CMPXCHG_LOCK (M64, R64) - Latency

Experiment 1 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: MOV R12, [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;XOR R14, R12; XOR R14, R12
• Chain latency: ≥17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 8b 26             	mov    r12,QWORD 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 31 e6             	xor    r14,r12
    35:	4d 31 e6             	xor    r14,r12
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 18.0
  • Core cycles: 32.01
  • Reference cycles: 16.01
  • UOPS_RETIRED.ALL: 23.0

Experiment 2 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: MOV R12, [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;XOR R14, R12; XOR R14, R12
• Chain latency: ≥17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 8b 26             	mov    r12,QWORD 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 31 e6             	xor    r14,r12
    35:	4d 31 e6             	xor    r14,r12
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 18.0
  • Core cycles: 32.02
  • Reference cycles: 15.97
  • UOPS_RETIRED.ALL: 23.0

Experiment 3 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: MOV R12, [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;XOR R14, R12; XOR R14, R12
• Chain latency: ≥17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 8b 26             	mov    r12,QWORD 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 31 e6             	xor    r14,r12
    35:	4d 31 e6             	xor    r14,r12
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 18.0
  • Core cycles: 32.01
  • Reference cycles: 16.01
  • UOPS_RETIRED.ALL: 23.0

Experiment 4 (with additional nop, with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: MOV R12, [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;XOR R14, R12; XOR R14, R12;nop
• Chain latency: ≥17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 8b 26             	mov    r12,QWORD 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 31 e6             	xor    r14,r12
    35:	4d 31 e6             	xor    r14,r12
    38:	90                   	nop
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 19.0
  • Core cycles: 41.91
  • Reference cycles: 20.95
  • UOPS_RETIRED.ALL: 24.0

Experiment 5 (with additional nop, with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: MOV R12, [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;XOR R14, R12; XOR R14, R12;nop
• Chain latency: ≥17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 8b 26             	mov    r12,QWORD 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 31 e6             	xor    r14,r12
    35:	4d 31 e6             	xor    r14,r12
    38:	90                   	nop
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 19.0
  • Core cycles: 41.91
  • Reference cycles: 20.97
  • UOPS_RETIRED.ALL: 24.0

Experiment 6 (with additional nop, with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: MOV R12, [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;XOR R14, R12; XOR R14, R12;nop
• Chain latency: ≥17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 8b 26             	mov    r12,QWORD 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 31 e6             	xor    r14,r12
    35:	4d 31 e6             	xor    r14,r12
    38:	90                   	nop
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 19.0
  • Core cycles: 41.91
  • Reference cycles: 21.0
  • UOPS_RETIRED.ALL: 24.0

Experiment 1

• Instruction: LOCK CMPXCHG qword ptr [R14+R13], R8
• Chain instructions: MOV R12, [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;XOR R13, R12; XOR R13, R12
• Chain latency: ≥17
• Code:

     0:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     6:	4f 8b 24 2e          	mov    r12,QWORD 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 31 e5             	xor    r13,r12
    37:	4d 31 e5             	xor    r13,r12
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 18.0
  • Core cycles: 32.01
  • Reference cycles: 15.97
  • UOPS_RETIRED.ALL: 23.0

Experiment 2 (with additional nop)

• Instruction: LOCK CMPXCHG qword ptr [R14+R13], R8
• Chain instructions: MOV R12, [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;XOR R13, R12; XOR R13, R12;nop
• Chain latency: ≥17
• Code:

     0:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     6:	4f 8b 24 2e          	mov    r12,QWORD 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 31 e5             	xor    r13,r12
    37:	4d 31 e5             	xor    r13,r12
    3a:	90                   	nop
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 19.0
  • Core cycles: 41.69
  • Reference cycles: 20.82
  • UOPS_RETIRED.ALL: 24.0

Experiment 1 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: MOV R12, [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], R12
• Chain latency: 14
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 8b 26             	mov    r12,QWORD 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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 13.0
  • Core cycles: 33.66
  • Reference cycles: 16.86
  • UOPS_RETIRED.ALL: 18.0

Experiment 2 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: MOV R12, [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], R12
• Chain latency: 14
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 8b 26             	mov    r12,QWORD 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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 13.0
  • Core cycles: 33.8
  • Reference cycles: 16.92
  • UOPS_RETIRED.ALL: 18.0

