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;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;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: ≥35
• 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 63 e4             	movsxd r12,r12d
    35:	4d 63 e4             	movsxd r12,r12d
    38:	4d 63 e4             	movsxd r12,r12d
    3b:	4d 63 e4             	movsxd r12,r12d
    3e:	4d 63 e4             	movsxd r12,r12d
    41:	4d 63 e4             	movsxd r12,r12d
    44:	4d 63 e4             	movsxd r12,r12d
    47:	4d 63 e4             	movsxd r12,r12d
    4a:	4d 63 e4             	movsxd r12,r12d
    4d:	4d 63 e4             	movsxd r12,r12d
    50:	4d 63 e4             	movsxd r12,r12d
    53:	4d 63 e4             	movsxd r12,r12d
    56:	4d 63 e4             	movsxd r12,r12d
    59:	4d 63 e4             	movsxd r12,r12d
    5c:	4d 63 e4             	movsxd r12,r12d
    5f:	4d 63 e4             	movsxd r12,r12d
    62:	4d 63 e4             	movsxd r12,r12d
    65:	4d 63 e4             	movsxd r12,r12d
    68:	4d 31 e6             	xor    r14,r12
    6b:	4d 31 e6             	xor    r14,r12
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • MPERF: 40.12
  • APERF: 46.02
  • UOPS: 41.0

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;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;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: ≥35
• 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 63 e4             	movsxd r12,r12d
    35:	4d 63 e4             	movsxd r12,r12d
    38:	4d 63 e4             	movsxd r12,r12d
    3b:	4d 63 e4             	movsxd r12,r12d
    3e:	4d 63 e4             	movsxd r12,r12d
    41:	4d 63 e4             	movsxd r12,r12d
    44:	4d 63 e4             	movsxd r12,r12d
    47:	4d 63 e4             	movsxd r12,r12d
    4a:	4d 63 e4             	movsxd r12,r12d
    4d:	4d 63 e4             	movsxd r12,r12d
    50:	4d 63 e4             	movsxd r12,r12d
    53:	4d 63 e4             	movsxd r12,r12d
    56:	4d 63 e4             	movsxd r12,r12d
    59:	4d 63 e4             	movsxd r12,r12d
    5c:	4d 63 e4             	movsxd r12,r12d
    5f:	4d 63 e4             	movsxd r12,r12d
    62:	4d 63 e4             	movsxd r12,r12d
    65:	4d 63 e4             	movsxd r12,r12d
    68:	4d 31 e6             	xor    r14,r12
    6b:	4d 31 e6             	xor    r14,r12
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • MPERF: 40.12
  • APERF: 46.02
  • UOPS: 41.0

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;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;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: ≥35
• 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 63 e4             	movsxd r12,r12d
    35:	4d 63 e4             	movsxd r12,r12d
    38:	4d 63 e4             	movsxd r12,r12d
    3b:	4d 63 e4             	movsxd r12,r12d
    3e:	4d 63 e4             	movsxd r12,r12d
    41:	4d 63 e4             	movsxd r12,r12d
    44:	4d 63 e4             	movsxd r12,r12d
    47:	4d 63 e4             	movsxd r12,r12d
    4a:	4d 63 e4             	movsxd r12,r12d
    4d:	4d 63 e4             	movsxd r12,r12d
    50:	4d 63 e4             	movsxd r12,r12d
    53:	4d 63 e4             	movsxd r12,r12d
    56:	4d 63 e4             	movsxd r12,r12d
    59:	4d 63 e4             	movsxd r12,r12d
    5c:	4d 63 e4             	movsxd r12,r12d
    5f:	4d 63 e4             	movsxd r12,r12d
    62:	4d 63 e4             	movsxd r12,r12d
    65:	4d 63 e4             	movsxd r12,r12d
    68:	4d 31 e6             	xor    r14,r12
    6b:	4d 31 e6             	xor    r14,r12
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • MPERF: 40.12
  • APERF: 46.02
  • UOPS: 41.0

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;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;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: ≥35
• 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 63 e4             	movsxd r12,r12d
    35:	4d 63 e4             	movsxd r12,r12d
    38:	4d 63 e4             	movsxd r12,r12d
    3b:	4d 63 e4             	movsxd r12,r12d
    3e:	4d 63 e4             	movsxd r12,r12d
    41:	4d 63 e4             	movsxd r12,r12d
    44:	4d 63 e4             	movsxd r12,r12d
    47:	4d 63 e4             	movsxd r12,r12d
    4a:	4d 63 e4             	movsxd r12,r12d
    4d:	4d 63 e4             	movsxd r12,r12d
    50:	4d 63 e4             	movsxd r12,r12d
    53:	4d 63 e4             	movsxd r12,r12d
    56:	4d 63 e4             	movsxd r12,r12d
    59:	4d 63 e4             	movsxd r12,r12d
    5c:	4d 63 e4             	movsxd r12,r12d
    5f:	4d 63 e4             	movsxd r12,r12d
    62:	4d 63 e4             	movsxd r12,r12d
    65:	4d 63 e4             	movsxd r12,r12d
    68:	4d 31 e6             	xor    r14,r12
    6b:	4d 31 e6             	xor    r14,r12
    6e:	90                   	nop
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • MPERF: 40.12
  • APERF: 46.02
  • UOPS: 42.0

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;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;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: ≥35
• 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 63 e4             	movsxd r12,r12d
    35:	4d 63 e4             	movsxd r12,r12d
    38:	4d 63 e4             	movsxd r12,r12d
    3b:	4d 63 e4             	movsxd r12,r12d
    3e:	4d 63 e4             	movsxd r12,r12d
    41:	4d 63 e4             	movsxd r12,r12d
    44:	4d 63 e4             	movsxd r12,r12d
    47:	4d 63 e4             	movsxd r12,r12d
    4a:	4d 63 e4             	movsxd r12,r12d
    4d:	4d 63 e4             	movsxd r12,r12d
    50:	4d 63 e4             	movsxd r12,r12d
    53:	4d 63 e4             	movsxd r12,r12d
    56:	4d 63 e4             	movsxd r12,r12d
    59:	4d 63 e4             	movsxd r12,r12d
    5c:	4d 63 e4             	movsxd r12,r12d
    5f:	4d 63 e4             	movsxd r12,r12d
    62:	4d 63 e4             	movsxd r12,r12d
    65:	4d 63 e4             	movsxd r12,r12d
    68:	4d 31 e6             	xor    r14,r12
    6b:	4d 31 e6             	xor    r14,r12
    6e:	90                   	nop
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • MPERF: 40.12
  • APERF: 46.02
  • UOPS: 42.0

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;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;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: ≥35
• 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 63 e4             	movsxd r12,r12d
    35:	4d 63 e4             	movsxd r12,r12d
    38:	4d 63 e4             	movsxd r12,r12d
    3b:	4d 63 e4             	movsxd r12,r12d
    3e:	4d 63 e4             	movsxd r12,r12d
    41:	4d 63 e4             	movsxd r12,r12d
    44:	4d 63 e4             	movsxd r12,r12d
    47:	4d 63 e4             	movsxd r12,r12d
    4a:	4d 63 e4             	movsxd r12,r12d
    4d:	4d 63 e4             	movsxd r12,r12d
    50:	4d 63 e4             	movsxd r12,r12d
    53:	4d 63 e4             	movsxd r12,r12d
    56:	4d 63 e4             	movsxd r12,r12d
    59:	4d 63 e4             	movsxd r12,r12d
    5c:	4d 63 e4             	movsxd r12,r12d
    5f:	4d 63 e4             	movsxd r12,r12d
    62:	4d 63 e4             	movsxd r12,r12d
    65:	4d 63 e4             	movsxd r12,r12d
    68:	4d 31 e6             	xor    r14,r12
    6b:	4d 31 e6             	xor    r14,r12
    6e:	90                   	nop
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • MPERF: 40.12
  • APERF: 46.02
  • UOPS: 42.0

