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:
- MPERF: 18.87
- APERF: 23.0
- UOPS: 14.0

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:
- MPERF: 21.28
- APERF: 26.0
- UOPS: 14.0

Latency operand 1 → 2 (address, index register): 14 ≤ lat ≤ 17

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:
- MPERF: 18.99
- APERF: 23.0
- UOPS: 14.0

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:
- MPERF: 21.28
- APERF: 26.0
- UOPS: 14.0

Latency operand 1 → 3 (address, base register): 14 ≤ lat ≤ 17

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:
- MPERF: 18.81
- APERF: 23.0
- UOPS: 14.0

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:
- MPERF: 21.34
- APERF: 26.0
- UOPS: 14.0

Latency operand 1 → 3 (address, index register): 14 ≤ lat ≤ 17

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:
- MPERF: 18.93
- APERF: 23.0
- UOPS: 14.0

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:
- MPERF: 21.34
- APERF: 26.0
- UOPS: 14.0

Latency operand 2 → 2: 10 ≤ lat ≤ 13

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:
- MPERF: 16.34
- APERF: 20.0
- UOPS: 14.0

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:
- MPERF: 18.81
- APERF: 23.0
- UOPS: 14.0

Latency operand 2 → 3: 10 ≤ lat ≤ 13

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:
- MPERF: 17.27
- APERF: 21.0
- UOPS: 15.0

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:
- MPERF: 19.8
- APERF: 24.0
- UOPS: 15.0

Latency operand 3 → 2: 11 ≤ lat ≤ 14

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:
- MPERF: 18.13
- APERF: 22.0
- UOPS: 15.0

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:
- MPERF: 20.47
- APERF: 25.0
- UOPS: 15.0

Latency operand 3 → 3: 11 ≤ lat ≤ 14

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:
- MPERF: 17.21
- APERF: 21.0
- UOPS: 14.0

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:
- MPERF: 19.61
- APERF: 24.0
- UOPS: 14.0

IDIV (M32) - Latency

Operands

Latency operand 1 → 2 (address, base register): 14 ≤ lat ≤ 17

Latency operand 1 → 2 (address, index register): 14 ≤ lat ≤ 17

Latency operand 1 → 3 (address, base register): 14 ≤ lat ≤ 17

Latency operand 1 → 3 (address, index register): 14 ≤ lat ≤ 17

Latency operand 2 → 2: 10 ≤ lat ≤ 13

Latency operand 2 → 3: 10 ≤ lat ≤ 13

Latency operand 3 → 2: 11 ≤ lat ≤ 14

Latency operand 3 → 3: 11 ≤ lat ≤ 14

Latency operand 1 → 2 (address, base register): 14 ≤ lat ≤ 17

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 1 → 2 (address, index register): 14 ≤ lat ≤ 17

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 1 → 3 (address, base register): 14 ≤ lat ≤ 17

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 1 → 3 (address, index register): 14 ≤ lat ≤ 17

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 2 → 2: 10 ≤ lat ≤ 13

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 2 → 3: 10 ≤ lat ≤ 13

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 3 → 2: 11 ≤ lat ≤ 14

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 3 → 3: 11 ≤ lat ≤ 14

Experiment 1 (fast division)

Experiment 2 (slow division)