Experiment 3 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: MOV R12, [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], R12
• Chain latency: 14
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 8b 26             	mov    r12,QWORD 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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 13.0
  • Core cycles: 33.94
  • Reference cycles: 17.01
  • UOPS_RETIRED.ALL: 18.0

Experiment 4 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Code:

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

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 11.99
  • Reference cycles: 6.0
  • UOPS_RETIRED.ALL: 6.0

Experiment 5 (with R8=0, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: MOV RAX, 0
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	48 c7 c0 00 00 00 00 	mov    rax,0x0
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 12.55
  • Reference cycles: 6.26
  • UOPS_RETIRED.ALL: 7.0

Experiment 6 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Code:

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

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 11.99
  • Reference cycles: 5.96
  • UOPS_RETIRED.ALL: 6.0

Experiment 7 (with R8=1, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: MOV RAX, 0
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	48 c7 c0 00 00 00 00 	mov    rax,0x0
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 12.51
  • Reference cycles: 6.24
  • UOPS_RETIRED.ALL: 7.0

Experiment 8 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Code:

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

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 11.99
  • Reference cycles: 6.02
  • UOPS_RETIRED.ALL: 6.0

Experiment 9 (with R8=2, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: MOV RAX, 0
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	48 c7 c0 00 00 00 00 	mov    rax,0x0
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 12.52
  • Reference cycles: 6.26
  • UOPS_RETIRED.ALL: 7.0

Experiment 1 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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
• Chain latency: 15
• Code:

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

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 16.0
  • Core cycles: 28.3
  • Reference cycles: 14.13
  • UOPS_RETIRED.ALL: 21.0

Experiment 2 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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
• Chain latency: 15
• Code:

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

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 16.0
  • Core cycles: 28.3
  • Reference cycles: 14.15
  • UOPS_RETIRED.ALL: 21.0

Experiment 3 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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
• Chain latency: 15
• Code:

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

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 16.0
  • Core cycles: 28.3
  • Reference cycles: 14.17
  • UOPS_RETIRED.ALL: 21.0

Experiment 1

• Instruction: LOCK CMPXCHG qword ptr [R14+R13], R8
• 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
• Chain latency: 15
• Code:

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

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 16.0
  • Core cycles: 28.3
  • Reference cycles: 14.15
  • UOPS_RETIRED.ALL: 21.0

Experiment 1 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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;mov [R14], R12
• Chain latency: ≥15
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 16.0
  • Core cycles: 26.5
  • Reference cycles: 13.26
  • UOPS_RETIRED.ALL: 21.0

Experiment 2 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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;mov [R14], R12
• Chain latency: ≥15
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 16.0
  • Core cycles: 26.5
  • Reference cycles: 13.28
  • UOPS_RETIRED.ALL: 21.0

Experiment 3 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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;mov [R14], R12
• Chain latency: ≥15
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 16.0
  • Core cycles: 26.5
  • Reference cycles: 13.2
  • UOPS_RETIRED.ALL: 21.0

Experiment 1 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVZ R14, R14
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 44 f6          	cmove  r14,r14
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 14.76
  • Reference cycles: 7.39
  • UOPS_RETIRED.ALL: 7.0

Experiment 2 (with R8=0, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVZ R14, R14;MOV qword ptr [R14], 0
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 44 f6          	cmove  r14,r14
     9:	49 c7 06 00 00 00 00 	mov    QWORD PTR [r14],0x0
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 17.0
  • Reference cycles: 8.47
  • UOPS_RETIRED.ALL: 8.0

Experiment 3 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVZ R14, R14
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 44 f6          	cmove  r14,r14
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 14.76
  • Reference cycles: 7.35
  • UOPS_RETIRED.ALL: 7.0

Experiment 4 (with R8=1, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVZ R14, R14;MOV qword ptr [R14], 0
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 44 f6          	cmove  r14,r14
     9:	49 c7 06 00 00 00 00 	mov    QWORD PTR [r14],0x0
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 17.0
  • Reference cycles: 8.47
  • UOPS_RETIRED.ALL: 8.0

Experiment 5 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVZ R14, R14
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 44 f6          	cmove  r14,r14
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 14.76
  • Reference cycles: 7.41
  • UOPS_RETIRED.ALL: 7.0