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;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;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: ≥35
• 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 63 e4             	movsxd r12,r12d
    37:	4d 63 e4             	movsxd r12,r12d
    3a:	4d 63 e4             	movsxd r12,r12d
    3d:	4d 63 e4             	movsxd r12,r12d
    40:	4d 63 e4             	movsxd r12,r12d
    43:	4d 63 e4             	movsxd r12,r12d
    46:	4d 63 e4             	movsxd r12,r12d
    49:	4d 63 e4             	movsxd r12,r12d
    4c:	4d 63 e4             	movsxd r12,r12d
    4f:	4d 63 e4             	movsxd r12,r12d
    52:	4d 63 e4             	movsxd r12,r12d
    55:	4d 63 e4             	movsxd r12,r12d
    58:	4d 63 e4             	movsxd r12,r12d
    5b:	4d 63 e4             	movsxd r12,r12d
    5e:	4d 63 e4             	movsxd r12,r12d
    61:	4d 63 e4             	movsxd r12,r12d
    64:	4d 63 e4             	movsxd r12,r12d
    67:	4d 63 e4             	movsxd r12,r12d
    6a:	4d 31 e5             	xor    r13,r12
    6d:	4d 31 e5             	xor    r13,r12
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • MPERF: 40.18
  • APERF: 46.02
  • UOPS: 41.0

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;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;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: ≥35
• 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 63 e4             	movsxd r12,r12d
    37:	4d 63 e4             	movsxd r12,r12d
    3a:	4d 63 e4             	movsxd r12,r12d
    3d:	4d 63 e4             	movsxd r12,r12d
    40:	4d 63 e4             	movsxd r12,r12d
    43:	4d 63 e4             	movsxd r12,r12d
    46:	4d 63 e4             	movsxd r12,r12d
    49:	4d 63 e4             	movsxd r12,r12d
    4c:	4d 63 e4             	movsxd r12,r12d
    4f:	4d 63 e4             	movsxd r12,r12d
    52:	4d 63 e4             	movsxd r12,r12d
    55:	4d 63 e4             	movsxd r12,r12d
    58:	4d 63 e4             	movsxd r12,r12d
    5b:	4d 63 e4             	movsxd r12,r12d
    5e:	4d 63 e4             	movsxd r12,r12d
    61:	4d 63 e4             	movsxd r12,r12d
    64:	4d 63 e4             	movsxd r12,r12d
    67:	4d 63 e4             	movsxd r12,r12d
    6a:	4d 31 e5             	xor    r13,r12
    6d:	4d 31 e5             	xor    r13,r12
    70:	90                   	nop
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • MPERF: 40.06
  • APERF: 46.02
  • UOPS: 42.0

Experiment 1 (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:
  • MPERF: 23.8
  • APERF: 27.38
  • UOPS: 6.0

Experiment 2 (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:
  • MPERF: 23.8
  • APERF: 27.38
  • UOPS: 7.0

Experiment 3 (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:
  • MPERF: 23.8
  • APERF: 27.38
  • UOPS: 6.0

Experiment 4 (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:
  • MPERF: 23.8
  • APERF: 27.38
  • UOPS: 7.0

Experiment 5 (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:
  • MPERF: 23.8
  • APERF: 27.38
  • UOPS: 6.0

Experiment 6 (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:
  • MPERF: 23.86
  • APERF: 27.38
  • UOPS: 7.0

Experiment 7 (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: 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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • MPERF: 22.84
  • APERF: 26.26
  • UOPS: 18.0

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

• 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;MOV RAX, 0
• 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 89 26             	mov    QWORD PTR [r14],r12
    29:	48 c7 c0 00 00 00 00 	mov    rax,0x0
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • MPERF: 22.67
  • APERF: 26.0
  • UOPS: 19.0

Experiment 9 (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: 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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • MPERF: 22.78
  • APERF: 26.26
  • UOPS: 18.0

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

• 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;MOV RAX, 0
• 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 89 26             	mov    QWORD PTR [r14],r12
    29:	48 c7 c0 00 00 00 00 	mov    rax,0x0
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • MPERF: 22.67
  • APERF: 26.0
  • UOPS: 19.0

Experiment 11 (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: 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 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • MPERF: 22.84
  • APERF: 26.26
  • UOPS: 18.0

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

• 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;MOV RAX, 0
• 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 89 26             	mov    QWORD PTR [r14],r12
    29:	48 c7 c0 00 00 00 00 	mov    rax,0x0
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • MPERF: 22.67
  • APERF: 26.0
  • UOPS: 19.0

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;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX
• Chain latency: 33
• 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
    32:	49 31 c6             	xor    r14,rax
    35:	49 31 c6             	xor    r14,rax
    38:	49 31 c6             	xor    r14,rax
    3b:	49 31 c6             	xor    r14,rax
    3e:	49 31 c6             	xor    r14,rax
    41:	49 31 c6             	xor    r14,rax
    44:	49 31 c6             	xor    r14,rax
    47:	49 31 c6             	xor    r14,rax
    4a:	49 31 c6             	xor    r14,rax
    4d:	49 31 c6             	xor    r14,rax
    50:	49 31 c6             	xor    r14,rax
    53:	49 31 c6             	xor    r14,rax
    56:	49 31 c6             	xor    r14,rax
    59:	49 31 c6             	xor    r14,rax
    5c:	49 31 c6             	xor    r14,rax
    5f:	49 31 c6             	xor    r14,rax
    62:	49 31 c6             	xor    r14,rax
    65:	49 31 c6             	xor    r14,rax
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • MPERF: 35.02
  • APERF: 40.0
  • UOPS: 39.0

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;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX
• Chain latency: 33
• 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
    32:	49 31 c6             	xor    r14,rax
    35:	49 31 c6             	xor    r14,rax
    38:	49 31 c6             	xor    r14,rax
    3b:	49 31 c6             	xor    r14,rax
    3e:	49 31 c6             	xor    r14,rax
    41:	49 31 c6             	xor    r14,rax
    44:	49 31 c6             	xor    r14,rax
    47:	49 31 c6             	xor    r14,rax
    4a:	49 31 c6             	xor    r14,rax
    4d:	49 31 c6             	xor    r14,rax
    50:	49 31 c6             	xor    r14,rax
    53:	49 31 c6             	xor    r14,rax
    56:	49 31 c6             	xor    r14,rax
    59:	49 31 c6             	xor    r14,rax
    5c:	49 31 c6             	xor    r14,rax
    5f:	49 31 c6             	xor    r14,rax
    62:	49 31 c6             	xor    r14,rax
    65:	49 31 c6             	xor    r14,rax
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • MPERF: 34.85
  • APERF: 40.0
  • UOPS: 39.0

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;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX;XOR R14, RAX
• Chain latency: 33
• 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
    32:	49 31 c6             	xor    r14,rax
    35:	49 31 c6             	xor    r14,rax
    38:	49 31 c6             	xor    r14,rax
    3b:	49 31 c6             	xor    r14,rax
    3e:	49 31 c6             	xor    r14,rax
    41:	49 31 c6             	xor    r14,rax
    44:	49 31 c6             	xor    r14,rax
    47:	49 31 c6             	xor    r14,rax
    4a:	49 31 c6             	xor    r14,rax
    4d:	49 31 c6             	xor    r14,rax
    50:	49 31 c6             	xor    r14,rax
    53:	49 31 c6             	xor    r14,rax
    56:	49 31 c6             	xor    r14,rax
    59:	49 31 c6             	xor    r14,rax
    5c:	49 31 c6             	xor    r14,rax
    5f:	49 31 c6             	xor    r14,rax
    62:	49 31 c6             	xor    r14,rax
    65:	49 31 c6             	xor    r14,rax
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • MPERF: 34.96
  • APERF: 40.0
  • UOPS: 39.0

