CMPXCHG_LOCK (M32, R32) - Latency

Experiment 1 (with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOV R12D, [R14];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR R14, R12; XOR R14, R12
• Chain latency: ≥26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 8b 26             	mov    r12d,DWORD PTR [r14]
     8:	4d 63 e4             	movsxd r12,r12d
     b:	4d 63 e4             	movsxd r12,r12d
     e:	4d 63 e4             	movsxd r12,r12d
    11:	4d 63 e4             	movsxd r12,r12d
    14:	4d 63 e4             	movsxd r12,r12d
    17:	4d 63 e4             	movsxd r12,r12d
    1a:	4d 63 e4             	movsxd r12,r12d
    1d:	4d 63 e4             	movsxd r12,r12d
    20:	4d 63 e4             	movsxd r12,r12d
    23:	4d 63 e4             	movsxd r12,r12d
    26:	4d 63 e4             	movsxd r12,r12d
    29:	4d 63 e4             	movsxd r12,r12d
    2c:	4d 63 e4             	movsxd r12,r12d
    2f:	4d 63 e4             	movsxd r12,r12d
    32:	4d 63 e4             	movsxd r12,r12d
    35:	4d 63 e4             	movsxd r12,r12d
    38:	4d 63 e4             	movsxd r12,r12d
    3b:	4d 63 e4             	movsxd r12,r12d
    3e:	4d 63 e4             	movsxd r12,r12d
    41:	4d 63 e4             	movsxd r12,r12d
    44:	4d 63 e4             	movsxd r12,r12d
    47:	4d 63 e4             	movsxd r12,r12d
    4a:	4d 63 e4             	movsxd r12,r12d
    4d:	4d 63 e4             	movsxd r12,r12d
    50:	4d 31 e6             	xor    r14,r12
    53:	4d 31 e6             	xor    r14,r12
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 28.0
  • Core cycles: 59.15
  • Reference cycles: 29.12
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 2 (with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOV R12D, [R14];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR R14, R12; XOR R14, R12
• Chain latency: ≥26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 8b 26             	mov    r12d,DWORD PTR [r14]
     8:	4d 63 e4             	movsxd r12,r12d
     b:	4d 63 e4             	movsxd r12,r12d
     e:	4d 63 e4             	movsxd r12,r12d
    11:	4d 63 e4             	movsxd r12,r12d
    14:	4d 63 e4             	movsxd r12,r12d
    17:	4d 63 e4             	movsxd r12,r12d
    1a:	4d 63 e4             	movsxd r12,r12d
    1d:	4d 63 e4             	movsxd r12,r12d
    20:	4d 63 e4             	movsxd r12,r12d
    23:	4d 63 e4             	movsxd r12,r12d
    26:	4d 63 e4             	movsxd r12,r12d
    29:	4d 63 e4             	movsxd r12,r12d
    2c:	4d 63 e4             	movsxd r12,r12d
    2f:	4d 63 e4             	movsxd r12,r12d
    32:	4d 63 e4             	movsxd r12,r12d
    35:	4d 63 e4             	movsxd r12,r12d
    38:	4d 63 e4             	movsxd r12,r12d
    3b:	4d 63 e4             	movsxd r12,r12d
    3e:	4d 63 e4             	movsxd r12,r12d
    41:	4d 63 e4             	movsxd r12,r12d
    44:	4d 63 e4             	movsxd r12,r12d
    47:	4d 63 e4             	movsxd r12,r12d
    4a:	4d 63 e4             	movsxd r12,r12d
    4d:	4d 63 e4             	movsxd r12,r12d
    50:	4d 31 e6             	xor    r14,r12
    53:	4d 31 e6             	xor    r14,r12
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 28.0
  • Core cycles: 59.14
  • Reference cycles: 29.12
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 3 (with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOV R12D, [R14];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR R14, R12; XOR R14, R12
• Chain latency: ≥26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 8b 26             	mov    r12d,DWORD PTR [r14]
     8:	4d 63 e4             	movsxd r12,r12d
     b:	4d 63 e4             	movsxd r12,r12d
     e:	4d 63 e4             	movsxd r12,r12d
    11:	4d 63 e4             	movsxd r12,r12d
    14:	4d 63 e4             	movsxd r12,r12d
    17:	4d 63 e4             	movsxd r12,r12d
    1a:	4d 63 e4             	movsxd r12,r12d
    1d:	4d 63 e4             	movsxd r12,r12d
    20:	4d 63 e4             	movsxd r12,r12d
    23:	4d 63 e4             	movsxd r12,r12d
    26:	4d 63 e4             	movsxd r12,r12d
    29:	4d 63 e4             	movsxd r12,r12d
    2c:	4d 63 e4             	movsxd r12,r12d
    2f:	4d 63 e4             	movsxd r12,r12d
    32:	4d 63 e4             	movsxd r12,r12d
    35:	4d 63 e4             	movsxd r12,r12d
    38:	4d 63 e4             	movsxd r12,r12d
    3b:	4d 63 e4             	movsxd r12,r12d
    3e:	4d 63 e4             	movsxd r12,r12d
    41:	4d 63 e4             	movsxd r12,r12d
    44:	4d 63 e4             	movsxd r12,r12d
    47:	4d 63 e4             	movsxd r12,r12d
    4a:	4d 63 e4             	movsxd r12,r12d
    4d:	4d 63 e4             	movsxd r12,r12d
    50:	4d 31 e6             	xor    r14,r12
    53:	4d 31 e6             	xor    r14,r12
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 28.0
  • Core cycles: 59.14
  • Reference cycles: 29.12
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 4 (with additional nop, with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOV R12D, [R14];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR R14, R12; XOR R14, R12;nop
• Chain latency: ≥26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 8b 26             	mov    r12d,DWORD PTR [r14]
     8:	4d 63 e4             	movsxd r12,r12d
     b:	4d 63 e4             	movsxd r12,r12d
     e:	4d 63 e4             	movsxd r12,r12d
    11:	4d 63 e4             	movsxd r12,r12d
    14:	4d 63 e4             	movsxd r12,r12d
    17:	4d 63 e4             	movsxd r12,r12d
    1a:	4d 63 e4             	movsxd r12,r12d
    1d:	4d 63 e4             	movsxd r12,r12d
    20:	4d 63 e4             	movsxd r12,r12d
    23:	4d 63 e4             	movsxd r12,r12d
    26:	4d 63 e4             	movsxd r12,r12d
    29:	4d 63 e4             	movsxd r12,r12d
    2c:	4d 63 e4             	movsxd r12,r12d
    2f:	4d 63 e4             	movsxd r12,r12d
    32:	4d 63 e4             	movsxd r12,r12d
    35:	4d 63 e4             	movsxd r12,r12d
    38:	4d 63 e4             	movsxd r12,r12d
    3b:	4d 63 e4             	movsxd r12,r12d
    3e:	4d 63 e4             	movsxd r12,r12d
    41:	4d 63 e4             	movsxd r12,r12d
    44:	4d 63 e4             	movsxd r12,r12d
    47:	4d 63 e4             	movsxd r12,r12d
    4a:	4d 63 e4             	movsxd r12,r12d
    4d:	4d 63 e4             	movsxd r12,r12d
    50:	4d 31 e6             	xor    r14,r12
    53:	4d 31 e6             	xor    r14,r12
    56:	90                   	nop
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 29.0
  • Core cycles: 60.12
  • Reference cycles: 29.64
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 5 (with additional nop, with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOV R12D, [R14];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR R14, R12; XOR R14, R12;nop
• Chain latency: ≥26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 8b 26             	mov    r12d,DWORD PTR [r14]
     8:	4d 63 e4             	movsxd r12,r12d
     b:	4d 63 e4             	movsxd r12,r12d
     e:	4d 63 e4             	movsxd r12,r12d
    11:	4d 63 e4             	movsxd r12,r12d
    14:	4d 63 e4             	movsxd r12,r12d
    17:	4d 63 e4             	movsxd r12,r12d
    1a:	4d 63 e4             	movsxd r12,r12d
    1d:	4d 63 e4             	movsxd r12,r12d
    20:	4d 63 e4             	movsxd r12,r12d
    23:	4d 63 e4             	movsxd r12,r12d
    26:	4d 63 e4             	movsxd r12,r12d
    29:	4d 63 e4             	movsxd r12,r12d
    2c:	4d 63 e4             	movsxd r12,r12d
    2f:	4d 63 e4             	movsxd r12,r12d
    32:	4d 63 e4             	movsxd r12,r12d
    35:	4d 63 e4             	movsxd r12,r12d
    38:	4d 63 e4             	movsxd r12,r12d
    3b:	4d 63 e4             	movsxd r12,r12d
    3e:	4d 63 e4             	movsxd r12,r12d
    41:	4d 63 e4             	movsxd r12,r12d
    44:	4d 63 e4             	movsxd r12,r12d
    47:	4d 63 e4             	movsxd r12,r12d
    4a:	4d 63 e4             	movsxd r12,r12d
    4d:	4d 63 e4             	movsxd r12,r12d
    50:	4d 31 e6             	xor    r14,r12
    53:	4d 31 e6             	xor    r14,r12
    56:	90                   	nop
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 29.0
  • Core cycles: 60.13
  • Reference cycles: 29.99
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 6 (with additional nop, with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOV R12D, [R14];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR R14, R12; XOR R14, R12;nop
• Chain latency: ≥26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 8b 26             	mov    r12d,DWORD PTR [r14]
     8:	4d 63 e4             	movsxd r12,r12d
     b:	4d 63 e4             	movsxd r12,r12d
     e:	4d 63 e4             	movsxd r12,r12d
    11:	4d 63 e4             	movsxd r12,r12d
    14:	4d 63 e4             	movsxd r12,r12d
    17:	4d 63 e4             	movsxd r12,r12d
    1a:	4d 63 e4             	movsxd r12,r12d
    1d:	4d 63 e4             	movsxd r12,r12d
    20:	4d 63 e4             	movsxd r12,r12d
    23:	4d 63 e4             	movsxd r12,r12d
    26:	4d 63 e4             	movsxd r12,r12d
    29:	4d 63 e4             	movsxd r12,r12d
    2c:	4d 63 e4             	movsxd r12,r12d
    2f:	4d 63 e4             	movsxd r12,r12d
    32:	4d 63 e4             	movsxd r12,r12d
    35:	4d 63 e4             	movsxd r12,r12d
    38:	4d 63 e4             	movsxd r12,r12d
    3b:	4d 63 e4             	movsxd r12,r12d
    3e:	4d 63 e4             	movsxd r12,r12d
    41:	4d 63 e4             	movsxd r12,r12d
    44:	4d 63 e4             	movsxd r12,r12d
    47:	4d 63 e4             	movsxd r12,r12d
    4a:	4d 63 e4             	movsxd r12,r12d
    4d:	4d 63 e4             	movsxd r12,r12d
    50:	4d 31 e6             	xor    r14,r12
    53:	4d 31 e6             	xor    r14,r12
    56:	90                   	nop
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 29.0
  • Core cycles: 60.12
  • Reference cycles: 29.47
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 1

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instructions: MOV R12D, [R14+R13];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR R13, R12; XOR R13, R12
• Chain latency: ≥26
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	47 8b 24 2e          	mov    r12d,DWORD PTR [r14+r13*1]
     a:	4d 63 e4             	movsxd r12,r12d
     d:	4d 63 e4             	movsxd r12,r12d
    10:	4d 63 e4             	movsxd r12,r12d
    13:	4d 63 e4             	movsxd r12,r12d
    16:	4d 63 e4             	movsxd r12,r12d
    19:	4d 63 e4             	movsxd r12,r12d
    1c:	4d 63 e4             	movsxd r12,r12d
    1f:	4d 63 e4             	movsxd r12,r12d
    22:	4d 63 e4             	movsxd r12,r12d
    25:	4d 63 e4             	movsxd r12,r12d
    28:	4d 63 e4             	movsxd r12,r12d
    2b:	4d 63 e4             	movsxd r12,r12d
    2e:	4d 63 e4             	movsxd r12,r12d
    31:	4d 63 e4             	movsxd r12,r12d
    34:	4d 63 e4             	movsxd r12,r12d
    37:	4d 63 e4             	movsxd r12,r12d
    3a:	4d 63 e4             	movsxd r12,r12d
    3d:	4d 63 e4             	movsxd r12,r12d
    40:	4d 63 e4             	movsxd r12,r12d
    43:	4d 63 e4             	movsxd r12,r12d
    46:	4d 63 e4             	movsxd r12,r12d
    49:	4d 63 e4             	movsxd r12,r12d
    4c:	4d 63 e4             	movsxd r12,r12d
    4f:	4d 63 e4             	movsxd r12,r12d
    52:	4d 31 e5             	xor    r13,r12
    55:	4d 31 e5             	xor    r13,r12
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 28.0
  • Core cycles: 59.15
  • Reference cycles: 29.12
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 2 (with additional nop)

