IDIV (M32)

Experiment 1 (fast division)

Instruction: IDIV dword ptr [R14]
Chain instructions: MOVSX R12, EAX; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; ; MOV EAX, R8D;MOV EDX, R9D
Chain latency: 9

Code:

   0:	41 f7 3e             	idiv   DWORD PTR [r14]
   3:	4c 63 e0             	movsxd r12,eax
   6:	4d 31 e6             	xor    r14,r12
   9:	4d 31 e6             	xor    r14,r12
   c:	4d 31 e6             	xor    r14,r12
   f:	4d 31 e6             	xor    r14,r12
  12:	4d 31 e6             	xor    r14,r12
  15:	4d 31 e6             	xor    r14,r12
  18:	4d 31 e6             	xor    r14,r12
  1b:	4d 31 e6             	xor    r14,r12
  1e:	44 89 c0             	mov    eax,r8d
  21:	44 89 ca             	mov    edx,r9d

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV [R14], RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 12.0
- Core cycles: 24.63
- Reference cycles: 14.72
- UOPS_EXECUTED.THREAD: 15.97

Experiment 2 (slow division)

Instruction: IDIV dword ptr [R14]
Chain instructions: MOVSX R12, EAX; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; ; MOV EAX, R8D;MOV EDX, R9D
Chain latency: 9

Code:

   0:	41 f7 3e             	idiv   DWORD PTR [r14]
   3:	4c 63 e0             	movsxd r12,eax
   6:	4d 31 e6             	xor    r14,r12
   9:	4d 31 e6             	xor    r14,r12
   c:	4d 31 e6             	xor    r14,r12
   f:	4d 31 e6             	xor    r14,r12
  12:	4d 31 e6             	xor    r14,r12
  15:	4d 31 e6             	xor    r14,r12
  18:	4d 31 e6             	xor    r14,r12
  1b:	4d 31 e6             	xor    r14,r12
  1e:	44 89 c0             	mov    eax,r8d
  21:	44 89 ca             	mov    edx,r9d

Init:

MOV R8, 133;
MOV R9, 0x343a9ed7;
MOV RCX, 0x75e6e44f;
MOV [R14], RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 12.0
- Core cycles: 24.63
- Reference cycles: 14.6
- UOPS_EXECUTED.THREAD: 15.97

Latency operand 1 → 2 (address, index register): 15

Experiment 1 (fast division)

Instruction: IDIV dword ptr [R14]
Chain instructions: MOVSX R12, EAX; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; ; MOV EAX, R8D;MOV EDX, R9D
Chain latency: 9

Code:

   0:	41 f7 3e             	idiv   DWORD PTR [r14]
   3:	4c 63 e0             	movsxd r12,eax
   6:	4d 31 e6             	xor    r14,r12
   9:	4d 31 e6             	xor    r14,r12
   c:	4d 31 e6             	xor    r14,r12
   f:	4d 31 e6             	xor    r14,r12
  12:	4d 31 e6             	xor    r14,r12
  15:	4d 31 e6             	xor    r14,r12
  18:	4d 31 e6             	xor    r14,r12
  1b:	4d 31 e6             	xor    r14,r12
  1e:	44 89 c0             	mov    eax,r8d
  21:	44 89 ca             	mov    edx,r9d

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV [R14], RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 12.0
- Core cycles: 24.63
- Reference cycles: 14.84
- UOPS_EXECUTED.THREAD: 15.97

Experiment 2 (slow division)

Instruction: IDIV dword ptr [R14]
Chain instructions: MOVSX R12, EAX; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; ; MOV EAX, R8D;MOV EDX, R9D
Chain latency: 9

Code:

   0:	41 f7 3e             	idiv   DWORD PTR [r14]
   3:	4c 63 e0             	movsxd r12,eax
   6:	4d 31 e6             	xor    r14,r12
   9:	4d 31 e6             	xor    r14,r12
   c:	4d 31 e6             	xor    r14,r12
   f:	4d 31 e6             	xor    r14,r12
  12:	4d 31 e6             	xor    r14,r12
  15:	4d 31 e6             	xor    r14,r12
  18:	4d 31 e6             	xor    r14,r12
  1b:	4d 31 e6             	xor    r14,r12
  1e:	44 89 c0             	mov    eax,r8d
  21:	44 89 ca             	mov    edx,r9d

Init:

MOV R8, 133;
MOV R9, 0x343a9ed7;
MOV RCX, 0x75e6e44f;
MOV [R14], RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 12.0
- Core cycles: 24.63
- Reference cycles: 14.6
- UOPS_EXECUTED.THREAD: 15.97

Latency operand 1 → 3 (address, base register): 19

Experiment 1 (fast division)

