IDIV (R64)

Experiment 1 (fast division)

Instruction: IDIV RBX
Chain instructions: AND RBX, RAX; AND RBX, RCX; OR RBX, RCX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; ; MOV RAX, R8;MOV RDX, R9
Chain latency: 17

Code:

   0:	48 f7 fb             	idiv   rbx
   3:	48 21 c3             	and    rbx,rax
   6:	48 21 cb             	and    rbx,rcx
   9:	48 09 cb             	or     rbx,rcx
   c:	48 09 db             	or     rbx,rbx
   f:	48 09 db             	or     rbx,rbx
  12:	48 09 db             	or     rbx,rbx
  15:	48 09 db             	or     rbx,rbx
  18:	48 09 db             	or     rbx,rbx
  1b:	48 09 db             	or     rbx,rbx
  1e:	48 09 db             	or     rbx,rbx
  21:	48 09 db             	or     rbx,rbx
  24:	48 09 db             	or     rbx,rbx
  27:	48 09 db             	or     rbx,rbx
  2a:	48 09 db             	or     rbx,rbx
  2d:	48 09 db             	or     rbx,rbx
  30:	48 09 db             	or     rbx,rbx
  33:	48 09 db             	or     rbx,rbx
  36:	4c 89 c0             	mov    rax,r8
  39:	4c 89 ca             	mov    rdx,r9

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV RBX, RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 20.0
- Core cycles: 31.31
- Reference cycles: 10.44
- UOPS_EXECUTED.THREAD: 23.0

Experiment 2 (slow division)

Instruction: IDIV RBX
Chain instructions: AND RBX, RAX; AND RBX, RCX; OR RBX, RCX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; ; MOV RAX, R8;MOV RDX, R9
Chain latency: 17

Code:

   0:	48 f7 fb             	idiv   rbx
   3:	48 21 c3             	and    rbx,rax
   6:	48 21 cb             	and    rbx,rcx
   9:	48 09 cb             	or     rbx,rcx
   c:	48 09 db             	or     rbx,rbx
   f:	48 09 db             	or     rbx,rbx
  12:	48 09 db             	or     rbx,rbx
  15:	48 09 db             	or     rbx,rbx
  18:	48 09 db             	or     rbx,rbx
  1b:	48 09 db             	or     rbx,rbx
  1e:	48 09 db             	or     rbx,rbx
  21:	48 09 db             	or     rbx,rbx
  24:	48 09 db             	or     rbx,rbx
  27:	48 09 db             	or     rbx,rbx
  2a:	48 09 db             	or     rbx,rbx
  2d:	48 09 db             	or     rbx,rbx
  30:	48 09 db             	or     rbx,rbx
  33:	48 09 db             	or     rbx,rbx
  36:	4c 89 c0             	mov    rax,r8
  39:	4c 89 ca             	mov    rdx,r9

Init:

MOV R8, 133;
MOV R9, 0x343a9ed744556677;
MOV RCX, 0x75e6e44fccddeeff;
MOV RBX, RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 20.0
- Core cycles: 31.37
- Reference cycles: 10.33
- UOPS_EXECUTED.THREAD: 23.04

Latency operand 1 → 3: 18

Experiment 1 (fast division)

Instruction: IDIV RBX
Chain instructions: AND RBX, RDX; AND RBX, RCX; OR RBX, RCX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; ; MOV RAX, R8;MOV RDX, R9
Chain latency: 17

Code:

   0:	48 f7 fb             	idiv   rbx
   3:	48 21 d3             	and    rbx,rdx
   6:	48 21 cb             	and    rbx,rcx
   9:	48 09 cb             	or     rbx,rcx
   c:	48 09 db             	or     rbx,rbx
   f:	48 09 db             	or     rbx,rbx
  12:	48 09 db             	or     rbx,rbx
  15:	48 09 db             	or     rbx,rbx
  18:	48 09 db             	or     rbx,rbx
  1b:	48 09 db             	or     rbx,rbx
  1e:	48 09 db             	or     rbx,rbx
  21:	48 09 db             	or     rbx,rbx
  24:	48 09 db             	or     rbx,rbx
  27:	48 09 db             	or     rbx,rbx
  2a:	48 09 db             	or     rbx,rbx
  2d:	48 09 db             	or     rbx,rbx
  30:	48 09 db             	or     rbx,rbx
  33:	48 09 db             	or     rbx,rbx
  36:	4c 89 c0             	mov    rax,r8
  39:	4c 89 ca             	mov    rdx,r9

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV RBX, RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 20.0
- Core cycles: 35.0
- Reference cycles: 11.68
- UOPS_EXECUTED.THREAD: 23.0

