 50    	lock cmpxchg8b QWORD PTR [r14+0x50]
    47:	f0 41 0f c7 4e 58    	lock cmpxchg8b QWORD PTR [r14+0x58]
    4d:	f0 41 0f c7 4e 60    	lock cmpxchg8b QWORD PTR [r14+0x60]
    53:	f0 41 0f c7 4e 68    	lock cmpxchg8b QWORD PTR [r14+0x68]
    59:	f0 41 0f c7 4e 70    	lock cmpxchg8b QWORD PTR [r14+0x70]
    5f:	f0 41 0f c7 4e 78    	lock cmpxchg8b QWORD PTR [r14+0x78]
  

• Show nanoBench command
• Results:
  • Instructions retired: 18.2
  • Core cycles: 324.34
  • Reference cycles: 244.05
  • UOPS_EXECUTED.THREAD: 288.1
  • RETIRE_SLOTS: 322.1
  • UOPS_MITE: 2.1
  • UOPS_MS: 319.98
  • UOPS_PORT_0: 43.14
  • UOPS_PORT_1: 53.24
  • UOPS_PORT_6: 73.53
  • UOPS_PORT_49: 16.0
  • UOPS_PORT_78: 16.0
  • UOPS_PORT_5B: 76.6
  • UOPS_PORT_5B>=2: 14.68
  • UOPS_PORT_23A: 16.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With additional dependency-breaking instructions (before each instruction)

With unroll_count=100 and no inner loop

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     b:	48 31 d2             	xor    rdx,rdx
     e:	48 31 c0             	xor    rax,rax
    11:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
    17:	48 31 d2             	xor    rdx,rdx
    1a:	48 31 c0             	xor    rax,rax
    1d:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    23:	48 31 d2             	xor    rdx,rdx
    26:	48 31 c0             	xor    rax,rax
    29:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
    2f:	48 31 d2             	xor    rdx,rdx
    32:	48 31 c0             	xor    rax,rax
    35:	f0 41 0f c7 4e 20    	lock cmpxchg8b QWORD PTR [r14+0x20]
    3b:	48 31 d2             	xor    rdx,rdx
    3e:	48 31 c0             	xor    rax,rax
    41:	f0 41 0f c7 4e 28    	lock cmpxchg8b QWORD PTR [r14+0x28]
    47:	48 31 d2             	xor    rdx,rdx
    4a:	48 31 c0             	xor    rax,rax
    4d:	f0 41 0f c7 4e 30    	lock cmpxchg8b QWORD PTR [r14+0x30]
    53:	48 31 d2             	xor    rdx,rdx
    56:	48 31 c0             	xor    rax,rax
    59:	f0 41 0f c7 4e 38    	lock cmpxchg8b QWORD PTR [r14+0x38]
    5f:	48 31 d2             	xor    rdx,rdx
    62:	48 31 c0             	xor    rax,rax
    65:	f0 41 0f c7 4e 40    	lock cmpxchg8b QWORD PTR [r14+0x40]
    6b:	48 31 d2             	xor    rdx,rdx
    6e:	48 31 c0             	xor    rax,rax
    71:	f0 41 0f c7 4e 48    	lock cmpxchg8b QWORD PTR [r14+0x48]
    77:	48 31 d2             	xor    rdx,rdx
    7a:	48 31 c0             	xor    rax,rax
    7d:	f0 41 0f c7 4e 50    	lock cmpxchg8b QWORD PTR [r14+0x50]
    83:	48 31 d2             	xor    rdx,rdx
    86:	48 31 c0             	xor    rax,rax
    89:	f0 41 0f c7 4e 58    	lock cmpxchg8b QWORD PTR [r14+0x58]
    8f:	48 31 d2             	xor    rdx,rdx
    92:	48 31 c0             	xor    rax,rax
    95:	f0 41 0f c7 4e 60    	lock cmpxchg8b QWORD PTR [r14+0x60]
    9b:	48 31 d2             	xor    rdx,rdx
    9e:	48 31 c0             	xor    rax,rax
    a1:	f0 41 0f c7 4e 68    	lock cmpxchg8b QWORD PTR [r14+0x68]
    a7:	48 31 d2             	xor    rdx,rdx
    aa:	48 31 c0             	xor    rax,rax
    ad:	f0 41 0f c7 4e 70    	lock cmpxchg8b QWORD PTR [r14+0x70]
    b3:	48 31 d2             	xor    rdx,rdx
    b6:	48 31 c0             	xor    rax,rax
    b9:	f0 41 0f c7 4e 78    	lock cmpxchg8b QWORD PTR [r14+0x78]
  

• Show nanoBench command
• Results:
  • Instructions retired: 48.0
  • Core cycles: 320.83
  • Reference cycles: 241.12
  • UOPS_EXECUTED.THREAD: 288.02
  • RETIRE_SLOTS: 352.01
  • UOPS_MITE: 31.98
  • UOPS_MS: 320.0
  • UOPS_PORT_0: 43.93
  • UOPS_PORT_1: 64.66
  • UOPS_PORT_6: 74.5
  • UOPS_PORT_49: 16.0
  • UOPS_PORT_78: 16.0
  • UOPS_PORT_5B: 77.5
  • UOPS_PORT_5B>=2: 10.68
  • UOPS_PORT_23A: 16.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 16.0

With loop_count=1000 and unroll_count=1

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     b:	48 31 d2             	xor    rdx,rdx
     e:	48 31 c0             	xor    rax,rax
    11:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
    17:	48 31 d2             	xor    rdx,rdx
    1a:	48 31 c0             	xor    rax,rax
    1d:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    23:	48 31 d2             	xor    rdx,rdx
    26:	48 31 c0             	xor    rax,rax
    29:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
    2f:	48 31 d2             	xor    rdx,rdx
    32:	48 31 c0             	xor    rax,rax
    35:	f0 41 0f c7 4e 20    	lock cmpxchg8b QWORD PTR [r14+0x20]
    3b:	48 31 d2             	xor    rdx,rdx
    3e:	48 31 c0             	xor    rax,rax
    41:	f0 41 0f c7 4e 28    	lock cmpxchg8b QWORD PTR [r14+0x28]
    47:	48 31 d2             	xor    rdx,rdx
    4a:	48 31 c0             	xor    rax,rax
    4d:	f0 41 0f c7 4e 30    	lock cmpxchg8b QWORD PTR [r14+0x30]
    53:	48 31 d2             	xor    rdx,rdx
    56:	48 31 c0             	xor    rax,rax
    59:	f0 41 0f c7 4e 38    	lock cmpxchg8b QWORD PTR [r14+0x38]
    5f:	48 31 d2             	xor    rdx,rdx
    62:	48 31 c0             	xor    rax,rax
    65:	f0 41 0f c7 4e 40    	lock cmpxchg8b QWORD PTR [r14+0x40]
    6b:	48 31 d2             	xor    rdx,rdx
    6e:	48 31 c0             	xor    rax,rax
    71:	f0 41 0f c7 4e 48    	lock cmpxchg8b QWORD PTR [r14+0x48]
    77:	48 31 d2             	xor    rdx,rdx
    7a:	48 31 c0             	xor    rax,rax
    7d:	f0 41 0f c7 4e 50    	lock cmpxchg8b QWORD PTR [r14+0x50]
    83:	48 31 d2             	xor    rdx,rdx
    86:	48 31 c0             	xor    rax,rax
    89:	f0 41 0f c7 4e 58    	lock cmpxchg8b QWORD PTR [r14+0x58]
    8f:	48 31 d2             	xor    rdx,rdx
    92:	48 31 c0             	xor    rax,rax
    95:	f0 41 0f c7 4e 60    	lock cmpxchg8b QWORD PTR [r14+0x60]
    9b:	48 31 d2             	xor    rdx,rdx
    9e:	48 31 c0             	xor    rax,rax
    a1:	f0 41 0f c7 4e 68    	lock cmpxchg8b QWORD PTR [r14+0x68]
    a7:	48 31 d2             	xor    rdx,rdx
    aa:	48 31 c0             	xor    rax,rax
    ad:	f0 41 0f c7 4e 70    	lock cmpxchg8b QWORD PTR [r14+0x70]
    b3:	48 31 d2             	xor    rdx,rdx
    b6:	48 31 c0             	xor    rax,rax
    b9:	f0 41 0f c7 4e 78    	lock cmpxchg8b QWORD PTR [r14+0x78]
  