Experiment 6 (with R8=2, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVZ R14, R14;MOV qword ptr [R14], 0
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 44 f6          	cmove  r14,r14
     9:	49 c7 06 00 00 00 00 	mov    QWORD PTR [r14],0x0
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 17.0
  • Reference cycles: 8.49
  • UOPS_RETIRED.ALL: 8.0

Experiment 7 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVS R14, R14
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 48 f6          	cmovs  r14,r14
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 14.78
  • Reference cycles: 7.41
  • UOPS_RETIRED.ALL: 7.0

Experiment 8 (with R8=0, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVS R14, R14;MOV qword ptr [R14], 0
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 48 f6          	cmovs  r14,r14
     9:	49 c7 06 00 00 00 00 	mov    QWORD PTR [r14],0x0
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 17.0
  • Reference cycles: 8.49
  • UOPS_RETIRED.ALL: 8.0

Experiment 9 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVS R14, R14
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 48 f6          	cmovs  r14,r14
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 14.76
  • Reference cycles: 7.41
  • UOPS_RETIRED.ALL: 7.0

Experiment 10 (with R8=1, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVS R14, R14;MOV qword ptr [R14], 0
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 48 f6          	cmovs  r14,r14
     9:	49 c7 06 00 00 00 00 	mov    QWORD PTR [r14],0x0
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 17.0
  • Reference cycles: 8.49
  • UOPS_RETIRED.ALL: 8.0

Experiment 11 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVS R14, R14
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 48 f6          	cmovs  r14,r14
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 14.76
  • Reference cycles: 7.41
  • UOPS_RETIRED.ALL: 7.0

Experiment 12 (with R8=2, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVS R14, R14;MOV qword ptr [R14], 0
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 48 f6          	cmovs  r14,r14
     9:	49 c7 06 00 00 00 00 	mov    QWORD PTR [r14],0x0
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 17.0
  • Reference cycles: 8.49
  • UOPS_RETIRED.ALL: 8.0

Experiment 13 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVC R14, R14
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 42 f6          	cmovb  r14,r14
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 14.76
  • Reference cycles: 7.35
  • UOPS_RETIRED.ALL: 7.0

Experiment 14 (with R8=0, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVC R14, R14;MOV qword ptr [R14], 0
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 42 f6          	cmovb  r14,r14
     9:	49 c7 06 00 00 00 00 	mov    QWORD PTR [r14],0x0
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 17.0
  • Reference cycles: 8.47
  • UOPS_RETIRED.ALL: 8.0

Experiment 15 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVC R14, R14
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 42 f6          	cmovb  r14,r14
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 14.76
  • Reference cycles: 7.41
  • UOPS_RETIRED.ALL: 7.0

Experiment 16 (with R8=1, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVC R14, R14;MOV qword ptr [R14], 0
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 42 f6          	cmovb  r14,r14
     9:	49 c7 06 00 00 00 00 	mov    QWORD PTR [r14],0x0
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 17.0
  • Reference cycles: 8.49
  • UOPS_RETIRED.ALL: 8.0

Experiment 17 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVC R14, R14
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 42 f6          	cmovb  r14,r14
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 14.76
  • Reference cycles: 7.41
  • UOPS_RETIRED.ALL: 7.0

Experiment 18 (with R8=2, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVC R14, R14;MOV qword ptr [R14], 0
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 42 f6          	cmovb  r14,r14
     9:	49 c7 06 00 00 00 00 	mov    QWORD PTR [r14],0x0
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 17.0
  • Reference cycles: 8.47
  • UOPS_RETIRED.ALL: 8.0

Experiment 19 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVP R14, R14
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 4a f6          	cmovp  r14,r14
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 14.76
  • Reference cycles: 7.41
  • UOPS_RETIRED.ALL: 7.0

Experiment 20 (with R8=0, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVP R14, R14;MOV qword ptr [R14], 0
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 4a f6          	cmovp  r14,r14
     9:	49 c7 06 00 00 00 00 	mov    QWORD PTR [r14],0x0
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 17.0
  • Reference cycles: 8.49
  • UOPS_RETIRED.ALL: 8.0

Experiment 21 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVP R14, R14
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 4a f6          	cmovp  r14,r14
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 14.76
  • Reference cycles: 7.41
  • UOPS_RETIRED.ALL: 7.0