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;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX;XOR R13, RAX
• Chain latency: 33
• 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
    33:	49 31 c5             	xor    r13,rax
    36:	49 31 c5             	xor    r13,rax
    39:	49 31 c5             	xor    r13,rax
    3c:	49 31 c5             	xor    r13,rax
    3f:	49 31 c5             	xor    r13,rax
    42:	49 31 c5             	xor    r13,rax
    45:	49 31 c5             	xor    r13,rax
    48:	49 31 c5             	xor    r13,rax
    4b:	49 31 c5             	xor    r13,rax
    4e:	49 31 c5             	xor    r13,rax
    51:	49 31 c5             	xor    r13,rax
    54:	49 31 c5             	xor    r13,rax
    57:	49 31 c5             	xor    r13,rax
    5a:	49 31 c5             	xor    r13,rax
    5d:	49 31 c5             	xor    r13,rax
    60:	49 31 c5             	xor    r13,rax
    63:	49 31 c5             	xor    r13,rax
    66:	49 31 c5             	xor    r13,rax
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • MPERF: 34.85
  • APERF: 40.0
  • UOPS: 39.0

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;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;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: ≥33
• 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 63 e4             	movsxd r12,r12d
    32:	4d 63 e4             	movsxd r12,r12d
    35:	4d 63 e4             	movsxd r12,r12d
    38:	4d 63 e4             	movsxd r12,r12d
    3b:	4d 63 e4             	movsxd r12,r12d
    3e:	4d 63 e4             	movsxd r12,r12d
    41:	4d 63 e4             	movsxd r12,r12d
    44:	4d 63 e4             	movsxd r12,r12d
    47:	4d 63 e4             	movsxd r12,r12d
    4a:	4d 63 e4             	movsxd r12,r12d
    4d:	4d 63 e4             	movsxd r12,r12d
    50:	4d 63 e4             	movsxd r12,r12d
    53:	4d 63 e4             	movsxd r12,r12d
    56:	4d 63 e4             	movsxd r12,r12d
    59:	4d 63 e4             	movsxd r12,r12d
    5c:	4d 63 e4             	movsxd r12,r12d
    5f:	4d 63 e4             	movsxd r12,r12d
    62:	4d 63 e4             	movsxd r12,r12d
    65:	4d 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • MPERF: 36.61
  • APERF: 42.0
  • UOPS: 39.0

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;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;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: ≥33
• 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 63 e4             	movsxd r12,r12d
    32:	4d 63 e4             	movsxd r12,r12d
    35:	4d 63 e4             	movsxd r12,r12d
    38:	4d 63 e4             	movsxd r12,r12d
    3b:	4d 63 e4             	movsxd r12,r12d
    3e:	4d 63 e4             	movsxd r12,r12d
    41:	4d 63 e4             	movsxd r12,r12d
    44:	4d 63 e4             	movsxd r12,r12d
    47:	4d 63 e4             	movsxd r12,r12d
    4a:	4d 63 e4             	movsxd r12,r12d
    4d:	4d 63 e4             	movsxd r12,r12d
    50:	4d 63 e4             	movsxd r12,r12d
    53:	4d 63 e4             	movsxd r12,r12d
    56:	4d 63 e4             	movsxd r12,r12d
    59:	4d 63 e4             	movsxd r12,r12d
    5c:	4d 63 e4             	movsxd r12,r12d
    5f:	4d 63 e4             	movsxd r12,r12d
    62:	4d 63 e4             	movsxd r12,r12d
    65:	4d 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • MPERF: 36.72
  • APERF: 42.0
  • UOPS: 39.0

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;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;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: ≥33
• 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 63 e4             	movsxd r12,r12d
    32:	4d 63 e4             	movsxd r12,r12d
    35:	4d 63 e4             	movsxd r12,r12d
    38:	4d 63 e4             	movsxd r12,r12d
    3b:	4d 63 e4             	movsxd r12,r12d
    3e:	4d 63 e4             	movsxd r12,r12d
    41:	4d 63 e4             	movsxd r12,r12d
    44:	4d 63 e4             	movsxd r12,r12d
    47:	4d 63 e4             	movsxd r12,r12d
    4a:	4d 63 e4             	movsxd r12,r12d
    4d:	4d 63 e4             	movsxd r12,r12d
    50:	4d 63 e4             	movsxd r12,r12d
    53:	4d 63 e4             	movsxd r12,r12d
    56:	4d 63 e4             	movsxd r12,r12d
    59:	4d 63 e4             	movsxd r12,r12d
    5c:	4d 63 e4             	movsxd r12,r12d
    5f:	4d 63 e4             	movsxd r12,r12d
    62:	4d 63 e4             	movsxd r12,r12d
    65:	4d 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • MPERF: 36.61
  • APERF: 42.0
  • UOPS: 39.0

Experiment 1 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVZ R14, R14
• Chain latency: 1
• 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:
  • MPERF: 24.2
  • APERF: 27.8
  • UOPS: 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: 1
• 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:
  • MPERF: 25.1
  • APERF: 28.75
  • UOPS: 8.0

Experiment 3 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVZ R14, R14
• Chain latency: 1
• 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:
  • MPERF: 24.2
  • APERF: 27.8
  • UOPS: 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: 1
• 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:
  • MPERF: 25.1
  • APERF: 28.75
  • UOPS: 8.0

Experiment 5 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVZ R14, R14
• Chain latency: 1
• 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:
  • MPERF: 24.25
  • APERF: 27.8
  • UOPS: 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: 1
• 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:
  • MPERF: 25.16
  • APERF: 28.75
  • UOPS: 8.0

Experiment 7 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVS R14, R14
• Chain latency: 1
• 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:
  • MPERF: 24.2
  • APERF: 27.8
  • UOPS: 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: 1
• 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:
  • MPERF: 25.1
  • APERF: 28.75
  • UOPS: 8.0

Experiment 9 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVS R14, R14
• Chain latency: 1
• 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:
  • MPERF: 24.2
  • APERF: 27.8
  • UOPS: 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: 1
• 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:
  • MPERF: 25.1
  • APERF: 28.75
  • UOPS: 8.0

Experiment 11 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVS R14, R14
• Chain latency: 1
• 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:
  • MPERF: 24.2
  • APERF: 27.8
  • UOPS: 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: 1
• 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:
  • MPERF: 25.16
  • APERF: 28.75
  • UOPS: 8.0

Experiment 13 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVO R14, R14
• Chain latency: 1
• 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:
  • MPERF: 24.2
  • APERF: 27.8
  • UOPS: 7.0

Experiment 14 (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: 1
• 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:
  • MPERF: 25.05
  • APERF: 28.75
  • UOPS: 8.0

Experiment 15 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVO R14, R14
• Chain latency: 1
• 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:
  • MPERF: 24.25
  • APERF: 27.8
  • UOPS: 7.0

Experiment 16 (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: 1
• 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:
  • MPERF: 25.16
  • APERF: 28.75
  • UOPS: 8.0

Experiment 17 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVO R14, R14
• Chain latency: 1
• 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:
  • MPERF: 24.25
  • APERF: 27.8
  • UOPS: 7.0

Experiment 18 (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: 1
• 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:
  • MPERF: 25.05
  • APERF: 28.75
  • UOPS: 8.0

Experiment 19 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVP R14, R14
• Chain latency: 1
• 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:
  • MPERF: 24.25
  • APERF: 27.8
  • UOPS: 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: 1
• 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:
  • MPERF: 25.16
  • APERF: 28.75
  • UOPS: 8.0