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instructions: MOV R12D, [R14+R13];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR R13, R12; XOR R13, R12;nop
• Chain latency: ≥26
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	47 8b 24 2e          	mov    r12d,DWORD PTR [r14+r13*1]
     a:	4d 63 e4             	movsxd r12,r12d
     d:	4d 63 e4             	movsxd r12,r12d
    10:	4d 63 e4             	movsxd r12,r12d
    13:	4d 63 e4             	movsxd r12,r12d
    16:	4d 63 e4             	movsxd r12,r12d
    19:	4d 63 e4             	movsxd r12,r12d
    1c:	4d 63 e4             	movsxd r12,r12d
    1f:	4d 63 e4             	movsxd r12,r12d
    22:	4d 63 e4             	movsxd r12,r12d
    25:	4d 63 e4             	movsxd r12,r12d
    28:	4d 63 e4             	movsxd r12,r12d
    2b:	4d 63 e4             	movsxd r12,r12d
    2e:	4d 63 e4             	movsxd r12,r12d
    31:	4d 63 e4             	movsxd r12,r12d
    34:	4d 63 e4             	movsxd r12,r12d
    37:	4d 63 e4             	movsxd r12,r12d
    3a:	4d 63 e4             	movsxd r12,r12d
    3d:	4d 63 e4             	movsxd r12,r12d
    40:	4d 63 e4             	movsxd r12,r12d
    43:	4d 63 e4             	movsxd r12,r12d
    46:	4d 63 e4             	movsxd r12,r12d
    49:	4d 63 e4             	movsxd r12,r12d
    4c:	4d 63 e4             	movsxd r12,r12d
    4f:	4d 63 e4             	movsxd r12,r12d
    52:	4d 31 e5             	xor    r13,r12
    55:	4d 31 e5             	xor    r13,r12
    58:	90                   	nop
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 29.0
  • Core cycles: 60.12
  • Reference cycles: 30.85
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 3 (with clean upper 32 bits)

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instructions: MOV R12D, [R14+R13];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR R13, R12; XOR R13, R12
• Chain latency: ≥26
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	47 8b 24 2e          	mov    r12d,DWORD PTR [r14+r13*1]
     a:	4d 63 e4             	movsxd r12,r12d
     d:	4d 63 e4             	movsxd r12,r12d
    10:	4d 63 e4             	movsxd r12,r12d
    13:	4d 63 e4             	movsxd r12,r12d
    16:	4d 63 e4             	movsxd r12,r12d
    19:	4d 63 e4             	movsxd r12,r12d
    1c:	4d 63 e4             	movsxd r12,r12d
    1f:	4d 63 e4             	movsxd r12,r12d
    22:	4d 63 e4             	movsxd r12,r12d
    25:	4d 63 e4             	movsxd r12,r12d
    28:	4d 63 e4             	movsxd r12,r12d
    2b:	4d 63 e4             	movsxd r12,r12d
    2e:	4d 63 e4             	movsxd r12,r12d
    31:	4d 63 e4             	movsxd r12,r12d
    34:	4d 63 e4             	movsxd r12,r12d
    37:	4d 63 e4             	movsxd r12,r12d
    3a:	4d 63 e4             	movsxd r12,r12d
    3d:	4d 63 e4             	movsxd r12,r12d
    40:	4d 63 e4             	movsxd r12,r12d
    43:	4d 63 e4             	movsxd r12,r12d
    46:	4d 63 e4             	movsxd r12,r12d
    49:	4d 63 e4             	movsxd r12,r12d
    4c:	4d 63 e4             	movsxd r12,r12d
    4f:	4d 63 e4             	movsxd r12,r12d
    52:	4d 31 e5             	xor    r13,r12
    55:	4d 31 e5             	xor    r13,r12
  

• Init:

  XOR R13, R13;
  MOV R8D, R8D;

• Show nanoBench command
• Results:
  • Instructions retired: 28.0
  • Core cycles: 59.15
  • Reference cycles: 29.12
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 4 (with additional nop, with clean upper 32 bits)

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instructions: MOV R12D, [R14+R13];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR R13, R12; XOR R13, R12;nop
• Chain latency: ≥26
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	47 8b 24 2e          	mov    r12d,DWORD PTR [r14+r13*1]
     a:	4d 63 e4             	movsxd r12,r12d
     d:	4d 63 e4             	movsxd r12,r12d
    10:	4d 63 e4             	movsxd r12,r12d
    13:	4d 63 e4             	movsxd r12,r12d
    16:	4d 63 e4             	movsxd r12,r12d
    19:	4d 63 e4             	movsxd r12,r12d
    1c:	4d 63 e4             	movsxd r12,r12d
    1f:	4d 63 e4             	movsxd r12,r12d
    22:	4d 63 e4             	movsxd r12,r12d
    25:	4d 63 e4             	movsxd r12,r12d
    28:	4d 63 e4             	movsxd r12,r12d
    2b:	4d 63 e4             	movsxd r12,r12d
    2e:	4d 63 e4             	movsxd r12,r12d
    31:	4d 63 e4             	movsxd r12,r12d
    34:	4d 63 e4             	movsxd r12,r12d
    37:	4d 63 e4             	movsxd r12,r12d
    3a:	4d 63 e4             	movsxd r12,r12d
    3d:	4d 63 e4             	movsxd r12,r12d
    40:	4d 63 e4             	movsxd r12,r12d
    43:	4d 63 e4             	movsxd r12,r12d
    46:	4d 63 e4             	movsxd r12,r12d
    49:	4d 63 e4             	movsxd r12,r12d
    4c:	4d 63 e4             	movsxd r12,r12d
    4f:	4d 63 e4             	movsxd r12,r12d
    52:	4d 31 e5             	xor    r13,r12
    55:	4d 31 e5             	xor    r13,r12
    58:	90                   	nop
  

• Init:

  XOR R13, R13;
  MOV R8D, R8D;

• Show nanoBench command
• Results:
  • Instructions retired: 29.0
  • Core cycles: 60.12
  • Reference cycles: 29.64
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 1 (with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 21.02
  • Reference cycles: 10.4
  • UOPS_EXECUTED.THREAD: 8.0

Experiment 2 (with R8D=0, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instruction: MOV EAX, 0
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	b8 00 00 00 00       	mov    eax,0x0
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.07
  • Reference cycles: 10.23
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 3 (with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 21.02
  • Reference cycles: 10.23
  • UOPS_EXECUTED.THREAD: 8.0

Experiment 4 (with R8D=1, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instruction: MOV EAX, 0
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	b8 00 00 00 00       	mov    eax,0x0
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.04
  • Reference cycles: 10.92
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 5 (with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 21.02
  • Reference cycles: 10.4
  • UOPS_EXECUTED.THREAD: 8.0

Experiment 6 (with R8D=2, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instruction: MOV EAX, 0
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	b8 00 00 00 00       	mov    eax,0x0
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.04
  • Reference cycles: 11.27
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 7 (with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOV R12D, [R14];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOV [R14], R12D
• Chain latency: 10
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 8b 26             	mov    r12d,DWORD PTR [r14]
     8:	4d 63 e4             	movsxd r12,r12d
     b:	4d 63 e4             	movsxd r12,r12d
     e:	4d 63 e4             	movsxd r12,r12d
    11:	4d 63 e4             	movsxd r12,r12d
    14:	4d 63 e4             	movsxd r12,r12d
    17:	4d 63 e4             	movsxd r12,r12d
    1a:	4d 63 e4             	movsxd r12,r12d
    1d:	4d 63 e4             	movsxd r12,r12d
    20:	4d 63 e4             	movsxd r12,r12d
    23:	4d 63 e4             	movsxd r12,r12d
    26:	45 89 26             	mov    DWORD PTR [r14],r12d
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 13.0
  • Core cycles: 50.13
  • Reference cycles: 24.96
  • UOPS_EXECUTED.THREAD: 21.0

Experiment 8 (with R8D=0, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOV R12D, [R14];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOV [R14], R12D;MOV EAX, 0
• Chain latency: 10
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 8b 26             	mov    r12d,DWORD PTR [r14]
     8:	4d 63 e4             	movsxd r12,r12d
     b:	4d 63 e4             	movsxd r12,r12d
     e:	4d 63 e4             	movsxd r12,r12d
    11:	4d 63 e4             	movsxd r12,r12d
    14:	4d 63 e4             	movsxd r12,r12d
    17:	4d 63 e4             	movsxd r12,r12d
    1a:	4d 63 e4             	movsxd r12,r12d
    1d:	4d 63 e4             	movsxd r12,r12d
    20:	4d 63 e4             	movsxd r12,r12d
    23:	4d 63 e4             	movsxd r12,r12d
    26:	45 89 26             	mov    DWORD PTR [r14],r12d
    29:	b8 00 00 00 00       	mov    eax,0x0
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 14.0
  • Core cycles: 50.1
  • Reference cycles: 24.61
  • UOPS_EXECUTED.THREAD: 22.0

Experiment 9 (with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOV R12D, [R14];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOV [R14], R12D
• Chain latency: 10
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 8b 26             	mov    r12d,DWORD PTR [r14]
     8:	4d 63 e4             	movsxd r12,r12d
     b:	4d 63 e4             	movsxd r12,r12d
     e:	4d 63 e4             	movsxd r12,r12d
    11:	4d 63 e4             	movsxd r12,r12d
    14:	4d 63 e4             	movsxd r12,r12d
    17:	4d 63 e4             	movsxd r12,r12d
    1a:	4d 63 e4             	movsxd r12,r12d
    1d:	4d 63 e4             	movsxd r12,r12d
    20:	4d 63 e4             	movsxd r12,r12d
    23:	4d 63 e4             	movsxd r12,r12d
    26:	45 89 26             	mov    DWORD PTR [r14],r12d
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 13.0
  • Core cycles: 50.12
  • Reference cycles: 24.96
  • UOPS_EXECUTED.THREAD: 21.0

Experiment 10 (with R8D=1, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOV R12D, [R14];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOV [R14], R12D;MOV EAX, 0
• Chain latency: 10
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 8b 26             	mov    r12d,DWORD PTR [r14]
     8:	4d 63 e4             	movsxd r12,r12d
     b:	4d 63 e4             	movsxd r12,r12d
     e:	4d 63 e4             	movsxd r12,r12d
    11:	4d 63 e4             	movsxd r12,r12d
    14:	4d 63 e4             	movsxd r12,r12d
    17:	4d 63 e4             	movsxd r12,r12d
    1a:	4d 63 e4             	movsxd r12,r12d
    1d:	4d 63 e4             	movsxd r12,r12d
    20:	4d 63 e4             	movsxd r12,r12d
    23:	4d 63 e4             	movsxd r12,r12d
    26:	45 89 26             	mov    DWORD PTR [r14],r12d
    29:	b8 00 00 00 00       	mov    eax,0x0
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 14.0
  • Core cycles: 50.1
  • Reference cycles: 24.96
  • UOPS_EXECUTED.THREAD: 22.0

Experiment 11 (with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOV R12D, [R14];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOV [R14], R12D
• Chain latency: 10
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 8b 26             	mov    r12d,DWORD PTR [r14]
     8:	4d 63 e4             	movsxd r12,r12d
     b:	4d 63 e4             	movsxd r12,r12d
     e:	4d 63 e4             	movsxd r12,r12d
    11:	4d 63 e4             	movsxd r12,r12d
    14:	4d 63 e4             	movsxd r12,r12d
    17:	4d 63 e4             	movsxd r12,r12d
    1a:	4d 63 e4             	movsxd r12,r12d
    1d:	4d 63 e4             	movsxd r12,r12d
    20:	4d 63 e4             	movsxd r12,r12d
    23:	4d 63 e4             	movsxd r12,r12d
    26:	45 89 26             	mov    DWORD PTR [r14],r12d
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 13.0
  • Core cycles: 50.12
  • Reference cycles: 24.79
  • UOPS_EXECUTED.THREAD: 21.0

Experiment 12 (with R8D=2, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOV R12D, [R14];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOV [R14], R12D;MOV EAX, 0
• Chain latency: 10
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 8b 26             	mov    r12d,DWORD PTR [r14]
     8:	4d 63 e4             	movsxd r12,r12d
     b:	4d 63 e4             	movsxd r12,r12d
     e:	4d 63 e4             	movsxd r12,r12d
    11:	4d 63 e4             	movsxd r12,r12d
    14:	4d 63 e4             	movsxd r12,r12d
    17:	4d 63 e4             	movsxd r12,r12d
    1a:	4d 63 e4             	movsxd r12,r12d
    1d:	4d 63 e4             	movsxd r12,r12d
    20:	4d 63 e4             	movsxd r12,r12d
    23:	4d 63 e4             	movsxd r12,r12d
    26:	45 89 26             	mov    DWORD PTR [r14],r12d
    29:	b8 00 00 00 00       	mov    eax,0x0
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 14.0
  • Core cycles: 50.1
  • Reference cycles: 24.96
  • UOPS_EXECUTED.THREAD: 22.0