Experiment 2 (slow division)

Instruction: IDIV RBX
Chain instructions: AND RBX, RDX; AND RBX, RCX; OR RBX, RCX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; OR RBX, RBX; ; MOV RAX, R8;MOV RDX, R9
Chain latency: 17

Code:

   0:	48 f7 fb             	idiv   rbx
   3:	48 21 d3             	and    rbx,rdx
   6:	48 21 cb             	and    rbx,rcx
   9:	48 09 cb             	or     rbx,rcx
   c:	48 09 db             	or     rbx,rbx
   f:	48 09 db             	or     rbx,rbx
  12:	48 09 db             	or     rbx,rbx
  15:	48 09 db             	or     rbx,rbx
  18:	48 09 db             	or     rbx,rbx
  1b:	48 09 db             	or     rbx,rbx
  1e:	48 09 db             	or     rbx,rbx
  21:	48 09 db             	or     rbx,rbx
  24:	48 09 db             	or     rbx,rbx
  27:	48 09 db             	or     rbx,rbx
  2a:	48 09 db             	or     rbx,rbx
  2d:	48 09 db             	or     rbx,rbx
  30:	48 09 db             	or     rbx,rbx
  33:	48 09 db             	or     rbx,rbx
  36:	4c 89 c0             	mov    rax,r8
  39:	4c 89 ca             	mov    rdx,r9

Init:

MOV R8, 133;
MOV R9, 0x343a9ed744556677;
MOV RCX, 0x75e6e44fccddeeff;
MOV RBX, RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 20.0
- Core cycles: 35.0
- Reference cycles: 11.63
- UOPS_EXECUTED.THREAD: 23.0

Latency operand 2 → 2: 14

Experiment 1 (fast division)

Instruction: IDIV RBX
Chain instructions: AND RAX, R8; OR RAX, R8; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; ; MOV RDX, R9
Chain latency: 16

Code:

   0:	48 f7 fb             	idiv   rbx
   3:	4c 21 c0             	and    rax,r8
   6:	4c 09 c0             	or     rax,r8
   9:	48 09 c0             	or     rax,rax
   c:	48 09 c0             	or     rax,rax
   f:	48 09 c0             	or     rax,rax
  12:	48 09 c0             	or     rax,rax
  15:	48 09 c0             	or     rax,rax
  18:	48 09 c0             	or     rax,rax
  1b:	48 09 c0             	or     rax,rax
  1e:	48 09 c0             	or     rax,rax
  21:	48 09 c0             	or     rax,rax
  24:	48 09 c0             	or     rax,rax
  27:	48 09 c0             	or     rax,rax
  2a:	48 09 c0             	or     rax,rax
  2d:	48 09 c0             	or     rax,rax
  30:	48 09 c0             	or     rax,rax
  33:	4c 89 ca             	mov    rdx,r9

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV RBX, RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 18.0
- Core cycles: 30.51
- Reference cycles: 10.18
- UOPS_EXECUTED.THREAD: 21.0

Experiment 2 (slow division)

Instruction: IDIV RBX
Chain instructions: AND RAX, R8; OR RAX, R8; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; ; MOV RDX, R9
Chain latency: 16

Code:

   0:	48 f7 fb             	idiv   rbx
   3:	4c 21 c0             	and    rax,r8
   6:	4c 09 c0             	or     rax,r8
   9:	48 09 c0             	or     rax,rax
   c:	48 09 c0             	or     rax,rax
   f:	48 09 c0             	or     rax,rax
  12:	48 09 c0             	or     rax,rax
  15:	48 09 c0             	or     rax,rax
  18:	48 09 c0             	or     rax,rax
  1b:	48 09 c0             	or     rax,rax
  1e:	48 09 c0             	or     rax,rax
  21:	48 09 c0             	or     rax,rax
  24:	48 09 c0             	or     rax,rax
  27:	48 09 c0             	or     rax,rax
  2a:	48 09 c0             	or     rax,rax
  2d:	48 09 c0             	or     rax,rax
  30:	48 09 c0             	or     rax,rax
  33:	4c 89 ca             	mov    rdx,r9

Init:

MOV R8, 133;
MOV R9, 0x343a9ed744556677;
MOV RCX, 0x75e6e44fccddeeff;
MOV RBX, RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 18.0
- Core cycles: 30.51
- Reference cycles: 10.23
- UOPS_EXECUTED.THREAD: 21.02

Latency operand 2 → 3: 18

Experiment 1 (fast division)

Instruction: IDIV RBX
Chain instructions: AND RAX, RDX; AND RAX, R8; OR RAX, R8; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; ; MOV RDX, R9
Chain latency: 17