Experiment 22 (with R8=1, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVP R14, R14;MOV qword ptr [R14], 0
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 4a f6          	cmovp  r14,r14
     9:	49 c7 06 00 00 00 00 	mov    QWORD PTR [r14],0x0
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 17.0
  • Reference cycles: 8.47
  • UOPS_RETIRED.ALL: 8.0

Experiment 23 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVP R14, R14
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 4a f6          	cmovp  r14,r14
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 14.76
  • Reference cycles: 7.41
  • UOPS_RETIRED.ALL: 7.0

Experiment 24 (with R8=2, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVP R14, R14;MOV qword ptr [R14], 0
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 4a f6          	cmovp  r14,r14
     9:	49 c7 06 00 00 00 00 	mov    QWORD PTR [r14],0x0
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 17.0
  • Reference cycles: 8.49
  • UOPS_RETIRED.ALL: 8.0

Experiment 25 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVO R14, R14
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 40 f6          	cmovo  r14,r14
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 14.76
  • Reference cycles: 7.39
  • UOPS_RETIRED.ALL: 7.0

Experiment 26 (with R8=0, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVO R14, R14;MOV qword ptr [R14], 0
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 40 f6          	cmovo  r14,r14
     9:	49 c7 06 00 00 00 00 	mov    QWORD PTR [r14],0x0
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 17.0
  • Reference cycles: 8.47
  • UOPS_RETIRED.ALL: 8.0

Experiment 27 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVO R14, R14
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 40 f6          	cmovo  r14,r14
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 14.76
  • Reference cycles: 7.35
  • UOPS_RETIRED.ALL: 7.0

Experiment 28 (with R8=1, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVO R14, R14;MOV qword ptr [R14], 0
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 40 f6          	cmovo  r14,r14
     9:	49 c7 06 00 00 00 00 	mov    QWORD PTR [r14],0x0
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 17.0
  • Reference cycles: 8.49
  • UOPS_RETIRED.ALL: 8.0

Experiment 29 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVO R14, R14
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 40 f6          	cmovo  r14,r14
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 14.76
  • Reference cycles: 7.41
  • UOPS_RETIRED.ALL: 7.0

Experiment 30 (with R8=2, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVO R14, R14;MOV qword ptr [R14], 0
• Chain latency: 2
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 40 f6          	cmovo  r14,r14
     9:	49 c7 06 00 00 00 00 	mov    QWORD PTR [r14],0x0
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 17.0
  • Reference cycles: 8.49
  • UOPS_RETIRED.ALL: 8.0

Experiment 1

• Instruction: LOCK CMPXCHG qword ptr [R14+R13], R8
• Chain instruction: CMOVZ R13, R13
• Chain latency: 2
• Code:

     0:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     6:	4d 0f 44 ed          	cmove  r13,r13
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 14.76
  • Reference cycles: 7.41
  • UOPS_RETIRED.ALL: 7.0

Experiment 2 (with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14+R13], R8
• Chain instructions: CMOVZ R13, R13;MOV qword ptr [R14], 0
• Chain latency: 2
• Code:

     0:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     6:	4d 0f 44 ed          	cmove  r13,r13
     a:	49 c7 06 00 00 00 00 	mov    QWORD PTR [r14],0x0
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 15.0
  • Reference cycles: 7.52
  • UOPS_RETIRED.ALL: 8.0

Experiment 3

• Instruction: LOCK CMPXCHG qword ptr [R14+R13], R8
• Chain instruction: CMOVS R13, R13
• Chain latency: 2
• Code:

     0:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     6:	4d 0f 48 ed          	cmovs  r13,r13
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 14.76
  • Reference cycles: 7.41
  • UOPS_RETIRED.ALL: 7.0

Experiment 4 (with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14+R13], R8
• Chain instructions: CMOVS R13, R13;MOV qword ptr [R14], 0
• Chain latency: 2
• Code:

     0:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     6:	4d 0f 48 ed          	cmovs  r13,r13
     a:	49 c7 06 00 00 00 00 	mov    QWORD PTR [r14],0x0
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 15.0
  • Reference cycles: 7.54
  • UOPS_RETIRED.ALL: 8.0

Experiment 5

• Instruction: LOCK CMPXCHG qword ptr [R14+R13], R8
• Chain instruction: CMOVC R13, R13
• Chain latency: 2
• Code:

     0:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     6:	4d 0f 42 ed          	cmovb  r13,r13
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 14.76
  • Reference cycles: 7.41
  • UOPS_RETIRED.ALL: 7.0