Experiment 1 (with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOVSX RAX, EAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX
• Chain latency: 25
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	48 63 c0             	movsxd rax,eax
     8:	49 31 c6             	xor    r14,rax
     b:	49 31 c6             	xor    r14,rax
     e:	49 31 c6             	xor    r14,rax
    11:	49 31 c6             	xor    r14,rax
    14:	49 31 c6             	xor    r14,rax
    17:	49 31 c6             	xor    r14,rax
    1a:	49 31 c6             	xor    r14,rax
    1d:	49 31 c6             	xor    r14,rax
    20:	49 31 c6             	xor    r14,rax
    23:	49 31 c6             	xor    r14,rax
    26:	49 31 c6             	xor    r14,rax
    29:	49 31 c6             	xor    r14,rax
    2c:	49 31 c6             	xor    r14,rax
    2f:	49 31 c6             	xor    r14,rax
    32:	49 31 c6             	xor    r14,rax
    35:	49 31 c6             	xor    r14,rax
    38:	49 31 c6             	xor    r14,rax
    3b:	49 31 c6             	xor    r14,rax
    3e:	49 31 c6             	xor    r14,rax
    41:	49 31 c6             	xor    r14,rax
    44:	49 31 c6             	xor    r14,rax
    47:	49 31 c6             	xor    r14,rax
    4a:	49 31 c6             	xor    r14,rax
    4d:	49 31 c6             	xor    r14,rax
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 26.0
  • Core cycles: 39.99
  • Reference cycles: 19.76
  • UOPS_EXECUTED.THREAD: 33.0

Experiment 2 (with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOVSX RAX, EAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX
• Chain latency: 25
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	48 63 c0             	movsxd rax,eax
     8:	49 31 c6             	xor    r14,rax
     b:	49 31 c6             	xor    r14,rax
     e:	49 31 c6             	xor    r14,rax
    11:	49 31 c6             	xor    r14,rax
    14:	49 31 c6             	xor    r14,rax
    17:	49 31 c6             	xor    r14,rax
    1a:	49 31 c6             	xor    r14,rax
    1d:	49 31 c6             	xor    r14,rax
    20:	49 31 c6             	xor    r14,rax
    23:	49 31 c6             	xor    r14,rax
    26:	49 31 c6             	xor    r14,rax
    29:	49 31 c6             	xor    r14,rax
    2c:	49 31 c6             	xor    r14,rax
    2f:	49 31 c6             	xor    r14,rax
    32:	49 31 c6             	xor    r14,rax
    35:	49 31 c6             	xor    r14,rax
    38:	49 31 c6             	xor    r14,rax
    3b:	49 31 c6             	xor    r14,rax
    3e:	49 31 c6             	xor    r14,rax
    41:	49 31 c6             	xor    r14,rax
    44:	49 31 c6             	xor    r14,rax
    47:	49 31 c6             	xor    r14,rax
    4a:	49 31 c6             	xor    r14,rax
    4d:	49 31 c6             	xor    r14,rax
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 26.0
  • Core cycles: 39.99
  • Reference cycles: 19.76
  • UOPS_EXECUTED.THREAD: 33.0

Experiment 3 (with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOVSX RAX, EAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX
• Chain latency: 25
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	48 63 c0             	movsxd rax,eax
     8:	49 31 c6             	xor    r14,rax
     b:	49 31 c6             	xor    r14,rax
     e:	49 31 c6             	xor    r14,rax
    11:	49 31 c6             	xor    r14,rax
    14:	49 31 c6             	xor    r14,rax
    17:	49 31 c6             	xor    r14,rax
    1a:	49 31 c6             	xor    r14,rax
    1d:	49 31 c6             	xor    r14,rax
    20:	49 31 c6             	xor    r14,rax
    23:	49 31 c6             	xor    r14,rax
    26:	49 31 c6             	xor    r14,rax
    29:	49 31 c6             	xor    r14,rax
    2c:	49 31 c6             	xor    r14,rax
    2f:	49 31 c6             	xor    r14,rax
    32:	49 31 c6             	xor    r14,rax
    35:	49 31 c6             	xor    r14,rax
    38:	49 31 c6             	xor    r14,rax
    3b:	49 31 c6             	xor    r14,rax
    3e:	49 31 c6             	xor    r14,rax
    41:	49 31 c6             	xor    r14,rax
    44:	49 31 c6             	xor    r14,rax
    47:	49 31 c6             	xor    r14,rax
    4a:	49 31 c6             	xor    r14,rax
    4d:	49 31 c6             	xor    r14,rax
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 26.0
  • Core cycles: 39.99
  • Reference cycles: 19.76
  • UOPS_EXECUTED.THREAD: 33.0

Experiment 1

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instructions: MOVSX RAX, EAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX
• Chain latency: 25
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	48 63 c0             	movsxd rax,eax
     9:	49 31 c5             	xor    r13,rax
     c:	49 31 c5             	xor    r13,rax
     f:	49 31 c5             	xor    r13,rax
    12:	49 31 c5             	xor    r13,rax
    15:	49 31 c5             	xor    r13,rax
    18:	49 31 c5             	xor    r13,rax
    1b:	49 31 c5             	xor    r13,rax
    1e:	49 31 c5             	xor    r13,rax
    21:	49 31 c5             	xor    r13,rax
    24:	49 31 c5             	xor    r13,rax
    27:	49 31 c5             	xor    r13,rax
    2a:	49 31 c5             	xor    r13,rax
    2d:	49 31 c5             	xor    r13,rax
    30:	49 31 c5             	xor    r13,rax
    33:	49 31 c5             	xor    r13,rax
    36:	49 31 c5             	xor    r13,rax
    39:	49 31 c5             	xor    r13,rax
    3c:	49 31 c5             	xor    r13,rax
    3f:	49 31 c5             	xor    r13,rax
    42:	49 31 c5             	xor    r13,rax
    45:	49 31 c5             	xor    r13,rax
    48:	49 31 c5             	xor    r13,rax
    4b:	49 31 c5             	xor    r13,rax
    4e:	49 31 c5             	xor    r13,rax
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 26.0
  • Core cycles: 40.0
  • Reference cycles: 19.76
  • UOPS_EXECUTED.THREAD: 33.0

Experiment 2 (with clean upper 32 bits)

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instructions: MOVSX RAX, EAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX
• Chain latency: 25
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	48 63 c0             	movsxd rax,eax
     9:	49 31 c5             	xor    r13,rax
     c:	49 31 c5             	xor    r13,rax
     f:	49 31 c5             	xor    r13,rax
    12:	49 31 c5             	xor    r13,rax
    15:	49 31 c5             	xor    r13,rax
    18:	49 31 c5             	xor    r13,rax
    1b:	49 31 c5             	xor    r13,rax
    1e:	49 31 c5             	xor    r13,rax
    21:	49 31 c5             	xor    r13,rax
    24:	49 31 c5             	xor    r13,rax
    27:	49 31 c5             	xor    r13,rax
    2a:	49 31 c5             	xor    r13,rax
    2d:	49 31 c5             	xor    r13,rax
    30:	49 31 c5             	xor    r13,rax
    33:	49 31 c5             	xor    r13,rax
    36:	49 31 c5             	xor    r13,rax
    39:	49 31 c5             	xor    r13,rax
    3c:	49 31 c5             	xor    r13,rax
    3f:	49 31 c5             	xor    r13,rax
    42:	49 31 c5             	xor    r13,rax
    45:	49 31 c5             	xor    r13,rax
    48:	49 31 c5             	xor    r13,rax
    4b:	49 31 c5             	xor    r13,rax
    4e:	49 31 c5             	xor    r13,rax
  

• Init:

  XOR R13, R13;
  MOV R8D, R8D;

• Show nanoBench command
• Results:
  • Instructions retired: 26.0
  • Core cycles: 39.99
  • Reference cycles: 19.76
  • UOPS_EXECUTED.THREAD: 33.0

Experiment 1 (with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOVSX R12, EAX;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12D
• Chain latency: ≥24
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4c 63 e0             	movsxd r12,eax
     8:	4d 63 e4             	movsxd r12,r12d
     b:	4d 63 e4             	movsxd r12,r12d
     e:	4d 63 e4             	movsxd r12,r12d
    11:	4d 63 e4             	movsxd r12,r12d
    14:	4d 63 e4             	movsxd r12,r12d
    17:	4d 63 e4             	movsxd r12,r12d
    1a:	4d 63 e4             	movsxd r12,r12d
    1d:	4d 63 e4             	movsxd r12,r12d
    20:	4d 63 e4             	movsxd r12,r12d
    23:	4d 63 e4             	movsxd r12,r12d
    26:	4d 63 e4             	movsxd r12,r12d
    29:	4d 63 e4             	movsxd r12,r12d
    2c:	4d 63 e4             	movsxd r12,r12d
    2f:	4d 63 e4             	movsxd r12,r12d
    32:	4d 63 e4             	movsxd r12,r12d
    35:	4d 63 e4             	movsxd r12,r12d
    38:	4d 63 e4             	movsxd r12,r12d
    3b:	4d 63 e4             	movsxd r12,r12d
    3e:	4d 63 e4             	movsxd r12,r12d
    41:	4d 63 e4             	movsxd r12,r12d
    44:	4d 63 e4             	movsxd r12,r12d
    47:	4d 63 e4             	movsxd r12,r12d
    4a:	4d 63 e4             	movsxd r12,r12d
    4d:	45 89 26             	mov    DWORD PTR [r14],r12d
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 26.0
  • Core cycles: 45.63
  • Reference cycles: 22.53
  • UOPS_EXECUTED.THREAD: 34.0

Experiment 2 (with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOVSX R12, EAX;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12D
• Chain latency: ≥24
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4c 63 e0             	movsxd r12,eax
     8:	4d 63 e4             	movsxd r12,r12d
     b:	4d 63 e4             	movsxd r12,r12d
     e:	4d 63 e4             	movsxd r12,r12d
    11:	4d 63 e4             	movsxd r12,r12d
    14:	4d 63 e4             	movsxd r12,r12d
    17:	4d 63 e4             	movsxd r12,r12d
    1a:	4d 63 e4             	movsxd r12,r12d
    1d:	4d 63 e4             	movsxd r12,r12d
    20:	4d 63 e4             	movsxd r12,r12d
    23:	4d 63 e4             	movsxd r12,r12d
    26:	4d 63 e4             	movsxd r12,r12d
    29:	4d 63 e4             	movsxd r12,r12d
    2c:	4d 63 e4             	movsxd r12,r12d
    2f:	4d 63 e4             	movsxd r12,r12d
    32:	4d 63 e4             	movsxd r12,r12d
    35:	4d 63 e4             	movsxd r12,r12d
    38:	4d 63 e4             	movsxd r12,r12d
    3b:	4d 63 e4             	movsxd r12,r12d
    3e:	4d 63 e4             	movsxd r12,r12d
    41:	4d 63 e4             	movsxd r12,r12d
    44:	4d 63 e4             	movsxd r12,r12d
    47:	4d 63 e4             	movsxd r12,r12d
    4a:	4d 63 e4             	movsxd r12,r12d
    4d:	45 89 26             	mov    DWORD PTR [r14],r12d
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 26.0
  • Core cycles: 45.62
  • Reference cycles: 23.57
  • UOPS_EXECUTED.THREAD: 34.0

Experiment 3 (with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOVSX R12, EAX;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12D
• Chain latency: ≥24
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4c 63 e0             	movsxd r12,eax
     8:	4d 63 e4             	movsxd r12,r12d
     b:	4d 63 e4             	movsxd r12,r12d
     e:	4d 63 e4             	movsxd r12,r12d
    11:	4d 63 e4             	movsxd r12,r12d
    14:	4d 63 e4             	movsxd r12,r12d
    17:	4d 63 e4             	movsxd r12,r12d
    1a:	4d 63 e4             	movsxd r12,r12d
    1d:	4d 63 e4             	movsxd r12,r12d
    20:	4d 63 e4             	movsxd r12,r12d
    23:	4d 63 e4             	movsxd r12,r12d
    26:	4d 63 e4             	movsxd r12,r12d
    29:	4d 63 e4             	movsxd r12,r12d
    2c:	4d 63 e4             	movsxd r12,r12d
    2f:	4d 63 e4             	movsxd r12,r12d
    32:	4d 63 e4             	movsxd r12,r12d
    35:	4d 63 e4             	movsxd r12,r12d
    38:	4d 63 e4             	movsxd r12,r12d
    3b:	4d 63 e4             	movsxd r12,r12d
    3e:	4d 63 e4             	movsxd r12,r12d
    41:	4d 63 e4             	movsxd r12,r12d
    44:	4d 63 e4             	movsxd r12,r12d
    47:	4d 63 e4             	movsxd r12,r12d
    4a:	4d 63 e4             	movsxd r12,r12d
    4d:	45 89 26             	mov    DWORD PTR [r14],r12d
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 26.0
  • Core cycles: 45.61
  • Reference cycles: 23.23
  • UOPS_EXECUTED.THREAD: 34.0