Experiment 21 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVP R14, R14
• Chain latency: 1
• 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:
  • MPERF: 24.25
  • APERF: 27.8
  • UOPS: 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: 1
• 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:
  • MPERF: 25.16
  • APERF: 28.75
  • UOPS: 8.0

Experiment 23 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVP R14, R14
• Chain latency: 1
• 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:
  • MPERF: 24.2
  • APERF: 27.8
  • UOPS: 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: 1
• 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:
  • MPERF: 25.1
  • APERF: 28.75
  • UOPS: 8.0

Experiment 25 (with R8=0)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVC R14, R14
• Chain latency: 1
• 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:
  • MPERF: 24.31
  • APERF: 27.8
  • UOPS: 7.0

Experiment 26 (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: 1
• 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:
  • MPERF: 25.1
  • APERF: 28.75
  • UOPS: 8.0

Experiment 27 (with R8=1)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVC R14, R14
• Chain latency: 1
• 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:
  • MPERF: 24.2
  • APERF: 27.8
  • UOPS: 7.0

Experiment 28 (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: 1
• 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:
  • MPERF: 25.16
  • APERF: 28.75
  • UOPS: 8.0

Experiment 29 (with R8=2)

• Instruction: LOCK CMPXCHG qword ptr [R14], R8
• Chain instruction: CMOVC R14, R14
• Chain latency: 1
• 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:
  • MPERF: 24.25
  • APERF: 27.8
  • UOPS: 7.0

Experiment 30 (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: 1
• 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:
  • MPERF: 25.1
  • APERF: 28.75
  • UOPS: 8.0

Experiment 1

• Instruction: LOCK CMPXCHG qword ptr [R14+R13], R8
• Chain instruction: CMOVZ R13, R13
• Chain latency: 1
• 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:
  • MPERF: 24.2
  • APERF: 27.8
  • UOPS: 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: 1
• 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:
  • MPERF: 25.27
  • APERF: 29.0
  • UOPS: 8.0

Experiment 3

• Instruction: LOCK CMPXCHG qword ptr [R14+R13], R8
• Chain instruction: CMOVS R13, R13
• Chain latency: 1
• 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:
  • MPERF: 24.2
  • APERF: 27.8
  • UOPS: 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: 1
• 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:
  • MPERF: 25.44
  • APERF: 29.0
  • UOPS: 8.0

Experiment 5

• Instruction: LOCK CMPXCHG qword ptr [R14+R13], R8
• Chain instruction: CMOVO R13, R13
• Chain latency: 1
• 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:
  • MPERF: 24.2
  • APERF: 27.8
  • UOPS: 7.0

Experiment 6 (with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14+R13], R8
• Chain instructions: CMOVO R13, R13;MOV qword ptr [R14], 0
• Chain latency: 1
• 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:
  • MPERF: 25.33
  • APERF: 29.0
  • UOPS: 8.0

Experiment 7

• Instruction: LOCK CMPXCHG qword ptr [R14+R13], R8
• Chain instruction: CMOVP R13, R13
• Chain latency: 1
• 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:
  • MPERF: 24.25
  • APERF: 27.8
  • UOPS: 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: 1
• 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:
  • MPERF: 25.27
  • APERF: 29.0
  • UOPS: 8.0

Experiment 9

• Instruction: LOCK CMPXCHG qword ptr [R14+R13], R8
• Chain instruction: CMOVC R13, R13
• Chain latency: 1
• 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:
  • MPERF: 24.25
  • APERF: 27.8
  • UOPS: 7.0

Experiment 10 (with dependency-breaking instructions)

• Instruction: LOCK CMPXCHG qword ptr [R14+R13], R8
• Chain instructions: CMOVC R13, R13;MOV qword ptr [R14], 0
• Chain latency: 1
• 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:
  • MPERF: 25.39
  • APERF: 29.0
  • UOPS: 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;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;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: ≥34
• 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 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	4d 63 e4             	movsxd r12,r12d
    54:	4d 63 e4             	movsxd r12,r12d
    57:	4d 63 e4             	movsxd r12,r12d
    5a:	4d 63 e4             	movsxd r12,r12d
    5d:	4d 63 e4             	movsxd r12,r12d
    60:	4d 63 e4             	movsxd r12,r12d
    63:	4d 63 e4             	movsxd r12,r12d
    66:	4d 63 e4             	movsxd r12,r12d
    69:	4d 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • MPERF: 36.38
  • APERF: 41.71
  • UOPS: 40.0

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;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;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: ≥34
• 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 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	4d 63 e4             	movsxd r12,r12d
    54:	4d 63 e4             	movsxd r12,r12d
    57:	4d 63 e4             	movsxd r12,r12d
    5a:	4d 63 e4             	movsxd r12,r12d
    5d:	4d 63 e4             	movsxd r12,r12d
    60:	4d 63 e4             	movsxd r12,r12d
    63:	4d 63 e4             	movsxd r12,r12d
    66:	4d 63 e4             	movsxd r12,r12d
    69:	4d 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • MPERF: 36.38
  • APERF: 41.71
  • UOPS: 40.0

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;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;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: ≥34
• 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 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	4d 63 e4             	movsxd r12,r12d
    54:	4d 63 e4             	movsxd r12,r12d
    57:	4d 63 e4             	movsxd r12,r12d
    5a:	4d 63 e4             	movsxd r12,r12d
    5d:	4d 63 e4             	movsxd r12,r12d
    60:	4d 63 e4             	movsxd r12,r12d
    63:	4d 63 e4             	movsxd r12,r12d
    66:	4d 63 e4             	movsxd r12,r12d
    69:	4d 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • MPERF: 36.38
  • APERF: 41.71
  • UOPS: 40.0

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;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;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: ≥34
• 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 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	4d 63 e4             	movsxd r12,r12d
    54:	4d 63 e4             	movsxd r12,r12d
    57:	4d 63 e4             	movsxd r12,r12d
    5a:	4d 63 e4             	movsxd r12,r12d
    5d:	4d 63 e4             	movsxd r12,r12d
    60:	4d 63 e4             	movsxd r12,r12d
    63:	4d 63 e4             	movsxd r12,r12d
    66:	4d 63 e4             	movsxd r12,r12d
    69:	4d 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • MPERF: 36.38
  • APERF: 41.71
  • UOPS: 40.0

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;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;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: ≥34
• 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 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	4d 63 e4             	movsxd r12,r12d
    54:	4d 63 e4             	movsxd r12,r12d
    57:	4d 63 e4             	movsxd r12,r12d
    5a:	4d 63 e4             	movsxd r12,r12d
    5d:	4d 63 e4             	movsxd r12,r12d
    60:	4d 63 e4             	movsxd r12,r12d
    63:	4d 63 e4             	movsxd r12,r12d
    66:	4d 63 e4             	movsxd r12,r12d
    69:	4d 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • MPERF: 36.38
  • APERF: 41.71
  • UOPS: 40.0

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;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;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: ≥34
• 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 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	4d 63 e4             	movsxd r12,r12d
    54:	4d 63 e4             	movsxd r12,r12d
    57:	4d 63 e4             	movsxd r12,r12d
    5a:	4d 63 e4             	movsxd r12,r12d
    5d:	4d 63 e4             	movsxd r12,r12d
    60:	4d 63 e4             	movsxd r12,r12d
    63:	4d 63 e4             	movsxd r12,r12d
    66:	4d 63 e4             	movsxd r12,r12d
    69:	4d 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • MPERF: 36.38
  • APERF: 41.71
  • UOPS: 40.0