Experiment 6 (with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14+R13], R8
• Chain instructions: CMOVC R13, R13;MOV qword ptr [R14], 0
• Chain latency: 2
• Code:

     0:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     6:	4d 0f 42 ed          	cmovb  r13,r13
     a:	49 c7 06 00 00 00 00 	mov    QWORD PTR [r14],0x0
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 15.0
  • Reference cycles: 7.54
  • UOPS_RETIRED.ALL: 8.0

Experiment 7

• Instruction: LOCK CMPXCHG qword ptr [R14+R13], R8
• Chain instruction: CMOVP R13, R13
• Chain latency: 2
• Code:

     0:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     6:	4d 0f 4a ed          	cmovp  r13,r13
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 14.76
  • Reference cycles: 7.39
  • UOPS_RETIRED.ALL: 7.0

Experiment 8 (with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14+R13], R8
• Chain instructions: CMOVP R13, R13;MOV qword ptr [R14], 0
• Chain latency: 2
• Code:

     0:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     6:	4d 0f 4a ed          	cmovp  r13,r13
     a:	49 c7 06 00 00 00 00 	mov    QWORD PTR [r14],0x0
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 15.0
  • Reference cycles: 7.52
  • UOPS_RETIRED.ALL: 8.0

Experiment 9

• Instruction: LOCK CMPXCHG qword ptr [R14+R13], R8
• Chain instruction: CMOVO R13, R13
• Chain latency: 2
• Code:

     0:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     6:	4d 0f 40 ed          	cmovo  r13,r13
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 14.76
  • Reference cycles: 7.41
  • UOPS_RETIRED.ALL: 7.0

Experiment 10 (with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14+R13], R8
• Chain instructions: CMOVO R13, R13;MOV qword ptr [R14], 0
• Chain latency: 2
• Code:

     0:	f0 4f 0f b1 04 2e    	lock cmpxchg QWORD PTR [r14+r13*1],r8
     6:	4d 0f 40 ed          	cmovo  r13,r13
     a:	49 c7 06 00 00 00 00 	mov    QWORD PTR [r14],0x0
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 15.03
  • Reference cycles: 7.5
  • UOPS_RETIRED.ALL: 8.0

Experiment 1 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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;mov [R14], R12
• Chain latency: ≥17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 29.0
  • Reference cycles: 14.5
  • UOPS_RETIRED.ALL: 22.0

Experiment 2 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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;mov [R14], R12
• Chain latency: ≥17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 29.0
  • Reference cycles: 14.5
  • UOPS_RETIRED.ALL: 22.0

Experiment 3 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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;mov [R14], R12
• Chain latency: ≥17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 29.0
  • Reference cycles: 14.5
  • UOPS_RETIRED.ALL: 22.0

Experiment 4 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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;mov [R14], R12
• Chain latency: ≥17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 29.01
  • Reference cycles: 14.5
  • UOPS_RETIRED.ALL: 22.0

Experiment 5 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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;mov [R14], R12
• Chain latency: ≥17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 29.0
  • Reference cycles: 14.5
  • UOPS_RETIRED.ALL: 22.0

Experiment 6 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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;mov [R14], R12
• Chain latency: ≥17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 29.0
  • Reference cycles: 14.5
  • UOPS_RETIRED.ALL: 22.0

Experiment 7 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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;mov [R14], R12
• Chain latency: ≥17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 29.0
  • Reference cycles: 14.5
  • UOPS_RETIRED.ALL: 22.0

Experiment 8 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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;mov [R14], R12
• Chain latency: ≥17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 29.0
  • Reference cycles: 14.47
  • UOPS_RETIRED.ALL: 22.0

Experiment 9 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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;mov [R14], R12
• Chain latency: ≥17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 29.0
  • Reference cycles: 14.52
  • UOPS_RETIRED.ALL: 22.0

Experiment 10 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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;mov [R14], R12
• Chain latency: ≥17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 29.0
  • Reference cycles: 14.47
  • UOPS_RETIRED.ALL: 22.0

Experiment 11 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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;mov [R14], R12
• Chain latency: ≥17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 29.0
  • Reference cycles: 14.52
  • UOPS_RETIRED.ALL: 22.0

Experiment 12 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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;mov [R14], R12
• Chain latency: ≥17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 29.0
  • Reference cycles: 14.52
  • UOPS_RETIRED.ALL: 22.0