Experiment 1 (with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instruction: CMOVO R14, R14
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 40 f6          	cmovo  r14,r14
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.09
  • Reference cycles: 10.23
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 2 (with R8D=0, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVO R14, R14;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 40 f6          	cmovo  r14,r14
     9:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 23.27
  • Reference cycles: 11.27
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 3 (with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instruction: CMOVO R14, R14
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 40 f6          	cmovo  r14,r14
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.1
  • Reference cycles: 10.57
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 4 (with R8D=1, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVO R14, R14;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 40 f6          	cmovo  r14,r14
     9:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 23.28
  • Reference cycles: 11.44
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 5 (with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instruction: CMOVO R14, R14
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 40 f6          	cmovo  r14,r14
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.09
  • Reference cycles: 10.4
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 6 (with R8D=2, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVO R14, R14;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 40 f6          	cmovo  r14,r14
     9:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 23.27
  • Reference cycles: 11.44
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 7 (with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instruction: CMOVP R14, R14
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 4a f6          	cmovp  r14,r14
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.1
  • Reference cycles: 10.4
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 8 (with R8D=0, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVP R14, R14;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 4a f6          	cmovp  r14,r14
     9:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 23.27
  • Reference cycles: 12.48
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 9 (with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instruction: CMOVP R14, R14
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 4a f6          	cmovp  r14,r14
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.09
  • Reference cycles: 10.4
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 10 (with R8D=1, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVP R14, R14;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 4a f6          	cmovp  r14,r14
     9:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 23.27
  • Reference cycles: 11.44
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 11 (with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instruction: CMOVP R14, R14
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 4a f6          	cmovp  r14,r14
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.11
  • Reference cycles: 10.4
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 12 (with R8D=2, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVP R14, R14;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 4a f6          	cmovp  r14,r14
     9:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 23.03
  • Reference cycles: 11.61
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 13 (with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instruction: CMOVZ R14, R14
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 44 f6          	cmove  r14,r14
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.1
  • Reference cycles: 10.57
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 14 (with R8D=0, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVZ R14, R14;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 44 f6          	cmove  r14,r14
     9:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 23.04
  • Reference cycles: 11.27
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 15 (with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instruction: CMOVZ R14, R14
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 44 f6          	cmove  r14,r14
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.09
  • Reference cycles: 10.4
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 16 (with R8D=1, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVZ R14, R14;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 44 f6          	cmove  r14,r14
     9:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 22.95
  • Reference cycles: 11.44
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 17 (with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instruction: CMOVZ R14, R14
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 44 f6          	cmove  r14,r14
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.09
  • Reference cycles: 10.4
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 18 (with R8D=2, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVZ R14, R14;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 44 f6          	cmove  r14,r14
     9:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 23.27
  • Reference cycles: 12.31
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 19 (with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instruction: CMOVS R14, R14
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 48 f6          	cmovs  r14,r14
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.1
  • Reference cycles: 10.4
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 20 (with R8D=0, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVS R14, R14;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 48 f6          	cmovs  r14,r14
     9:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 23.28
  • Reference cycles: 11.27
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 21 (with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instruction: CMOVS R14, R14
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 48 f6          	cmovs  r14,r14
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.1
  • Reference cycles: 10.4
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 22 (with R8D=1, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVS R14, R14;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 48 f6          	cmovs  r14,r14
     9:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 23.27
  • Reference cycles: 11.27
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 23 (with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instruction: CMOVS R14, R14
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 48 f6          	cmovs  r14,r14
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.1
  • Reference cycles: 10.4
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 24 (with R8D=2, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVS R14, R14;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 48 f6          	cmovs  r14,r14
     9:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 22.94
  • Reference cycles: 11.44
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 25 (with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instruction: CMOVC R14, R14
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 42 f6          	cmovb  r14,r14
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.1
  • Reference cycles: 10.57
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 26 (with R8D=0, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVC R14, R14;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 42 f6          	cmovb  r14,r14
     9:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 23.26
  • Reference cycles: 11.44
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 27 (with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instruction: CMOVC R14, R14
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 42 f6          	cmovb  r14,r14
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.09
  • Reference cycles: 10.4
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 28 (with R8D=1, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVC R14, R14;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 42 f6          	cmovb  r14,r14
     9:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 23.03
  • Reference cycles: 11.44
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 29 (with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instruction: CMOVC R14, R14
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 42 f6          	cmovb  r14,r14
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.11
  • Reference cycles: 10.4
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 30 (with R8D=2, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVC R14, R14;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 42 f6          	cmovb  r14,r14
     9:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 23.03
  • Reference cycles: 11.44
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 1

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instruction: CMOVO R13, R13
• Chain latency: 1
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	4d 0f 40 ed          	cmovo  r13,r13
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.11
  • Reference cycles: 10.4
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 2 (with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instructions: CMOVO R13, R13;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	4d 0f 40 ed          	cmovo  r13,r13
     a:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 27.09
  • Reference cycles: 13.0
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 3

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instruction: CMOVP R13, R13
• Chain latency: 1
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	4d 0f 4a ed          	cmovp  r13,r13
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.09
  • Reference cycles: 11.27
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 4 (with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instructions: CMOVP R13, R13;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	4d 0f 4a ed          	cmovp  r13,r13
     a:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 27.1
  • Reference cycles: 13.87
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 5

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instruction: CMOVZ R13, R13
• Chain latency: 1
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	4d 0f 44 ed          	cmove  r13,r13
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.11
  • Reference cycles: 10.57
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 6 (with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instructions: CMOVZ R13, R13;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	4d 0f 44 ed          	cmove  r13,r13
     a:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 27.04
  • Reference cycles: 14.56
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 7

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instruction: CMOVS R13, R13
• Chain latency: 1
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	4d 0f 48 ed          	cmovs  r13,r13
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.09
  • Reference cycles: 10.4
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 8 (with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instructions: CMOVS R13, R13;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	4d 0f 48 ed          	cmovs  r13,r13
     a:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 27.1
  • Reference cycles: 13.17
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 9

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instruction: CMOVC R13, R13
• Chain latency: 1
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	4d 0f 42 ed          	cmovb  r13,r13
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.11
  • Reference cycles: 10.4
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 10 (with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instructions: CMOVC R13, R13;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	4d 0f 42 ed          	cmovb  r13,r13
     a:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 27.05
  • Reference cycles: 14.56
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 11 (with clean upper 32 bits)

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instruction: CMOVO R13, R13
• Chain latency: 1
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	4d 0f 40 ed          	cmovo  r13,r13
  

• Init:

  XOR R13, R13;
  MOV R8D, R8D;

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.11
  • Reference cycles: 10.57
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 12 (with clean upper 32 bits, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instructions: CMOVO R13, R13;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	4d 0f 40 ed          	cmovo  r13,r13
     a:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  XOR R13, R13;
  MOV R8D, R8D;

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 27.1
  • Reference cycles: 13.35
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 13 (with clean upper 32 bits)

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instruction: CMOVP R13, R13
• Chain latency: 1
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	4d 0f 4a ed          	cmovp  r13,r13
  

• Init:

  XOR R13, R13;
  MOV R8D, R8D;

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.1
  • Reference cycles: 10.4
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 14 (with clean upper 32 bits, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instructions: CMOVP R13, R13;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	4d 0f 4a ed          	cmovp  r13,r13
     a:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  XOR R13, R13;
  MOV R8D, R8D;

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 27.09
  • Reference cycles: 14.04
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 15 (with clean upper 32 bits)

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instruction: CMOVZ R13, R13
• Chain latency: 1
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	4d 0f 44 ed          	cmove  r13,r13
  

• Init:

  XOR R13, R13;
  MOV R8D, R8D;

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.1
  • Reference cycles: 10.4
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 16 (with clean upper 32 bits, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instructions: CMOVZ R13, R13;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	4d 0f 44 ed          	cmove  r13,r13
     a:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  XOR R13, R13;
  MOV R8D, R8D;

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 27.09
  • Reference cycles: 13.69
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 17 (with clean upper 32 bits)

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instruction: CMOVS R13, R13
• Chain latency: 1
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	4d 0f 48 ed          	cmovs  r13,r13
  

• Init:

  XOR R13, R13;
  MOV R8D, R8D;

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.11
  • Reference cycles: 10.57
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 18 (with clean upper 32 bits, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instructions: CMOVS R13, R13;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	4d 0f 48 ed          	cmovs  r13,r13
     a:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  XOR R13, R13;
  MOV R8D, R8D;

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 27.1
  • Reference cycles: 14.56
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 19 (with clean upper 32 bits)

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instruction: CMOVC R13, R13
• Chain latency: 1
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	4d 0f 42 ed          	cmovb  r13,r13
  

• Init:

  XOR R13, R13;
  MOV R8D, R8D;

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 21.09
  • Reference cycles: 10.57
  • UOPS_EXECUTED.THREAD: 9.0

Experiment 20 (with clean upper 32 bits, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14+R13], R8D
• Chain instructions: CMOVC R13, R13;MOV dword ptr [R14], 0
• Chain latency: 1
• Code:

     0:	f0 47 0f b1 04 2e    	lock cmpxchg DWORD PTR [r14+r13*1],r8d
     6:	4d 0f 42 ed          	cmovb  r13,r13
     a:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  XOR R13, R13;
  MOV R8D, R8D;

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 27.1
  • Reference cycles: 13.0
  • UOPS_EXECUTED.THREAD: 11.0