Instruction: IDIV dword ptr [R14]
Chain instructions: MOVSX R12, EDX; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; ; MOV EAX, R8D;MOV EDX, R9D
Chain latency: 9

Code:

   0:	41 f7 3e             	idiv   DWORD PTR [r14]
   3:	4c 63 e2             	movsxd r12,edx
   6:	4d 31 e6             	xor    r14,r12
   9:	4d 31 e6             	xor    r14,r12
   c:	4d 31 e6             	xor    r14,r12
   f:	4d 31 e6             	xor    r14,r12
  12:	4d 31 e6             	xor    r14,r12
  15:	4d 31 e6             	xor    r14,r12
  18:	4d 31 e6             	xor    r14,r12
  1b:	4d 31 e6             	xor    r14,r12
  1e:	44 89 c0             	mov    eax,r8d
  21:	44 89 ca             	mov    edx,r9d

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV [R14], RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 12.0
- Core cycles: 28.02
- Reference cycles: 16.91
- UOPS_EXECUTED.THREAD: 15.97

Experiment 2 (slow division)

Instruction: IDIV dword ptr [R14]
Chain instructions: MOVSX R12, EDX; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; ; MOV EAX, R8D;MOV EDX, R9D
Chain latency: 9

Code:

   0:	41 f7 3e             	idiv   DWORD PTR [r14]
   3:	4c 63 e2             	movsxd r12,edx
   6:	4d 31 e6             	xor    r14,r12
   9:	4d 31 e6             	xor    r14,r12
   c:	4d 31 e6             	xor    r14,r12
   f:	4d 31 e6             	xor    r14,r12
  12:	4d 31 e6             	xor    r14,r12
  15:	4d 31 e6             	xor    r14,r12
  18:	4d 31 e6             	xor    r14,r12
  1b:	4d 31 e6             	xor    r14,r12
  1e:	44 89 c0             	mov    eax,r8d
  21:	44 89 ca             	mov    edx,r9d

Init:

MOV R8, 133;
MOV R9, 0x343a9ed7;
MOV RCX, 0x75e6e44f;
MOV [R14], RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 12.0
- Core cycles: 28.02
- Reference cycles: 16.79
- UOPS_EXECUTED.THREAD: 15.97

Latency operand 1 → 3 (address, index register): 19

Experiment 1 (fast division)

Instruction: IDIV dword ptr [R14]
Chain instructions: MOVSX R12, EDX; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; ; MOV EAX, R8D;MOV EDX, R9D
Chain latency: 9

Code:

   0:	41 f7 3e             	idiv   DWORD PTR [r14]
   3:	4c 63 e2             	movsxd r12,edx
   6:	4d 31 e6             	xor    r14,r12
   9:	4d 31 e6             	xor    r14,r12
   c:	4d 31 e6             	xor    r14,r12
   f:	4d 31 e6             	xor    r14,r12
  12:	4d 31 e6             	xor    r14,r12
  15:	4d 31 e6             	xor    r14,r12
  18:	4d 31 e6             	xor    r14,r12
  1b:	4d 31 e6             	xor    r14,r12
  1e:	44 89 c0             	mov    eax,r8d
  21:	44 89 ca             	mov    edx,r9d

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV [R14], RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 12.0
- Core cycles: 28.02
- Reference cycles: 16.79
- UOPS_EXECUTED.THREAD: 15.97

Experiment 2 (slow division)

Instruction: IDIV dword ptr [R14]
Chain instructions: MOVSX R12, EDX; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; ; MOV EAX, R8D;MOV EDX, R9D
Chain latency: 9

Code:

   0:	41 f7 3e             	idiv   DWORD PTR [r14]
   3:	4c 63 e2             	movsxd r12,edx
   6:	4d 31 e6             	xor    r14,r12
   9:	4d 31 e6             	xor    r14,r12
   c:	4d 31 e6             	xor    r14,r12
   f:	4d 31 e6             	xor    r14,r12
  12:	4d 31 e6             	xor    r14,r12
  15:	4d 31 e6             	xor    r14,r12
  18:	4d 31 e6             	xor    r14,r12
  1b:	4d 31 e6             	xor    r14,r12
  1e:	44 89 c0             	mov    eax,r8d
  21:	44 89 ca             	mov    edx,r9d

Init:

MOV R8, 133;
MOV R9, 0x343a9ed7;
MOV RCX, 0x75e6e44f;
MOV [R14], RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 12.0
- Core cycles: 28.02
- Reference cycles: 16.55
- UOPS_EXECUTED.THREAD: 15.97

Latency operand 2 → 2: 11

Experiment 1 (fast division)