Experiment 13 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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;mov [R14], R12
• Chain latency: ≥17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 29.0
  • Reference cycles: 14.5
  • UOPS_RETIRED.ALL: 22.0

Experiment 14 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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;mov [R14], R12
• Chain latency: ≥17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 29.0
  • Reference cycles: 14.47
  • UOPS_RETIRED.ALL: 22.0

Experiment 15 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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;mov [R14], R12
• Chain latency: ≥17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 29.0
  • Reference cycles: 14.5
  • UOPS_RETIRED.ALL: 22.0

Experiment 1

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: MOV R8, [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
• Chain latency: ≥15
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 8b 06             	mov    r8,QWORD 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
  

• Show nanoBench command
• Results:
  • Instructions retired: 16.0
  • Core cycles: 26.5
  • Reference cycles: 13.22
  • UOPS_RETIRED.ALL: 21.0

Experiment 1

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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
• Chain latency: 15
• Code:

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

• Show nanoBench command
• Results:
  • Instructions retired: 16.0
  • Core cycles: 27.5
  • Reference cycles: 13.78
  • UOPS_RETIRED.ALL: 21.0

Experiment 1

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVZ R15, R15;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
• Chain latency: 17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 44 ff          	cmove  r15,r15
     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
  

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 27.0
  • Reference cycles: 13.52
  • UOPS_RETIRED.ALL: 22.0

Experiment 2

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVS R15, R15;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
• Chain latency: 17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 48 ff          	cmovs  r15,r15
     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
  

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 27.0
  • Reference cycles: 13.52
  • UOPS_RETIRED.ALL: 22.0

Experiment 3

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVC R15, R15;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
• Chain latency: 17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 42 ff          	cmovb  r15,r15
     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
  

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 27.0
  • Reference cycles: 13.52
  • UOPS_RETIRED.ALL: 22.0

Experiment 4

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVP R15, R15;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
• Chain latency: 17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 4a ff          	cmovp  r15,r15
     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
  

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 27.0
  • Reference cycles: 13.52
  • UOPS_RETIRED.ALL: 22.0

Experiment 5

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVO R15, R15;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
• Chain latency: 17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 40 ff          	cmovo  r15,r15
     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
  

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 27.0
  • Reference cycles: 13.52
  • UOPS_RETIRED.ALL: 22.0

Experiment 1 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: MOV RAX, [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
• Chain latency: ≥15
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	49 8b 06             	mov    rax,QWORD 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
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 16.0
  • Core cycles: 26.5
  • Reference cycles: 13.26
  • UOPS_RETIRED.ALL: 21.0

Experiment 2 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: MOV RAX, [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
• Chain latency: ≥15
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	49 8b 06             	mov    rax,QWORD 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
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 16.0
  • Core cycles: 26.5
  • Reference cycles: 13.24
  • UOPS_RETIRED.ALL: 21.0

Experiment 3 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: MOV RAX, [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
• Chain latency: ≥15
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	49 8b 06             	mov    rax,QWORD 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
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 16.0
  • Core cycles: 26.5
  • Reference cycles: 13.24
  • UOPS_RETIRED.ALL: 21.0

Experiment 1 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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
• Chain latency: 15
• Code:

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

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 16.0
  • Core cycles: 27.5
  • Reference cycles: 13.78
  • UOPS_RETIRED.ALL: 21.0

Experiment 2 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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
• Chain latency: 15
• Code:

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

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 16.0
  • Core cycles: 27.5
  • Reference cycles: 13.76
  • UOPS_RETIRED.ALL: 21.0

Experiment 3 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• 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
• Chain latency: 15
• Code:

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

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 16.0
  • Core cycles: 27.5
  • Reference cycles: 13.78
  • UOPS_RETIRED.ALL: 21.0

Experiment 4 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Code:

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

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 12.0
  • Reference cycles: 5.98
  • UOPS_RETIRED.ALL: 6.0

Experiment 5 (with R8=0, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: MOV qword ptr [R14], 0
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	49 c7 06 00 00 00 00 	mov    QWORD PTR [r14],0x0
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 13.0
  • Reference cycles: 6.54
  • UOPS_RETIRED.ALL: 7.0

Experiment 6 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Code:

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

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 12.0
  • Reference cycles: 5.96
  • UOPS_RETIRED.ALL: 6.0