• Show nanoBench command
• Results:
  • Instructions retired: 50.0
  • Core cycles: 320.8
  • Reference cycles: 241.39
  • UOPS_EXECUTED.THREAD: 289.0
  • RETIRE_SLOTS: 353.0
  • UOPS_MITE: 33.01
  • UOPS_MS: 320.08
  • UOPS_PORT_0: 44.81
  • UOPS_PORT_1: 66.42
  • UOPS_PORT_6: 76.38
  • UOPS_PORT_49: 16.0
  • UOPS_PORT_78: 16.0
  • UOPS_PORT_5B: 79.49
  • UOPS_PORT_5B>=2: 11.67
  • UOPS_PORT_23A: 16.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 16.01

With loop_count=100 and unroll_count=10

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 41 0f c7 0e       	lock cmpxchg8b QWORD PTR [r14]
     b:	48 31 d2             	xor    rdx,rdx
     e:	48 31 c0             	xor    rax,rax
    11:	f0 41 0f c7 4e 08    	lock cmpxchg8b QWORD PTR [r14+0x8]
    17:	48 31 d2             	xor    rdx,rdx
    1a:	48 31 c0             	xor    rax,rax
    1d:	f0 41 0f c7 4e 10    	lock cmpxchg8b QWORD PTR [r14+0x10]
    23:	48 31 d2             	xor    rdx,rdx
    26:	48 31 c0             	xor    rax,rax
    29:	f0 41 0f c7 4e 18    	lock cmpxchg8b QWORD PTR [r14+0x18]
    2f:	48 31 d2             	xor    rdx,rdx
    32:	48 31 c0             	xor    rax,rax
    35:	f0 41 0f c7 4e 20    	lock cmpxchg8b QWORD PTR [r14+0x20]
    3b:	48 31 d2             	xor    rdx,rdx
    3e:	48 31 c0             	xor    rax,rax
    41:	f0 41 0f c7 4e 28    	lock cmpxchg8b QWORD PTR [r14+0x28]
    47:	48 31 d2             	xor    rdx,rdx
    4a:	48 31 c0             	xor    rax,rax
    4d:	f0 41 0f c7 4e 30    	lock cmpxchg8b QWORD PTR [r14+0x30]
    53:	48 31 d2             	xor    rdx,rdx
    56:	48 31 c0             	xor    rax,rax
    59:	f0 41 0f c7 4e 38    	lock cmpxchg8b QWORD PTR [r14+0x38]
    5f:	48 31 d2             	xor    rdx,rdx
    62:	48 31 c0             	xor    rax,rax
    65:	f0 41 0f c7 4e 40    	lock cmpxchg8b QWORD PTR [r14+0x40]
    6b:	48 31 d2             	xor    rdx,rdx
    6e:	48 31 c0             	xor    rax,rax
    71:	f0 41 0f c7 4e 48    	lock cmpxchg8b QWORD PTR [r14+0x48]
    77:	48 31 d2             	xor    rdx,rdx
    7a:	48 31 c0             	xor    rax,rax
    7d:	f0 41 0f c7 4e 50    	lock cmpxchg8b QWORD PTR [r14+0x50]
    83:	48 31 d2             	xor    rdx,rdx
    86:	48 31 c0             	xor    rax,rax
    89:	f0 41 0f c7 4e 58    	lock cmpxchg8b QWORD PTR [r14+0x58]
    8f:	48 31 d2             	xor    rdx,rdx
    92:	48 31 c0             	xor    rax,rax
    95:	f0 41 0f c7 4e 60    	lock cmpxchg8b QWORD PTR [r14+0x60]
    9b:	48 31 d2             	xor    rdx,rdx
    9e:	48 31 c0             	xor    rax,rax
    a1:	f0 41 0f c7 4e 68    	lock cmpxchg8b QWORD PTR [r14+0x68]
    a7:	48 31 d2             	xor    rdx,rdx
    aa:	48 31 c0             	xor    rax,rax
    ad:	f0 41 0f c7 4e 70    	lock cmpxchg8b QWORD PTR [r14+0x70]
    b3:	48 31 d2             	xor    rdx,rdx
    b6:	48 31 c0             	xor    rax,rax
    b9:	f0 41 0f c7 4e 78    	lock cmpxchg8b QWORD PTR [r14+0x78]
  

• Show nanoBench command
• Results:
  • Instructions retired: 48.2
  • Core cycles: 320.73
  • Reference cycles: 241.34
  • UOPS_EXECUTED.THREAD: 288.1
  • RETIRE_SLOTS: 352.1
  • UOPS_MITE: 32.14
  • UOPS_MS: 319.98
  • UOPS_PORT_0: 43.79
  • UOPS_PORT_1: 64.67
  • UOPS_PORT_6: 74.59
  • UOPS_PORT_49: 16.0
  • UOPS_PORT_78: 16.0
  • UOPS_PORT_5B: 77.4
  • UOPS_PORT_5B>=2: 10.62
  • UOPS_PORT_23A: 16.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 16.01

With unroll_count=500 and no inner loop

• Code:

     0:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 20.39
  • Reference cycles: 15.36
  • UOPS_EXECUTED.THREAD: 18.0
  • RETIRE_SLOTS: 20.0
  • UOPS_MITE: 0.0
  • UOPS_MS: 19.96
  • UOPS_PORT_0: 3.71
  • UOPS_PORT_1: 4.44
  • UOPS_PORT_6: 5.74
  • UOPS_PORT_49: 1.0
  • UOPS_PORT_78: 1.0
  • UOPS_PORT_5B: 6.9
  • UOPS_PORT_5B>=2: 1.53
  • UOPS_PORT_23A: 1.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.0

With unroll_count=500, no inner loop, and 1 NOP

• Code:

     0:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     6:	90                   	nop
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 20.4
  • Reference cycles: 15.39
  • UOPS_EXECUTED.THREAD: 18.0
  • RETIRE_SLOTS: 21.0
  • UOPS_MITE: 1.0
  • UOPS_MS: 19.99
  • UOPS_PORT_0: 3.95
  • UOPS_PORT_1: 4.02
  • UOPS_PORT_6: 5.93
  • UOPS_PORT_49: 1.0
  • UOPS_PORT_78: 1.0
  • UOPS_PORT_5B: 7.57
  • UOPS_PORT_5B>=2: 1.47
  • UOPS_PORT_23A: 1.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With loop_count=1000 and unroll_count=10

• Code:

     0:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 1.2
  • Core cycles: 20.33
  • Reference cycles: 15.3
  • UOPS_EXECUTED.THREAD: 18.1
  • RETIRE_SLOTS: 20.1
  • UOPS_MITE: 0.1
  • UOPS_MS: 20.01
  • UOPS_PORT_0: 3.63
  • UOPS_PORT_1: 4.38
  • UOPS_PORT_6: 5.79
  • UOPS_PORT_49: 1.0
  • UOPS_PORT_78: 1.0
  • UOPS_PORT_5B: 6.89
  • UOPS_PORT_5B>=2: 1.6
  • UOPS_PORT_23A: 1.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.1

With loop_count=100 and unroll_count=100

• Code:

     0:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 1.02
  • Core cycles: 20.37
  • Reference cycles: 15.33
  • UOPS_EXECUTED.THREAD: 18.01
  • RETIRE_SLOTS: 20.01
  • UOPS_MITE: 0.01
  • UOPS_MS: 20.0
  • UOPS_PORT_0: 3.66
  • UOPS_PORT_1: 4.43
  • UOPS_PORT_6: 5.74
  • UOPS_PORT_49: 1.0
  • UOPS_PORT_78: 1.0
  • UOPS_PORT_5B: 6.87
  • UOPS_PORT_5B>=2: 1.53
  • UOPS_PORT_23A: 1.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.01

With additional dependency-breaking instructions

With unroll_count=500 and no inner loop

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 20.09
  • Reference cycles: 15.14
  • UOPS_EXECUTED.THREAD: 18.0
  • RETIRE_SLOTS: 22.0
  • UOPS_MITE: 2.0
  • UOPS_MS: 19.97
  • UOPS_PORT_0: 3.95
  • UOPS_PORT_1: 5.43
  • UOPS_PORT_6: 5.6
  • UOPS_PORT_49: 1.0
  • UOPS_PORT_78: 1.0
  • UOPS_PORT_5B: 7.67
  • UOPS_PORT_5B>=2: 1.54
  • UOPS_PORT_23A: 1.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With loop_count=1000 and unroll_count=10

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 3.2
  • Core cycles: 20.08
  • Reference cycles: 15.11
  • UOPS_EXECUTED.THREAD: 18.1
  • RETIRE_SLOTS: 22.1
  • UOPS_MITE: 2.1
  • UOPS_MS: 20.01
  • UOPS_PORT_0: 4.0
  • UOPS_PORT_1: 5.57
  • UOPS_PORT_6: 5.81
  • UOPS_PORT_49: 1.0
  • UOPS_PORT_78: 1.0
  • UOPS_PORT_5B: 7.78
  • UOPS_PORT_5B>=2: 1.56
  • UOPS_PORT_23A: 1.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With loop_count=100 and unroll_count=100

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 3.02
  • Core cycles: 20.07
  • Reference cycles: 15.11
  • UOPS_EXECUTED.THREAD: 18.01
  • RETIRE_SLOTS: 22.01
  • UOPS_MITE: 2.01
  • UOPS_MS: 20.0
  • UOPS_PORT_0: 3.94
  • UOPS_PORT_1: 5.41
  • UOPS_PORT_6: 5.6
  • UOPS_PORT_49: 1.0
  • UOPS_PORT_78: 1.0
  • UOPS_PORT_5B: 7.63
  • UOPS_PORT_5B>=2: 1.5
  • UOPS_PORT_23A: 1.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With unroll_count=200 and no inner loop

• Code:

     0:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     6:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
     d:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    14:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 4.0
  • Core cycles: 81.33
  • Reference cycles: 61.12
  • UOPS_EXECUTED.THREAD: 72.0
  • RETIRE_SLOTS: 80.0
  • UOPS_MITE: 0.0
  • UOPS_MS: 79.92
  • UOPS_PORT_0: 13.84
  • UOPS_PORT_1: 17.99
  • UOPS_PORT_6: 22.77
  • UOPS_PORT_49: 4.0
  • UOPS_PORT_78: 4.0
  • UOPS_PORT_5B: 21.31
  • UOPS_PORT_5B>=2: 4.16
  • UOPS_PORT_23A: 4.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.01

With loop_count=1000 and unroll_count=2

• Code:

     0:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     6:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
     d:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    14:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 5.0
  • Core cycles: 81.09
  • Reference cycles: 61.02
  • UOPS_EXECUTED.THREAD: 72.5
  • RETIRE_SLOTS: 80.5
  • UOPS_MITE: 0.5
  • UOPS_MS: 80.04
  • UOPS_PORT_0: 13.52
  • UOPS_PORT_1: 17.32
  • UOPS_PORT_6: 23.37
  • UOPS_PORT_49: 4.0
  • UOPS_PORT_78: 4.0
  • UOPS_PORT_5B: 21.81
  • UOPS_PORT_5B>=2: 4.52
  • UOPS_PORT_23A: 4.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.5

With loop_count=100 and unroll_count=20

• Code:

     0:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     6:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
     d:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    14:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 4.1
  • Core cycles: 81.23
  • Reference cycles: 61.1
  • UOPS_EXECUTED.THREAD: 72.05
  • RETIRE_SLOTS: 80.05
  • UOPS_MITE: 0.05
  • UOPS_MS: 79.99
  • UOPS_PORT_0: 13.79
  • UOPS_PORT_1: 17.95
  • UOPS_PORT_6: 22.84
  • UOPS_PORT_49: 4.0
  • UOPS_PORT_78: 4.0
  • UOPS_PORT_5B: 21.24
  • UOPS_PORT_5B>=2: 4.21
  • UOPS_PORT_23A: 4.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.05

With additional dependency-breaking instructions

With unroll_count=200 and no inner loop

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     c:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
    13:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    1a:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 6.0
  • Core cycles: 80.69
  • Reference cycles: 60.56
  • UOPS_EXECUTED.THREAD: 72.0
  • RETIRE_SLOTS: 82.0
  • UOPS_MITE: 1.93
  • UOPS_MS: 79.97
  • UOPS_PORT_0: 15.2
  • UOPS_PORT_1: 19.01
  • UOPS_PORT_6: 23.5
  • UOPS_PORT_49: 4.0
  • UOPS_PORT_78: 4.0
  • UOPS_PORT_5B: 25.9
  • UOPS_PORT_5B>=2: 6.04
  • UOPS_PORT_23A: 4.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With loop_count=1000 and unroll_count=2