Experiment 1 (with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVO R12, R12;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12D
• Chain latency: ≥25
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 40 e4          	cmovo  r12,r12
     9:	4d 63 e4             	movsxd r12,r12d
     c:	4d 63 e4             	movsxd r12,r12d
     f:	4d 63 e4             	movsxd r12,r12d
    12:	4d 63 e4             	movsxd r12,r12d
    15:	4d 63 e4             	movsxd r12,r12d
    18:	4d 63 e4             	movsxd r12,r12d
    1b:	4d 63 e4             	movsxd r12,r12d
    1e:	4d 63 e4             	movsxd r12,r12d
    21:	4d 63 e4             	movsxd r12,r12d
    24:	4d 63 e4             	movsxd r12,r12d
    27:	4d 63 e4             	movsxd r12,r12d
    2a:	4d 63 e4             	movsxd r12,r12d
    2d:	4d 63 e4             	movsxd r12,r12d
    30:	4d 63 e4             	movsxd r12,r12d
    33:	4d 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	45 89 26             	mov    DWORD PTR [r14],r12d
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 45.97
  • Reference cycles: 22.88
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 2 (with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVO R12, R12;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12D
• Chain latency: ≥25
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 40 e4          	cmovo  r12,r12
     9:	4d 63 e4             	movsxd r12,r12d
     c:	4d 63 e4             	movsxd r12,r12d
     f:	4d 63 e4             	movsxd r12,r12d
    12:	4d 63 e4             	movsxd r12,r12d
    15:	4d 63 e4             	movsxd r12,r12d
    18:	4d 63 e4             	movsxd r12,r12d
    1b:	4d 63 e4             	movsxd r12,r12d
    1e:	4d 63 e4             	movsxd r12,r12d
    21:	4d 63 e4             	movsxd r12,r12d
    24:	4d 63 e4             	movsxd r12,r12d
    27:	4d 63 e4             	movsxd r12,r12d
    2a:	4d 63 e4             	movsxd r12,r12d
    2d:	4d 63 e4             	movsxd r12,r12d
    30:	4d 63 e4             	movsxd r12,r12d
    33:	4d 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	45 89 26             	mov    DWORD PTR [r14],r12d
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 46.01
  • Reference cycles: 22.88
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 3 (with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVO R12, R12;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12D
• Chain latency: ≥25
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 40 e4          	cmovo  r12,r12
     9:	4d 63 e4             	movsxd r12,r12d
     c:	4d 63 e4             	movsxd r12,r12d
     f:	4d 63 e4             	movsxd r12,r12d
    12:	4d 63 e4             	movsxd r12,r12d
    15:	4d 63 e4             	movsxd r12,r12d
    18:	4d 63 e4             	movsxd r12,r12d
    1b:	4d 63 e4             	movsxd r12,r12d
    1e:	4d 63 e4             	movsxd r12,r12d
    21:	4d 63 e4             	movsxd r12,r12d
    24:	4d 63 e4             	movsxd r12,r12d
    27:	4d 63 e4             	movsxd r12,r12d
    2a:	4d 63 e4             	movsxd r12,r12d
    2d:	4d 63 e4             	movsxd r12,r12d
    30:	4d 63 e4             	movsxd r12,r12d
    33:	4d 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	45 89 26             	mov    DWORD PTR [r14],r12d
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 45.97
  • Reference cycles: 22.88
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 4 (with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVP R12, R12;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12D
• Chain latency: ≥25
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 4a e4          	cmovp  r12,r12
     9:	4d 63 e4             	movsxd r12,r12d
     c:	4d 63 e4             	movsxd r12,r12d
     f:	4d 63 e4             	movsxd r12,r12d
    12:	4d 63 e4             	movsxd r12,r12d
    15:	4d 63 e4             	movsxd r12,r12d
    18:	4d 63 e4             	movsxd r12,r12d
    1b:	4d 63 e4             	movsxd r12,r12d
    1e:	4d 63 e4             	movsxd r12,r12d
    21:	4d 63 e4             	movsxd r12,r12d
    24:	4d 63 e4             	movsxd r12,r12d
    27:	4d 63 e4             	movsxd r12,r12d
    2a:	4d 63 e4             	movsxd r12,r12d
    2d:	4d 63 e4             	movsxd r12,r12d
    30:	4d 63 e4             	movsxd r12,r12d
    33:	4d 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	45 89 26             	mov    DWORD PTR [r14],r12d
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 45.99
  • Reference cycles: 23.57
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 5 (with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVP R12, R12;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12D
• Chain latency: ≥25
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 4a e4          	cmovp  r12,r12
     9:	4d 63 e4             	movsxd r12,r12d
     c:	4d 63 e4             	movsxd r12,r12d
     f:	4d 63 e4             	movsxd r12,r12d
    12:	4d 63 e4             	movsxd r12,r12d
    15:	4d 63 e4             	movsxd r12,r12d
    18:	4d 63 e4             	movsxd r12,r12d
    1b:	4d 63 e4             	movsxd r12,r12d
    1e:	4d 63 e4             	movsxd r12,r12d
    21:	4d 63 e4             	movsxd r12,r12d
    24:	4d 63 e4             	movsxd r12,r12d
    27:	4d 63 e4             	movsxd r12,r12d
    2a:	4d 63 e4             	movsxd r12,r12d
    2d:	4d 63 e4             	movsxd r12,r12d
    30:	4d 63 e4             	movsxd r12,r12d
    33:	4d 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	45 89 26             	mov    DWORD PTR [r14],r12d
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 45.97
  • Reference cycles: 22.71
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 6 (with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVP R12, R12;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12D
• Chain latency: ≥25
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 4a e4          	cmovp  r12,r12
     9:	4d 63 e4             	movsxd r12,r12d
     c:	4d 63 e4             	movsxd r12,r12d
     f:	4d 63 e4             	movsxd r12,r12d
    12:	4d 63 e4             	movsxd r12,r12d
    15:	4d 63 e4             	movsxd r12,r12d
    18:	4d 63 e4             	movsxd r12,r12d
    1b:	4d 63 e4             	movsxd r12,r12d
    1e:	4d 63 e4             	movsxd r12,r12d
    21:	4d 63 e4             	movsxd r12,r12d
    24:	4d 63 e4             	movsxd r12,r12d
    27:	4d 63 e4             	movsxd r12,r12d
    2a:	4d 63 e4             	movsxd r12,r12d
    2d:	4d 63 e4             	movsxd r12,r12d
    30:	4d 63 e4             	movsxd r12,r12d
    33:	4d 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	45 89 26             	mov    DWORD PTR [r14],r12d
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 45.97
  • Reference cycles: 23.23
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 7 (with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVZ R12, R12;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12D
• Chain latency: ≥25
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 44 e4          	cmove  r12,r12
     9:	4d 63 e4             	movsxd r12,r12d
     c:	4d 63 e4             	movsxd r12,r12d
     f:	4d 63 e4             	movsxd r12,r12d
    12:	4d 63 e4             	movsxd r12,r12d
    15:	4d 63 e4             	movsxd r12,r12d
    18:	4d 63 e4             	movsxd r12,r12d
    1b:	4d 63 e4             	movsxd r12,r12d
    1e:	4d 63 e4             	movsxd r12,r12d
    21:	4d 63 e4             	movsxd r12,r12d
    24:	4d 63 e4             	movsxd r12,r12d
    27:	4d 63 e4             	movsxd r12,r12d
    2a:	4d 63 e4             	movsxd r12,r12d
    2d:	4d 63 e4             	movsxd r12,r12d
    30:	4d 63 e4             	movsxd r12,r12d
    33:	4d 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	45 89 26             	mov    DWORD PTR [r14],r12d
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 45.98
  • Reference cycles: 23.57
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 8 (with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVZ R12, R12;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12D
• Chain latency: ≥25
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 44 e4          	cmove  r12,r12
     9:	4d 63 e4             	movsxd r12,r12d
     c:	4d 63 e4             	movsxd r12,r12d
     f:	4d 63 e4             	movsxd r12,r12d
    12:	4d 63 e4             	movsxd r12,r12d
    15:	4d 63 e4             	movsxd r12,r12d
    18:	4d 63 e4             	movsxd r12,r12d
    1b:	4d 63 e4             	movsxd r12,r12d
    1e:	4d 63 e4             	movsxd r12,r12d
    21:	4d 63 e4             	movsxd r12,r12d
    24:	4d 63 e4             	movsxd r12,r12d
    27:	4d 63 e4             	movsxd r12,r12d
    2a:	4d 63 e4             	movsxd r12,r12d
    2d:	4d 63 e4             	movsxd r12,r12d
    30:	4d 63 e4             	movsxd r12,r12d
    33:	4d 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	45 89 26             	mov    DWORD PTR [r14],r12d
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 45.97
  • Reference cycles: 23.23
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 9 (with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVZ R12, R12;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12D
• Chain latency: ≥25
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 44 e4          	cmove  r12,r12
     9:	4d 63 e4             	movsxd r12,r12d
     c:	4d 63 e4             	movsxd r12,r12d
     f:	4d 63 e4             	movsxd r12,r12d
    12:	4d 63 e4             	movsxd r12,r12d
    15:	4d 63 e4             	movsxd r12,r12d
    18:	4d 63 e4             	movsxd r12,r12d
    1b:	4d 63 e4             	movsxd r12,r12d
    1e:	4d 63 e4             	movsxd r12,r12d
    21:	4d 63 e4             	movsxd r12,r12d
    24:	4d 63 e4             	movsxd r12,r12d
    27:	4d 63 e4             	movsxd r12,r12d
    2a:	4d 63 e4             	movsxd r12,r12d
    2d:	4d 63 e4             	movsxd r12,r12d
    30:	4d 63 e4             	movsxd r12,r12d
    33:	4d 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	45 89 26             	mov    DWORD PTR [r14],r12d
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 45.97
  • Reference cycles: 23.4
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 10 (with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVS R12, R12;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12D
• Chain latency: ≥25
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 48 e4          	cmovs  r12,r12
     9:	4d 63 e4             	movsxd r12,r12d
     c:	4d 63 e4             	movsxd r12,r12d
     f:	4d 63 e4             	movsxd r12,r12d
    12:	4d 63 e4             	movsxd r12,r12d
    15:	4d 63 e4             	movsxd r12,r12d
    18:	4d 63 e4             	movsxd r12,r12d
    1b:	4d 63 e4             	movsxd r12,r12d
    1e:	4d 63 e4             	movsxd r12,r12d
    21:	4d 63 e4             	movsxd r12,r12d
    24:	4d 63 e4             	movsxd r12,r12d
    27:	4d 63 e4             	movsxd r12,r12d
    2a:	4d 63 e4             	movsxd r12,r12d
    2d:	4d 63 e4             	movsxd r12,r12d
    30:	4d 63 e4             	movsxd r12,r12d
    33:	4d 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	45 89 26             	mov    DWORD PTR [r14],r12d
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 45.97
  • Reference cycles: 23.4
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 11 (with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVS R12, R12;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12D
• Chain latency: ≥25
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 48 e4          	cmovs  r12,r12
     9:	4d 63 e4             	movsxd r12,r12d
     c:	4d 63 e4             	movsxd r12,r12d
     f:	4d 63 e4             	movsxd r12,r12d
    12:	4d 63 e4             	movsxd r12,r12d
    15:	4d 63 e4             	movsxd r12,r12d
    18:	4d 63 e4             	movsxd r12,r12d
    1b:	4d 63 e4             	movsxd r12,r12d
    1e:	4d 63 e4             	movsxd r12,r12d
    21:	4d 63 e4             	movsxd r12,r12d
    24:	4d 63 e4             	movsxd r12,r12d
    27:	4d 63 e4             	movsxd r12,r12d
    2a:	4d 63 e4             	movsxd r12,r12d
    2d:	4d 63 e4             	movsxd r12,r12d
    30:	4d 63 e4             	movsxd r12,r12d
    33:	4d 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	45 89 26             	mov    DWORD PTR [r14],r12d
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 45.97
  • Reference cycles: 23.4
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 12 (with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVS R12, R12;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12D
• Chain latency: ≥25
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 48 e4          	cmovs  r12,r12
     9:	4d 63 e4             	movsxd r12,r12d
     c:	4d 63 e4             	movsxd r12,r12d
     f:	4d 63 e4             	movsxd r12,r12d
    12:	4d 63 e4             	movsxd r12,r12d
    15:	4d 63 e4             	movsxd r12,r12d
    18:	4d 63 e4             	movsxd r12,r12d
    1b:	4d 63 e4             	movsxd r12,r12d
    1e:	4d 63 e4             	movsxd r12,r12d
    21:	4d 63 e4             	movsxd r12,r12d
    24:	4d 63 e4             	movsxd r12,r12d
    27:	4d 63 e4             	movsxd r12,r12d
    2a:	4d 63 e4             	movsxd r12,r12d
    2d:	4d 63 e4             	movsxd r12,r12d
    30:	4d 63 e4             	movsxd r12,r12d
    33:	4d 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	45 89 26             	mov    DWORD PTR [r14],r12d
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 45.98
  • Reference cycles: 22.71
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 13 (with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVC R12, R12;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12D
• Chain latency: ≥25
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 42 e4          	cmovb  r12,r12
     9:	4d 63 e4             	movsxd r12,r12d
     c:	4d 63 e4             	movsxd r12,r12d
     f:	4d 63 e4             	movsxd r12,r12d
    12:	4d 63 e4             	movsxd r12,r12d
    15:	4d 63 e4             	movsxd r12,r12d
    18:	4d 63 e4             	movsxd r12,r12d
    1b:	4d 63 e4             	movsxd r12,r12d
    1e:	4d 63 e4             	movsxd r12,r12d
    21:	4d 63 e4             	movsxd r12,r12d
    24:	4d 63 e4             	movsxd r12,r12d
    27:	4d 63 e4             	movsxd r12,r12d
    2a:	4d 63 e4             	movsxd r12,r12d
    2d:	4d 63 e4             	movsxd r12,r12d
    30:	4d 63 e4             	movsxd r12,r12d
    33:	4d 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	45 89 26             	mov    DWORD PTR [r14],r12d
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 46.07
  • Reference cycles: 23.23
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 14 (with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVC R12, R12;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12D
• Chain latency: ≥25
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 42 e4          	cmovb  r12,r12
     9:	4d 63 e4             	movsxd r12,r12d
     c:	4d 63 e4             	movsxd r12,r12d
     f:	4d 63 e4             	movsxd r12,r12d
    12:	4d 63 e4             	movsxd r12,r12d
    15:	4d 63 e4             	movsxd r12,r12d
    18:	4d 63 e4             	movsxd r12,r12d
    1b:	4d 63 e4             	movsxd r12,r12d
    1e:	4d 63 e4             	movsxd r12,r12d
    21:	4d 63 e4             	movsxd r12,r12d
    24:	4d 63 e4             	movsxd r12,r12d
    27:	4d 63 e4             	movsxd r12,r12d
    2a:	4d 63 e4             	movsxd r12,r12d
    2d:	4d 63 e4             	movsxd r12,r12d
    30:	4d 63 e4             	movsxd r12,r12d
    33:	4d 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	45 89 26             	mov    DWORD PTR [r14],r12d
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 45.97
  • Reference cycles: 23.05
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 15 (with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVC R12, R12;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12D
• Chain latency: ≥25
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4d 0f 42 e4          	cmovb  r12,r12
     9:	4d 63 e4             	movsxd r12,r12d
     c:	4d 63 e4             	movsxd r12,r12d
     f:	4d 63 e4             	movsxd r12,r12d
    12:	4d 63 e4             	movsxd r12,r12d
    15:	4d 63 e4             	movsxd r12,r12d
    18:	4d 63 e4             	movsxd r12,r12d
    1b:	4d 63 e4             	movsxd r12,r12d
    1e:	4d 63 e4             	movsxd r12,r12d
    21:	4d 63 e4             	movsxd r12,r12d
    24:	4d 63 e4             	movsxd r12,r12d
    27:	4d 63 e4             	movsxd r12,r12d
    2a:	4d 63 e4             	movsxd r12,r12d
    2d:	4d 63 e4             	movsxd r12,r12d
    30:	4d 63 e4             	movsxd r12,r12d
    33:	4d 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	45 89 26             	mov    DWORD PTR [r14],r12d
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 45.97
  • Reference cycles: 23.23
  • UOPS_EXECUTED.THREAD: 35.0