Experiment 7 (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;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;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: ≥34
• 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 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	4d 63 e4             	movsxd r12,r12d
    54:	4d 63 e4             	movsxd r12,r12d
    57:	4d 63 e4             	movsxd r12,r12d
    5a:	4d 63 e4             	movsxd r12,r12d
    5d:	4d 63 e4             	movsxd r12,r12d
    60:	4d 63 e4             	movsxd r12,r12d
    63:	4d 63 e4             	movsxd r12,r12d
    66:	4d 63 e4             	movsxd r12,r12d
    69:	4d 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • MPERF: 36.38
  • APERF: 41.71
  • UOPS: 40.0

Experiment 8 (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;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;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: ≥34
• 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 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	4d 63 e4             	movsxd r12,r12d
    54:	4d 63 e4             	movsxd r12,r12d
    57:	4d 63 e4             	movsxd r12,r12d
    5a:	4d 63 e4             	movsxd r12,r12d
    5d:	4d 63 e4             	movsxd r12,r12d
    60:	4d 63 e4             	movsxd r12,r12d
    63:	4d 63 e4             	movsxd r12,r12d
    66:	4d 63 e4             	movsxd r12,r12d
    69:	4d 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • MPERF: 36.44
  • APERF: 41.71
  • UOPS: 40.0

Experiment 9 (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;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;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: ≥34
• 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 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	4d 63 e4             	movsxd r12,r12d
    54:	4d 63 e4             	movsxd r12,r12d
    57:	4d 63 e4             	movsxd r12,r12d
    5a:	4d 63 e4             	movsxd r12,r12d
    5d:	4d 63 e4             	movsxd r12,r12d
    60:	4d 63 e4             	movsxd r12,r12d
    63:	4d 63 e4             	movsxd r12,r12d
    66:	4d 63 e4             	movsxd r12,r12d
    69:	4d 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • MPERF: 36.38
  • APERF: 41.71
  • UOPS: 40.0

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;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;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: ≥34
• 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 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	4d 63 e4             	movsxd r12,r12d
    54:	4d 63 e4             	movsxd r12,r12d
    57:	4d 63 e4             	movsxd r12,r12d
    5a:	4d 63 e4             	movsxd r12,r12d
    5d:	4d 63 e4             	movsxd r12,r12d
    60:	4d 63 e4             	movsxd r12,r12d
    63:	4d 63 e4             	movsxd r12,r12d
    66:	4d 63 e4             	movsxd r12,r12d
    69:	4d 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • MPERF: 36.44
  • APERF: 41.71
  • UOPS: 40.0

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;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;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: ≥34
• 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 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	4d 63 e4             	movsxd r12,r12d
    54:	4d 63 e4             	movsxd r12,r12d
    57:	4d 63 e4             	movsxd r12,r12d
    5a:	4d 63 e4             	movsxd r12,r12d
    5d:	4d 63 e4             	movsxd r12,r12d
    60:	4d 63 e4             	movsxd r12,r12d
    63:	4d 63 e4             	movsxd r12,r12d
    66:	4d 63 e4             	movsxd r12,r12d
    69:	4d 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • MPERF: 36.38
  • APERF: 41.71
  • UOPS: 40.0

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;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;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: ≥34
• 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 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	4d 63 e4             	movsxd r12,r12d
    54:	4d 63 e4             	movsxd r12,r12d
    57:	4d 63 e4             	movsxd r12,r12d
    5a:	4d 63 e4             	movsxd r12,r12d
    5d:	4d 63 e4             	movsxd r12,r12d
    60:	4d 63 e4             	movsxd r12,r12d
    63:	4d 63 e4             	movsxd r12,r12d
    66:	4d 63 e4             	movsxd r12,r12d
    69:	4d 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • MPERF: 36.38
  • APERF: 41.71
  • UOPS: 40.0

Experiment 13 (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;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;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: ≥34
• 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 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	4d 63 e4             	movsxd r12,r12d
    54:	4d 63 e4             	movsxd r12,r12d
    57:	4d 63 e4             	movsxd r12,r12d
    5a:	4d 63 e4             	movsxd r12,r12d
    5d:	4d 63 e4             	movsxd r12,r12d
    60:	4d 63 e4             	movsxd r12,r12d
    63:	4d 63 e4             	movsxd r12,r12d
    66:	4d 63 e4             	movsxd r12,r12d
    69:	4d 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • MPERF: 36.38
  • APERF: 41.71
  • UOPS: 40.0

Experiment 14 (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;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;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: ≥34
• 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 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	4d 63 e4             	movsxd r12,r12d
    54:	4d 63 e4             	movsxd r12,r12d
    57:	4d 63 e4             	movsxd r12,r12d
    5a:	4d 63 e4             	movsxd r12,r12d
    5d:	4d 63 e4             	movsxd r12,r12d
    60:	4d 63 e4             	movsxd r12,r12d
    63:	4d 63 e4             	movsxd r12,r12d
    66:	4d 63 e4             	movsxd r12,r12d
    69:	4d 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • MPERF: 36.49
  • APERF: 41.71
  • UOPS: 40.0

Experiment 15 (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;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;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: ≥34
• 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 63 e4             	movsxd r12,r12d
    36:	4d 63 e4             	movsxd r12,r12d
    39:	4d 63 e4             	movsxd r12,r12d
    3c:	4d 63 e4             	movsxd r12,r12d
    3f:	4d 63 e4             	movsxd r12,r12d
    42:	4d 63 e4             	movsxd r12,r12d
    45:	4d 63 e4             	movsxd r12,r12d
    48:	4d 63 e4             	movsxd r12,r12d
    4b:	4d 63 e4             	movsxd r12,r12d
    4e:	4d 63 e4             	movsxd r12,r12d
    51:	4d 63 e4             	movsxd r12,r12d
    54:	4d 63 e4             	movsxd r12,r12d
    57:	4d 63 e4             	movsxd r12,r12d
    5a:	4d 63 e4             	movsxd r12,r12d
    5d:	4d 63 e4             	movsxd r12,r12d
    60:	4d 63 e4             	movsxd r12,r12d
    63:	4d 63 e4             	movsxd r12,r12d
    66:	4d 63 e4             	movsxd r12,r12d
    69:	4d 89 26             	mov    QWORD PTR [r14],r12
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • MPERF: 36.38
  • APERF: 41.71
  • UOPS: 40.0

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;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
• Chain latency: ≥33
• 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
    32:	4d 63 c0             	movsxd r8,r8d
    35:	4d 63 c0             	movsxd r8,r8d
    38:	4d 63 c0             	movsxd r8,r8d
    3b:	4d 63 c0             	movsxd r8,r8d
    3e:	4d 63 c0             	movsxd r8,r8d
    41:	4d 63 c0             	movsxd r8,r8d
    44:	4d 63 c0             	movsxd r8,r8d
    47:	4d 63 c0             	movsxd r8,r8d
    4a:	4d 63 c0             	movsxd r8,r8d
    4d:	4d 63 c0             	movsxd r8,r8d
    50:	4d 63 c0             	movsxd r8,r8d
    53:	4d 63 c0             	movsxd r8,r8d
    56:	4d 63 c0             	movsxd r8,r8d
    59:	4d 63 c0             	movsxd r8,r8d
    5c:	4d 63 c0             	movsxd r8,r8d
    5f:	4d 63 c0             	movsxd r8,r8d
    62:	4d 63 c0             	movsxd r8,r8d
    65:	4d 63 c0             	movsxd r8,r8d
  

• Show nanoBench command
• Results:
  • MPERF: 34.74
  • APERF: 39.99
  • UOPS: 39.0