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     c:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
    13:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    1a:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 7.0
  • Core cycles: 80.66
  • Reference cycles: 60.68
  • UOPS_EXECUTED.THREAD: 72.5
  • RETIRE_SLOTS: 82.5
  • UOPS_MITE: 2.5
  • UOPS_MS: 80.04
  • UOPS_PORT_0: 15.14
  • UOPS_PORT_1: 19.15
  • UOPS_PORT_6: 23.97
  • UOPS_PORT_49: 4.0
  • UOPS_PORT_78: 4.0
  • UOPS_PORT_5B: 25.82
  • UOPS_PORT_5B>=2: 6.28
  • UOPS_PORT_23A: 4.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With loop_count=100 and unroll_count=20

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     c:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
    13:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    1a:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 6.1
  • Core cycles: 80.62
  • Reference cycles: 60.65
  • UOPS_EXECUTED.THREAD: 72.05
  • RETIRE_SLOTS: 82.05
  • UOPS_MITE: 2.06
  • UOPS_MS: 80.0
  • UOPS_PORT_0: 15.19
  • UOPS_PORT_1: 19.05
  • UOPS_PORT_6: 23.55
  • UOPS_PORT_49: 4.0
  • UOPS_PORT_78: 4.0
  • UOPS_PORT_5B: 25.83
  • UOPS_PORT_5B>=2: 6.01
  • UOPS_PORT_23A: 4.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With additional dependency-breaking instructions (before each instruction)

With unroll_count=200 and no inner loop

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     c:	48 31 d2             	xor    rdx,rdx
     f:	48 31 c0             	xor    rax,rax
    12:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
    19:	48 31 d2             	xor    rdx,rdx
    1c:	48 31 c0             	xor    rax,rax
    1f:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    26:	48 31 d2             	xor    rdx,rdx
    29:	48 31 c0             	xor    rax,rax
    2c:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 12.0
  • Core cycles: 80.33
  • Reference cycles: 60.48
  • UOPS_EXECUTED.THREAD: 71.99
  • RETIRE_SLOTS: 88.0
  • UOPS_MITE: 8.0
  • UOPS_MS: 79.9
  • UOPS_PORT_0: 17.12
  • UOPS_PORT_1: 22.07
  • UOPS_PORT_6: 23.04
  • UOPS_PORT_49: 4.0
  • UOPS_PORT_78: 4.0
  • UOPS_PORT_5B: 33.6
  • UOPS_PORT_5B>=2: 8.87
  • UOPS_PORT_23A: 4.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 4.0

With loop_count=1000 and unroll_count=2

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     c:	48 31 d2             	xor    rdx,rdx
     f:	48 31 c0             	xor    rax,rax
    12:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
    19:	48 31 d2             	xor    rdx,rdx
    1c:	48 31 c0             	xor    rax,rax
    1f:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    26:	48 31 d2             	xor    rdx,rdx
    29:	48 31 c0             	xor    rax,rax
    2c:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 13.0
  • Core cycles: 80.32
  • Reference cycles: 60.45
  • UOPS_EXECUTED.THREAD: 72.5
  • RETIRE_SLOTS: 88.5
  • UOPS_MITE: 8.5
  • UOPS_MS: 80.04
  • UOPS_PORT_0: 17.28
  • UOPS_PORT_1: 22.88
  • UOPS_PORT_6: 24.25
  • UOPS_PORT_49: 4.0
  • UOPS_PORT_78: 4.0
  • UOPS_PORT_5B: 33.85
  • UOPS_PORT_5B>=2: 8.76
  • UOPS_PORT_23A: 4.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 4.0

With loop_count=100 and unroll_count=20

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     c:	48 31 d2             	xor    rdx,rdx
     f:	48 31 c0             	xor    rax,rax
    12:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
    19:	48 31 d2             	xor    rdx,rdx
    1c:	48 31 c0             	xor    rax,rax
    1f:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    26:	48 31 d2             	xor    rdx,rdx
    29:	48 31 c0             	xor    rax,rax
    2c:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 12.1
  • Core cycles: 80.3
  • Reference cycles: 60.41
  • UOPS_EXECUTED.THREAD: 72.05
  • RETIRE_SLOTS: 88.05
  • UOPS_MITE: 8.05
  • UOPS_MS: 79.99
  • UOPS_PORT_0: 17.1
  • UOPS_PORT_1: 22.08
  • UOPS_PORT_6: 23.21
  • UOPS_PORT_49: 4.0
  • UOPS_PORT_78: 4.0
  • UOPS_PORT_5B: 33.51
  • UOPS_PORT_5B>=2: 8.82
  • UOPS_PORT_23A: 4.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 4.0

With unroll_count=100 and no inner loop

• Code:

     0:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     6:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
     d:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    14:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
    1b:	f0 43 0f c7 4c 2e 20 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x20]
    22:	f0 43 0f c7 4c 2e 28 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x28]
    29:	f0 43 0f c7 4c 2e 30 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x30]
    30:	f0 43 0f c7 4c 2e 38 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x38]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 8.0
  • Core cycles: 162.59
  • Reference cycles: 122.08
  • UOPS_EXECUTED.THREAD: 143.98
  • RETIRE_SLOTS: 160.0
  • UOPS_MITE: 0.02
  • UOPS_MS: 159.8
  • UOPS_PORT_0: 31.59
  • UOPS_PORT_1: 38.44
  • UOPS_PORT_6: 50.36
  • UOPS_PORT_49: 8.0
  • UOPS_PORT_78: 8.0
  • UOPS_PORT_5B: 45.44
  • UOPS_PORT_5B>=2: 7.55
  • UOPS_PORT_23A: 8.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.01

With loop_count=1000 and unroll_count=1

• Code:

     0:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     6:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
     d:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    14:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
    1b:	f0 43 0f c7 4c 2e 20 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x20]
    22:	f0 43 0f c7 4c 2e 28 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x28]
    29:	f0 43 0f c7 4c 2e 30 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x30]
    30:	f0 43 0f c7 4c 2e 38 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x38]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 10.0
  • Core cycles: 162.21
  • Reference cycles: 122.05
  • UOPS_EXECUTED.THREAD: 145.0
  • RETIRE_SLOTS: 161.0
  • UOPS_MITE: 0.98
  • UOPS_MS: 160.1
  • UOPS_PORT_0: 30.51
  • UOPS_PORT_1: 37.19
  • UOPS_PORT_6: 51.85
  • UOPS_PORT_49: 8.0
  • UOPS_PORT_78: 8.0
  • UOPS_PORT_5B: 47.53
  • UOPS_PORT_5B>=2: 8.27
  • UOPS_PORT_23A: 8.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With loop_count=100 and unroll_count=10

• Code:

     0:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     6:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
     d:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    14:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
    1b:	f0 43 0f c7 4c 2e 20 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x20]
    22:	f0 43 0f c7 4c 2e 28 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x28]
    29:	f0 43 0f c7 4c 2e 30 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x30]
    30:	f0 43 0f c7 4c 2e 38 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x38]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 8.2
  • Core cycles: 162.48
  • Reference cycles: 122.35
  • UOPS_EXECUTED.THREAD: 144.1
  • RETIRE_SLOTS: 160.1
  • UOPS_MITE: 0.1
  • UOPS_MS: 159.98
  • UOPS_PORT_0: 31.44
  • UOPS_PORT_1: 38.69
  • UOPS_PORT_6: 50.66
  • UOPS_PORT_49: 8.0
  • UOPS_PORT_78: 8.0
  • UOPS_PORT_5B: 45.77
  • UOPS_PORT_5B>=2: 7.64
  • UOPS_PORT_23A: 8.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.1

With additional dependency-breaking instructions

With unroll_count=100 and no inner loop

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     c:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
    13:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    1a:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
    21:	f0 43 0f c7 4c 2e 20 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x20]
    28:	f0 43 0f c7 4c 2e 28 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x28]
    2f:	f0 43 0f c7 4c 2e 30 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x30]
    36:	f0 43 0f c7 4c 2e 38 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x38]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 10.0
  • Core cycles: 162.0
  • Reference cycles: 121.92
  • UOPS_EXECUTED.THREAD: 144.02
  • RETIRE_SLOTS: 162.0
  • UOPS_MITE: 2.0
  • UOPS_MS: 159.91
  • UOPS_PORT_0: 32.03
  • UOPS_PORT_1: 39.66
  • UOPS_PORT_6: 51.5
  • UOPS_PORT_49: 8.0
  • UOPS_PORT_78: 8.0
  • UOPS_PORT_5B: 52.61
  • UOPS_PORT_5B>=2: 10.97
  • UOPS_PORT_23A: 8.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With loop_count=1000 and unroll_count=1

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     c:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
    13:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    1a:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
    21:	f0 43 0f c7 4c 2e 20 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x20]
    28:	f0 43 0f c7 4c 2e 28 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x28]
    2f:	f0 43 0f c7 4c 2e 30 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x30]
    36:	f0 43 0f c7 4c 2e 38 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x38]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 12.0
  • Core cycles: 162.03
  • Reference cycles: 121.94
  • UOPS_EXECUTED.THREAD: 145.06
  • RETIRE_SLOTS: 163.06
  • UOPS_MITE: 3.06
  • UOPS_MS: 160.1
  • UOPS_PORT_0: 32.65
  • UOPS_PORT_1: 40.07
  • UOPS_PORT_6: 53.34
  • UOPS_PORT_49: 8.0
  • UOPS_PORT_78: 8.0
  • UOPS_PORT_5B: 52.86
  • UOPS_PORT_5B>=2: 10.83
  • UOPS_PORT_23A: 8.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With loop_count=100 and unroll_count=10

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     c:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
    13:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    1a:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
    21:	f0 43 0f c7 4c 2e 20 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x20]
    28:	f0 43 0f c7 4c 2e 28 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x28]
    2f:	f0 43 0f c7 4c 2e 30 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x30]
    36:	f0 43 0f c7 4c 2e 38 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x38]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 10.2
  • Core cycles: 161.92
  • Reference cycles: 121.84
  • UOPS_EXECUTED.THREAD: 144.1
  • RETIRE_SLOTS: 162.1
  • UOPS_MITE: 2.1
  • UOPS_MS: 159.98
  • UOPS_PORT_0: 32.35
  • UOPS_PORT_1: 39.96
  • UOPS_PORT_6: 51.34
  • UOPS_PORT_49: 8.0
  • UOPS_PORT_78: 8.0
  • UOPS_PORT_5B: 52.71
  • UOPS_PORT_5B>=2: 10.97
  • UOPS_PORT_23A: 8.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With additional dependency-breaking instructions (before each instruction)

With unroll_count=100 and no inner loop

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     c:	48 31 d2             	xor    rdx,rdx
     f:	48 31 c0             	xor    rax,rax
    12:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
    19:	48 31 d2             	xor    rdx,rdx
    1c:	48 31 c0             	xor    rax,rax
    1f:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    26:	48 31 d2             	xor    rdx,rdx
    29:	48 31 c0             	xor    rax,rax
    2c:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
    33:	48 31 d2             	xor    rdx,rdx
    36:	48 31 c0             	xor    rax,rax
    39:	f0 43 0f c7 4c 2e 20 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x20]
    40:	48 31 d2             	xor    rdx,rdx
    43:	48 31 c0             	xor    rax,rax
    46:	f0 43 0f c7 4c 2e 28 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x28]
    4d:	48 31 d2             	xor    rdx,rdx
    50:	48 31 c0             	xor    rax,rax
    53:	f0 43 0f c7 4c 2e 30 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x30]
    5a:	48 31 d2             	xor    rdx,rdx
    5d:	48 31 c0             	xor    rax,rax
    60:	f0 43 0f c7 4c 2e 38 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x38]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 24.0
  • Core cycles: 160.69
  • Reference cycles: 120.8
  • UOPS_EXECUTED.THREAD: 144.0
  • RETIRE_SLOTS: 176.0
  • UOPS_MITE: 15.93
  • UOPS_MS: 159.8
  • UOPS_PORT_0: 40.43
  • UOPS_PORT_1: 50.33
  • UOPS_PORT_6: 50.8
  • UOPS_PORT_49: 8.0
  • UOPS_PORT_78: 8.0
  • UOPS_PORT_5B: 82.56
  • UOPS_PORT_5B>=2: 21.16
  • UOPS_PORT_23A: 8.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 8.0

With loop_count=1000 and unroll_count=1

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     c:	48 31 d2             	xor    rdx,rdx
     f:	48 31 c0             	xor    rax,rax
    12:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
    19:	48 31 d2             	xor    rdx,rdx
    1c:	48 31 c0             	xor    rax,rax
    1f:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    26:	48 31 d2             	xor    rdx,rdx
    29:	48 31 c0             	xor    rax,rax
    2c:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
    33:	48 31 d2             	xor    rdx,rdx
    36:	48 31 c0             	xor    rax,rax
    39:	f0 43 0f c7 4c 2e 20 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x20]
    40:	48 31 d2             	xor    rdx,rdx
    43:	48 31 c0             	xor    rax,rax
    46:	f0 43 0f c7 4c 2e 28 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x28]
    4d:	48 31 d2             	xor    rdx,rdx
    50:	48 31 c0             	xor    rax,rax
    53:	f0 43 0f c7 4c 2e 30 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x30]
    5a:	48 31 d2             	xor    rdx,rdx
    5d:	48 31 c0             	xor    rax,rax
    60:	f0 43 0f c7 4c 2e 38 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x38]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 26.0
  • Core cycles: 160.61
  • Reference cycles: 120.86
  • UOPS_EXECUTED.THREAD: 145.0
  • RETIRE_SLOTS: 177.0
  • UOPS_MITE: 17.04
  • UOPS_MS: 160.09
  • UOPS_PORT_0: 40.13
  • UOPS_PORT_1: 51.64
  • UOPS_PORT_6: 53.28
  • UOPS_PORT_49: 8.0
  • UOPS_PORT_78: 8.0
  • UOPS_PORT_5B: 82.76
  • UOPS_PORT_5B>=2: 20.73
  • UOPS_PORT_23A: 8.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 8.01

