IDIV (R32)

Experiment 1 (fast division)

Instruction: IDIV EBX
Chain instructions: AND EBX, EAX; AND EBX, ECX; OR EBX, ECX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; ; MOV EAX, R8D;MOV EDX, R9D
Chain latency: 11

Code:

   0:	f7 fb                	idiv   ebx
   2:	21 c3                	and    ebx,eax
   4:	21 cb                	and    ebx,ecx
   6:	09 cb                	or     ebx,ecx
   8:	09 db                	or     ebx,ebx
   a:	09 db                	or     ebx,ebx
   c:	09 db                	or     ebx,ebx
   e:	09 db                	or     ebx,ebx
  10:	09 db                	or     ebx,ebx
  12:	09 db                	or     ebx,ebx
  14:	09 db                	or     ebx,ebx
  16:	09 db                	or     ebx,ebx
  18:	44 89 c0             	mov    eax,r8d
  1b:	44 89 ca             	mov    edx,r9d

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV EBX, ECX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- MPERF: 16.77
- APERF: 20.33
- UOPS: 15.0

Experiment 2 (slow division)

Instruction: IDIV EBX
Chain instructions: AND EBX, EAX; AND EBX, ECX; OR EBX, ECX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; ; MOV EAX, R8D;MOV EDX, R9D
Chain latency: 11

Code:

   0:	f7 fb                	idiv   ebx
   2:	21 c3                	and    ebx,eax
   4:	21 cb                	and    ebx,ecx
   6:	09 cb                	or     ebx,ecx
   8:	09 db                	or     ebx,ebx
   a:	09 db                	or     ebx,ebx
   c:	09 db                	or     ebx,ebx
   e:	09 db                	or     ebx,ebx
  10:	09 db                	or     ebx,ebx
  12:	09 db                	or     ebx,ebx
  14:	09 db                	or     ebx,ebx
  16:	09 db                	or     ebx,ebx
  18:	44 89 c0             	mov    eax,r8d
  1b:	44 89 ca             	mov    edx,r9d

Init:

MOV R8, 133;
MOV R9, 0x343a9ed7;
MOV RCX, 0x75e6e44f;
MOV EBX, ECX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- MPERF: 19.06
- APERF: 23.33
- UOPS: 15.0

Latency operand 1 → 3: 10 ≤ lat ≤ 13

Experiment 1 (fast division)

Instruction: IDIV EBX
Chain instructions: AND EBX, EDX; AND EBX, ECX; OR EBX, ECX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; ; MOV EAX, R8D;MOV EDX, R9D
Chain latency: 11

Code:

   0:	f7 fb                	idiv   ebx
   2:	21 d3                	and    ebx,edx
   4:	21 cb                	and    ebx,ecx
   6:	09 cb                	or     ebx,ecx
   8:	09 db                	or     ebx,ebx
   a:	09 db                	or     ebx,ebx
   c:	09 db                	or     ebx,ebx
   e:	09 db                	or     ebx,ebx
  10:	09 db                	or     ebx,ebx
  12:	09 db                	or     ebx,ebx
  14:	09 db                	or     ebx,ebx
  16:	09 db                	or     ebx,ebx
  18:	44 89 c0             	mov    eax,r8d
  1b:	44 89 ca             	mov    edx,r9d

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV EBX, ECX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- MPERF: 17.33
- APERF: 21.0
- UOPS: 15.0

Experiment 2 (slow division)

Instruction: IDIV EBX
Chain instructions: AND EBX, EDX; AND EBX, ECX; OR EBX, ECX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; OR EBX, EBX; ; MOV EAX, R8D;MOV EDX, R9D
Chain latency: 11

Code:

   0:	f7 fb                	idiv   ebx
   2:	21 d3                	and    ebx,edx
   4:	21 cb                	and    ebx,ecx
   6:	09 cb                	or     ebx,ecx
   8:	09 db                	or     ebx,ebx
   a:	09 db                	or     ebx,ebx
   c:	09 db                	or     ebx,ebx
   e:	09 db                	or     ebx,ebx
  10:	09 db                	or     ebx,ebx
  12:	09 db                	or     ebx,ebx
  14:	09 db                	or     ebx,ebx
  16:	09 db                	or     ebx,ebx
  18:	44 89 c0             	mov    eax,r8d
  1b:	44 89 ca             	mov    edx,r9d

Init:

MOV R8, 133;
MOV R9, 0x343a9ed7;
MOV RCX, 0x75e6e44f;
MOV EBX, ECX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- MPERF: 19.61
- APERF: 24.0
- UOPS: 15.0

Latency operand 2 → 2: 9 ≤ lat ≤ 12

Experiment 1 (fast division)

Instruction: IDIV EBX
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:	f7 fb                	idiv   ebx
   2:	44 21 c0             	and    eax,r8d
   5:	44 09 c0             	or     eax,r8d
   8:	09 c0                	or     eax,eax
   a:	09 c0                	or     eax,eax
   c:	09 c0                	or     eax,eax
   e:	09 c0                	or     eax,eax
  10:	09 c0                	or     eax,eax
  12:	09 c0                	or     eax,eax
  14:	09 c0                	or     eax,eax
  16:	09 c0                	or     eax,eax
  18:	44 89 ca             	mov    edx,r9d

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV EBX, ECX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- MPERF: 15.42
- APERF: 19.0
- UOPS: 13.0

Experiment 2 (slow division)

Instruction: IDIV EBX
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:	f7 fb                	idiv   ebx
   2:	44 21 c0             	and    eax,r8d
   5:	44 09 c0             	or     eax,r8d
   8:	09 c0                	or     eax,eax
   a:	09 c0                	or     eax,eax
   c:	09 c0                	or     eax,eax
   e:	09 c0                	or     eax,eax
  10:	09 c0                	or     eax,eax
  12:	09 c0                	or     eax,eax
  14:	09 c0                	or     eax,eax
  16:	09 c0                	or     eax,eax
  18:	44 89 ca             	mov    edx,r9d

Init:

MOV R8, 133;
MOV R9, 0x343a9ed7;
MOV RCX, 0x75e6e44f;
MOV EBX, ECX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- MPERF: 18.13
- APERF: 22.0
- UOPS: 13.0

Latency operand 2 → 3: 10 ≤ lat ≤ 13

Experiment 1 (fast division)

Instruction: IDIV EBX
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:	f7 fb                	idiv   ebx
   2:	21 d0                	and    eax,edx
   4:	44 21 c0             	and    eax,r8d
   7:	44 09 c0             	or     eax,r8d
   a:	09 c0                	or     eax,eax
   c:	09 c0                	or     eax,eax
   e:	09 c0                	or     eax,eax
  10:	09 c0                	or     eax,eax
  12:	09 c0                	or     eax,eax
  14:	09 c0                	or     eax,eax
  16:	09 c0                	or     eax,eax
  18:	09 c0                	or     eax,eax
  1a:	44 89 ca             	mov    edx,r9d

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV EBX, ECX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- MPERF: 17.27
- APERF: 21.0
- UOPS: 14.0

Experiment 2 (slow division)

Instruction: IDIV EBX
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:	f7 fb                	idiv   ebx
   2:	21 d0                	and    eax,edx
   4:	44 21 c0             	and    eax,r8d
   7:	44 09 c0             	or     eax,r8d
   a:	09 c0                	or     eax,eax
   c:	09 c0                	or     eax,eax
   e:	09 c0                	or     eax,eax
  10:	09 c0                	or     eax,eax
  12:	09 c0                	or     eax,eax
  14:	09 c0                	or     eax,eax
  16:	09 c0                	or     eax,eax
  18:	09 c0                	or     eax,eax
  1a:	44 89 ca             	mov    edx,r9d

Init:

MOV R8, 133;
MOV R9, 0x343a9ed7;
MOV RCX, 0x75e6e44f;
MOV EBX, ECX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- MPERF: 19.61
- APERF: 24.0
- UOPS: 14.0