Code:

   0:	48 f7 fb             	idiv   rbx
   3:	48 21 d0             	and    rax,rdx
   6:	4c 21 c0             	and    rax,r8
   9:	4c 09 c0             	or     rax,r8
   c:	48 09 c0             	or     rax,rax
   f:	48 09 c0             	or     rax,rax
  12:	48 09 c0             	or     rax,rax
  15:	48 09 c0             	or     rax,rax
  18:	48 09 c0             	or     rax,rax
  1b:	48 09 c0             	or     rax,rax
  1e:	48 09 c0             	or     rax,rax
  21:	48 09 c0             	or     rax,rax
  24:	48 09 c0             	or     rax,rax
  27:	48 09 c0             	or     rax,rax
  2a:	48 09 c0             	or     rax,rax
  2d:	48 09 c0             	or     rax,rax
  30:	48 09 c0             	or     rax,rax
  33:	48 09 c0             	or     rax,rax
  36:	4c 89 ca             	mov    rdx,r9

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV RBX, RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 19.0
- Core cycles: 35.0
- Reference cycles: 11.68
- UOPS_EXECUTED.THREAD: 22.0

Experiment 2 (slow division)

Instruction: IDIV RBX
Chain instructions: AND RAX, RDX; AND RAX, R8; OR RAX, R8; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; OR RAX, RAX; ; MOV RDX, R9
Chain latency: 17

Code:

   0:	48 f7 fb             	idiv   rbx
   3:	48 21 d0             	and    rax,rdx
   6:	4c 21 c0             	and    rax,r8
   9:	4c 09 c0             	or     rax,r8
   c:	48 09 c0             	or     rax,rax
   f:	48 09 c0             	or     rax,rax
  12:	48 09 c0             	or     rax,rax
  15:	48 09 c0             	or     rax,rax
  18:	48 09 c0             	or     rax,rax
  1b:	48 09 c0             	or     rax,rax
  1e:	48 09 c0             	or     rax,rax
  21:	48 09 c0             	or     rax,rax
  24:	48 09 c0             	or     rax,rax
  27:	48 09 c0             	or     rax,rax
  2a:	48 09 c0             	or     rax,rax
  2d:	48 09 c0             	or     rax,rax
  30:	48 09 c0             	or     rax,rax
  33:	48 09 c0             	or     rax,rax
  36:	4c 89 ca             	mov    rdx,r9

Init:

MOV R8, 133;
MOV R9, 0x343a9ed744556677;
MOV RCX, 0x75e6e44fccddeeff;
MOV RBX, RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 19.0
- Core cycles: 34.99
- Reference cycles: 11.73
- UOPS_EXECUTED.THREAD: 22.0

Latency operand 3 → 2: 18

Experiment 1 (fast division)

Instruction: IDIV RBX
Chain instructions: AND RDX, RAX; AND RDX, R9; OR RDX, R9; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; ; MOV RAX, R8
Chain latency: 17

Code:

   0:	48 f7 fb             	idiv   rbx
   3:	48 21 c2             	and    rdx,rax
   6:	4c 21 ca             	and    rdx,r9
   9:	4c 09 ca             	or     rdx,r9
   c:	48 09 d2             	or     rdx,rdx
   f:	48 09 d2             	or     rdx,rdx
  12:	48 09 d2             	or     rdx,rdx
  15:	48 09 d2             	or     rdx,rdx
  18:	48 09 d2             	or     rdx,rdx
  1b:	48 09 d2             	or     rdx,rdx
  1e:	48 09 d2             	or     rdx,rdx
  21:	48 09 d2             	or     rdx,rdx
  24:	48 09 d2             	or     rdx,rdx
  27:	48 09 d2             	or     rdx,rdx
  2a:	48 09 d2             	or     rdx,rdx
  2d:	48 09 d2             	or     rdx,rdx
  30:	48 09 d2             	or     rdx,rdx
  33:	48 09 d2             	or     rdx,rdx
  36:	4c 89 c0             	mov    rax,r8

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV RBX, RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 19.0
- Core cycles: 35.0
- Reference cycles: 11.63
- UOPS_EXECUTED.THREAD: 22.0

Experiment 2 (slow division)

Instruction: IDIV RBX
Chain instructions: AND RDX, RAX; AND RDX, R9; OR RDX, R9; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; ; MOV RAX, R8
Chain latency: 17

Code:

   0:	48 f7 fb             	idiv   rbx
   3:	48 21 c2             	and    rdx,rax
   6:	4c 21 ca             	and    rdx,r9
   9:	4c 09 ca             	or     rdx,r9
   c:	48 09 d2             	or     rdx,rdx
   f:	48 09 d2             	or     rdx,rdx
  12:	48 09 d2             	or     rdx,rdx
  15:	48 09 d2             	or     rdx,rdx
  18:	48 09 d2             	or     rdx,rdx
  1b:	48 09 d2             	or     rdx,rdx
  1e:	48 09 d2             	or     rdx,rdx
  21:	48 09 d2             	or     rdx,rdx
  24:	48 09 d2             	or     rdx,rdx
  27:	48 09 d2             	or     rdx,rdx
  2a:	48 09 d2             	or     rdx,rdx
  2d:	48 09 d2             	or     rdx,rdx
  30:	48 09 d2             	or     rdx,rdx
  33:	48 09 d2             	or     rdx,rdx
  36:	4c 89 c0             	mov    rax,r8

Init:

MOV R8, 133;
MOV R9, 0x343a9ed744556677;
MOV RCX, 0x75e6e44fccddeeff;
MOV RBX, RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 19.0
- Core cycles: 34.99
- Reference cycles: 11.63
- UOPS_EXECUTED.THREAD: 22.0

Latency operand 3 → 3: 18

Experiment 1 (fast division)

Instruction: IDIV RBX
Chain instructions: AND RDX, R9; OR RDX, R9; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; ; MOV RAX, R8
Chain latency: 16

Code:

   0:	48 f7 fb             	idiv   rbx
   3:	4c 21 ca             	and    rdx,r9
   6:	4c 09 ca             	or     rdx,r9
   9:	48 09 d2             	or     rdx,rdx
   c:	48 09 d2             	or     rdx,rdx
   f:	48 09 d2             	or     rdx,rdx
  12:	48 09 d2             	or     rdx,rdx
  15:	48 09 d2             	or     rdx,rdx
  18:	48 09 d2             	or     rdx,rdx
  1b:	48 09 d2             	or     rdx,rdx
  1e:	48 09 d2             	or     rdx,rdx
  21:	48 09 d2             	or     rdx,rdx
  24:	48 09 d2             	or     rdx,rdx
  27:	48 09 d2             	or     rdx,rdx
  2a:	48 09 d2             	or     rdx,rdx
  2d:	48 09 d2             	or     rdx,rdx
  30:	48 09 d2             	or     rdx,rdx
  33:	4c 89 c0             	mov    rax,r8

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV RBX, RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 18.0
- Core cycles: 34.0
- Reference cycles: 11.32
- UOPS_EXECUTED.THREAD: 21.04

Experiment 2 (slow division)

Instruction: IDIV RBX
Chain instructions: AND RDX, R9; OR RDX, R9; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; OR RDX, RDX; ; MOV RAX, R8
Chain latency: 16

Code:

   0:	48 f7 fb             	idiv   rbx
   3:	4c 21 ca             	and    rdx,r9
   6:	4c 09 ca             	or     rdx,r9
   9:	48 09 d2             	or     rdx,rdx
   c:	48 09 d2             	or     rdx,rdx
   f:	48 09 d2             	or     rdx,rdx
  12:	48 09 d2             	or     rdx,rdx
  15:	48 09 d2             	or     rdx,rdx
  18:	48 09 d2             	or     rdx,rdx
  1b:	48 09 d2             	or     rdx,rdx
  1e:	48 09 d2             	or     rdx,rdx
  21:	48 09 d2             	or     rdx,rdx
  24:	48 09 d2             	or     rdx,rdx
  27:	48 09 d2             	or     rdx,rdx
  2a:	48 09 d2             	or     rdx,rdx
  2d:	48 09 d2             	or     rdx,rdx
  30:	48 09 d2             	or     rdx,rdx
  33:	4c 89 c0             	mov    rax,r8

Init:

MOV R8, 133;
MOV R9, 0x343a9ed744556677;
MOV RCX, 0x75e6e44fccddeeff;
MOV RBX, RCX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 18.0
- Core cycles: 34.0
- Reference cycles: 11.32
- UOPS_EXECUTED.THREAD: 20.96

IDIV (R64) - Latency

Operands

Latency operand 1 → 2: 14

Latency operand 1 → 3: 18

Latency operand 2 → 2: 14

Latency operand 2 → 3: 18

Latency operand 3 → 2: 18

Latency operand 3 → 3: 18

Latency operand 1 → 2: 14

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 1 → 3: 18

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 2 → 2: 14

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 2 → 3: 18

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 3 → 2: 18

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 3 → 3: 18

Experiment 1 (fast division)

Experiment 2 (slow division)