Experiment 1

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOV R8D, [R14];MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
• Chain latency: ≥24
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 8b 06             	mov    r8d,DWORD PTR [r14]
     8:	4d 63 c0             	movsxd r8,r8d
     b:	4d 63 c0             	movsxd r8,r8d
     e:	4d 63 c0             	movsxd r8,r8d
    11:	4d 63 c0             	movsxd r8,r8d
    14:	4d 63 c0             	movsxd r8,r8d
    17:	4d 63 c0             	movsxd r8,r8d
    1a:	4d 63 c0             	movsxd r8,r8d
    1d:	4d 63 c0             	movsxd r8,r8d
    20:	4d 63 c0             	movsxd r8,r8d
    23:	4d 63 c0             	movsxd r8,r8d
    26:	4d 63 c0             	movsxd r8,r8d
    29:	4d 63 c0             	movsxd r8,r8d
    2c:	4d 63 c0             	movsxd r8,r8d
    2f:	4d 63 c0             	movsxd r8,r8d
    32:	4d 63 c0             	movsxd r8,r8d
    35:	4d 63 c0             	movsxd r8,r8d
    38:	4d 63 c0             	movsxd r8,r8d
    3b:	4d 63 c0             	movsxd r8,r8d
    3e:	4d 63 c0             	movsxd r8,r8d
    41:	4d 63 c0             	movsxd r8,r8d
    44:	4d 63 c0             	movsxd r8,r8d
    47:	4d 63 c0             	movsxd r8,r8d
    4a:	4d 63 c0             	movsxd r8,r8d
    4d:	4d 63 c0             	movsxd r8,r8d
  

• Show nanoBench command
• Results:
  • Instructions retired: 26.0
  • Core cycles: 57.0
  • Reference cycles: 28.08
  • UOPS_EXECUTED.THREAD: 33.0

Experiment 1

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOVSX R8, EAX;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
• Chain latency: 25
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	4c 63 c0             	movsxd r8,eax
     8:	4d 63 c0             	movsxd r8,r8d
     b:	4d 63 c0             	movsxd r8,r8d
     e:	4d 63 c0             	movsxd r8,r8d
    11:	4d 63 c0             	movsxd r8,r8d
    14:	4d 63 c0             	movsxd r8,r8d
    17:	4d 63 c0             	movsxd r8,r8d
    1a:	4d 63 c0             	movsxd r8,r8d
    1d:	4d 63 c0             	movsxd r8,r8d
    20:	4d 63 c0             	movsxd r8,r8d
    23:	4d 63 c0             	movsxd r8,r8d
    26:	4d 63 c0             	movsxd r8,r8d
    29:	4d 63 c0             	movsxd r8,r8d
    2c:	4d 63 c0             	movsxd r8,r8d
    2f:	4d 63 c0             	movsxd r8,r8d
    32:	4d 63 c0             	movsxd r8,r8d
    35:	4d 63 c0             	movsxd r8,r8d
    38:	4d 63 c0             	movsxd r8,r8d
    3b:	4d 63 c0             	movsxd r8,r8d
    3e:	4d 63 c0             	movsxd r8,r8d
    41:	4d 63 c0             	movsxd r8,r8d
    44:	4d 63 c0             	movsxd r8,r8d
    47:	4d 63 c0             	movsxd r8,r8d
    4a:	4d 63 c0             	movsxd r8,r8d
    4d:	4d 63 c0             	movsxd r8,r8d
  

• Show nanoBench command
• Results:
  • Instructions retired: 26.0
  • Core cycles: 39.99
  • Reference cycles: 19.76
  • UOPS_EXECUTED.THREAD: 33.0

Experiment 1

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVO R15D, R15D;MOVSX R8, R15D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
• Chain latency: 26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 0f 40 ff          	cmovo  r15d,r15d
     9:	4d 63 c7             	movsxd r8,r15d
     c:	4d 63 c0             	movsxd r8,r8d
     f:	4d 63 c0             	movsxd r8,r8d
    12:	4d 63 c0             	movsxd r8,r8d
    15:	4d 63 c0             	movsxd r8,r8d
    18:	4d 63 c0             	movsxd r8,r8d
    1b:	4d 63 c0             	movsxd r8,r8d
    1e:	4d 63 c0             	movsxd r8,r8d
    21:	4d 63 c0             	movsxd r8,r8d
    24:	4d 63 c0             	movsxd r8,r8d
    27:	4d 63 c0             	movsxd r8,r8d
    2a:	4d 63 c0             	movsxd r8,r8d
    2d:	4d 63 c0             	movsxd r8,r8d
    30:	4d 63 c0             	movsxd r8,r8d
    33:	4d 63 c0             	movsxd r8,r8d
    36:	4d 63 c0             	movsxd r8,r8d
    39:	4d 63 c0             	movsxd r8,r8d
    3c:	4d 63 c0             	movsxd r8,r8d
    3f:	4d 63 c0             	movsxd r8,r8d
    42:	4d 63 c0             	movsxd r8,r8d
    45:	4d 63 c0             	movsxd r8,r8d
    48:	4d 63 c0             	movsxd r8,r8d
    4b:	4d 63 c0             	movsxd r8,r8d
    4e:	4d 63 c0             	movsxd r8,r8d
    51:	4d 63 c0             	movsxd r8,r8d
  

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 39.71
  • Reference cycles: 19.93
  • UOPS_EXECUTED.THREAD: 34.0

Experiment 2

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVP R15D, R15D;MOVSX R8, R15D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
• Chain latency: 26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 0f 4a ff          	cmovp  r15d,r15d
     9:	4d 63 c7             	movsxd r8,r15d
     c:	4d 63 c0             	movsxd r8,r8d
     f:	4d 63 c0             	movsxd r8,r8d
    12:	4d 63 c0             	movsxd r8,r8d
    15:	4d 63 c0             	movsxd r8,r8d
    18:	4d 63 c0             	movsxd r8,r8d
    1b:	4d 63 c0             	movsxd r8,r8d
    1e:	4d 63 c0             	movsxd r8,r8d
    21:	4d 63 c0             	movsxd r8,r8d
    24:	4d 63 c0             	movsxd r8,r8d
    27:	4d 63 c0             	movsxd r8,r8d
    2a:	4d 63 c0             	movsxd r8,r8d
    2d:	4d 63 c0             	movsxd r8,r8d
    30:	4d 63 c0             	movsxd r8,r8d
    33:	4d 63 c0             	movsxd r8,r8d
    36:	4d 63 c0             	movsxd r8,r8d
    39:	4d 63 c0             	movsxd r8,r8d
    3c:	4d 63 c0             	movsxd r8,r8d
    3f:	4d 63 c0             	movsxd r8,r8d
    42:	4d 63 c0             	movsxd r8,r8d
    45:	4d 63 c0             	movsxd r8,r8d
    48:	4d 63 c0             	movsxd r8,r8d
    4b:	4d 63 c0             	movsxd r8,r8d
    4e:	4d 63 c0             	movsxd r8,r8d
    51:	4d 63 c0             	movsxd r8,r8d
  

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 39.77
  • Reference cycles: 19.76
  • UOPS_EXECUTED.THREAD: 34.0

Experiment 3

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVZ R15D, R15D;MOVSX R8, R15D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
• Chain latency: 26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 0f 44 ff          	cmove  r15d,r15d
     9:	4d 63 c7             	movsxd r8,r15d
     c:	4d 63 c0             	movsxd r8,r8d
     f:	4d 63 c0             	movsxd r8,r8d
    12:	4d 63 c0             	movsxd r8,r8d
    15:	4d 63 c0             	movsxd r8,r8d
    18:	4d 63 c0             	movsxd r8,r8d
    1b:	4d 63 c0             	movsxd r8,r8d
    1e:	4d 63 c0             	movsxd r8,r8d
    21:	4d 63 c0             	movsxd r8,r8d
    24:	4d 63 c0             	movsxd r8,r8d
    27:	4d 63 c0             	movsxd r8,r8d
    2a:	4d 63 c0             	movsxd r8,r8d
    2d:	4d 63 c0             	movsxd r8,r8d
    30:	4d 63 c0             	movsxd r8,r8d
    33:	4d 63 c0             	movsxd r8,r8d
    36:	4d 63 c0             	movsxd r8,r8d
    39:	4d 63 c0             	movsxd r8,r8d
    3c:	4d 63 c0             	movsxd r8,r8d
    3f:	4d 63 c0             	movsxd r8,r8d
    42:	4d 63 c0             	movsxd r8,r8d
    45:	4d 63 c0             	movsxd r8,r8d
    48:	4d 63 c0             	movsxd r8,r8d
    4b:	4d 63 c0             	movsxd r8,r8d
    4e:	4d 63 c0             	movsxd r8,r8d
    51:	4d 63 c0             	movsxd r8,r8d
  

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 39.79
  • Reference cycles: 20.63
  • UOPS_EXECUTED.THREAD: 34.0

Experiment 4

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVS R15D, R15D;MOVSX R8, R15D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
• Chain latency: 26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 0f 48 ff          	cmovs  r15d,r15d
     9:	4d 63 c7             	movsxd r8,r15d
     c:	4d 63 c0             	movsxd r8,r8d
     f:	4d 63 c0             	movsxd r8,r8d
    12:	4d 63 c0             	movsxd r8,r8d
    15:	4d 63 c0             	movsxd r8,r8d
    18:	4d 63 c0             	movsxd r8,r8d
    1b:	4d 63 c0             	movsxd r8,r8d
    1e:	4d 63 c0             	movsxd r8,r8d
    21:	4d 63 c0             	movsxd r8,r8d
    24:	4d 63 c0             	movsxd r8,r8d
    27:	4d 63 c0             	movsxd r8,r8d
    2a:	4d 63 c0             	movsxd r8,r8d
    2d:	4d 63 c0             	movsxd r8,r8d
    30:	4d 63 c0             	movsxd r8,r8d
    33:	4d 63 c0             	movsxd r8,r8d
    36:	4d 63 c0             	movsxd r8,r8d
    39:	4d 63 c0             	movsxd r8,r8d
    3c:	4d 63 c0             	movsxd r8,r8d
    3f:	4d 63 c0             	movsxd r8,r8d
    42:	4d 63 c0             	movsxd r8,r8d
    45:	4d 63 c0             	movsxd r8,r8d
    48:	4d 63 c0             	movsxd r8,r8d
    4b:	4d 63 c0             	movsxd r8,r8d
    4e:	4d 63 c0             	movsxd r8,r8d
    51:	4d 63 c0             	movsxd r8,r8d
  

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 39.79
  • Reference cycles: 19.41
  • UOPS_EXECUTED.THREAD: 34.0

Experiment 5

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVC R15D, R15D;MOVSX R8, R15D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
• Chain latency: 26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 0f 42 ff          	cmovb  r15d,r15d
     9:	4d 63 c7             	movsxd r8,r15d
     c:	4d 63 c0             	movsxd r8,r8d
     f:	4d 63 c0             	movsxd r8,r8d
    12:	4d 63 c0             	movsxd r8,r8d
    15:	4d 63 c0             	movsxd r8,r8d
    18:	4d 63 c0             	movsxd r8,r8d
    1b:	4d 63 c0             	movsxd r8,r8d
    1e:	4d 63 c0             	movsxd r8,r8d
    21:	4d 63 c0             	movsxd r8,r8d
    24:	4d 63 c0             	movsxd r8,r8d
    27:	4d 63 c0             	movsxd r8,r8d
    2a:	4d 63 c0             	movsxd r8,r8d
    2d:	4d 63 c0             	movsxd r8,r8d
    30:	4d 63 c0             	movsxd r8,r8d
    33:	4d 63 c0             	movsxd r8,r8d
    36:	4d 63 c0             	movsxd r8,r8d
    39:	4d 63 c0             	movsxd r8,r8d
    3c:	4d 63 c0             	movsxd r8,r8d
    3f:	4d 63 c0             	movsxd r8,r8d
    42:	4d 63 c0             	movsxd r8,r8d
    45:	4d 63 c0             	movsxd r8,r8d
    48:	4d 63 c0             	movsxd r8,r8d
    4b:	4d 63 c0             	movsxd r8,r8d
    4e:	4d 63 c0             	movsxd r8,r8d
    51:	4d 63 c0             	movsxd r8,r8d
  

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 39.71
  • Reference cycles: 19.93
  • UOPS_EXECUTED.THREAD: 34.0

Experiment 1 (with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOV EAX, [R14];MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX
• Chain latency: ≥24
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	41 8b 06             	mov    eax,DWORD PTR [r14]
     8:	48 63 c0             	movsxd rax,eax
     b:	48 63 c0             	movsxd rax,eax
     e:	48 63 c0             	movsxd rax,eax
    11:	48 63 c0             	movsxd rax,eax
    14:	48 63 c0             	movsxd rax,eax
    17:	48 63 c0             	movsxd rax,eax
    1a:	48 63 c0             	movsxd rax,eax
    1d:	48 63 c0             	movsxd rax,eax
    20:	48 63 c0             	movsxd rax,eax
    23:	48 63 c0             	movsxd rax,eax
    26:	48 63 c0             	movsxd rax,eax
    29:	48 63 c0             	movsxd rax,eax
    2c:	48 63 c0             	movsxd rax,eax
    2f:	48 63 c0             	movsxd rax,eax
    32:	48 63 c0             	movsxd rax,eax
    35:	48 63 c0             	movsxd rax,eax
    38:	48 63 c0             	movsxd rax,eax
    3b:	48 63 c0             	movsxd rax,eax
    3e:	48 63 c0             	movsxd rax,eax
    41:	48 63 c0             	movsxd rax,eax
    44:	48 63 c0             	movsxd rax,eax
    47:	48 63 c0             	movsxd rax,eax
    4a:	48 63 c0             	movsxd rax,eax
    4d:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 26.0
  • Core cycles: 56.99
  • Reference cycles: 28.43
  • UOPS_EXECUTED.THREAD: 33.0