Latency operand 3 → 2: 11 ≤ lat ≤ 14

Experiment 1 (fast division)

Instruction: IDIV EBX
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:	f7 fb                	idiv   ebx
   2:	21 c2                	and    edx,eax
   4:	44 21 ca             	and    edx,r9d
   7:	44 09 ca             	or     edx,r9d
   a:	09 d2                	or     edx,edx
   c:	09 d2                	or     edx,edx
   e:	09 d2                	or     edx,edx
  10:	09 d2                	or     edx,edx
  12:	09 d2                	or     edx,edx
  14:	09 d2                	or     edx,edx
  16:	09 d2                	or     edx,edx
  18:	09 d2                	or     edx,edx
  1a:	44 89 c0             	mov    eax,r8d

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV EBX, ECX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- MPERF: 17.95
- APERF: 22.0
- UOPS: 14.0

Experiment 2 (slow division)

Instruction: IDIV EBX
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:	f7 fb                	idiv   ebx
   2:	21 c2                	and    edx,eax
   4:	44 21 ca             	and    edx,r9d
   7:	44 09 ca             	or     edx,r9d
   a:	09 d2                	or     edx,edx
   c:	09 d2                	or     edx,edx
   e:	09 d2                	or     edx,edx
  10:	09 d2                	or     edx,edx
  12:	09 d2                	or     edx,edx
  14:	09 d2                	or     edx,edx
  16:	09 d2                	or     edx,edx
  18:	09 d2                	or     edx,edx
  1a:	44 89 c0             	mov    eax,r8d

Init:

MOV R8, 133;
MOV R9, 0x343a9ed7;
MOV RCX, 0x75e6e44f;
MOV EBX, ECX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- MPERF: 20.54
- APERF: 25.0
- UOPS: 14.0

Latency operand 3 → 3: 11 ≤ lat ≤ 14

Experiment 1 (fast division)

Instruction: IDIV EBX
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:	f7 fb                	idiv   ebx
   2:	44 21 ca             	and    edx,r9d
   5:	44 09 ca             	or     edx,r9d
   8:	09 d2                	or     edx,edx
   a:	09 d2                	or     edx,edx
   c:	09 d2                	or     edx,edx
   e:	09 d2                	or     edx,edx
  10:	09 d2                	or     edx,edx
  12:	09 d2                	or     edx,edx
  14:	09 d2                	or     edx,edx
  16:	09 d2                	or     edx,edx
  18:	44 89 c0             	mov    eax,r8d

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV EBX, ECX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- MPERF: 17.27
- APERF: 21.0
- UOPS: 13.0

Experiment 2 (slow division)

Instruction: IDIV EBX
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:	f7 fb                	idiv   ebx
   2:	44 21 ca             	and    edx,r9d
   5:	44 09 ca             	or     edx,r9d
   8:	09 d2                	or     edx,edx
   a:	09 d2                	or     edx,edx
   c:	09 d2                	or     edx,edx
   e:	09 d2                	or     edx,edx
  10:	09 d2                	or     edx,edx
  12:	09 d2                	or     edx,edx
  14:	09 d2                	or     edx,edx
  16:	09 d2                	or     edx,edx
  18:	44 89 c0             	mov    eax,r8d

Init:

MOV R8, 133;
MOV R9, 0x343a9ed7;
MOV RCX, 0x75e6e44f;
MOV EBX, ECX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- MPERF: 19.61
- APERF: 24.0
- UOPS: 13.0

IDIV (R32) - Latency

Operands

Latency operand 1 → 2: 9 ≤ lat ≤ 12

Latency operand 1 → 3: 10 ≤ lat ≤ 13

Latency operand 2 → 2: 9 ≤ lat ≤ 12

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: 9 ≤ lat ≤ 12

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 1 → 3: 10 ≤ lat ≤ 13

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 2 → 2: 9 ≤ lat ≤ 12

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)