Experiment 7 (with R8=1, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: MOV qword ptr [R14], 0
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	49 c7 06 00 00 00 00 	mov    QWORD PTR [r14],0x0
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 13.0
  • Reference cycles: 6.48
  • UOPS_RETIRED.ALL: 7.0

Experiment 8 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Code:

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

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 12.0
  • Reference cycles: 6.0
  • UOPS_RETIRED.ALL: 6.0

Experiment 9 (with R8=2, with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: MOV qword ptr [R14], 0
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	49 c7 06 00 00 00 00 	mov    QWORD PTR [r14],0x0
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 13.0
  • Reference cycles: 6.52
  • UOPS_RETIRED.ALL: 7.0

Experiment 1 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVZ R15, R15;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
• Chain latency: 17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 44 ff          	cmove  r15,r15
     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
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 28.0
  • Reference cycles: 14.04
  • UOPS_RETIRED.ALL: 22.0

Experiment 2 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVZ R15, R15;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
• Chain latency: 17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 44 ff          	cmove  r15,r15
     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
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 28.0
  • Reference cycles: 14.04
  • UOPS_RETIRED.ALL: 22.0

Experiment 3 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVZ R15, R15;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
• Chain latency: 17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 44 ff          	cmove  r15,r15
     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
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 28.0
  • Reference cycles: 14.04
  • UOPS_RETIRED.ALL: 22.0

Experiment 4 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVS R15, R15;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
• Chain latency: 17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 48 ff          	cmovs  r15,r15
     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
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 28.0
  • Reference cycles: 14.04
  • UOPS_RETIRED.ALL: 22.0

Experiment 5 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVS R15, R15;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
• Chain latency: 17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 48 ff          	cmovs  r15,r15
     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
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 28.0
  • Reference cycles: 14.04
  • UOPS_RETIRED.ALL: 22.0

Experiment 6 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVS R15, R15;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
• Chain latency: 17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 48 ff          	cmovs  r15,r15
     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
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 28.0
  • Reference cycles: 14.04
  • UOPS_RETIRED.ALL: 22.0

Experiment 7 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVC R15, R15;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
• Chain latency: 17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 42 ff          	cmovb  r15,r15
     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
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 28.0
  • Reference cycles: 14.04
  • UOPS_RETIRED.ALL: 22.0

Experiment 8 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVC R15, R15;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
• Chain latency: 17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 42 ff          	cmovb  r15,r15
     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
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 28.0
  • Reference cycles: 14.04
  • UOPS_RETIRED.ALL: 22.0

Experiment 9 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVC R15, R15;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
• Chain latency: 17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 42 ff          	cmovb  r15,r15
     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
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 28.0
  • Reference cycles: 14.04
  • UOPS_RETIRED.ALL: 22.0

Experiment 10 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVP R15, R15;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
• Chain latency: 17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 4a ff          	cmovp  r15,r15
     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
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 28.0
  • Reference cycles: 14.04
  • UOPS_RETIRED.ALL: 22.0

Experiment 11 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVP R15, R15;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
• Chain latency: 17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 4a ff          	cmovp  r15,r15
     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
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 28.0
  • Reference cycles: 14.04
  • UOPS_RETIRED.ALL: 22.0

Experiment 12 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVP R15, R15;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
• Chain latency: 17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 4a ff          	cmovp  r15,r15
     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
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 28.0
  • Reference cycles: 14.04
  • UOPS_RETIRED.ALL: 22.0

Experiment 13 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVO R15, R15;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
• Chain latency: 17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 40 ff          	cmovo  r15,r15
     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
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 28.0
  • Reference cycles: 14.04
  • UOPS_RETIRED.ALL: 22.0

Experiment 14 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVO R15, R15;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
• Chain latency: 17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 40 ff          	cmovo  r15,r15
     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
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 28.0
  • Reference cycles: 14.04
  • UOPS_RETIRED.ALL: 22.0

Experiment 15 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instructions: CMOVO R15, R15;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
• Chain latency: 17
• Code:

     0:	f0 4d 0f b1 06       	lock cmpxchg QWORD PTR [r14],r8
     5:	4d 0f 40 ff          	cmovo  r15,r15
     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
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • Instructions retired: 17.0
  • Core cycles: 28.0
  • Reference cycles: 14.04
  • UOPS_RETIRED.ALL: 22.0