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;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
• Chain latency: 33
• 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
    32:	4d 63 c0             	movsxd r8,r8d
    35:	4d 63 c0             	movsxd r8,r8d
    38:	4d 63 c0             	movsxd r8,r8d
    3b:	4d 63 c0             	movsxd r8,r8d
    3e:	4d 63 c0             	movsxd r8,r8d
    41:	4d 63 c0             	movsxd r8,r8d
    44:	4d 63 c0             	movsxd r8,r8d
    47:	4d 63 c0             	movsxd r8,r8d
    4a:	4d 63 c0             	movsxd r8,r8d
    4d:	4d 63 c0             	movsxd r8,r8d
    50:	4d 63 c0             	movsxd r8,r8d
    53:	4d 63 c0             	movsxd r8,r8d
    56:	4d 63 c0             	movsxd r8,r8d
    59:	4d 63 c0             	movsxd r8,r8d
    5c:	4d 63 c0             	movsxd r8,r8d
    5f:	4d 63 c0             	movsxd r8,r8d
    62:	4d 63 c0             	movsxd r8,r8d
    65:	4d 63 c0             	movsxd r8,r8d
  

• Show nanoBench command
• Results:
  • MPERF: 20.46
  • APERF: 23.5
  • UOPS: 39.0

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;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
• Chain latency: 34
• 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
    36:	4d 63 c0             	movsxd r8,r8d
    39:	4d 63 c0             	movsxd r8,r8d
    3c:	4d 63 c0             	movsxd r8,r8d
    3f:	4d 63 c0             	movsxd r8,r8d
    42:	4d 63 c0             	movsxd r8,r8d
    45:	4d 63 c0             	movsxd r8,r8d
    48:	4d 63 c0             	movsxd r8,r8d
    4b:	4d 63 c0             	movsxd r8,r8d
    4e:	4d 63 c0             	movsxd r8,r8d
    51:	4d 63 c0             	movsxd r8,r8d
    54:	4d 63 c0             	movsxd r8,r8d
    57:	4d 63 c0             	movsxd r8,r8d
    5a:	4d 63 c0             	movsxd r8,r8d
    5d:	4d 63 c0             	movsxd r8,r8d
    60:	4d 63 c0             	movsxd r8,r8d
    63:	4d 63 c0             	movsxd r8,r8d
    66:	4d 63 c0             	movsxd r8,r8d
    69:	4d 63 c0             	movsxd r8,r8d
  

• Show nanoBench command
• Results:
  • MPERF: 20.57
  • APERF: 23.59
  • UOPS: 40.0

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;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
• Chain latency: 34
• 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
    36:	4d 63 c0             	movsxd r8,r8d
    39:	4d 63 c0             	movsxd r8,r8d
    3c:	4d 63 c0             	movsxd r8,r8d
    3f:	4d 63 c0             	movsxd r8,r8d
    42:	4d 63 c0             	movsxd r8,r8d
    45:	4d 63 c0             	movsxd r8,r8d
    48:	4d 63 c0             	movsxd r8,r8d
    4b:	4d 63 c0             	movsxd r8,r8d
    4e:	4d 63 c0             	movsxd r8,r8d
    51:	4d 63 c0             	movsxd r8,r8d
    54:	4d 63 c0             	movsxd r8,r8d
    57:	4d 63 c0             	movsxd r8,r8d
    5a:	4d 63 c0             	movsxd r8,r8d
    5d:	4d 63 c0             	movsxd r8,r8d
    60:	4d 63 c0             	movsxd r8,r8d
    63:	4d 63 c0             	movsxd r8,r8d
    66:	4d 63 c0             	movsxd r8,r8d
    69:	4d 63 c0             	movsxd r8,r8d
  

• Show nanoBench command
• Results:
  • MPERF: 20.57
  • APERF: 23.59
  • UOPS: 40.0

Experiment 3

• 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;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
• Chain latency: 34
• 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
    36:	4d 63 c0             	movsxd r8,r8d
    39:	4d 63 c0             	movsxd r8,r8d
    3c:	4d 63 c0             	movsxd r8,r8d
    3f:	4d 63 c0             	movsxd r8,r8d
    42:	4d 63 c0             	movsxd r8,r8d
    45:	4d 63 c0             	movsxd r8,r8d
    48:	4d 63 c0             	movsxd r8,r8d
    4b:	4d 63 c0             	movsxd r8,r8d
    4e:	4d 63 c0             	movsxd r8,r8d
    51:	4d 63 c0             	movsxd r8,r8d
    54:	4d 63 c0             	movsxd r8,r8d
    57:	4d 63 c0             	movsxd r8,r8d
    5a:	4d 63 c0             	movsxd r8,r8d
    5d:	4d 63 c0             	movsxd r8,r8d
    60:	4d 63 c0             	movsxd r8,r8d
    63:	4d 63 c0             	movsxd r8,r8d
    66:	4d 63 c0             	movsxd r8,r8d
    69:	4d 63 c0             	movsxd r8,r8d
  

• Show nanoBench command
• Results:
  • MPERF: 20.57
  • APERF: 23.59
  • UOPS: 40.0

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;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
• Chain latency: 34
• 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
    36:	4d 63 c0             	movsxd r8,r8d
    39:	4d 63 c0             	movsxd r8,r8d
    3c:	4d 63 c0             	movsxd r8,r8d
    3f:	4d 63 c0             	movsxd r8,r8d
    42:	4d 63 c0             	movsxd r8,r8d
    45:	4d 63 c0             	movsxd r8,r8d
    48:	4d 63 c0             	movsxd r8,r8d
    4b:	4d 63 c0             	movsxd r8,r8d
    4e:	4d 63 c0             	movsxd r8,r8d
    51:	4d 63 c0             	movsxd r8,r8d
    54:	4d 63 c0             	movsxd r8,r8d
    57:	4d 63 c0             	movsxd r8,r8d
    5a:	4d 63 c0             	movsxd r8,r8d
    5d:	4d 63 c0             	movsxd r8,r8d
    60:	4d 63 c0             	movsxd r8,r8d
    63:	4d 63 c0             	movsxd r8,r8d
    66:	4d 63 c0             	movsxd r8,r8d
    69:	4d 63 c0             	movsxd r8,r8d
  

• Show nanoBench command
• Results:
  • MPERF: 20.51
  • APERF: 23.59
  • UOPS: 40.0

Experiment 5

• 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;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
• Chain latency: 34
• 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
    36:	4d 63 c0             	movsxd r8,r8d
    39:	4d 63 c0             	movsxd r8,r8d
    3c:	4d 63 c0             	movsxd r8,r8d
    3f:	4d 63 c0             	movsxd r8,r8d
    42:	4d 63 c0             	movsxd r8,r8d
    45:	4d 63 c0             	movsxd r8,r8d
    48:	4d 63 c0             	movsxd r8,r8d
    4b:	4d 63 c0             	movsxd r8,r8d
    4e:	4d 63 c0             	movsxd r8,r8d
    51:	4d 63 c0             	movsxd r8,r8d
    54:	4d 63 c0             	movsxd r8,r8d
    57:	4d 63 c0             	movsxd r8,r8d
    5a:	4d 63 c0             	movsxd r8,r8d
    5d:	4d 63 c0             	movsxd r8,r8d
    60:	4d 63 c0             	movsxd r8,r8d
    63:	4d 63 c0             	movsxd r8,r8d
    66:	4d 63 c0             	movsxd r8,r8d
    69:	4d 63 c0             	movsxd r8,r8d
  

• Show nanoBench command
• Results:
  • MPERF: 20.63
  • APERF: 23.59
  • UOPS: 40.0