With loop_count=100 and unroll_count=10

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     c:	48 31 d2             	xor    rdx,rdx
     f:	48 31 c0             	xor    rax,rax
    12:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
    19:	48 31 d2             	xor    rdx,rdx
    1c:	48 31 c0             	xor    rax,rax
    1f:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    26:	48 31 d2             	xor    rdx,rdx
    29:	48 31 c0             	xor    rax,rax
    2c:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
    33:	48 31 d2             	xor    rdx,rdx
    36:	48 31 c0             	xor    rax,rax
    39:	f0 43 0f c7 4c 2e 20 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x20]
    40:	48 31 d2             	xor    rdx,rdx
    43:	48 31 c0             	xor    rax,rax
    46:	f0 43 0f c7 4c 2e 28 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x28]
    4d:	48 31 d2             	xor    rdx,rdx
    50:	48 31 c0             	xor    rax,rax
    53:	f0 43 0f c7 4c 2e 30 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x30]
    5a:	48 31 d2             	xor    rdx,rdx
    5d:	48 31 c0             	xor    rax,rax
    60:	f0 43 0f c7 4c 2e 38 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x38]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 24.2
  • Core cycles: 160.6
  • Reference cycles: 120.96
  • UOPS_EXECUTED.THREAD: 144.1
  • RETIRE_SLOTS: 176.1
  • UOPS_MITE: 16.1
  • UOPS_MS: 159.99
  • UOPS_PORT_0: 40.4
  • UOPS_PORT_1: 50.48
  • UOPS_PORT_6: 51.24
  • UOPS_PORT_49: 8.0
  • UOPS_PORT_78: 8.0
  • UOPS_PORT_5B: 82.92
  • UOPS_PORT_5B>=2: 21.07
  • UOPS_PORT_23A: 8.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 8.0

With unroll_count=100 and no inner loop

• Code:

     0:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     6:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
     d:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    14:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
    1b:	f0 43 0f c7 4c 2e 20 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x20]
    22:	f0 43 0f c7 4c 2e 28 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x28]
    29:	f0 43 0f c7 4c 2e 30 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x30]
    30:	f0 43 0f c7 4c 2e 38 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x38]
    37:	f0 43 0f c7 4c 2e 40 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x40]
    3e:	f0 43 0f c7 4c 2e 48 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x48]
    45:	f0 43 0f c7 4c 2e 50 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x50]
    4c:	f0 43 0f c7 4c 2e 58 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x58]
    53:	f0 43 0f c7 4c 2e 60 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x60]
    5a:	f0 43 0f c7 4c 2e 68 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x68]
    61:	f0 43 0f c7 4c 2e 70 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x70]
    68:	f0 43 0f c7 4c 2e 78 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x78]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 16.0
  • Core cycles: 325.04
  • Reference cycles: 244.64
  • UOPS_EXECUTED.THREAD: 288.01
  • RETIRE_SLOTS: 320.0
  • UOPS_MITE: 0.0
  • UOPS_MS: 319.8
  • UOPS_PORT_0: 43.14
  • UOPS_PORT_1: 52.28
  • UOPS_PORT_6: 74.0
  • UOPS_PORT_49: 16.0
  • UOPS_PORT_78: 16.0
  • UOPS_PORT_5B: 76.15
  • UOPS_PORT_5B>=2: 13.87
  • UOPS_PORT_23A: 16.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.01

With loop_count=1000 and unroll_count=1

• Code:

     0:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     6:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
     d:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    14:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
    1b:	f0 43 0f c7 4c 2e 20 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x20]
    22:	f0 43 0f c7 4c 2e 28 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x28]
    29:	f0 43 0f c7 4c 2e 30 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x30]
    30:	f0 43 0f c7 4c 2e 38 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x38]
    37:	f0 43 0f c7 4c 2e 40 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x40]
    3e:	f0 43 0f c7 4c 2e 48 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x48]
    45:	f0 43 0f c7 4c 2e 50 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x50]
    4c:	f0 43 0f c7 4c 2e 58 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x58]
    53:	f0 43 0f c7 4c 2e 60 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x60]
    5a:	f0 43 0f c7 4c 2e 68 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x68]
    61:	f0 43 0f c7 4c 2e 70 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x70]
    68:	f0 43 0f c7 4c 2e 78 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x78]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 18.0
  • Core cycles: 324.6
  • Reference cycles: 244.37
  • UOPS_EXECUTED.THREAD: 289.0
  • RETIRE_SLOTS: 321.0
  • UOPS_MITE: 1.0
  • UOPS_MS: 320.08
  • UOPS_PORT_0: 42.98
  • UOPS_PORT_1: 51.9
  • UOPS_PORT_6: 74.45
  • UOPS_PORT_49: 16.0
  • UOPS_PORT_78: 16.0
  • UOPS_PORT_5B: 76.31
  • UOPS_PORT_5B>=2: 14.38
  • UOPS_PORT_23A: 16.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With loop_count=100 and unroll_count=10

• Code:

     0:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     6:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
     d:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    14:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
    1b:	f0 43 0f c7 4c 2e 20 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x20]
    22:	f0 43 0f c7 4c 2e 28 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x28]
    29:	f0 43 0f c7 4c 2e 30 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x30]
    30:	f0 43 0f c7 4c 2e 38 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x38]
    37:	f0 43 0f c7 4c 2e 40 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x40]
    3e:	f0 43 0f c7 4c 2e 48 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x48]
    45:	f0 43 0f c7 4c 2e 50 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x50]
    4c:	f0 43 0f c7 4c 2e 58 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x58]
    53:	f0 43 0f c7 4c 2e 60 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x60]
    5a:	f0 43 0f c7 4c 2e 68 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x68]
    61:	f0 43 0f c7 4c 2e 70 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x70]
    68:	f0 43 0f c7 4c 2e 78 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x78]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 16.2
  • Core cycles: 324.99
  • Reference cycles: 244.59
  • UOPS_EXECUTED.THREAD: 288.1
  • RETIRE_SLOTS: 320.1
  • UOPS_MITE: 0.1
  • UOPS_MS: 319.99
  • UOPS_PORT_0: 43.04
  • UOPS_PORT_1: 52.24
  • UOPS_PORT_6: 73.96
  • UOPS_PORT_49: 16.0
  • UOPS_PORT_78: 16.0
  • UOPS_PORT_5B: 76.1
  • UOPS_PORT_5B>=2: 13.84
  • UOPS_PORT_23A: 16.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.1