Experiment 2 (with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOV EAX, [R14];MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX
• Chain latency: ≥24
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	41 8b 06             	mov    eax,DWORD PTR [r14]
     8:	48 63 c0             	movsxd rax,eax
     b:	48 63 c0             	movsxd rax,eax
     e:	48 63 c0             	movsxd rax,eax
    11:	48 63 c0             	movsxd rax,eax
    14:	48 63 c0             	movsxd rax,eax
    17:	48 63 c0             	movsxd rax,eax
    1a:	48 63 c0             	movsxd rax,eax
    1d:	48 63 c0             	movsxd rax,eax
    20:	48 63 c0             	movsxd rax,eax
    23:	48 63 c0             	movsxd rax,eax
    26:	48 63 c0             	movsxd rax,eax
    29:	48 63 c0             	movsxd rax,eax
    2c:	48 63 c0             	movsxd rax,eax
    2f:	48 63 c0             	movsxd rax,eax
    32:	48 63 c0             	movsxd rax,eax
    35:	48 63 c0             	movsxd rax,eax
    38:	48 63 c0             	movsxd rax,eax
    3b:	48 63 c0             	movsxd rax,eax
    3e:	48 63 c0             	movsxd rax,eax
    41:	48 63 c0             	movsxd rax,eax
    44:	48 63 c0             	movsxd rax,eax
    47:	48 63 c0             	movsxd rax,eax
    4a:	48 63 c0             	movsxd rax,eax
    4d:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 26.0
  • Core cycles: 56.99
  • Reference cycles: 28.43
  • UOPS_EXECUTED.THREAD: 33.0

Experiment 3 (with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOV EAX, [R14];MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX
• Chain latency: ≥24
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	41 8b 06             	mov    eax,DWORD PTR [r14]
     8:	48 63 c0             	movsxd rax,eax
     b:	48 63 c0             	movsxd rax,eax
     e:	48 63 c0             	movsxd rax,eax
    11:	48 63 c0             	movsxd rax,eax
    14:	48 63 c0             	movsxd rax,eax
    17:	48 63 c0             	movsxd rax,eax
    1a:	48 63 c0             	movsxd rax,eax
    1d:	48 63 c0             	movsxd rax,eax
    20:	48 63 c0             	movsxd rax,eax
    23:	48 63 c0             	movsxd rax,eax
    26:	48 63 c0             	movsxd rax,eax
    29:	48 63 c0             	movsxd rax,eax
    2c:	48 63 c0             	movsxd rax,eax
    2f:	48 63 c0             	movsxd rax,eax
    32:	48 63 c0             	movsxd rax,eax
    35:	48 63 c0             	movsxd rax,eax
    38:	48 63 c0             	movsxd rax,eax
    3b:	48 63 c0             	movsxd rax,eax
    3e:	48 63 c0             	movsxd rax,eax
    41:	48 63 c0             	movsxd rax,eax
    44:	48 63 c0             	movsxd rax,eax
    47:	48 63 c0             	movsxd rax,eax
    4a:	48 63 c0             	movsxd rax,eax
    4d:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 26.0
  • Core cycles: 56.99
  • Reference cycles: 28.6
  • UOPS_EXECUTED.THREAD: 33.0

Experiment 1 (with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX
• Chain latency: 25
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	48 63 c0             	movsxd rax,eax
     8:	48 63 c0             	movsxd rax,eax
     b:	48 63 c0             	movsxd rax,eax
     e:	48 63 c0             	movsxd rax,eax
    11:	48 63 c0             	movsxd rax,eax
    14:	48 63 c0             	movsxd rax,eax
    17:	48 63 c0             	movsxd rax,eax
    1a:	48 63 c0             	movsxd rax,eax
    1d:	48 63 c0             	movsxd rax,eax
    20:	48 63 c0             	movsxd rax,eax
    23:	48 63 c0             	movsxd rax,eax
    26:	48 63 c0             	movsxd rax,eax
    29:	48 63 c0             	movsxd rax,eax
    2c:	48 63 c0             	movsxd rax,eax
    2f:	48 63 c0             	movsxd rax,eax
    32:	48 63 c0             	movsxd rax,eax
    35:	48 63 c0             	movsxd rax,eax
    38:	48 63 c0             	movsxd rax,eax
    3b:	48 63 c0             	movsxd rax,eax
    3e:	48 63 c0             	movsxd rax,eax
    41:	48 63 c0             	movsxd rax,eax
    44:	48 63 c0             	movsxd rax,eax
    47:	48 63 c0             	movsxd rax,eax
    4a:	48 63 c0             	movsxd rax,eax
    4d:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 26.0
  • Core cycles: 39.99
  • Reference cycles: 19.76
  • UOPS_EXECUTED.THREAD: 33.0

Experiment 2 (with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX
• Chain latency: 25
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	48 63 c0             	movsxd rax,eax
     8:	48 63 c0             	movsxd rax,eax
     b:	48 63 c0             	movsxd rax,eax
     e:	48 63 c0             	movsxd rax,eax
    11:	48 63 c0             	movsxd rax,eax
    14:	48 63 c0             	movsxd rax,eax
    17:	48 63 c0             	movsxd rax,eax
    1a:	48 63 c0             	movsxd rax,eax
    1d:	48 63 c0             	movsxd rax,eax
    20:	48 63 c0             	movsxd rax,eax
    23:	48 63 c0             	movsxd rax,eax
    26:	48 63 c0             	movsxd rax,eax
    29:	48 63 c0             	movsxd rax,eax
    2c:	48 63 c0             	movsxd rax,eax
    2f:	48 63 c0             	movsxd rax,eax
    32:	48 63 c0             	movsxd rax,eax
    35:	48 63 c0             	movsxd rax,eax
    38:	48 63 c0             	movsxd rax,eax
    3b:	48 63 c0             	movsxd rax,eax
    3e:	48 63 c0             	movsxd rax,eax
    41:	48 63 c0             	movsxd rax,eax
    44:	48 63 c0             	movsxd rax,eax
    47:	48 63 c0             	movsxd rax,eax
    4a:	48 63 c0             	movsxd rax,eax
    4d:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 26.0
  • Core cycles: 40.0
  • Reference cycles: 19.76
  • UOPS_EXECUTED.THREAD: 33.0

Experiment 3 (with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX
• Chain latency: 25
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	48 63 c0             	movsxd rax,eax
     8:	48 63 c0             	movsxd rax,eax
     b:	48 63 c0             	movsxd rax,eax
     e:	48 63 c0             	movsxd rax,eax
    11:	48 63 c0             	movsxd rax,eax
    14:	48 63 c0             	movsxd rax,eax
    17:	48 63 c0             	movsxd rax,eax
    1a:	48 63 c0             	movsxd rax,eax
    1d:	48 63 c0             	movsxd rax,eax
    20:	48 63 c0             	movsxd rax,eax
    23:	48 63 c0             	movsxd rax,eax
    26:	48 63 c0             	movsxd rax,eax
    29:	48 63 c0             	movsxd rax,eax
    2c:	48 63 c0             	movsxd rax,eax
    2f:	48 63 c0             	movsxd rax,eax
    32:	48 63 c0             	movsxd rax,eax
    35:	48 63 c0             	movsxd rax,eax
    38:	48 63 c0             	movsxd rax,eax
    3b:	48 63 c0             	movsxd rax,eax
    3e:	48 63 c0             	movsxd rax,eax
    41:	48 63 c0             	movsxd rax,eax
    44:	48 63 c0             	movsxd rax,eax
    47:	48 63 c0             	movsxd rax,eax
    4a:	48 63 c0             	movsxd rax,eax
    4d:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 26.0
  • Core cycles: 39.99
  • Reference cycles: 19.76
  • UOPS_EXECUTED.THREAD: 33.0

Experiment 4 (with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 21.0
  • Reference cycles: 10.57
  • UOPS_EXECUTED.THREAD: 8.0

Experiment 5 (with R8D=0, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instruction: MOV dword ptr [R14], 0
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 27.08
  • Reference cycles: 14.04
  • UOPS_EXECUTED.THREAD: 10.0

Experiment 6 (with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 21.0
  • Reference cycles: 10.57
  • UOPS_EXECUTED.THREAD: 8.0

Experiment 7 (with R8D=1, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instruction: MOV dword ptr [R14], 0
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 27.07
  • Reference cycles: 12.65
  • UOPS_EXECUTED.THREAD: 10.0

Experiment 8 (with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 21.0
  • Reference cycles: 10.57
  • UOPS_EXECUTED.THREAD: 8.0

Experiment 9 (with R8D=2, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instruction: MOV dword ptr [R14], 0
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	41 c7 06 00 00 00 00 	mov    DWORD PTR [r14],0x0
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 27.06
  • Reference cycles: 13.52
  • UOPS_EXECUTED.THREAD: 10.0

Experiment 1 (with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVO R15D, R15D;MOVSX RAX, R15D;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX
• Chain latency: 26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 0f 40 ff          	cmovo  r15d,r15d
     9:	49 63 c7             	movsxd rax,r15d
     c:	48 63 c0             	movsxd rax,eax
     f:	48 63 c0             	movsxd rax,eax
    12:	48 63 c0             	movsxd rax,eax
    15:	48 63 c0             	movsxd rax,eax
    18:	48 63 c0             	movsxd rax,eax
    1b:	48 63 c0             	movsxd rax,eax
    1e:	48 63 c0             	movsxd rax,eax
    21:	48 63 c0             	movsxd rax,eax
    24:	48 63 c0             	movsxd rax,eax
    27:	48 63 c0             	movsxd rax,eax
    2a:	48 63 c0             	movsxd rax,eax
    2d:	48 63 c0             	movsxd rax,eax
    30:	48 63 c0             	movsxd rax,eax
    33:	48 63 c0             	movsxd rax,eax
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 39.79
  • Reference cycles: 19.76
  • UOPS_EXECUTED.THREAD: 34.0

Experiment 2 (with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVO R15D, R15D;MOVSX RAX, R15D;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX
• Chain latency: 26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 0f 40 ff          	cmovo  r15d,r15d
     9:	49 63 c7             	movsxd rax,r15d
     c:	48 63 c0             	movsxd rax,eax
     f:	48 63 c0             	movsxd rax,eax
    12:	48 63 c0             	movsxd rax,eax
    15:	48 63 c0             	movsxd rax,eax
    18:	48 63 c0             	movsxd rax,eax
    1b:	48 63 c0             	movsxd rax,eax
    1e:	48 63 c0             	movsxd rax,eax
    21:	48 63 c0             	movsxd rax,eax
    24:	48 63 c0             	movsxd rax,eax
    27:	48 63 c0             	movsxd rax,eax
    2a:	48 63 c0             	movsxd rax,eax
    2d:	48 63 c0             	movsxd rax,eax
    30:	48 63 c0             	movsxd rax,eax
    33:	48 63 c0             	movsxd rax,eax
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 39.75
  • Reference cycles: 19.76
  • UOPS_EXECUTED.THREAD: 34.0

Experiment 3 (with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVO R15D, R15D;MOVSX RAX, R15D;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX
• Chain latency: 26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 0f 40 ff          	cmovo  r15d,r15d
     9:	49 63 c7             	movsxd rax,r15d
     c:	48 63 c0             	movsxd rax,eax
     f:	48 63 c0             	movsxd rax,eax
    12:	48 63 c0             	movsxd rax,eax
    15:	48 63 c0             	movsxd rax,eax
    18:	48 63 c0             	movsxd rax,eax
    1b:	48 63 c0             	movsxd rax,eax
    1e:	48 63 c0             	movsxd rax,eax
    21:	48 63 c0             	movsxd rax,eax
    24:	48 63 c0             	movsxd rax,eax
    27:	48 63 c0             	movsxd rax,eax
    2a:	48 63 c0             	movsxd rax,eax
    2d:	48 63 c0             	movsxd rax,eax
    30:	48 63 c0             	movsxd rax,eax
    33:	48 63 c0             	movsxd rax,eax
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 39.77
  • Reference cycles: 19.76
  • UOPS_EXECUTED.THREAD: 34.0

Experiment 4 (with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVP R15D, R15D;MOVSX RAX, R15D;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX
• Chain latency: 26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 0f 4a ff          	cmovp  r15d,r15d
     9:	49 63 c7             	movsxd rax,r15d
     c:	48 63 c0             	movsxd rax,eax
     f:	48 63 c0             	movsxd rax,eax
    12:	48 63 c0             	movsxd rax,eax
    15:	48 63 c0             	movsxd rax,eax
    18:	48 63 c0             	movsxd rax,eax
    1b:	48 63 c0             	movsxd rax,eax
    1e:	48 63 c0             	movsxd rax,eax
    21:	48 63 c0             	movsxd rax,eax
    24:	48 63 c0             	movsxd rax,eax
    27:	48 63 c0             	movsxd rax,eax
    2a:	48 63 c0             	movsxd rax,eax
    2d:	48 63 c0             	movsxd rax,eax
    30:	48 63 c0             	movsxd rax,eax
    33:	48 63 c0             	movsxd rax,eax
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 39.79
  • Reference cycles: 19.76
  • UOPS_EXECUTED.THREAD: 34.0

