CMPXCHG_LOCK (M64, R64) - Throughput and Uops

With unroll_count=500 and no inner loop

• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 21.27
  • Reference cycles: 22.37
  • UOPS_EXECUTED.THREAD: 9.0
  • RETIRE_SLOTS: 10.0
  • UOPS_MITE: 0.0
  • UOPS_MS: 10.0
  • UOPS_PORT_0: 1.13
  • UOPS_PORT_1: 1.09
  • UOPS_PORT_2: 1.2
  • UOPS_PORT_3: 0.87
  • UOPS_PORT_4: 1.0
  • UOPS_PORT_5: 0.95
  • UOPS_PORT_6: 2.88
  • UOPS_PORT_7: 0.0
  • 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 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	90                   	nop
  

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.0
  • Reference cycles: 22.09
  • UOPS_EXECUTED.THREAD: 9.0
  • RETIRE_SLOTS: 11.0
  • UOPS_MITE: 1.0
  • UOPS_MS: 10.0
  • UOPS_PORT_0: 1.05
  • UOPS_PORT_1: 1.09
  • UOPS_PORT_2: 0.94
  • UOPS_PORT_3: 1.06
  • UOPS_PORT_4: 1.0
  • UOPS_PORT_5: 0.91
  • UOPS_PORT_6: 2.95
  • UOPS_PORT_7: 0.0
  • 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 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 1.2
  • Core cycles: 21.0
  • Reference cycles: 22.11
  • UOPS_EXECUTED.THREAD: 9.1
  • RETIRE_SLOTS: 10.1
  • UOPS_MITE: 0.1
  • UOPS_MS: 10.01
  • UOPS_PORT_0: 1.05
  • UOPS_PORT_1: 1.0
  • UOPS_PORT_2: 1.04
  • UOPS_PORT_3: 0.96
  • UOPS_PORT_4: 1.0
  • UOPS_PORT_5: 1.0
  • UOPS_PORT_6: 3.05
  • UOPS_PORT_7: 0.0
  • 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 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 1.02
  • Core cycles: 21.0
  • Reference cycles: 22.11
  • UOPS_EXECUTED.THREAD: 9.01
  • RETIRE_SLOTS: 10.01
  • UOPS_MITE: 0.01
  • UOPS_MS: 10.01
  • UOPS_PORT_0: 1.07
  • UOPS_PORT_1: 0.93
  • UOPS_PORT_2: 1.06
  • UOPS_PORT_3: 0.94
  • UOPS_PORT_4: 1.0
  • UOPS_PORT_5: 1.07
  • UOPS_PORT_6: 2.94
  • UOPS_PORT_7: 0.0
  • 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 c0             	xor    rax,rax
     3:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.0
  • Reference cycles: 22.11
  • UOPS_EXECUTED.THREAD: 9.0
  • RETIRE_SLOTS: 11.0
  • UOPS_MITE: 1.0
  • UOPS_MS: 10.0
  • UOPS_PORT_0: 1.45
  • UOPS_PORT_1: 1.5
  • UOPS_PORT_2: 0.98
  • UOPS_PORT_3: 1.02
  • UOPS_PORT_4: 1.0
  • UOPS_PORT_5: 1.4
  • UOPS_PORT_6: 3.4
  • UOPS_PORT_7: 0.0
  • 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 c0             	xor    rax,rax
     3:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 2.2
  • Core cycles: 21.0
  • Reference cycles: 22.11
  • UOPS_EXECUTED.THREAD: 9.1
  • RETIRE_SLOTS: 11.1
  • UOPS_MITE: 1.1
  • UOPS_MS: 10.01
  • UOPS_PORT_0: 1.51
  • UOPS_PORT_1: 1.5
  • UOPS_PORT_2: 0.97
  • UOPS_PORT_3: 1.03
  • UOPS_PORT_4: 1.0
  • UOPS_PORT_5: 1.45
  • UOPS_PORT_6: 3.5
  • UOPS_PORT_7: 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:	48 31 c0             	xor    rax,rax
     3:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 2.02
  • Core cycles: 21.0
  • Reference cycles: 22.11
  • UOPS_EXECUTED.THREAD: 9.01
  • RETIRE_SLOTS: 11.01
  • UOPS_MITE: 1.01
  • UOPS_MS: 10.01
  • UOPS_PORT_0: 1.48
  • UOPS_PORT_1: 1.52
  • UOPS_PORT_2: 0.96
  • UOPS_PORT_3: 1.04
  • UOPS_PORT_4: 1.0
  • UOPS_PORT_5: 1.39
  • UOPS_PORT_6: 3.39
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.01

With unroll_count=200 and no inner loop

• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	f0 4d 0f b1 46 08    	lock cmpxchg QWORD PTR [r14+0x8],r8
     b:	f0 4d 0f b1 46 10    	lock cmpxchg QWORD PTR [r14+0x10],r8
    11:	f0 4d 0f b1 46 18    	lock cmpxchg QWORD PTR [r14+0x18],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 4.0
  • Core cycles: 92.0
  • Reference cycles: 96.82
  • UOPS_EXECUTED.THREAD: 36.0
  • RETIRE_SLOTS: 40.0
  • UOPS_MITE: 0.0
  • UOPS_MS: 40.0
  • UOPS_PORT_0: 8.35
  • UOPS_PORT_1: 6.09
  • UOPS_PORT_2: 4.4
  • UOPS_PORT_3: 3.6
  • UOPS_PORT_4: 4.0
  • UOPS_PORT_5: 5.92
  • UOPS_PORT_6: 14.78
  • UOPS_PORT_7: 0.0
  • 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 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	f0 4d 0f b1 46 08    	lock cmpxchg QWORD PTR [r14+0x8],r8
     b:	f0 4d 0f b1 46 10    	lock cmpxchg QWORD PTR [r14+0x10],r8
    11:	f0 4d 0f b1 46 18    	lock cmpxchg QWORD PTR [r14+0x18],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 5.0
  • Core cycles: 92.5
  • Reference cycles: 97.37
  • UOPS_EXECUTED.THREAD: 36.5
  • RETIRE_SLOTS: 40.5
  • UOPS_MITE: 0.5
  • UOPS_MS: 40.03
  • UOPS_PORT_0: 6.93
  • UOPS_PORT_1: 6.17
  • UOPS_PORT_2: 4.11
  • UOPS_PORT_3: 3.89
  • UOPS_PORT_4: 4.0
  • UOPS_PORT_5: 5.83
  • UOPS_PORT_6: 15.19
  • UOPS_PORT_7: 0.0
  • 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 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	f0 4d 0f b1 46 08    	lock cmpxchg QWORD PTR [r14+0x8],r8
     b:	f0 4d 0f b1 46 10    	lock cmpxchg QWORD PTR [r14+0x10],r8
    11:	f0 4d 0f b1 46 18    	lock cmpxchg QWORD PTR [r14+0x18],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 4.1
  • Core cycles: 92.05
  • Reference cycles: 96.9
  • UOPS_EXECUTED.THREAD: 36.05
  • RETIRE_SLOTS: 40.05
  • UOPS_MITE: 0.05
  • UOPS_MS: 40.03
  • UOPS_PORT_0: 7.4
  • UOPS_PORT_1: 5.81
  • UOPS_PORT_2: 4.23
  • UOPS_PORT_3: 3.77
  • UOPS_PORT_4: 4.0
  • UOPS_PORT_5: 6.19
  • UOPS_PORT_6: 14.58
  • UOPS_PORT_7: 0.0
  • 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 c0             	xor    rax,rax
     3:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     8:	48 31 c0             	xor    rax,rax
     b:	f0 4d 0f b1 46 08    	lock cmpxchg QWORD PTR [r14+0x8],r8
    11:	48 31 c0             	xor    rax,rax
    14:	f0 4d 0f b1 46 10    	lock cmpxchg QWORD PTR [r14+0x10],r8
    1a:	48 31 c0             	xor    rax,rax
    1d:	f0 4d 0f b1 46 18    	lock cmpxchg QWORD PTR [r14+0x18],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 8.0
  • Core cycles: 95.99
  • Reference cycles: 101.05
  • UOPS_EXECUTED.THREAD: 36.0
  • RETIRE_SLOTS: 44.0
  • UOPS_MITE: 4.0
  • UOPS_MS: 40.0
  • UOPS_PORT_0: 11.31
  • UOPS_PORT_1: 10.1
  • UOPS_PORT_2: 3.98
  • UOPS_PORT_3: 4.02
  • UOPS_PORT_4: 4.0
  • UOPS_PORT_5: 9.18
  • UOPS_PORT_6: 19.12
  • UOPS_PORT_7: 0.0
  • 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 c0             	xor    rax,rax
     3:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     8:	48 31 c0             	xor    rax,rax
     b:	f0 4d 0f b1 46 08    	lock cmpxchg QWORD PTR [r14+0x8],r8
    11:	48 31 c0             	xor    rax,rax
    14:	f0 4d 0f b1 46 10    	lock cmpxchg QWORD PTR [r14+0x10],r8
    1a:	48 31 c0             	xor    rax,rax
    1d:	f0 4d 0f b1 46 18    	lock cmpxchg QWORD PTR [r14+0x18],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 9.0
  • Core cycles: 96.0
  • Reference cycles: 101.05
  • UOPS_EXECUTED.THREAD: 36.5
  • RETIRE_SLOTS: 44.5
  • UOPS_MITE: 4.5
  • UOPS_MS: 40.03
  • UOPS_PORT_0: 11.61
  • UOPS_PORT_1: 9.86
  • UOPS_PORT_2: 3.91
  • UOPS_PORT_3: 4.09
  • UOPS_PORT_4: 4.0
  • UOPS_PORT_5: 9.78
  • UOPS_PORT_6: 19.31
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 4.5