With additional dependency-breaking instructions

With unroll_count=100 and no inner loop

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     c:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
    13:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    1a:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
    21:	f0 43 0f c7 4c 2e 20 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x20]
    28:	f0 43 0f c7 4c 2e 28 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x28]
    2f:	f0 43 0f c7 4c 2e 30 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x30]
    36:	f0 43 0f c7 4c 2e 38 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x38]
    3d:	f0 43 0f c7 4c 2e 40 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x40]
    44:	f0 43 0f c7 4c 2e 48 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x48]
    4b:	f0 43 0f c7 4c 2e 50 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x50]
    52:	f0 43 0f c7 4c 2e 58 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x58]
    59:	f0 43 0f c7 4c 2e 60 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x60]
    60:	f0 43 0f c7 4c 2e 68 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x68]
    67:	f0 43 0f c7 4c 2e 70 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x70]
    6e:	f0 43 0f c7 4c 2e 78 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x78]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 18.0
  • Core cycles: 324.39
  • Reference cycles: 244.16
  • UOPS_EXECUTED.THREAD: 288.0
  • RETIRE_SLOTS: 322.0
  • UOPS_MITE: 1.96
  • UOPS_MS: 319.88
  • UOPS_PORT_0: 43.15
  • UOPS_PORT_1: 53.23
  • UOPS_PORT_6: 73.24
  • UOPS_PORT_49: 16.0
  • UOPS_PORT_78: 16.0
  • UOPS_PORT_5B: 76.45
  • UOPS_PORT_5B>=2: 14.81
  • UOPS_PORT_23A: 16.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.92

With loop_count=1000 and unroll_count=1

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     c:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
    13:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    1a:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
    21:	f0 43 0f c7 4c 2e 20 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x20]
    28:	f0 43 0f c7 4c 2e 28 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x28]
    2f:	f0 43 0f c7 4c 2e 30 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x30]
    36:	f0 43 0f c7 4c 2e 38 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x38]
    3d:	f0 43 0f c7 4c 2e 40 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x40]
    44:	f0 43 0f c7 4c 2e 48 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x48]
    4b:	f0 43 0f c7 4c 2e 50 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x50]
    52:	f0 43 0f c7 4c 2e 58 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x58]
    59:	f0 43 0f c7 4c 2e 60 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x60]
    60:	f0 43 0f c7 4c 2e 68 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x68]
    67:	f0 43 0f c7 4c 2e 70 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x70]
    6e:	f0 43 0f c7 4c 2e 78 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x78]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 20.0
  • Core cycles: 324.46
  • Reference cycles: 244.18
  • UOPS_EXECUTED.THREAD: 289.0
  • RETIRE_SLOTS: 323.0
  • UOPS_MITE: 3.0
  • UOPS_MS: 320.09
  • UOPS_PORT_0: 43.98
  • UOPS_PORT_1: 53.76
  • UOPS_PORT_6: 75.28
  • UOPS_PORT_49: 16.0
  • UOPS_PORT_78: 16.0
  • UOPS_PORT_5B: 77.73
  • UOPS_PORT_5B>=2: 14.73
  • UOPS_PORT_23A: 16.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With loop_count=100 and unroll_count=10

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     c:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
    13:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    1a:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
    21:	f0 43 0f c7 4c 2e 20 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x20]
    28:	f0 43 0f c7 4c 2e 28 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x28]
    2f:	f0 43 0f c7 4c 2e 30 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x30]
    36:	f0 43 0f c7 4c 2e 38 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x38]
    3d:	f0 43 0f c7 4c 2e 40 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x40]
    44:	f0 43 0f c7 4c 2e 48 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x48]
    4b:	f0 43 0f c7 4c 2e 50 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x50]
    52:	f0 43 0f c7 4c 2e 58 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x58]
    59:	f0 43 0f c7 4c 2e 60 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x60]
    60:	f0 43 0f c7 4c 2e 68 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x68]
    67:	f0 43 0f c7 4c 2e 70 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x70]
    6e:	f0 43 0f c7 4c 2e 78 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x78]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 18.2
  • Core cycles: 324.33
  • Reference cycles: 244.03
  • UOPS_EXECUTED.THREAD: 288.1
  • RETIRE_SLOTS: 322.1
  • UOPS_MITE: 2.09
  • UOPS_MS: 319.98
  • UOPS_PORT_0: 43.14
  • UOPS_PORT_1: 53.24
  • UOPS_PORT_6: 73.48
  • UOPS_PORT_49: 16.0
  • UOPS_PORT_78: 16.0
  • UOPS_PORT_5B: 76.68
  • UOPS_PORT_5B>=2: 14.67
  • UOPS_PORT_23A: 16.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With additional dependency-breaking instructions (before each instruction)

With unroll_count=100 and no inner loop

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     c:	48 31 d2             	xor    rdx,rdx
     f:	48 31 c0             	xor    rax,rax
    12:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
    19:	48 31 d2             	xor    rdx,rdx
    1c:	48 31 c0             	xor    rax,rax
    1f:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    26:	48 31 d2             	xor    rdx,rdx
    29:	48 31 c0             	xor    rax,rax
    2c:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
    33:	48 31 d2             	xor    rdx,rdx
    36:	48 31 c0             	xor    rax,rax
    39:	f0 43 0f c7 4c 2e 20 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x20]
    40:	48 31 d2             	xor    rdx,rdx
    43:	48 31 c0             	xor    rax,rax
    46:	f0 43 0f c7 4c 2e 28 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x28]
    4d:	48 31 d2             	xor    rdx,rdx
    50:	48 31 c0             	xor    rax,rax
    53:	f0 43 0f c7 4c 2e 30 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x30]
    5a:	48 31 d2             	xor    rdx,rdx
    5d:	48 31 c0             	xor    rax,rax
    60:	f0 43 0f c7 4c 2e 38 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x38]
    67:	48 31 d2             	xor    rdx,rdx
    6a:	48 31 c0             	xor    rax,rax
    6d:	f0 43 0f c7 4c 2e 40 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x40]
    74:	48 31 d2             	xor    rdx,rdx
    77:	48 31 c0             	xor    rax,rax
    7a:	f0 43 0f c7 4c 2e 48 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x48]
    81:	48 31 d2             	xor    rdx,rdx
    84:	48 31 c0             	xor    rax,rax
    87:	f0 43 0f c7 4c 2e 50 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x50]
    8e:	48 31 d2             	xor    rdx,rdx
    91:	48 31 c0             	xor    rax,rax
    94:	f0 43 0f c7 4c 2e 58 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x58]
    9b:	48 31 d2             	xor    rdx,rdx
    9e:	48 31 c0             	xor    rax,rax
    a1:	f0 43 0f c7 4c 2e 60 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x60]
    a8:	48 31 d2             	xor    rdx,rdx
    ab:	48 31 c0             	xor    rax,rax
    ae:	f0 43 0f c7 4c 2e 68 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x68]
    b5:	48 31 d2             	xor    rdx,rdx
    b8:	48 31 c0             	xor    rax,rax
    bb:	f0 43 0f c7 4c 2e 70 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x70]
    c2:	48 31 d2             	xor    rdx,rdx
    c5:	48 31 c0             	xor    rax,rax
    c8:	f0 43 0f c7 4c 2e 78 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x78]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 48.0
  • Core cycles: 320.86
  • Reference cycles: 241.28
  • UOPS_EXECUTED.THREAD: 288.0
  • RETIRE_SLOTS: 352.0
  • UOPS_MITE: 32.0
  • UOPS_MS: 319.89
  • UOPS_PORT_0: 43.91
  • UOPS_PORT_1: 64.68
  • UOPS_PORT_6: 74.58
  • UOPS_PORT_49: 16.0
  • UOPS_PORT_78: 16.0
  • UOPS_PORT_5B: 77.56
  • UOPS_PORT_5B>=2: 10.66
  • UOPS_PORT_23A: 16.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 15.96