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;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;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: ≥33
• 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
    32:	48 63 c0             	movsxd rax,eax
    35:	48 63 c0             	movsxd rax,eax
    38:	48 63 c0             	movsxd rax,eax
    3b:	48 63 c0             	movsxd rax,eax
    3e:	48 63 c0             	movsxd rax,eax
    41:	48 63 c0             	movsxd rax,eax
    44:	48 63 c0             	movsxd rax,eax
    47:	48 63 c0             	movsxd rax,eax
    4a:	48 63 c0             	movsxd rax,eax
    4d:	48 63 c0             	movsxd rax,eax
    50:	48 63 c0             	movsxd rax,eax
    53:	48 63 c0             	movsxd rax,eax
    56:	48 63 c0             	movsxd rax,eax
    59:	48 63 c0             	movsxd rax,eax
    5c:	48 63 c0             	movsxd rax,eax
    5f:	48 63 c0             	movsxd rax,eax
    62:	48 63 c0             	movsxd rax,eax
    65:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • MPERF: 36.04
  • APERF: 41.18
  • UOPS: 39.0

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;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;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: ≥33
• 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
    32:	48 63 c0             	movsxd rax,eax
    35:	48 63 c0             	movsxd rax,eax
    38:	48 63 c0             	movsxd rax,eax
    3b:	48 63 c0             	movsxd rax,eax
    3e:	48 63 c0             	movsxd rax,eax
    41:	48 63 c0             	movsxd rax,eax
    44:	48 63 c0             	movsxd rax,eax
    47:	48 63 c0             	movsxd rax,eax
    4a:	48 63 c0             	movsxd rax,eax
    4d:	48 63 c0             	movsxd rax,eax
    50:	48 63 c0             	movsxd rax,eax
    53:	48 63 c0             	movsxd rax,eax
    56:	48 63 c0             	movsxd rax,eax
    59:	48 63 c0             	movsxd rax,eax
    5c:	48 63 c0             	movsxd rax,eax
    5f:	48 63 c0             	movsxd rax,eax
    62:	48 63 c0             	movsxd rax,eax
    65:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • MPERF: 36.04
  • APERF: 41.18
  • UOPS: 39.0

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;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;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: ≥33
• 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
    32:	48 63 c0             	movsxd rax,eax
    35:	48 63 c0             	movsxd rax,eax
    38:	48 63 c0             	movsxd rax,eax
    3b:	48 63 c0             	movsxd rax,eax
    3e:	48 63 c0             	movsxd rax,eax
    41:	48 63 c0             	movsxd rax,eax
    44:	48 63 c0             	movsxd rax,eax
    47:	48 63 c0             	movsxd rax,eax
    4a:	48 63 c0             	movsxd rax,eax
    4d:	48 63 c0             	movsxd rax,eax
    50:	48 63 c0             	movsxd rax,eax
    53:	48 63 c0             	movsxd rax,eax
    56:	48 63 c0             	movsxd rax,eax
    59:	48 63 c0             	movsxd rax,eax
    5c:	48 63 c0             	movsxd rax,eax
    5f:	48 63 c0             	movsxd rax,eax
    62:	48 63 c0             	movsxd rax,eax
    65:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • MPERF: 35.98
  • APERF: 41.18
  • UOPS: 39.0

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;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;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: 33
• 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
    32:	48 63 c0             	movsxd rax,eax
    35:	48 63 c0             	movsxd rax,eax
    38:	48 63 c0             	movsxd rax,eax
    3b:	48 63 c0             	movsxd rax,eax
    3e:	48 63 c0             	movsxd rax,eax
    41:	48 63 c0             	movsxd rax,eax
    44:	48 63 c0             	movsxd rax,eax
    47:	48 63 c0             	movsxd rax,eax
    4a:	48 63 c0             	movsxd rax,eax
    4d:	48 63 c0             	movsxd rax,eax
    50:	48 63 c0             	movsxd rax,eax
    53:	48 63 c0             	movsxd rax,eax
    56:	48 63 c0             	movsxd rax,eax
    59:	48 63 c0             	movsxd rax,eax
    5c:	48 63 c0             	movsxd rax,eax
    5f:	48 63 c0             	movsxd rax,eax
    62:	48 63 c0             	movsxd rax,eax
    65:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • MPERF: 31.11
  • APERF: 35.62
  • UOPS: 39.0

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;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;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: 33
• 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
    32:	48 63 c0             	movsxd rax,eax
    35:	48 63 c0             	movsxd rax,eax
    38:	48 63 c0             	movsxd rax,eax
    3b:	48 63 c0             	movsxd rax,eax
    3e:	48 63 c0             	movsxd rax,eax
    41:	48 63 c0             	movsxd rax,eax
    44:	48 63 c0             	movsxd rax,eax
    47:	48 63 c0             	movsxd rax,eax
    4a:	48 63 c0             	movsxd rax,eax
    4d:	48 63 c0             	movsxd rax,eax
    50:	48 63 c0             	movsxd rax,eax
    53:	48 63 c0             	movsxd rax,eax
    56:	48 63 c0             	movsxd rax,eax
    59:	48 63 c0             	movsxd rax,eax
    5c:	48 63 c0             	movsxd rax,eax
    5f:	48 63 c0             	movsxd rax,eax
    62:	48 63 c0             	movsxd rax,eax
    65:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • MPERF: 31.11
  • APERF: 35.62
  • UOPS: 39.0

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;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;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: 33
• 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
    32:	48 63 c0             	movsxd rax,eax
    35:	48 63 c0             	movsxd rax,eax
    38:	48 63 c0             	movsxd rax,eax
    3b:	48 63 c0             	movsxd rax,eax
    3e:	48 63 c0             	movsxd rax,eax
    41:	48 63 c0             	movsxd rax,eax
    44:	48 63 c0             	movsxd rax,eax
    47:	48 63 c0             	movsxd rax,eax
    4a:	48 63 c0             	movsxd rax,eax
    4d:	48 63 c0             	movsxd rax,eax
    50:	48 63 c0             	movsxd rax,eax
    53:	48 63 c0             	movsxd rax,eax
    56:	48 63 c0             	movsxd rax,eax
    59:	48 63 c0             	movsxd rax,eax
    5c:	48 63 c0             	movsxd rax,eax
    5f:	48 63 c0             	movsxd rax,eax
    62:	48 63 c0             	movsxd rax,eax
    65:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • MPERF: 31.05
  • APERF: 35.62
  • UOPS: 39.0

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:
  • MPERF: 24.48
  • APERF: 28.04
  • UOPS: 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:
  • MPERF: 25.16
  • APERF: 28.75
  • UOPS: 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:
  • MPERF: 24.48
  • APERF: 28.04
  • UOPS: 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:
  • MPERF: 25.16
  • APERF: 28.75
  • UOPS: 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:
  • MPERF: 24.48
  • APERF: 28.04
  • UOPS: 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:
  • MPERF: 25.16
  • APERF: 28.75
  • UOPS: 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;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;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: 34
• 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
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
    54:	48 63 c0             	movsxd rax,eax
    57:	48 63 c0             	movsxd rax,eax
    5a:	48 63 c0             	movsxd rax,eax
    5d:	48 63 c0             	movsxd rax,eax
    60:	48 63 c0             	movsxd rax,eax
    63:	48 63 c0             	movsxd rax,eax
    66:	48 63 c0             	movsxd rax,eax
    69:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • MPERF: 30.88
  • APERF: 35.42
  • UOPS: 40.0

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;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;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: 34
• 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
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
    54:	48 63 c0             	movsxd rax,eax
    57:	48 63 c0             	movsxd rax,eax
    5a:	48 63 c0             	movsxd rax,eax
    5d:	48 63 c0             	movsxd rax,eax
    60:	48 63 c0             	movsxd rax,eax
    63:	48 63 c0             	movsxd rax,eax
    66:	48 63 c0             	movsxd rax,eax
    69:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • MPERF: 30.83
  • APERF: 35.42
  • UOPS: 40.0