With loop_count=100 and unroll_count=20

• Code:

     0:	48 31 c0             	xor    rax,rax
     3:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     8:	48 31 c0             	xor    rax,rax
     b:	f0 4d 0f b1 46 08    	lock cmpxchg QWORD PTR [r14+0x8],r8
    11:	48 31 c0             	xor    rax,rax
    14:	f0 4d 0f b1 46 10    	lock cmpxchg QWORD PTR [r14+0x10],r8
    1a:	48 31 c0             	xor    rax,rax
    1d:	f0 4d 0f b1 46 18    	lock cmpxchg QWORD PTR [r14+0x18],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 8.1
  • Core cycles: 96.0
  • Reference cycles: 101.05
  • UOPS_EXECUTED.THREAD: 36.05
  • RETIRE_SLOTS: 44.05
  • UOPS_MITE: 4.05
  • UOPS_MS: 40.03
  • UOPS_PORT_0: 11.48
  • UOPS_PORT_1: 9.94
  • UOPS_PORT_2: 3.86
  • UOPS_PORT_3: 4.14
  • UOPS_PORT_4: 4.0
  • UOPS_PORT_5: 9.63
  • UOPS_PORT_6: 18.94
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 4.05

With unroll_count=100 and no inner loop

• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	f0 4d 0f b1 46 08    	lock cmpxchg QWORD PTR [r14+0x8],r8
     b:	f0 4d 0f b1 46 10    	lock cmpxchg QWORD PTR [r14+0x10],r8
    11:	f0 4d 0f b1 46 18    	lock cmpxchg QWORD PTR [r14+0x18],r8
    17:	f0 4d 0f b1 46 20    	lock cmpxchg QWORD PTR [r14+0x20],r8
    1d:	f0 4d 0f b1 46 28    	lock cmpxchg QWORD PTR [r14+0x28],r8
    23:	f0 4d 0f b1 46 30    	lock cmpxchg QWORD PTR [r14+0x30],r8
    29:	f0 4d 0f b1 46 38    	lock cmpxchg QWORD PTR [r14+0x38],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 8.0
  • Core cycles: 183.97
  • Reference cycles: 193.6
  • UOPS_EXECUTED.THREAD: 72.0
  • RETIRE_SLOTS: 80.0
  • UOPS_MITE: 0.0
  • UOPS_MS: 80.0
  • UOPS_PORT_0: 16.5
  • UOPS_PORT_1: 12.24
  • UOPS_PORT_2: 8.89
  • UOPS_PORT_3: 7.11
  • UOPS_PORT_4: 8.0
  • UOPS_PORT_5: 11.75
  • UOPS_PORT_6: 29.67
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.0

With loop_count=1000 and unroll_count=1

• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	f0 4d 0f b1 46 08    	lock cmpxchg QWORD PTR [r14+0x8],r8
     b:	f0 4d 0f b1 46 10    	lock cmpxchg QWORD PTR [r14+0x10],r8
    11:	f0 4d 0f b1 46 18    	lock cmpxchg QWORD PTR [r14+0x18],r8
    17:	f0 4d 0f b1 46 20    	lock cmpxchg QWORD PTR [r14+0x20],r8
    1d:	f0 4d 0f b1 46 28    	lock cmpxchg QWORD PTR [r14+0x28],r8
    23:	f0 4d 0f b1 46 30    	lock cmpxchg QWORD PTR [r14+0x30],r8
    29:	f0 4d 0f b1 46 38    	lock cmpxchg QWORD PTR [r14+0x38],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 10.0
  • Core cycles: 185.0
  • Reference cycles: 194.74
  • UOPS_EXECUTED.THREAD: 73.0
  • RETIRE_SLOTS: 81.0
  • UOPS_MITE: 1.0
  • UOPS_MS: 80.06
  • UOPS_PORT_0: 13.87
  • UOPS_PORT_1: 12.35
  • UOPS_PORT_2: 8.22
  • UOPS_PORT_3: 7.78
  • UOPS_PORT_4: 8.0
  • UOPS_PORT_5: 11.66
  • UOPS_PORT_6: 30.37
  • UOPS_PORT_7: 0.0
  • 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 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	f0 4d 0f b1 46 08    	lock cmpxchg QWORD PTR [r14+0x8],r8
     b:	f0 4d 0f b1 46 10    	lock cmpxchg QWORD PTR [r14+0x10],r8
    11:	f0 4d 0f b1 46 18    	lock cmpxchg QWORD PTR [r14+0x18],r8
    17:	f0 4d 0f b1 46 20    	lock cmpxchg QWORD PTR [r14+0x20],r8
    1d:	f0 4d 0f b1 46 28    	lock cmpxchg QWORD PTR [r14+0x28],r8
    23:	f0 4d 0f b1 46 30    	lock cmpxchg QWORD PTR [r14+0x30],r8
    29:	f0 4d 0f b1 46 38    	lock cmpxchg QWORD PTR [r14+0x38],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 8.2
  • Core cycles: 184.1
  • Reference cycles: 193.79
  • UOPS_EXECUTED.THREAD: 72.11
  • RETIRE_SLOTS: 80.1
  • UOPS_MITE: 0.1
  • UOPS_MS: 80.06
  • UOPS_PORT_0: 14.89
  • UOPS_PORT_1: 11.56
  • UOPS_PORT_2: 8.43
  • UOPS_PORT_3: 7.57
  • UOPS_PORT_4: 8.0
  • UOPS_PORT_5: 12.44
  • UOPS_PORT_6: 29.18
  • UOPS_PORT_7: 0.0
  • 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 c0             	xor    rax,rax
     3:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     8:	48 31 c0             	xor    rax,rax
     b:	f0 4d 0f b1 46 08    	lock cmpxchg QWORD PTR [r14+0x8],r8
    11:	48 31 c0             	xor    rax,rax
    14:	f0 4d 0f b1 46 10    	lock cmpxchg QWORD PTR [r14+0x10],r8
    1a:	48 31 c0             	xor    rax,rax
    1d:	f0 4d 0f b1 46 18    	lock cmpxchg QWORD PTR [r14+0x18],r8
    23:	48 31 c0             	xor    rax,rax
    26:	f0 4d 0f b1 46 20    	lock cmpxchg QWORD PTR [r14+0x20],r8
    2c:	48 31 c0             	xor    rax,rax
    2f:	f0 4d 0f b1 46 28    	lock cmpxchg QWORD PTR [r14+0x28],r8
    35:	48 31 c0             	xor    rax,rax
    38:	f0 4d 0f b1 46 30    	lock cmpxchg QWORD PTR [r14+0x30],r8
    3e:	48 31 c0             	xor    rax,rax
    41:	f0 4d 0f b1 46 38    	lock cmpxchg QWORD PTR [r14+0x38],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 16.0
  • Core cycles: 191.94
  • Reference cycles: 202.03
  • UOPS_EXECUTED.THREAD: 72.0
  • RETIRE_SLOTS: 88.0
  • UOPS_MITE: 8.0
  • UOPS_MS: 80.0
  • UOPS_PORT_0: 21.97
  • UOPS_PORT_1: 20.21
  • UOPS_PORT_2: 7.95
  • UOPS_PORT_3: 8.06
  • UOPS_PORT_4: 8.0
  • UOPS_PORT_5: 18.4
  • UOPS_PORT_6: 36.92
  • UOPS_PORT_7: 0.0
  • 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 c0             	xor    rax,rax
     3:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     8:	48 31 c0             	xor    rax,rax
     b:	f0 4d 0f b1 46 08    	lock cmpxchg QWORD PTR [r14+0x8],r8
    11:	48 31 c0             	xor    rax,rax
    14:	f0 4d 0f b1 46 10    	lock cmpxchg QWORD PTR [r14+0x10],r8
    1a:	48 31 c0             	xor    rax,rax
    1d:	f0 4d 0f b1 46 18    	lock cmpxchg QWORD PTR [r14+0x18],r8
    23:	48 31 c0             	xor    rax,rax
    26:	f0 4d 0f b1 46 20    	lock cmpxchg QWORD PTR [r14+0x20],r8
    2c:	48 31 c0             	xor    rax,rax
    2f:	f0 4d 0f b1 46 28    	lock cmpxchg QWORD PTR [r14+0x28],r8
    35:	48 31 c0             	xor    rax,rax
    38:	f0 4d 0f b1 46 30    	lock cmpxchg QWORD PTR [r14+0x30],r8
    3e:	48 31 c0             	xor    rax,rax
    41:	f0 4d 0f b1 46 38    	lock cmpxchg QWORD PTR [r14+0x38],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 18.0
  • Core cycles: 191.99
  • Reference cycles: 202.1
  • UOPS_EXECUTED.THREAD: 73.0
  • RETIRE_SLOTS: 89.0
  • UOPS_MITE: 9.0
  • UOPS_MS: 80.06
  • UOPS_PORT_0: 23.25
  • UOPS_PORT_1: 19.71
  • UOPS_PORT_2: 7.8
  • UOPS_PORT_3: 8.2
  • UOPS_PORT_4: 8.0
  • UOPS_PORT_5: 19.51
  • UOPS_PORT_6: 38.61
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 9.01

With loop_count=100 and unroll_count=10

• Code:

     0:	48 31 c0             	xor    rax,rax
     3:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     8:	48 31 c0             	xor    rax,rax
     b:	f0 4d 0f b1 46 08    	lock cmpxchg QWORD PTR [r14+0x8],r8
    11:	48 31 c0             	xor    rax,rax
    14:	f0 4d 0f b1 46 10    	lock cmpxchg QWORD PTR [r14+0x10],r8
    1a:	48 31 c0             	xor    rax,rax
    1d:	f0 4d 0f b1 46 18    	lock cmpxchg QWORD PTR [r14+0x18],r8
    23:	48 31 c0             	xor    rax,rax
    26:	f0 4d 0f b1 46 20    	lock cmpxchg QWORD PTR [r14+0x20],r8
    2c:	48 31 c0             	xor    rax,rax
    2f:	f0 4d 0f b1 46 28    	lock cmpxchg QWORD PTR [r14+0x28],r8
    35:	48 31 c0             	xor    rax,rax
    38:	f0 4d 0f b1 46 30    	lock cmpxchg QWORD PTR [r14+0x30],r8
    3e:	48 31 c0             	xor    rax,rax
    41:	f0 4d 0f b1 46 38    	lock cmpxchg QWORD PTR [r14+0x38],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 16.2
  • Core cycles: 192.0
  • Reference cycles: 202.1
  • UOPS_EXECUTED.THREAD: 72.1
  • RETIRE_SLOTS: 88.1
  • UOPS_MITE: 8.1
  • UOPS_MS: 80.06
  • UOPS_PORT_0: 22.79
  • UOPS_PORT_1: 19.88
  • UOPS_PORT_2: 7.69
  • UOPS_PORT_3: 8.31
  • UOPS_PORT_4: 8.0
  • UOPS_PORT_5: 19.19
  • UOPS_PORT_6: 37.69
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 8.11

With unroll_count=100 and no inner loop

• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	f0 4d 0f b1 46 08    	lock cmpxchg QWORD PTR [r14+0x8],r8
     b:	f0 4d 0f b1 46 10    	lock cmpxchg QWORD PTR [r14+0x10],r8
    11:	f0 4d 0f b1 46 18    	lock cmpxchg QWORD PTR [r14+0x18],r8
    17:	f0 4d 0f b1 46 20    	lock cmpxchg QWORD PTR [r14+0x20],r8
    1d:	f0 4d 0f b1 46 28    	lock cmpxchg QWORD PTR [r14+0x28],r8
    23:	f0 4d 0f b1 46 30    	lock cmpxchg QWORD PTR [r14+0x30],r8
    29:	f0 4d 0f b1 46 38    	lock cmpxchg QWORD PTR [r14+0x38],r8
    2f:	f0 4d 0f b1 46 40    	lock cmpxchg QWORD PTR [r14+0x40],r8
    35:	f0 4d 0f b1 46 48    	lock cmpxchg QWORD PTR [r14+0x48],r8
    3b:	f0 4d 0f b1 46 50    	lock cmpxchg QWORD PTR [r14+0x50],r8
    41:	f0 4d 0f b1 46 58    	lock cmpxchg QWORD PTR [r14+0x58],r8
    47:	f0 4d 0f b1 46 60    	lock cmpxchg QWORD PTR [r14+0x60],r8
    4d:	f0 4d 0f b1 46 68    	lock cmpxchg QWORD PTR [r14+0x68],r8
    53:	f0 4d 0f b1 46 70    	lock cmpxchg QWORD PTR [r14+0x70],r8
    59:	f0 4d 0f b1 46 78    	lock cmpxchg QWORD PTR [r14+0x78],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 16.0
  • Core cycles: 338.88
  • Reference cycles: 356.67
  • UOPS_EXECUTED.THREAD: 144.0
  • RETIRE_SLOTS: 160.0
  • UOPS_MITE: 0.0
  • UOPS_MS: 160.0
  • UOPS_PORT_0: 19.43
  • UOPS_PORT_1: 17.05
  • UOPS_PORT_2: 17.77
  • UOPS_PORT_3: 14.23
  • UOPS_PORT_4: 16.0
  • UOPS_PORT_5: 16.39
  • UOPS_PORT_6: 47.24
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.0

With loop_count=1000 and unroll_count=1

• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	f0 4d 0f b1 46 08    	lock cmpxchg QWORD PTR [r14+0x8],r8
     b:	f0 4d 0f b1 46 10    	lock cmpxchg QWORD PTR [r14+0x10],r8
    11:	f0 4d 0f b1 46 18    	lock cmpxchg QWORD PTR [r14+0x18],r8
    17:	f0 4d 0f b1 46 20    	lock cmpxchg QWORD PTR [r14+0x20],r8
    1d:	f0 4d 0f b1 46 28    	lock cmpxchg QWORD PTR [r14+0x28],r8
    23:	f0 4d 0f b1 46 30    	lock cmpxchg QWORD PTR [r14+0x30],r8
    29:	f0 4d 0f b1 46 38    	lock cmpxchg QWORD PTR [r14+0x38],r8
    2f:	f0 4d 0f b1 46 40    	lock cmpxchg QWORD PTR [r14+0x40],r8
    35:	f0 4d 0f b1 46 48    	lock cmpxchg QWORD PTR [r14+0x48],r8
    3b:	f0 4d 0f b1 46 50    	lock cmpxchg QWORD PTR [r14+0x50],r8
    41:	f0 4d 0f b1 46 58    	lock cmpxchg QWORD PTR [r14+0x58],r8
    47:	f0 4d 0f b1 46 60    	lock cmpxchg QWORD PTR [r14+0x60],r8
    4d:	f0 4d 0f b1 46 68    	lock cmpxchg QWORD PTR [r14+0x68],r8
    53:	f0 4d 0f b1 46 70    	lock cmpxchg QWORD PTR [r14+0x70],r8
    59:	f0 4d 0f b1 46 78    	lock cmpxchg QWORD PTR [r14+0x78],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 18.0
  • Core cycles: 342.45
  • Reference cycles: 360.48
  • UOPS_EXECUTED.THREAD: 145.0
  • RETIRE_SLOTS: 161.0
  • UOPS_MITE: 1.0
  • UOPS_MS: 160.05
  • UOPS_PORT_0: 19.49
  • UOPS_PORT_1: 17.38
  • UOPS_PORT_2: 16.8
  • UOPS_PORT_3: 15.21
  • UOPS_PORT_4: 16.0
  • UOPS_PORT_5: 17.7
  • UOPS_PORT_6: 50.09
  • UOPS_PORT_7: 0.0
  • 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 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	f0 4d 0f b1 46 08    	lock cmpxchg QWORD PTR [r14+0x8],r8
     b:	f0 4d 0f b1 46 10    	lock cmpxchg QWORD PTR [r14+0x10],r8
    11:	f0 4d 0f b1 46 18    	lock cmpxchg QWORD PTR [r14+0x18],r8
    17:	f0 4d 0f b1 46 20    	lock cmpxchg QWORD PTR [r14+0x20],r8
    1d:	f0 4d 0f b1 46 28    	lock cmpxchg QWORD PTR [r14+0x28],r8
    23:	f0 4d 0f b1 46 30    	lock cmpxchg QWORD PTR [r14+0x30],r8
    29:	f0 4d 0f b1 46 38    	lock cmpxchg QWORD PTR [r14+0x38],r8
    2f:	f0 4d 0f b1 46 40    	lock cmpxchg QWORD PTR [r14+0x40],r8
    35:	f0 4d 0f b1 46 48    	lock cmpxchg QWORD PTR [r14+0x48],r8
    3b:	f0 4d 0f b1 46 50    	lock cmpxchg QWORD PTR [r14+0x50],r8
    41:	f0 4d 0f b1 46 58    	lock cmpxchg QWORD PTR [r14+0x58],r8
    47:	f0 4d 0f b1 46 60    	lock cmpxchg QWORD PTR [r14+0x60],r8
    4d:	f0 4d 0f b1 46 68    	lock cmpxchg QWORD PTR [r14+0x68],r8
    53:	f0 4d 0f b1 46 70    	lock cmpxchg QWORD PTR [r14+0x70],r8
    59:	f0 4d 0f b1 46 78    	lock cmpxchg QWORD PTR [r14+0x78],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 16.2
  • Core cycles: 345.46
  • Reference cycles: 363.65
  • UOPS_EXECUTED.THREAD: 145.93
  • RETIRE_SLOTS: 160.63
  • UOPS_MITE: 0.1
  • UOPS_MS: 164.06
  • UOPS_PORT_0: 19.89
  • UOPS_PORT_1: 16.49
  • UOPS_PORT_2: 17.04
  • UOPS_PORT_3: 15.11
  • UOPS_PORT_4: 16.0
  • UOPS_PORT_5: 18.58
  • UOPS_PORT_6: 48.91
  • UOPS_PORT_7: 0.0
  • 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 c0             	xor    rax,rax
     3:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     8:	48 31 c0             	xor    rax,rax
     b:	f0 4d 0f b1 46 08    	lock cmpxchg QWORD PTR [r14+0x8],r8
    11:	48 31 c0             	xor    rax,rax
    14:	f0 4d 0f b1 46 10    	lock cmpxchg QWORD PTR [r14+0x10],r8
    1a:	48 31 c0             	xor    rax,rax
    1d:	f0 4d 0f b1 46 18    	lock cmpxchg QWORD PTR [r14+0x18],r8
    23:	48 31 c0             	xor    rax,rax
    26:	f0 4d 0f b1 46 20    	lock cmpxchg QWORD PTR [r14+0x20],r8
    2c:	48 31 c0             	xor    rax,rax
    2f:	f0 4d 0f b1 46 28    	lock cmpxchg QWORD PTR [r14+0x28],r8
    35:	48 31 c0             	xor    rax,rax
    38:	f0 4d 0f b1 46 30    	lock cmpxchg QWORD PTR [r14+0x30],r8
    3e:	48 31 c0             	xor    rax,rax
    41:	f0 4d 0f b1 46 38    	lock cmpxchg QWORD PTR [r14+0x38],r8
    47:	48 31 c0             	xor    rax,rax
    4a:	f0 4d 0f b1 46 40    	lock cmpxchg QWORD PTR [r14+0x40],r8
    50:	48 31 c0             	xor    rax,rax
    53:	f0 4d 0f b1 46 48    	lock cmpxchg QWORD PTR [r14+0x48],r8
    59:	48 31 c0             	xor    rax,rax
    5c:	f0 4d 0f b1 46 50    	lock cmpxchg QWORD PTR [r14+0x50],r8
    62:	48 31 c0             	xor    rax,rax
    65:	f0 4d 0f b1 46 58    	lock cmpxchg QWORD PTR [r14+0x58],r8
    6b:	48 31 c0             	xor    rax,rax
    6e:	f0 4d 0f b1 46 60    	lock cmpxchg QWORD PTR [r14+0x60],r8
    74:	48 31 c0             	xor    rax,rax
    77:	f0 4d 0f b1 46 68    	lock cmpxchg QWORD PTR [r14+0x68],r8
    7d:	48 31 c0             	xor    rax,rax
    80:	f0 4d 0f b1 46 70    	lock cmpxchg QWORD PTR [r14+0x70],r8
    86:	48 31 c0             	xor    rax,rax
    89:	f0 4d 0f b1 46 78    	lock cmpxchg QWORD PTR [r14+0x78],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 32.0
  • Core cycles: 355.47
  • Reference cycles: 374.23
  • UOPS_EXECUTED.THREAD: 144.36
  • RETIRE_SLOTS: 176.1
  • UOPS_MITE: 16.07
  • UOPS_MS: 160.8
  • UOPS_PORT_0: 28.45
  • UOPS_PORT_1: 27.82
  • UOPS_PORT_2: 10.44
  • UOPS_PORT_3: 22.1
  • UOPS_PORT_4: 16.0
  • UOPS_PORT_5: 25.75
  • UOPS_PORT_6: 59.11
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 16.13