Instruction: IDIV dword ptr [R14]
Chain instructions: AND EAX, R8D; OR EAX, R8D; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; ; MOV EDX, R9D
Chain latency: 10

Code:

   0:	41 f7 3e             	idiv   DWORD PTR [r14]
   3:	44 21 c0             	and    eax,r8d
   6:	44 09 c0             	or     eax,r8d
   9:	09 c0                	or     eax,eax
   b:	09 c0                	or     eax,eax
   d:	09 c0                	or     eax,eax
   f:	09 c0                	or     eax,eax
  11:	09 c0                	or     eax,eax
  13:	09 c0                	or     eax,eax
  15:	09 c0                	or     eax,eax
  17:	09 c0                	or     eax,eax
  19:	44 89 ca             	mov    edx,r9d

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV [R14], RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 12.0
- Core cycles: 21.62
- Reference cycles: 12.65
- UOPS_EXECUTED.THREAD: 16.0

Experiment 2 (slow division)

Instruction: IDIV dword ptr [R14]
Chain instructions: AND EAX, R8D; OR EAX, R8D; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; ; MOV EDX, R9D
Chain latency: 10

Code:

   0:	41 f7 3e             	idiv   DWORD PTR [r14]
   3:	44 21 c0             	and    eax,r8d
   6:	44 09 c0             	or     eax,r8d
   9:	09 c0                	or     eax,eax
   b:	09 c0                	or     eax,eax
   d:	09 c0                	or     eax,eax
   f:	09 c0                	or     eax,eax
  11:	09 c0                	or     eax,eax
  13:	09 c0                	or     eax,eax
  15:	09 c0                	or     eax,eax
  17:	09 c0                	or     eax,eax
  19:	44 89 ca             	mov    edx,r9d

Init:

MOV R8, 133;
MOV R9, 0x343a9ed7;
MOV RCX, 0x75e6e44f;
MOV [R14], RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 12.0
- Core cycles: 21.62
- Reference cycles: 12.65
- UOPS_EXECUTED.THREAD: 16.0

Latency operand 2 → 3: 15

Experiment 1 (fast division)

Instruction: IDIV dword ptr [R14]
Chain instructions: AND EAX, EDX; AND EAX, R8D; OR EAX, R8D; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; ; MOV EDX, R9D
Chain latency: 11

Code:

   0:	41 f7 3e             	idiv   DWORD PTR [r14]
   3:	21 d0                	and    eax,edx
   5:	44 21 c0             	and    eax,r8d
   8:	44 09 c0             	or     eax,r8d
   b:	09 c0                	or     eax,eax
   d:	09 c0                	or     eax,eax
   f:	09 c0                	or     eax,eax
  11:	09 c0                	or     eax,eax
  13:	09 c0                	or     eax,eax
  15:	09 c0                	or     eax,eax
  17:	09 c0                	or     eax,eax
  19:	09 c0                	or     eax,eax
  1b:	44 89 ca             	mov    edx,r9d

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV [R14], RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 13.0
- Core cycles: 26.0
- Reference cycles: 15.45
- UOPS_EXECUTED.THREAD: 17.0

Experiment 2 (slow division)

Instruction: IDIV dword ptr [R14]
Chain instructions: AND EAX, EDX; AND EAX, R8D; OR EAX, R8D; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; OR EAX, EAX; ; MOV EDX, R9D
Chain latency: 11

Code:

   0:	41 f7 3e             	idiv   DWORD PTR [r14]
   3:	21 d0                	and    eax,edx
   5:	44 21 c0             	and    eax,r8d
   8:	44 09 c0             	or     eax,r8d
   b:	09 c0                	or     eax,eax
   d:	09 c0                	or     eax,eax
   f:	09 c0                	or     eax,eax
  11:	09 c0                	or     eax,eax
  13:	09 c0                	or     eax,eax
  15:	09 c0                	or     eax,eax
  17:	09 c0                	or     eax,eax
  19:	09 c0                	or     eax,eax
  1b:	44 89 ca             	mov    edx,r9d

Init:

MOV R8, 133;
MOV R9, 0x343a9ed7;
MOV RCX, 0x75e6e44f;
MOV [R14], RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 13.0
- Core cycles: 26.0
- Reference cycles: 15.57
- UOPS_EXECUTED.THREAD: 17.0

Latency operand 3 → 2: 15

Experiment 1 (fast division)

Instruction: IDIV dword ptr [R14]
Chain instructions: AND EDX, EAX; AND EDX, R9D; OR EDX, R9D; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; ; MOV EAX, R8D
Chain latency: 11

Code:

   0:	41 f7 3e             	idiv   DWORD PTR [r14]
   3:	21 c2                	and    edx,eax
   5:	44 21 ca             	and    edx,r9d
   8:	44 09 ca             	or     edx,r9d
   b:	09 d2                	or     edx,edx
   d:	09 d2                	or     edx,edx
   f:	09 d2                	or     edx,edx
  11:	09 d2                	or     edx,edx
  13:	09 d2                	or     edx,edx
  15:	09 d2                	or     edx,edx
  17:	09 d2                	or     edx,edx
  19:	09 d2                	or     edx,edx
  1b:	44 89 c0             	mov    eax,r8d

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV [R14], RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 13.0
- Core cycles: 26.0
- Reference cycles: 15.57
- UOPS_EXECUTED.THREAD: 17.0

Experiment 2 (slow division)

Instruction: IDIV dword ptr [R14]
Chain instructions: AND EDX, EAX; AND EDX, R9D; OR EDX, R9D; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; ; MOV EAX, R8D
Chain latency: 11

Code:

   0:	41 f7 3e             	idiv   DWORD PTR [r14]
   3:	21 c2                	and    edx,eax
   5:	44 21 ca             	and    edx,r9d
   8:	44 09 ca             	or     edx,r9d
   b:	09 d2                	or     edx,edx
   d:	09 d2                	or     edx,edx
   f:	09 d2                	or     edx,edx
  11:	09 d2                	or     edx,edx
  13:	09 d2                	or     edx,edx
  15:	09 d2                	or     edx,edx
  17:	09 d2                	or     edx,edx
  19:	09 d2                	or     edx,edx
  1b:	44 89 c0             	mov    eax,r8d

Init:

MOV R8, 133;
MOV R9, 0x343a9ed7;
MOV RCX, 0x75e6e44f;
MOV [R14], RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 13.0
- Core cycles: 26.0
- Reference cycles: 15.57
- UOPS_EXECUTED.THREAD: 17.0

Latency operand 3 → 3: 15

Experiment 1 (fast division)

Instruction: IDIV dword ptr [R14]
Chain instructions: AND EDX, R9D; OR EDX, R9D; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; ; MOV EAX, R8D
Chain latency: 10

Code:

   0:	41 f7 3e             	idiv   DWORD PTR [r14]
   3:	44 21 ca             	and    edx,r9d
   6:	44 09 ca             	or     edx,r9d
   9:	09 d2                	or     edx,edx
   b:	09 d2                	or     edx,edx
   d:	09 d2                	or     edx,edx
   f:	09 d2                	or     edx,edx
  11:	09 d2                	or     edx,edx
  13:	09 d2                	or     edx,edx
  15:	09 d2                	or     edx,edx
  17:	09 d2                	or     edx,edx
  19:	44 89 c0             	mov    eax,r8d

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV [R14], RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 12.0
- Core cycles: 25.02
- Reference cycles: 15.33
- UOPS_EXECUTED.THREAD: 16.0

Experiment 2 (slow division)

Instruction: IDIV dword ptr [R14]
Chain instructions: AND EDX, R9D; OR EDX, R9D; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; OR EDX, EDX; ; MOV EAX, R8D
Chain latency: 10

Code:

   0:	41 f7 3e             	idiv   DWORD PTR [r14]
   3:	44 21 ca             	and    edx,r9d
   6:	44 09 ca             	or     edx,r9d
   9:	09 d2                	or     edx,edx
   b:	09 d2                	or     edx,edx
   d:	09 d2                	or     edx,edx
   f:	09 d2                	or     edx,edx
  11:	09 d2                	or     edx,edx
  13:	09 d2                	or     edx,edx
  15:	09 d2                	or     edx,edx
  17:	09 d2                	or     edx,edx
  19:	44 89 c0             	mov    eax,r8d

Init:

MOV R8, 133;
MOV R9, 0x343a9ed7;
MOV RCX, 0x75e6e44f;
MOV [R14], RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 12.0
- Core cycles: 25.02
- Reference cycles: 15.21
- UOPS_EXECUTED.THREAD: 16.0

IDIV (M32) - Latency

Operands

Latency operand 1 → 2 (address, base register): 15

Latency operand 1 → 2 (address, index register): 15

Latency operand 1 → 3 (address, base register): 19

Latency operand 1 → 3 (address, index register): 19

Latency operand 2 → 2: 11

Latency operand 2 → 3: 15

Latency operand 3 → 2: 15

Latency operand 3 → 3: 15

Latency operand 1 → 2 (address, base register): 15

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 1 → 2 (address, index register): 15

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 1 → 3 (address, base register): 19

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 1 → 3 (address, index register): 19

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 2 → 2: 11

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 2 → 3: 15

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 3 → 2: 15

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 3 → 3: 15

Experiment 1 (fast division)

Experiment 2 (slow division)