With loop_count=1000 and unroll_count=1

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     c:	48 31 d2             	xor    rdx,rdx
     f:	48 31 c0             	xor    rax,rax
    12:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
    19:	48 31 d2             	xor    rdx,rdx
    1c:	48 31 c0             	xor    rax,rax
    1f:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    26:	48 31 d2             	xor    rdx,rdx
    29:	48 31 c0             	xor    rax,rax
    2c:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
    33:	48 31 d2             	xor    rdx,rdx
    36:	48 31 c0             	xor    rax,rax
    39:	f0 43 0f c7 4c 2e 20 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x20]
    40:	48 31 d2             	xor    rdx,rdx
    43:	48 31 c0             	xor    rax,rax
    46:	f0 43 0f c7 4c 2e 28 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x28]
    4d:	48 31 d2             	xor    rdx,rdx
    50:	48 31 c0             	xor    rax,rax
    53:	f0 43 0f c7 4c 2e 30 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x30]
    5a:	48 31 d2             	xor    rdx,rdx
    5d:	48 31 c0             	xor    rax,rax
    60:	f0 43 0f c7 4c 2e 38 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x38]
    67:	48 31 d2             	xor    rdx,rdx
    6a:	48 31 c0             	xor    rax,rax
    6d:	f0 43 0f c7 4c 2e 40 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x40]
    74:	48 31 d2             	xor    rdx,rdx
    77:	48 31 c0             	xor    rax,rax
    7a:	f0 43 0f c7 4c 2e 48 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x48]
    81:	48 31 d2             	xor    rdx,rdx
    84:	48 31 c0             	xor    rax,rax
    87:	f0 43 0f c7 4c 2e 50 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x50]
    8e:	48 31 d2             	xor    rdx,rdx
    91:	48 31 c0             	xor    rax,rax
    94:	f0 43 0f c7 4c 2e 58 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x58]
    9b:	48 31 d2             	xor    rdx,rdx
    9e:	48 31 c0             	xor    rax,rax
    a1:	f0 43 0f c7 4c 2e 60 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x60]
    a8:	48 31 d2             	xor    rdx,rdx
    ab:	48 31 c0             	xor    rax,rax
    ae:	f0 43 0f c7 4c 2e 68 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x68]
    b5:	48 31 d2             	xor    rdx,rdx
    b8:	48 31 c0             	xor    rax,rax
    bb:	f0 43 0f c7 4c 2e 70 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x70]
    c2:	48 31 d2             	xor    rdx,rdx
    c5:	48 31 c0             	xor    rax,rax
    c8:	f0 43 0f c7 4c 2e 78 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x78]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 50.0
  • Core cycles: 320.8
  • Reference cycles: 241.41
  • UOPS_EXECUTED.THREAD: 289.0
  • RETIRE_SLOTS: 353.0
  • UOPS_MITE: 33.02
  • UOPS_MS: 320.08
  • UOPS_PORT_0: 44.84
  • UOPS_PORT_1: 66.35
  • UOPS_PORT_6: 76.4
  • UOPS_PORT_49: 16.0
  • UOPS_PORT_78: 16.0
  • UOPS_PORT_5B: 79.46
  • UOPS_PORT_5B>=2: 11.67
  • UOPS_PORT_23A: 16.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 16.0

With loop_count=100 and unroll_count=10

• Code:

     0:	48 31 d2             	xor    rdx,rdx
     3:	48 31 c0             	xor    rax,rax
     6:	f0 43 0f c7 0c 2e    	lock cmpxchg8b QWORD PTR [r14+r13*1]
     c:	48 31 d2             	xor    rdx,rdx
     f:	48 31 c0             	xor    rax,rax
    12:	f0 43 0f c7 4c 2e 08 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x8]
    19:	48 31 d2             	xor    rdx,rdx
    1c:	48 31 c0             	xor    rax,rax
    1f:	f0 43 0f c7 4c 2e 10 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x10]
    26:	48 31 d2             	xor    rdx,rdx
    29:	48 31 c0             	xor    rax,rax
    2c:	f0 43 0f c7 4c 2e 18 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x18]
    33:	48 31 d2             	xor    rdx,rdx
    36:	48 31 c0             	xor    rax,rax
    39:	f0 43 0f c7 4c 2e 20 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x20]
    40:	48 31 d2             	xor    rdx,rdx
    43:	48 31 c0             	xor    rax,rax
    46:	f0 43 0f c7 4c 2e 28 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x28]
    4d:	48 31 d2             	xor    rdx,rdx
    50:	48 31 c0             	xor    rax,rax
    53:	f0 43 0f c7 4c 2e 30 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x30]
    5a:	48 31 d2             	xor    rdx,rdx
    5d:	48 31 c0             	xor    rax,rax
    60:	f0 43 0f c7 4c 2e 38 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x38]
    67:	48 31 d2             	xor    rdx,rdx
    6a:	48 31 c0             	xor    rax,rax
    6d:	f0 43 0f c7 4c 2e 40 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x40]
    74:	48 31 d2             	xor    rdx,rdx
    77:	48 31 c0             	xor    rax,rax
    7a:	f0 43 0f c7 4c 2e 48 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x48]
    81:	48 31 d2             	xor    rdx,rdx
    84:	48 31 c0             	xor    rax,rax
    87:	f0 43 0f c7 4c 2e 50 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x50]
    8e:	48 31 d2             	xor    rdx,rdx
    91:	48 31 c0             	xor    rax,rax
    94:	f0 43 0f c7 4c 2e 58 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x58]
    9b:	48 31 d2             	xor    rdx,rdx
    9e:	48 31 c0             	xor    rax,rax
    a1:	f0 43 0f c7 4c 2e 60 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x60]
    a8:	48 31 d2             	xor    rdx,rdx
    ab:	48 31 c0             	xor    rax,rax
    ae:	f0 43 0f c7 4c 2e 68 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x68]
    b5:	48 31 d2             	xor    rdx,rdx
    b8:	48 31 c0             	xor    rax,rax
    bb:	f0 43 0f c7 4c 2e 70 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x70]
    c2:	48 31 d2             	xor    rdx,rdx
    c5:	48 31 c0             	xor    rax,rax
    c8:	f0 43 0f c7 4c 2e 78 	lock cmpxchg8b QWORD PTR [r14+r13*1+0x78]
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 48.2
  • Core cycles: 320.74
  • Reference cycles: 241.34
  • UOPS_EXECUTED.THREAD: 288.1
  • RETIRE_SLOTS: 352.1
  • UOPS_MITE: 32.13
  • UOPS_MS: 319.98
  • UOPS_PORT_0: 43.84
  • UOPS_PORT_1: 64.66
  • UOPS_PORT_6: 74.58
  • UOPS_PORT_49: 16.0
  • UOPS_PORT_78: 16.0
  • UOPS_PORT_5B: 77.38
  • UOPS_PORT_5B>=2: 10.65
  • UOPS_PORT_23A: 16.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 16.01