With loop_count=1000 and unroll_count=1

• Code:

     0:	48 31 c0             	xor    rax,rax
     3:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     8:	48 31 c0             	xor    rax,rax
     b:	f0 4d 0f b1 46 08    	lock cmpxchg QWORD PTR [r14+0x8],r8
    11:	48 31 c0             	xor    rax,rax
    14:	f0 4d 0f b1 46 10    	lock cmpxchg QWORD PTR [r14+0x10],r8
    1a:	48 31 c0             	xor    rax,rax
    1d:	f0 4d 0f b1 46 18    	lock cmpxchg QWORD PTR [r14+0x18],r8
    23:	48 31 c0             	xor    rax,rax
    26:	f0 4d 0f b1 46 20    	lock cmpxchg QWORD PTR [r14+0x20],r8
    2c:	48 31 c0             	xor    rax,rax
    2f:	f0 4d 0f b1 46 28    	lock cmpxchg QWORD PTR [r14+0x28],r8
    35:	48 31 c0             	xor    rax,rax
    38:	f0 4d 0f b1 46 30    	lock cmpxchg QWORD PTR [r14+0x30],r8
    3e:	48 31 c0             	xor    rax,rax
    41:	f0 4d 0f b1 46 38    	lock cmpxchg QWORD PTR [r14+0x38],r8
    47:	48 31 c0             	xor    rax,rax
    4a:	f0 4d 0f b1 46 40    	lock cmpxchg QWORD PTR [r14+0x40],r8
    50:	48 31 c0             	xor    rax,rax
    53:	f0 4d 0f b1 46 48    	lock cmpxchg QWORD PTR [r14+0x48],r8
    59:	48 31 c0             	xor    rax,rax
    5c:	f0 4d 0f b1 46 50    	lock cmpxchg QWORD PTR [r14+0x50],r8
    62:	48 31 c0             	xor    rax,rax
    65:	f0 4d 0f b1 46 58    	lock cmpxchg QWORD PTR [r14+0x58],r8
    6b:	48 31 c0             	xor    rax,rax
    6e:	f0 4d 0f b1 46 60    	lock cmpxchg QWORD PTR [r14+0x60],r8
    74:	48 31 c0             	xor    rax,rax
    77:	f0 4d 0f b1 46 68    	lock cmpxchg QWORD PTR [r14+0x68],r8
    7d:	48 31 c0             	xor    rax,rax
    80:	f0 4d 0f b1 46 70    	lock cmpxchg QWORD PTR [r14+0x70],r8
    86:	48 31 c0             	xor    rax,rax
    89:	f0 4d 0f b1 46 78    	lock cmpxchg QWORD PTR [r14+0x78],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 34.0
  • Core cycles: 348.99
  • Reference cycles: 367.36
  • UOPS_EXECUTED.THREAD: 145.37
  • RETIRE_SLOTS: 177.1
  • UOPS_MITE: 17.07
  • UOPS_MS: 160.81
  • UOPS_PORT_0: 26.73
  • UOPS_PORT_1: 25.65
  • UOPS_PORT_2: 15.48
  • UOPS_PORT_3: 16.66
  • UOPS_PORT_4: 16.0
  • UOPS_PORT_5: 25.59
  • UOPS_PORT_6: 58.38
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 17.15

With loop_count=100 and unroll_count=10

• Code:

     0:	48 31 c0             	xor    rax,rax
     3:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     8:	48 31 c0             	xor    rax,rax
     b:	f0 4d 0f b1 46 08    	lock cmpxchg QWORD PTR [r14+0x8],r8
    11:	48 31 c0             	xor    rax,rax
    14:	f0 4d 0f b1 46 10    	lock cmpxchg QWORD PTR [r14+0x10],r8
    1a:	48 31 c0             	xor    rax,rax
    1d:	f0 4d 0f b1 46 18    	lock cmpxchg QWORD PTR [r14+0x18],r8
    23:	48 31 c0             	xor    rax,rax
    26:	f0 4d 0f b1 46 20    	lock cmpxchg QWORD PTR [r14+0x20],r8
    2c:	48 31 c0             	xor    rax,rax
    2f:	f0 4d 0f b1 46 28    	lock cmpxchg QWORD PTR [r14+0x28],r8
    35:	48 31 c0             	xor    rax,rax
    38:	f0 4d 0f b1 46 30    	lock cmpxchg QWORD PTR [r14+0x30],r8
    3e:	48 31 c0             	xor    rax,rax
    41:	f0 4d 0f b1 46 38    	lock cmpxchg QWORD PTR [r14+0x38],r8
    47:	48 31 c0             	xor    rax,rax
    4a:	f0 4d 0f b1 46 40    	lock cmpxchg QWORD PTR [r14+0x40],r8
    50:	48 31 c0             	xor    rax,rax
    53:	f0 4d 0f b1 46 48    	lock cmpxchg QWORD PTR [r14+0x48],r8
    59:	48 31 c0             	xor    rax,rax
    5c:	f0 4d 0f b1 46 50    	lock cmpxchg QWORD PTR [r14+0x50],r8
    62:	48 31 c0             	xor    rax,rax
    65:	f0 4d 0f b1 46 58    	lock cmpxchg QWORD PTR [r14+0x58],r8
    6b:	48 31 c0             	xor    rax,rax
    6e:	f0 4d 0f b1 46 60    	lock cmpxchg QWORD PTR [r14+0x60],r8
    74:	48 31 c0             	xor    rax,rax
    77:	f0 4d 0f b1 46 68    	lock cmpxchg QWORD PTR [r14+0x68],r8
    7d:	48 31 c0             	xor    rax,rax
    80:	f0 4d 0f b1 46 70    	lock cmpxchg QWORD PTR [r14+0x70],r8
    86:	48 31 c0             	xor    rax,rax
    89:	f0 4d 0f b1 46 78    	lock cmpxchg QWORD PTR [r14+0x78],r8
  

• Show nanoBench command
• Results:
  • Instructions retired: 32.2
  • Core cycles: 354.63
  • Reference cycles: 373.3
  • UOPS_EXECUTED.THREAD: 144.33
  • RETIRE_SLOTS: 176.16
  • UOPS_MITE: 16.15
  • UOPS_MS: 160.54
  • UOPS_PORT_0: 27.8
  • UOPS_PORT_1: 27.39
  • UOPS_PORT_2: 15.42
  • UOPS_PORT_3: 16.62
  • UOPS_PORT_4: 16.0
  • UOPS_PORT_5: 25.42
  • UOPS_PORT_6: 58.12
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 16.17

With unroll_count=500 and no inner loop

• Code:

     0:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 21.01
  • Reference cycles: 22.12
  • UOPS_EXECUTED.THREAD: 9.0
  • RETIRE_SLOTS: 10.0
  • UOPS_MITE: 0.0
  • UOPS_MS: 10.0
  • UOPS_PORT_0: 1.12
  • UOPS_PORT_1: 1.07
  • UOPS_PORT_2: 1.12
  • UOPS_PORT_3: 0.88
  • UOPS_PORT_4: 1.0
  • UOPS_PORT_5: 0.93
  • UOPS_PORT_6: 2.88
  • UOPS_PORT_7: 0.0
  • 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 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     6:	90                   	nop
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.0
  • Reference cycles: 22.08
  • UOPS_EXECUTED.THREAD: 9.0
  • RETIRE_SLOTS: 11.0
  • UOPS_MITE: 1.0
  • UOPS_MS: 10.0
  • UOPS_PORT_0: 1.05
  • UOPS_PORT_1: 1.09
  • UOPS_PORT_2: 0.94
  • UOPS_PORT_3: 1.06
  • UOPS_PORT_4: 1.0
  • UOPS_PORT_5: 0.91
  • UOPS_PORT_6: 2.95
  • UOPS_PORT_7: 0.0
  • 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 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 1.2
  • Core cycles: 21.0
  • Reference cycles: 22.11
  • UOPS_EXECUTED.THREAD: 9.1
  • RETIRE_SLOTS: 10.1
  • UOPS_MITE: 0.1
  • UOPS_MS: 10.01
  • UOPS_PORT_0: 1.05
  • UOPS_PORT_1: 1.0
  • UOPS_PORT_2: 1.04
  • UOPS_PORT_3: 0.96
  • UOPS_PORT_4: 1.0
  • UOPS_PORT_5: 1.0
  • UOPS_PORT_6: 3.05
  • UOPS_PORT_7: 0.0
  • 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 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 1.02
  • Core cycles: 21.0
  • Reference cycles: 22.11
  • UOPS_EXECUTED.THREAD: 9.01
  • RETIRE_SLOTS: 10.01
  • UOPS_MITE: 0.01
  • UOPS_MS: 10.01
  • UOPS_PORT_0: 1.07
  • UOPS_PORT_1: 0.93
  • UOPS_PORT_2: 1.06
  • UOPS_PORT_3: 0.94
  • UOPS_PORT_4: 1.0
  • UOPS_PORT_5: 1.07
  • UOPS_PORT_6: 2.94
  • UOPS_PORT_7: 0.0
  • 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 c0             	xor    rax,rax
     3:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.0
  • Reference cycles: 22.11
  • UOPS_EXECUTED.THREAD: 9.0
  • RETIRE_SLOTS: 11.0
  • UOPS_MITE: 1.0
  • UOPS_MS: 10.0
  • UOPS_PORT_0: 1.45
  • UOPS_PORT_1: 1.5
  • UOPS_PORT_2: 0.98
  • UOPS_PORT_3: 1.02
  • UOPS_PORT_4: 1.0
  • UOPS_PORT_5: 1.4
  • UOPS_PORT_6: 3.4
  • UOPS_PORT_7: 0.0
  • 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 c0             	xor    rax,rax
     3:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 2.2
  • Core cycles: 21.0
  • Reference cycles: 22.11
  • UOPS_EXECUTED.THREAD: 9.1
  • RETIRE_SLOTS: 11.1
  • UOPS_MITE: 1.1
  • UOPS_MS: 10.01
  • UOPS_PORT_0: 1.51
  • UOPS_PORT_1: 1.5
  • UOPS_PORT_2: 0.97
  • UOPS_PORT_3: 1.03
  • UOPS_PORT_4: 1.0
  • UOPS_PORT_5: 1.45
  • UOPS_PORT_6: 3.5
  • UOPS_PORT_7: 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:	48 31 c0             	xor    rax,rax
     3:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 2.02
  • Core cycles: 21.0
  • Reference cycles: 22.11
  • UOPS_EXECUTED.THREAD: 9.01
  • RETIRE_SLOTS: 11.01
  • UOPS_MITE: 1.01
  • UOPS_MS: 10.01
  • UOPS_PORT_0: 1.48
  • UOPS_PORT_1: 1.52
  • UOPS_PORT_2: 0.96
  • UOPS_PORT_3: 1.04
  • UOPS_PORT_4: 1.0
  • UOPS_PORT_5: 1.39
  • UOPS_PORT_6: 3.39
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.01

With unroll_count=200 and no inner loop

• Code:

     0:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     6:	f0 4f 0f b1 44 2e 08 	lock cmpxchg QWORD PTR [r14+r13*1+0x8],r8
     d:	f0 4f 0f b1 44 2e 10 	lock cmpxchg QWORD PTR [r14+r13*1+0x10],r8
    14:	f0 4f 0f b1 44 2e 18 	lock cmpxchg QWORD PTR [r14+r13*1+0x18],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 4.0
  • Core cycles: 92.0
  • Reference cycles: 96.87
  • UOPS_EXECUTED.THREAD: 36.0
  • RETIRE_SLOTS: 40.0
  • UOPS_MITE: 0.0
  • UOPS_MS: 40.0
  • UOPS_PORT_0: 8.35
  • UOPS_PORT_1: 6.09
  • UOPS_PORT_2: 4.4
  • UOPS_PORT_3: 3.6
  • UOPS_PORT_4: 4.0
  • UOPS_PORT_5: 5.92
  • UOPS_PORT_6: 14.78
  • UOPS_PORT_7: 0.0
  • 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 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     6:	f0 4f 0f b1 44 2e 08 	lock cmpxchg QWORD PTR [r14+r13*1+0x8],r8
     d:	f0 4f 0f b1 44 2e 10 	lock cmpxchg QWORD PTR [r14+r13*1+0x10],r8
    14:	f0 4f 0f b1 44 2e 18 	lock cmpxchg QWORD PTR [r14+r13*1+0x18],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 5.0
  • Core cycles: 92.5
  • Reference cycles: 97.37
  • UOPS_EXECUTED.THREAD: 36.5
  • RETIRE_SLOTS: 40.5
  • UOPS_MITE: 0.5
  • UOPS_MS: 40.03
  • UOPS_PORT_0: 6.93
  • UOPS_PORT_1: 6.17
  • UOPS_PORT_2: 4.11
  • UOPS_PORT_3: 3.89
  • UOPS_PORT_4: 4.0
  • UOPS_PORT_5: 5.83
  • UOPS_PORT_6: 15.19
  • UOPS_PORT_7: 0.0
  • 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 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     6:	f0 4f 0f b1 44 2e 08 	lock cmpxchg QWORD PTR [r14+r13*1+0x8],r8
     d:	f0 4f 0f b1 44 2e 10 	lock cmpxchg QWORD PTR [r14+r13*1+0x10],r8
    14:	f0 4f 0f b1 44 2e 18 	lock cmpxchg QWORD PTR [r14+r13*1+0x18],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 4.1
  • Core cycles: 92.05
  • Reference cycles: 96.89
  • UOPS_EXECUTED.THREAD: 36.05
  • RETIRE_SLOTS: 40.05
  • UOPS_MITE: 0.05
  • UOPS_MS: 40.03
  • UOPS_PORT_0: 7.4
  • UOPS_PORT_1: 5.81
  • UOPS_PORT_2: 4.23
  • UOPS_PORT_3: 3.77
  • UOPS_PORT_4: 4.0
  • UOPS_PORT_5: 6.19
  • UOPS_PORT_6: 14.58
  • UOPS_PORT_7: 0.0
  • 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 c0             	xor    rax,rax
     3:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     9:	48 31 c0             	xor    rax,rax
     c:	f0 4f 0f b1 44 2e 08 	lock cmpxchg QWORD PTR [r14+r13*1+0x8],r8
    13:	48 31 c0             	xor    rax,rax
    16:	f0 4f 0f b1 44 2e 10 	lock cmpxchg QWORD PTR [r14+r13*1+0x10],r8
    1d:	48 31 c0             	xor    rax,rax
    20:	f0 4f 0f b1 44 2e 18 	lock cmpxchg QWORD PTR [r14+r13*1+0x18],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 8.0
  • Core cycles: 95.99
  • Reference cycles: 101.05
  • UOPS_EXECUTED.THREAD: 36.0
  • RETIRE_SLOTS: 44.0
  • UOPS_MITE: 4.0
  • UOPS_MS: 40.0
  • UOPS_PORT_0: 11.31
  • UOPS_PORT_1: 10.1
  • UOPS_PORT_2: 3.98
  • UOPS_PORT_3: 4.02
  • UOPS_PORT_4: 4.0
  • UOPS_PORT_5: 9.18
  • UOPS_PORT_6: 19.12
  • UOPS_PORT_7: 0.0
  • 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 c0             	xor    rax,rax
     3:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     9:	48 31 c0             	xor    rax,rax
     c:	f0 4f 0f b1 44 2e 08 	lock cmpxchg QWORD PTR [r14+r13*1+0x8],r8
    13:	48 31 c0             	xor    rax,rax
    16:	f0 4f 0f b1 44 2e 10 	lock cmpxchg QWORD PTR [r14+r13*1+0x10],r8
    1d:	48 31 c0             	xor    rax,rax
    20:	f0 4f 0f b1 44 2e 18 	lock cmpxchg QWORD PTR [r14+r13*1+0x18],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 9.0
  • Core cycles: 96.0
  • Reference cycles: 101.05
  • UOPS_EXECUTED.THREAD: 36.5
  • RETIRE_SLOTS: 44.5
  • UOPS_MITE: 4.5
  • UOPS_MS: 40.03
  • UOPS_PORT_0: 11.61
  • UOPS_PORT_1: 9.86
  • UOPS_PORT_2: 3.91
  • UOPS_PORT_3: 4.09
  • UOPS_PORT_4: 4.0
  • UOPS_PORT_5: 9.78
  • UOPS_PORT_6: 19.31
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 4.5

With loop_count=100 and unroll_count=20

• Code:

     0:	48 31 c0             	xor    rax,rax
     3:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     9:	48 31 c0             	xor    rax,rax
     c:	f0 4f 0f b1 44 2e 08 	lock cmpxchg QWORD PTR [r14+r13*1+0x8],r8
    13:	48 31 c0             	xor    rax,rax
    16:	f0 4f 0f b1 44 2e 10 	lock cmpxchg QWORD PTR [r14+r13*1+0x10],r8
    1d:	48 31 c0             	xor    rax,rax
    20:	f0 4f 0f b1 44 2e 18 	lock cmpxchg QWORD PTR [r14+r13*1+0x18],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 8.1
  • Core cycles: 96.0
  • Reference cycles: 101.05
  • UOPS_EXECUTED.THREAD: 36.05
  • RETIRE_SLOTS: 44.05
  • UOPS_MITE: 4.05
  • UOPS_MS: 40.03
  • UOPS_PORT_0: 11.48
  • UOPS_PORT_1: 9.95
  • UOPS_PORT_2: 3.86
  • UOPS_PORT_3: 4.14
  • UOPS_PORT_4: 4.0
  • UOPS_PORT_5: 9.63
  • UOPS_PORT_6: 18.94
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 4.05