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;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;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: 34
• 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
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
    54:	48 63 c0             	movsxd rax,eax
    57:	48 63 c0             	movsxd rax,eax
    5a:	48 63 c0             	movsxd rax,eax
    5d:	48 63 c0             	movsxd rax,eax
    60:	48 63 c0             	movsxd rax,eax
    63:	48 63 c0             	movsxd rax,eax
    66:	48 63 c0             	movsxd rax,eax
    69:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • MPERF: 30.94
  • APERF: 35.42
  • UOPS: 40.0

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;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;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: 34
• 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
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
    54:	48 63 c0             	movsxd rax,eax
    57:	48 63 c0             	movsxd rax,eax
    5a:	48 63 c0             	movsxd rax,eax
    5d:	48 63 c0             	movsxd rax,eax
    60:	48 63 c0             	movsxd rax,eax
    63:	48 63 c0             	movsxd rax,eax
    66:	48 63 c0             	movsxd rax,eax
    69:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • MPERF: 30.83
  • APERF: 35.42
  • UOPS: 40.0

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;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;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: 34
• 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
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
    54:	48 63 c0             	movsxd rax,eax
    57:	48 63 c0             	movsxd rax,eax
    5a:	48 63 c0             	movsxd rax,eax
    5d:	48 63 c0             	movsxd rax,eax
    60:	48 63 c0             	movsxd rax,eax
    63:	48 63 c0             	movsxd rax,eax
    66:	48 63 c0             	movsxd rax,eax
    69:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • MPERF: 30.88
  • APERF: 35.42
  • UOPS: 40.0

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;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;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: 34
• 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
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
    54:	48 63 c0             	movsxd rax,eax
    57:	48 63 c0             	movsxd rax,eax
    5a:	48 63 c0             	movsxd rax,eax
    5d:	48 63 c0             	movsxd rax,eax
    60:	48 63 c0             	movsxd rax,eax
    63:	48 63 c0             	movsxd rax,eax
    66:	48 63 c0             	movsxd rax,eax
    69:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • MPERF: 30.77
  • APERF: 35.42
  • UOPS: 40.0

Experiment 7 (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;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;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: 34
• 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
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
    54:	48 63 c0             	movsxd rax,eax
    57:	48 63 c0             	movsxd rax,eax
    5a:	48 63 c0             	movsxd rax,eax
    5d:	48 63 c0             	movsxd rax,eax
    60:	48 63 c0             	movsxd rax,eax
    63:	48 63 c0             	movsxd rax,eax
    66:	48 63 c0             	movsxd rax,eax
    69:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • MPERF: 30.94
  • APERF: 35.42
  • UOPS: 40.0

Experiment 8 (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;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;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: 34
• 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
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
    54:	48 63 c0             	movsxd rax,eax
    57:	48 63 c0             	movsxd rax,eax
    5a:	48 63 c0             	movsxd rax,eax
    5d:	48 63 c0             	movsxd rax,eax
    60:	48 63 c0             	movsxd rax,eax
    63:	48 63 c0             	movsxd rax,eax
    66:	48 63 c0             	movsxd rax,eax
    69:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • MPERF: 30.77
  • APERF: 35.42
  • UOPS: 40.0

Experiment 9 (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;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;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: 34
• 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
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
    54:	48 63 c0             	movsxd rax,eax
    57:	48 63 c0             	movsxd rax,eax
    5a:	48 63 c0             	movsxd rax,eax
    5d:	48 63 c0             	movsxd rax,eax
    60:	48 63 c0             	movsxd rax,eax
    63:	48 63 c0             	movsxd rax,eax
    66:	48 63 c0             	movsxd rax,eax
    69:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • MPERF: 30.88
  • APERF: 35.42
  • UOPS: 40.0

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;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;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: 34
• 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
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
    54:	48 63 c0             	movsxd rax,eax
    57:	48 63 c0             	movsxd rax,eax
    5a:	48 63 c0             	movsxd rax,eax
    5d:	48 63 c0             	movsxd rax,eax
    60:	48 63 c0             	movsxd rax,eax
    63:	48 63 c0             	movsxd rax,eax
    66:	48 63 c0             	movsxd rax,eax
    69:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • MPERF: 30.83
  • APERF: 35.42
  • UOPS: 40.0

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;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;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: 34
• 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
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
    54:	48 63 c0             	movsxd rax,eax
    57:	48 63 c0             	movsxd rax,eax
    5a:	48 63 c0             	movsxd rax,eax
    5d:	48 63 c0             	movsxd rax,eax
    60:	48 63 c0             	movsxd rax,eax
    63:	48 63 c0             	movsxd rax,eax
    66:	48 63 c0             	movsxd rax,eax
    69:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • MPERF: 30.88
  • APERF: 35.42
  • UOPS: 40.0

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;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;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: 34
• 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
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
    54:	48 63 c0             	movsxd rax,eax
    57:	48 63 c0             	movsxd rax,eax
    5a:	48 63 c0             	movsxd rax,eax
    5d:	48 63 c0             	movsxd rax,eax
    60:	48 63 c0             	movsxd rax,eax
    63:	48 63 c0             	movsxd rax,eax
    66:	48 63 c0             	movsxd rax,eax
    69:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • MPERF: 30.77
  • APERF: 35.42
  • UOPS: 40.0

Experiment 13 (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;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;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: 34
• 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
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
    54:	48 63 c0             	movsxd rax,eax
    57:	48 63 c0             	movsxd rax,eax
    5a:	48 63 c0             	movsxd rax,eax
    5d:	48 63 c0             	movsxd rax,eax
    60:	48 63 c0             	movsxd rax,eax
    63:	48 63 c0             	movsxd rax,eax
    66:	48 63 c0             	movsxd rax,eax
    69:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8, 0

• Show nanoBench command
• Results:
  • MPERF: 30.88
  • APERF: 35.42
  • UOPS: 40.0

Experiment 14 (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;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;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: 34
• 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
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
    54:	48 63 c0             	movsxd rax,eax
    57:	48 63 c0             	movsxd rax,eax
    5a:	48 63 c0             	movsxd rax,eax
    5d:	48 63 c0             	movsxd rax,eax
    60:	48 63 c0             	movsxd rax,eax
    63:	48 63 c0             	movsxd rax,eax
    66:	48 63 c0             	movsxd rax,eax
    69:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8, 1

• Show nanoBench command
• Results:
  • MPERF: 30.83
  • APERF: 35.42
  • UOPS: 40.0

Experiment 15 (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;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;MOVSX RAX, EAX;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: 34
• 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
    36:	48 63 c0             	movsxd rax,eax
    39:	48 63 c0             	movsxd rax,eax
    3c:	48 63 c0             	movsxd rax,eax
    3f:	48 63 c0             	movsxd rax,eax
    42:	48 63 c0             	movsxd rax,eax
    45:	48 63 c0             	movsxd rax,eax
    48:	48 63 c0             	movsxd rax,eax
    4b:	48 63 c0             	movsxd rax,eax
    4e:	48 63 c0             	movsxd rax,eax
    51:	48 63 c0             	movsxd rax,eax
    54:	48 63 c0             	movsxd rax,eax
    57:	48 63 c0             	movsxd rax,eax
    5a:	48 63 c0             	movsxd rax,eax
    5d:	48 63 c0             	movsxd rax,eax
    60:	48 63 c0             	movsxd rax,eax
    63:	48 63 c0             	movsxd rax,eax
    66:	48 63 c0             	movsxd rax,eax
    69:	48 63 c0             	movsxd rax,eax
  

• Init:

  MOV R8, 2

• Show nanoBench command
• Results:
  • MPERF: 30.77
  • APERF: 35.42
  • UOPS: 40.0