Experiment 5 (with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVP R15D, R15D;MOVSX RAX, R15D;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX
• Chain latency: 26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 0f 4a ff          	cmovp  r15d,r15d
     9:	49 63 c7             	movsxd rax,r15d
     c:	48 63 c0             	movsxd rax,eax
     f:	48 63 c0             	movsxd rax,eax
    12:	48 63 c0             	movsxd rax,eax
    15:	48 63 c0             	movsxd rax,eax
    18:	48 63 c0             	movsxd rax,eax
    1b:	48 63 c0             	movsxd rax,eax
    1e:	48 63 c0             	movsxd rax,eax
    21:	48 63 c0             	movsxd rax,eax
    24:	48 63 c0             	movsxd rax,eax
    27:	48 63 c0             	movsxd rax,eax
    2a:	48 63 c0             	movsxd rax,eax
    2d:	48 63 c0             	movsxd rax,eax
    30:	48 63 c0             	movsxd rax,eax
    33:	48 63 c0             	movsxd rax,eax
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 39.77
  • Reference cycles: 19.76
  • UOPS_EXECUTED.THREAD: 34.0

Experiment 6 (with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVP R15D, R15D;MOVSX RAX, R15D;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX
• Chain latency: 26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 0f 4a ff          	cmovp  r15d,r15d
     9:	49 63 c7             	movsxd rax,r15d
     c:	48 63 c0             	movsxd rax,eax
     f:	48 63 c0             	movsxd rax,eax
    12:	48 63 c0             	movsxd rax,eax
    15:	48 63 c0             	movsxd rax,eax
    18:	48 63 c0             	movsxd rax,eax
    1b:	48 63 c0             	movsxd rax,eax
    1e:	48 63 c0             	movsxd rax,eax
    21:	48 63 c0             	movsxd rax,eax
    24:	48 63 c0             	movsxd rax,eax
    27:	48 63 c0             	movsxd rax,eax
    2a:	48 63 c0             	movsxd rax,eax
    2d:	48 63 c0             	movsxd rax,eax
    30:	48 63 c0             	movsxd rax,eax
    33:	48 63 c0             	movsxd rax,eax
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 39.75
  • Reference cycles: 19.93
  • UOPS_EXECUTED.THREAD: 34.0

Experiment 7 (with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVZ R15D, R15D;MOVSX RAX, R15D;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX
• Chain latency: 26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 0f 44 ff          	cmove  r15d,r15d
     9:	49 63 c7             	movsxd rax,r15d
     c:	48 63 c0             	movsxd rax,eax
     f:	48 63 c0             	movsxd rax,eax
    12:	48 63 c0             	movsxd rax,eax
    15:	48 63 c0             	movsxd rax,eax
    18:	48 63 c0             	movsxd rax,eax
    1b:	48 63 c0             	movsxd rax,eax
    1e:	48 63 c0             	movsxd rax,eax
    21:	48 63 c0             	movsxd rax,eax
    24:	48 63 c0             	movsxd rax,eax
    27:	48 63 c0             	movsxd rax,eax
    2a:	48 63 c0             	movsxd rax,eax
    2d:	48 63 c0             	movsxd rax,eax
    30:	48 63 c0             	movsxd rax,eax
    33:	48 63 c0             	movsxd rax,eax
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 39.75
  • Reference cycles: 19.93
  • UOPS_EXECUTED.THREAD: 34.0

Experiment 8 (with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVZ R15D, R15D;MOVSX RAX, R15D;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX
• Chain latency: 26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 0f 44 ff          	cmove  r15d,r15d
     9:	49 63 c7             	movsxd rax,r15d
     c:	48 63 c0             	movsxd rax,eax
     f:	48 63 c0             	movsxd rax,eax
    12:	48 63 c0             	movsxd rax,eax
    15:	48 63 c0             	movsxd rax,eax
    18:	48 63 c0             	movsxd rax,eax
    1b:	48 63 c0             	movsxd rax,eax
    1e:	48 63 c0             	movsxd rax,eax
    21:	48 63 c0             	movsxd rax,eax
    24:	48 63 c0             	movsxd rax,eax
    27:	48 63 c0             	movsxd rax,eax
    2a:	48 63 c0             	movsxd rax,eax
    2d:	48 63 c0             	movsxd rax,eax
    30:	48 63 c0             	movsxd rax,eax
    33:	48 63 c0             	movsxd rax,eax
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 39.75
  • Reference cycles: 19.76
  • UOPS_EXECUTED.THREAD: 34.0

Experiment 9 (with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVZ R15D, R15D;MOVSX RAX, R15D;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX
• Chain latency: 26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 0f 44 ff          	cmove  r15d,r15d
     9:	49 63 c7             	movsxd rax,r15d
     c:	48 63 c0             	movsxd rax,eax
     f:	48 63 c0             	movsxd rax,eax
    12:	48 63 c0             	movsxd rax,eax
    15:	48 63 c0             	movsxd rax,eax
    18:	48 63 c0             	movsxd rax,eax
    1b:	48 63 c0             	movsxd rax,eax
    1e:	48 63 c0             	movsxd rax,eax
    21:	48 63 c0             	movsxd rax,eax
    24:	48 63 c0             	movsxd rax,eax
    27:	48 63 c0             	movsxd rax,eax
    2a:	48 63 c0             	movsxd rax,eax
    2d:	48 63 c0             	movsxd rax,eax
    30:	48 63 c0             	movsxd rax,eax
    33:	48 63 c0             	movsxd rax,eax
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 39.75
  • Reference cycles: 19.93
  • UOPS_EXECUTED.THREAD: 34.0

Experiment 10 (with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVS R15D, R15D;MOVSX RAX, R15D;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX
• Chain latency: 26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 0f 48 ff          	cmovs  r15d,r15d
     9:	49 63 c7             	movsxd rax,r15d
     c:	48 63 c0             	movsxd rax,eax
     f:	48 63 c0             	movsxd rax,eax
    12:	48 63 c0             	movsxd rax,eax
    15:	48 63 c0             	movsxd rax,eax
    18:	48 63 c0             	movsxd rax,eax
    1b:	48 63 c0             	movsxd rax,eax
    1e:	48 63 c0             	movsxd rax,eax
    21:	48 63 c0             	movsxd rax,eax
    24:	48 63 c0             	movsxd rax,eax
    27:	48 63 c0             	movsxd rax,eax
    2a:	48 63 c0             	movsxd rax,eax
    2d:	48 63 c0             	movsxd rax,eax
    30:	48 63 c0             	movsxd rax,eax
    33:	48 63 c0             	movsxd rax,eax
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 39.79
  • Reference cycles: 19.59
  • UOPS_EXECUTED.THREAD: 34.0

Experiment 11 (with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVS R15D, R15D;MOVSX RAX, R15D;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX
• Chain latency: 26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 0f 48 ff          	cmovs  r15d,r15d
     9:	49 63 c7             	movsxd rax,r15d
     c:	48 63 c0             	movsxd rax,eax
     f:	48 63 c0             	movsxd rax,eax
    12:	48 63 c0             	movsxd rax,eax
    15:	48 63 c0             	movsxd rax,eax
    18:	48 63 c0             	movsxd rax,eax
    1b:	48 63 c0             	movsxd rax,eax
    1e:	48 63 c0             	movsxd rax,eax
    21:	48 63 c0             	movsxd rax,eax
    24:	48 63 c0             	movsxd rax,eax
    27:	48 63 c0             	movsxd rax,eax
    2a:	48 63 c0             	movsxd rax,eax
    2d:	48 63 c0             	movsxd rax,eax
    30:	48 63 c0             	movsxd rax,eax
    33:	48 63 c0             	movsxd rax,eax
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 39.78
  • Reference cycles: 19.41
  • UOPS_EXECUTED.THREAD: 34.0

Experiment 12 (with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVS R15D, R15D;MOVSX RAX, R15D;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX
• Chain latency: 26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 0f 48 ff          	cmovs  r15d,r15d
     9:	49 63 c7             	movsxd rax,r15d
     c:	48 63 c0             	movsxd rax,eax
     f:	48 63 c0             	movsxd rax,eax
    12:	48 63 c0             	movsxd rax,eax
    15:	48 63 c0             	movsxd rax,eax
    18:	48 63 c0             	movsxd rax,eax
    1b:	48 63 c0             	movsxd rax,eax
    1e:	48 63 c0             	movsxd rax,eax
    21:	48 63 c0             	movsxd rax,eax
    24:	48 63 c0             	movsxd rax,eax
    27:	48 63 c0             	movsxd rax,eax
    2a:	48 63 c0             	movsxd rax,eax
    2d:	48 63 c0             	movsxd rax,eax
    30:	48 63 c0             	movsxd rax,eax
    33:	48 63 c0             	movsxd rax,eax
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 39.77
  • Reference cycles: 19.93
  • UOPS_EXECUTED.THREAD: 34.0

Experiment 13 (with R8D=0)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVC R15D, R15D;MOVSX RAX, R15D;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX
• Chain latency: 26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 0f 42 ff          	cmovb  r15d,r15d
     9:	49 63 c7             	movsxd rax,r15d
     c:	48 63 c0             	movsxd rax,eax
     f:	48 63 c0             	movsxd rax,eax
    12:	48 63 c0             	movsxd rax,eax
    15:	48 63 c0             	movsxd rax,eax
    18:	48 63 c0             	movsxd rax,eax
    1b:	48 63 c0             	movsxd rax,eax
    1e:	48 63 c0             	movsxd rax,eax
    21:	48 63 c0             	movsxd rax,eax
    24:	48 63 c0             	movsxd rax,eax
    27:	48 63 c0             	movsxd rax,eax
    2a:	48 63 c0             	movsxd rax,eax
    2d:	48 63 c0             	movsxd rax,eax
    30:	48 63 c0             	movsxd rax,eax
    33:	48 63 c0             	movsxd rax,eax
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8D, 0

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 39.71
  • Reference cycles: 19.76
  • UOPS_EXECUTED.THREAD: 34.0

Experiment 14 (with R8D=1)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVC R15D, R15D;MOVSX RAX, R15D;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX
• Chain latency: 26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 0f 42 ff          	cmovb  r15d,r15d
     9:	49 63 c7             	movsxd rax,r15d
     c:	48 63 c0             	movsxd rax,eax
     f:	48 63 c0             	movsxd rax,eax
    12:	48 63 c0             	movsxd rax,eax
    15:	48 63 c0             	movsxd rax,eax
    18:	48 63 c0             	movsxd rax,eax
    1b:	48 63 c0             	movsxd rax,eax
    1e:	48 63 c0             	movsxd rax,eax
    21:	48 63 c0             	movsxd rax,eax
    24:	48 63 c0             	movsxd rax,eax
    27:	48 63 c0             	movsxd rax,eax
    2a:	48 63 c0             	movsxd rax,eax
    2d:	48 63 c0             	movsxd rax,eax
    30:	48 63 c0             	movsxd rax,eax
    33:	48 63 c0             	movsxd rax,eax
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8D, 1

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 39.79
  • Reference cycles: 20.63
  • UOPS_EXECUTED.THREAD: 34.0

Experiment 15 (with R8D=2)

• Instruction: LOCK CMPXCHG dword ptr [R14], R8D
• Chain instructions: CMOVC R15D, R15D;MOVSX RAX, R15D;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX
• Chain latency: 26
• Code:

     0:	f0 45 0f b1 06       	lock cmpxchg DWORD PTR [r14],r8d
     5:	45 0f 42 ff          	cmovb  r15d,r15d
     9:	49 63 c7             	movsxd rax,r15d
     c:	48 63 c0             	movsxd rax,eax
     f:	48 63 c0             	movsxd rax,eax
    12:	48 63 c0             	movsxd rax,eax
    15:	48 63 c0             	movsxd rax,eax
    18:	48 63 c0             	movsxd rax,eax
    1b:	48 63 c0             	movsxd rax,eax
    1e:	48 63 c0             	movsxd rax,eax
    21:	48 63 c0             	movsxd rax,eax
    24:	48 63 c0             	movsxd rax,eax
    27:	48 63 c0             	movsxd rax,eax
    2a:	48 63 c0             	movsxd rax,eax
    2d:	48 63 c0             	movsxd rax,eax
    30:	48 63 c0             	movsxd rax,eax
    33:	48 63 c0             	movsxd rax,eax
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8D, 2

• Show nanoBench command
• Results:
  • Instructions retired: 27.0
  • Core cycles: 39.71
  • Reference cycles: 19.93
  • UOPS_EXECUTED.THREAD: 34.0