With unroll_count=100 and no inner loop

• Code:

     0:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     6:	f0 4f 0f b1 44 2e 08 	lock cmpxchg QWORD PTR [r14+r13*1+0x8],r8
     d:	f0 4f 0f b1 44 2e 10 	lock cmpxchg QWORD PTR [r14+r13*1+0x10],r8
    14:	f0 4f 0f b1 44 2e 18 	lock cmpxchg QWORD PTR [r14+r13*1+0x18],r8
    1b:	f0 4f 0f b1 44 2e 20 	lock cmpxchg QWORD PTR [r14+r13*1+0x20],r8
    22:	f0 4f 0f b1 44 2e 28 	lock cmpxchg QWORD PTR [r14+r13*1+0x28],r8
    29:	f0 4f 0f b1 44 2e 30 	lock cmpxchg QWORD PTR [r14+r13*1+0x30],r8
    30:	f0 4f 0f b1 44 2e 38 	lock cmpxchg QWORD PTR [r14+r13*1+0x38],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 8.0
  • Core cycles: 183.97
  • Reference cycles: 193.6
  • UOPS_EXECUTED.THREAD: 72.0
  • RETIRE_SLOTS: 80.0
  • UOPS_MITE: 0.0
  • UOPS_MS: 80.0
  • UOPS_PORT_0: 16.5
  • UOPS_PORT_1: 12.24
  • UOPS_PORT_2: 8.89
  • UOPS_PORT_3: 7.11
  • UOPS_PORT_4: 8.0
  • UOPS_PORT_5: 11.75
  • UOPS_PORT_6: 29.67
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.0

With loop_count=1000 and unroll_count=1

• Code:

     0:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     6:	f0 4f 0f b1 44 2e 08 	lock cmpxchg QWORD PTR [r14+r13*1+0x8],r8
     d:	f0 4f 0f b1 44 2e 10 	lock cmpxchg QWORD PTR [r14+r13*1+0x10],r8
    14:	f0 4f 0f b1 44 2e 18 	lock cmpxchg QWORD PTR [r14+r13*1+0x18],r8
    1b:	f0 4f 0f b1 44 2e 20 	lock cmpxchg QWORD PTR [r14+r13*1+0x20],r8
    22:	f0 4f 0f b1 44 2e 28 	lock cmpxchg QWORD PTR [r14+r13*1+0x28],r8
    29:	f0 4f 0f b1 44 2e 30 	lock cmpxchg QWORD PTR [r14+r13*1+0x30],r8
    30:	f0 4f 0f b1 44 2e 38 	lock cmpxchg QWORD PTR [r14+r13*1+0x38],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 10.0
  • Core cycles: 185.0
  • Reference cycles: 194.74
  • UOPS_EXECUTED.THREAD: 73.0
  • RETIRE_SLOTS: 81.0
  • UOPS_MITE: 1.0
  • UOPS_MS: 80.06
  • UOPS_PORT_0: 13.87
  • UOPS_PORT_1: 12.35
  • UOPS_PORT_2: 8.22
  • UOPS_PORT_3: 7.78
  • UOPS_PORT_4: 8.0
  • UOPS_PORT_5: 11.66
  • UOPS_PORT_6: 30.37
  • UOPS_PORT_7: 0.0
  • 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 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     6:	f0 4f 0f b1 44 2e 08 	lock cmpxchg QWORD PTR [r14+r13*1+0x8],r8
     d:	f0 4f 0f b1 44 2e 10 	lock cmpxchg QWORD PTR [r14+r13*1+0x10],r8
    14:	f0 4f 0f b1 44 2e 18 	lock cmpxchg QWORD PTR [r14+r13*1+0x18],r8
    1b:	f0 4f 0f b1 44 2e 20 	lock cmpxchg QWORD PTR [r14+r13*1+0x20],r8
    22:	f0 4f 0f b1 44 2e 28 	lock cmpxchg QWORD PTR [r14+r13*1+0x28],r8
    29:	f0 4f 0f b1 44 2e 30 	lock cmpxchg QWORD PTR [r14+r13*1+0x30],r8
    30:	f0 4f 0f b1 44 2e 38 	lock cmpxchg QWORD PTR [r14+r13*1+0x38],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 8.2
  • Core cycles: 184.1
  • Reference cycles: 193.79
  • UOPS_EXECUTED.THREAD: 72.11
  • RETIRE_SLOTS: 80.1
  • UOPS_MITE: 0.1
  • UOPS_MS: 80.06
  • UOPS_PORT_0: 14.79
  • UOPS_PORT_1: 11.62
  • UOPS_PORT_2: 8.46
  • UOPS_PORT_3: 7.55
  • UOPS_PORT_4: 8.0
  • UOPS_PORT_5: 12.38
  • UOPS_PORT_6: 29.16
  • UOPS_PORT_7: 0.0
  • 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 c0             	xor    rax,rax
     3:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     9:	48 31 c0             	xor    rax,rax
     c:	f0 4f 0f b1 44 2e 08 	lock cmpxchg QWORD PTR [r14+r13*1+0x8],r8
    13:	48 31 c0             	xor    rax,rax
    16:	f0 4f 0f b1 44 2e 10 	lock cmpxchg QWORD PTR [r14+r13*1+0x10],r8
    1d:	48 31 c0             	xor    rax,rax
    20:	f0 4f 0f b1 44 2e 18 	lock cmpxchg QWORD PTR [r14+r13*1+0x18],r8
    27:	48 31 c0             	xor    rax,rax
    2a:	f0 4f 0f b1 44 2e 20 	lock cmpxchg QWORD PTR [r14+r13*1+0x20],r8
    31:	48 31 c0             	xor    rax,rax
    34:	f0 4f 0f b1 44 2e 28 	lock cmpxchg QWORD PTR [r14+r13*1+0x28],r8
    3b:	48 31 c0             	xor    rax,rax
    3e:	f0 4f 0f b1 44 2e 30 	lock cmpxchg QWORD PTR [r14+r13*1+0x30],r8
    45:	48 31 c0             	xor    rax,rax
    48:	f0 4f 0f b1 44 2e 38 	lock cmpxchg QWORD PTR [r14+r13*1+0x38],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 16.0
  • Core cycles: 191.94
  • Reference cycles: 202.0
  • UOPS_EXECUTED.THREAD: 72.0
  • RETIRE_SLOTS: 88.0
  • UOPS_MITE: 8.0
  • UOPS_MS: 80.0
  • UOPS_PORT_0: 21.97
  • UOPS_PORT_1: 20.21
  • UOPS_PORT_2: 7.95
  • UOPS_PORT_3: 8.06
  • UOPS_PORT_4: 8.0
  • UOPS_PORT_5: 18.4
  • UOPS_PORT_6: 36.92
  • UOPS_PORT_7: 0.0
  • 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 c0             	xor    rax,rax
     3:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     9:	48 31 c0             	xor    rax,rax
     c:	f0 4f 0f b1 44 2e 08 	lock cmpxchg QWORD PTR [r14+r13*1+0x8],r8
    13:	48 31 c0             	xor    rax,rax
    16:	f0 4f 0f b1 44 2e 10 	lock cmpxchg QWORD PTR [r14+r13*1+0x10],r8
    1d:	48 31 c0             	xor    rax,rax
    20:	f0 4f 0f b1 44 2e 18 	lock cmpxchg QWORD PTR [r14+r13*1+0x18],r8
    27:	48 31 c0             	xor    rax,rax
    2a:	f0 4f 0f b1 44 2e 20 	lock cmpxchg QWORD PTR [r14+r13*1+0x20],r8
    31:	48 31 c0             	xor    rax,rax
    34:	f0 4f 0f b1 44 2e 28 	lock cmpxchg QWORD PTR [r14+r13*1+0x28],r8
    3b:	48 31 c0             	xor    rax,rax
    3e:	f0 4f 0f b1 44 2e 30 	lock cmpxchg QWORD PTR [r14+r13*1+0x30],r8
    45:	48 31 c0             	xor    rax,rax
    48:	f0 4f 0f b1 44 2e 38 	lock cmpxchg QWORD PTR [r14+r13*1+0x38],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 18.0
  • Core cycles: 191.99
  • Reference cycles: 202.1
  • UOPS_EXECUTED.THREAD: 73.0
  • RETIRE_SLOTS: 89.0
  • UOPS_MITE: 9.01
  • UOPS_MS: 80.06
  • UOPS_PORT_0: 23.25
  • UOPS_PORT_1: 19.71
  • UOPS_PORT_2: 7.8
  • UOPS_PORT_3: 8.2
  • UOPS_PORT_4: 8.0
  • UOPS_PORT_5: 19.51
  • UOPS_PORT_6: 38.61
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 9.01

With loop_count=100 and unroll_count=10

• Code:

     0:	48 31 c0             	xor    rax,rax
     3:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     9:	48 31 c0             	xor    rax,rax
     c:	f0 4f 0f b1 44 2e 08 	lock cmpxchg QWORD PTR [r14+r13*1+0x8],r8
    13:	48 31 c0             	xor    rax,rax
    16:	f0 4f 0f b1 44 2e 10 	lock cmpxchg QWORD PTR [r14+r13*1+0x10],r8
    1d:	48 31 c0             	xor    rax,rax
    20:	f0 4f 0f b1 44 2e 18 	lock cmpxchg QWORD PTR [r14+r13*1+0x18],r8
    27:	48 31 c0             	xor    rax,rax
    2a:	f0 4f 0f b1 44 2e 20 	lock cmpxchg QWORD PTR [r14+r13*1+0x20],r8
    31:	48 31 c0             	xor    rax,rax
    34:	f0 4f 0f b1 44 2e 28 	lock cmpxchg QWORD PTR [r14+r13*1+0x28],r8
    3b:	48 31 c0             	xor    rax,rax
    3e:	f0 4f 0f b1 44 2e 30 	lock cmpxchg QWORD PTR [r14+r13*1+0x30],r8
    45:	48 31 c0             	xor    rax,rax
    48:	f0 4f 0f b1 44 2e 38 	lock cmpxchg QWORD PTR [r14+r13*1+0x38],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 16.2
  • Core cycles: 192.0
  • Reference cycles: 202.1
  • UOPS_EXECUTED.THREAD: 72.1
  • RETIRE_SLOTS: 88.1
  • UOPS_MITE: 8.11
  • UOPS_MS: 80.06
  • UOPS_PORT_0: 22.79
  • UOPS_PORT_1: 19.88
  • UOPS_PORT_2: 7.69
  • UOPS_PORT_3: 8.31
  • UOPS_PORT_4: 8.0
  • UOPS_PORT_5: 19.19
  • UOPS_PORT_6: 37.68
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 8.11

With unroll_count=100 and no inner loop

• Code:

     0:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     6:	f0 4f 0f b1 44 2e 08 	lock cmpxchg QWORD PTR [r14+r13*1+0x8],r8
     d:	f0 4f 0f b1 44 2e 10 	lock cmpxchg QWORD PTR [r14+r13*1+0x10],r8
    14:	f0 4f 0f b1 44 2e 18 	lock cmpxchg QWORD PTR [r14+r13*1+0x18],r8
    1b:	f0 4f 0f b1 44 2e 20 	lock cmpxchg QWORD PTR [r14+r13*1+0x20],r8
    22:	f0 4f 0f b1 44 2e 28 	lock cmpxchg QWORD PTR [r14+r13*1+0x28],r8
    29:	f0 4f 0f b1 44 2e 30 	lock cmpxchg QWORD PTR [r14+r13*1+0x30],r8
    30:	f0 4f 0f b1 44 2e 38 	lock cmpxchg QWORD PTR [r14+r13*1+0x38],r8
    37:	f0 4f 0f b1 44 2e 40 	lock cmpxchg QWORD PTR [r14+r13*1+0x40],r8
    3e:	f0 4f 0f b1 44 2e 48 	lock cmpxchg QWORD PTR [r14+r13*1+0x48],r8
    45:	f0 4f 0f b1 44 2e 50 	lock cmpxchg QWORD PTR [r14+r13*1+0x50],r8
    4c:	f0 4f 0f b1 44 2e 58 	lock cmpxchg QWORD PTR [r14+r13*1+0x58],r8
    53:	f0 4f 0f b1 44 2e 60 	lock cmpxchg QWORD PTR [r14+r13*1+0x60],r8
    5a:	f0 4f 0f b1 44 2e 68 	lock cmpxchg QWORD PTR [r14+r13*1+0x68],r8
    61:	f0 4f 0f b1 44 2e 70 	lock cmpxchg QWORD PTR [r14+r13*1+0x70],r8
    68:	f0 4f 0f b1 44 2e 78 	lock cmpxchg QWORD PTR [r14+r13*1+0x78],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 16.0
  • Core cycles: 338.88
  • Reference cycles: 356.67
  • UOPS_EXECUTED.THREAD: 144.0
  • RETIRE_SLOTS: 160.0
  • UOPS_MITE: 0.0
  • UOPS_MS: 160.0
  • UOPS_PORT_0: 19.43
  • UOPS_PORT_1: 17.05
  • UOPS_PORT_2: 17.77
  • UOPS_PORT_3: 14.23
  • UOPS_PORT_4: 16.0
  • UOPS_PORT_5: 16.39
  • UOPS_PORT_6: 47.24
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.0

With loop_count=1000 and unroll_count=1

• Code:

     0:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     6:	f0 4f 0f b1 44 2e 08 	lock cmpxchg QWORD PTR [r14+r13*1+0x8],r8
     d:	f0 4f 0f b1 44 2e 10 	lock cmpxchg QWORD PTR [r14+r13*1+0x10],r8
    14:	f0 4f 0f b1 44 2e 18 	lock cmpxchg QWORD PTR [r14+r13*1+0x18],r8
    1b:	f0 4f 0f b1 44 2e 20 	lock cmpxchg QWORD PTR [r14+r13*1+0x20],r8
    22:	f0 4f 0f b1 44 2e 28 	lock cmpxchg QWORD PTR [r14+r13*1+0x28],r8
    29:	f0 4f 0f b1 44 2e 30 	lock cmpxchg QWORD PTR [r14+r13*1+0x30],r8
    30:	f0 4f 0f b1 44 2e 38 	lock cmpxchg QWORD PTR [r14+r13*1+0x38],r8
    37:	f0 4f 0f b1 44 2e 40 	lock cmpxchg QWORD PTR [r14+r13*1+0x40],r8
    3e:	f0 4f 0f b1 44 2e 48 	lock cmpxchg QWORD PTR [r14+r13*1+0x48],r8
    45:	f0 4f 0f b1 44 2e 50 	lock cmpxchg QWORD PTR [r14+r13*1+0x50],r8
    4c:	f0 4f 0f b1 44 2e 58 	lock cmpxchg QWORD PTR [r14+r13*1+0x58],r8
    53:	f0 4f 0f b1 44 2e 60 	lock cmpxchg QWORD PTR [r14+r13*1+0x60],r8
    5a:	f0 4f 0f b1 44 2e 68 	lock cmpxchg QWORD PTR [r14+r13*1+0x68],r8
    61:	f0 4f 0f b1 44 2e 70 	lock cmpxchg QWORD PTR [r14+r13*1+0x70],r8
    68:	f0 4f 0f b1 44 2e 78 	lock cmpxchg QWORD PTR [r14+r13*1+0x78],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 18.0
  • Core cycles: 342.45
  • Reference cycles: 360.47
  • UOPS_EXECUTED.THREAD: 145.0
  • RETIRE_SLOTS: 161.0
  • UOPS_MITE: 1.0
  • UOPS_MS: 160.05
  • UOPS_PORT_0: 19.49
  • UOPS_PORT_1: 17.38
  • UOPS_PORT_2: 16.8
  • UOPS_PORT_3: 15.21
  • UOPS_PORT_4: 16.0
  • UOPS_PORT_5: 17.7
  • UOPS_PORT_6: 50.09
  • UOPS_PORT_7: 0.0
  • 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 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     6:	f0 4f 0f b1 44 2e 08 	lock cmpxchg QWORD PTR [r14+r13*1+0x8],r8
     d:	f0 4f 0f b1 44 2e 10 	lock cmpxchg QWORD PTR [r14+r13*1+0x10],r8
    14:	f0 4f 0f b1 44 2e 18 	lock cmpxchg QWORD PTR [r14+r13*1+0x18],r8
    1b:	f0 4f 0f b1 44 2e 20 	lock cmpxchg QWORD PTR [r14+r13*1+0x20],r8
    22:	f0 4f 0f b1 44 2e 28 	lock cmpxchg QWORD PTR [r14+r13*1+0x28],r8
    29:	f0 4f 0f b1 44 2e 30 	lock cmpxchg QWORD PTR [r14+r13*1+0x30],r8
    30:	f0 4f 0f b1 44 2e 38 	lock cmpxchg QWORD PTR [r14+r13*1+0x38],r8
    37:	f0 4f 0f b1 44 2e 40 	lock cmpxchg QWORD PTR [r14+r13*1+0x40],r8
    3e:	f0 4f 0f b1 44 2e 48 	lock cmpxchg QWORD PTR [r14+r13*1+0x48],r8
    45:	f0 4f 0f b1 44 2e 50 	lock cmpxchg QWORD PTR [r14+r13*1+0x50],r8
    4c:	f0 4f 0f b1 44 2e 58 	lock cmpxchg QWORD PTR [r14+r13*1+0x58],r8
    53:	f0 4f 0f b1 44 2e 60 	lock cmpxchg QWORD PTR [r14+r13*1+0x60],r8
    5a:	f0 4f 0f b1 44 2e 68 	lock cmpxchg QWORD PTR [r14+r13*1+0x68],r8
    61:	f0 4f 0f b1 44 2e 70 	lock cmpxchg QWORD PTR [r14+r13*1+0x70],r8
    68:	f0 4f 0f b1 44 2e 78 	lock cmpxchg QWORD PTR [r14+r13*1+0x78],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 16.2
  • Core cycles: 341.78
  • Reference cycles: 359.76
  • UOPS_EXECUTED.THREAD: 144.1
  • RETIRE_SLOTS: 160.1
  • UOPS_MITE: 0.1
  • UOPS_MS: 160.06
  • UOPS_PORT_0: 19.71
  • UOPS_PORT_1: 16.33
  • UOPS_PORT_2: 16.94
  • UOPS_PORT_3: 15.06
  • UOPS_PORT_4: 16.0
  • UOPS_PORT_5: 18.55
  • UOPS_PORT_6: 48.68
  • UOPS_PORT_7: 0.0
  • 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 c0             	xor    rax,rax
     3:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     9:	48 31 c0             	xor    rax,rax
     c:	f0 4f 0f b1 44 2e 08 	lock cmpxchg QWORD PTR [r14+r13*1+0x8],r8
    13:	48 31 c0             	xor    rax,rax
    16:	f0 4f 0f b1 44 2e 10 	lock cmpxchg QWORD PTR [r14+r13*1+0x10],r8
    1d:	48 31 c0             	xor    rax,rax
    20:	f0 4f 0f b1 44 2e 18 	lock cmpxchg QWORD PTR [r14+r13*1+0x18],r8
    27:	48 31 c0             	xor    rax,rax
    2a:	f0 4f 0f b1 44 2e 20 	lock cmpxchg QWORD PTR [r14+r13*1+0x20],r8
    31:	48 31 c0             	xor    rax,rax
    34:	f0 4f 0f b1 44 2e 28 	lock cmpxchg QWORD PTR [r14+r13*1+0x28],r8
    3b:	48 31 c0             	xor    rax,rax
    3e:	f0 4f 0f b1 44 2e 30 	lock cmpxchg QWORD PTR [r14+r13*1+0x30],r8
    45:	48 31 c0             	xor    rax,rax
    48:	f0 4f 0f b1 44 2e 38 	lock cmpxchg QWORD PTR [r14+r13*1+0x38],r8
    4f:	48 31 c0             	xor    rax,rax
    52:	f0 4f 0f b1 44 2e 40 	lock cmpxchg QWORD PTR [r14+r13*1+0x40],r8
    59:	48 31 c0             	xor    rax,rax
    5c:	f0 4f 0f b1 44 2e 48 	lock cmpxchg QWORD PTR [r14+r13*1+0x48],r8
    63:	48 31 c0             	xor    rax,rax
    66:	f0 4f 0f b1 44 2e 50 	lock cmpxchg QWORD PTR [r14+r13*1+0x50],r8
    6d:	48 31 c0             	xor    rax,rax
    70:	f0 4f 0f b1 44 2e 58 	lock cmpxchg QWORD PTR [r14+r13*1+0x58],r8
    77:	48 31 c0             	xor    rax,rax
    7a:	f0 4f 0f b1 44 2e 60 	lock cmpxchg QWORD PTR [r14+r13*1+0x60],r8
    81:	48 31 c0             	xor    rax,rax
    84:	f0 4f 0f b1 44 2e 68 	lock cmpxchg QWORD PTR [r14+r13*1+0x68],r8
    8b:	48 31 c0             	xor    rax,rax
    8e:	f0 4f 0f b1 44 2e 70 	lock cmpxchg QWORD PTR [r14+r13*1+0x70],r8
    95:	48 31 c0             	xor    rax,rax
    98:	f0 4f 0f b1 44 2e 78 	lock cmpxchg QWORD PTR [r14+r13*1+0x78],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 32.0
  • Core cycles: 354.06
  • Reference cycles: 372.77
  • UOPS_EXECUTED.THREAD: 144.0
  • RETIRE_SLOTS: 176.0
  • UOPS_MITE: 16.0
  • UOPS_MS: 160.0
  • UOPS_PORT_0: 28.08
  • UOPS_PORT_1: 27.53
  • UOPS_PORT_2: 15.47
  • UOPS_PORT_3: 16.53
  • UOPS_PORT_4: 16.0
  • UOPS_PORT_5: 25.2
  • UOPS_PORT_6: 57.88
  • UOPS_PORT_7: 0.0
  • 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 c0             	xor    rax,rax
     3:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     9:	48 31 c0             	xor    rax,rax
     c:	f0 4f 0f b1 44 2e 08 	lock cmpxchg QWORD PTR [r14+r13*1+0x8],r8
    13:	48 31 c0             	xor    rax,rax
    16:	f0 4f 0f b1 44 2e 10 	lock cmpxchg QWORD PTR [r14+r13*1+0x10],r8
    1d:	48 31 c0             	xor    rax,rax
    20:	f0 4f 0f b1 44 2e 18 	lock cmpxchg QWORD PTR [r14+r13*1+0x18],r8
    27:	48 31 c0             	xor    rax,rax
    2a:	f0 4f 0f b1 44 2e 20 	lock cmpxchg QWORD PTR [r14+r13*1+0x20],r8
    31:	48 31 c0             	xor    rax,rax
    34:	f0 4f 0f b1 44 2e 28 	lock cmpxchg QWORD PTR [r14+r13*1+0x28],r8
    3b:	48 31 c0             	xor    rax,rax
    3e:	f0 4f 0f b1 44 2e 30 	lock cmpxchg QWORD PTR [r14+r13*1+0x30],r8
    45:	48 31 c0             	xor    rax,rax
    48:	f0 4f 0f b1 44 2e 38 	lock cmpxchg QWORD PTR [r14+r13*1+0x38],r8
    4f:	48 31 c0             	xor    rax,rax
    52:	f0 4f 0f b1 44 2e 40 	lock cmpxchg QWORD PTR [r14+r13*1+0x40],r8
    59:	48 31 c0             	xor    rax,rax
    5c:	f0 4f 0f b1 44 2e 48 	lock cmpxchg QWORD PTR [r14+r13*1+0x48],r8
    63:	48 31 c0             	xor    rax,rax
    66:	f0 4f 0f b1 44 2e 50 	lock cmpxchg QWORD PTR [r14+r13*1+0x50],r8
    6d:	48 31 c0             	xor    rax,rax
    70:	f0 4f 0f b1 44 2e 58 	lock cmpxchg QWORD PTR [r14+r13*1+0x58],r8
    77:	48 31 c0             	xor    rax,rax
    7a:	f0 4f 0f b1 44 2e 60 	lock cmpxchg QWORD PTR [r14+r13*1+0x60],r8
    81:	48 31 c0             	xor    rax,rax
    84:	f0 4f 0f b1 44 2e 68 	lock cmpxchg QWORD PTR [r14+r13*1+0x68],r8
    8b:	48 31 c0             	xor    rax,rax
    8e:	f0 4f 0f b1 44 2e 70 	lock cmpxchg QWORD PTR [r14+r13*1+0x70],r8
    95:	48 31 c0             	xor    rax,rax
    98:	f0 4f 0f b1 44 2e 78 	lock cmpxchg QWORD PTR [r14+r13*1+0x78],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 34.0
  • Core cycles: 347.55
  • Reference cycles: 365.84
  • UOPS_EXECUTED.THREAD: 145.0
  • RETIRE_SLOTS: 177.0
  • UOPS_MITE: 17.01
  • UOPS_MS: 160.05
  • UOPS_PORT_0: 26.59
  • UOPS_PORT_1: 25.49
  • UOPS_PORT_2: 15.39
  • UOPS_PORT_3: 16.61
  • UOPS_PORT_4: 16.0
  • UOPS_PORT_5: 25.44
  • UOPS_PORT_6: 57.96
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 17.01

With loop_count=100 and unroll_count=10

• Code:

     0:	48 31 c0             	xor    rax,rax
     3:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     9:	48 31 c0             	xor    rax,rax
     c:	f0 4f 0f b1 44 2e 08 	lock cmpxchg QWORD PTR [r14+r13*1+0x8],r8
    13:	48 31 c0             	xor    rax,rax
    16:	f0 4f 0f b1 44 2e 10 	lock cmpxchg QWORD PTR [r14+r13*1+0x10],r8
    1d:	48 31 c0             	xor    rax,rax
    20:	f0 4f 0f b1 44 2e 18 	lock cmpxchg QWORD PTR [r14+r13*1+0x18],r8
    27:	48 31 c0             	xor    rax,rax
    2a:	f0 4f 0f b1 44 2e 20 	lock cmpxchg QWORD PTR [r14+r13*1+0x20],r8
    31:	48 31 c0             	xor    rax,rax
    34:	f0 4f 0f b1 44 2e 28 	lock cmpxchg QWORD PTR [r14+r13*1+0x28],r8
    3b:	48 31 c0             	xor    rax,rax
    3e:	f0 4f 0f b1 44 2e 30 	lock cmpxchg QWORD PTR [r14+r13*1+0x30],r8
    45:	48 31 c0             	xor    rax,rax
    48:	f0 4f 0f b1 44 2e 38 	lock cmpxchg QWORD PTR [r14+r13*1+0x38],r8
    4f:	48 31 c0             	xor    rax,rax
    52:	f0 4f 0f b1 44 2e 40 	lock cmpxchg QWORD PTR [r14+r13*1+0x40],r8
    59:	48 31 c0             	xor    rax,rax
    5c:	f0 4f 0f b1 44 2e 48 	lock cmpxchg QWORD PTR [r14+r13*1+0x48],r8
    63:	48 31 c0             	xor    rax,rax
    66:	f0 4f 0f b1 44 2e 50 	lock cmpxchg QWORD PTR [r14+r13*1+0x50],r8
    6d:	48 31 c0             	xor    rax,rax
    70:	f0 4f 0f b1 44 2e 58 	lock cmpxchg QWORD PTR [r14+r13*1+0x58],r8
    77:	48 31 c0             	xor    rax,rax
    7a:	f0 4f 0f b1 44 2e 60 	lock cmpxchg QWORD PTR [r14+r13*1+0x60],r8
    81:	48 31 c0             	xor    rax,rax
    84:	f0 4f 0f b1 44 2e 68 	lock cmpxchg QWORD PTR [r14+r13*1+0x68],r8
    8b:	48 31 c0             	xor    rax,rax
    8e:	f0 4f 0f b1 44 2e 70 	lock cmpxchg QWORD PTR [r14+r13*1+0x70],r8
    95:	48 31 c0             	xor    rax,rax
    98:	f0 4f 0f b1 44 2e 78 	lock cmpxchg QWORD PTR [r14+r13*1+0x78],r8
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 32.2
  • Core cycles: 353.56
  • Reference cycles: 372.17
  • UOPS_EXECUTED.THREAD: 144.1
  • RETIRE_SLOTS: 176.1
  • UOPS_MITE: 16.11
  • UOPS_MS: 160.06
  • UOPS_PORT_0: 27.68
  • UOPS_PORT_1: 27.17
  • UOPS_PORT_2: 15.42
  • UOPS_PORT_3: 16.59
  • UOPS_PORT_4: 16.0
  • UOPS_PORT_5: 25.43
  • UOPS_PORT_6: 57.91
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 16.11