IDIV (R16)

Experiment 1 (fast division)

Instruction: IDIV BX
Chain instructions: AND BX, AX; AND BX, CX; OR BX, CX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; ; MOV AX, R8W;MOV DX, R9W
Chain latency: 13

Code:

   0:	66 f7 fb             	idiv   bx
   3:	66 21 c3             	and    bx,ax
   6:	66 21 cb             	and    bx,cx
   9:	66 09 cb             	or     bx,cx
   c:	66 09 db             	or     bx,bx
   f:	66 09 db             	or     bx,bx
  12:	66 09 db             	or     bx,bx
  15:	66 09 db             	or     bx,bx
  18:	66 09 db             	or     bx,bx
  1b:	66 09 db             	or     bx,bx
  1e:	66 09 db             	or     bx,bx
  21:	66 09 db             	or     bx,bx
  24:	66 09 db             	or     bx,bx
  27:	66 09 db             	or     bx,bx
  2a:	66 44 89 c0          	mov    ax,r8w
  2e:	66 44 89 ca          	mov    dx,r9w

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV BX, CX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 16.0
- Core cycles: 30.63
- Reference cycles: 28.28
- UOPS_RETIRED.ANY: 23.0

Experiment 2 (slow division)

Instruction: IDIV BX
Chain instructions: AND BX, AX; AND BX, CX; OR BX, CX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; ; MOV AX, R8W;MOV DX, R9W
Chain latency: 13

Code:

   0:	66 f7 fb             	idiv   bx
   3:	66 21 c3             	and    bx,ax
   6:	66 21 cb             	and    bx,cx
   9:	66 09 cb             	or     bx,cx
   c:	66 09 db             	or     bx,bx
   f:	66 09 db             	or     bx,bx
  12:	66 09 db             	or     bx,bx
  15:	66 09 db             	or     bx,bx
  18:	66 09 db             	or     bx,bx
  1b:	66 09 db             	or     bx,bx
  1e:	66 09 db             	or     bx,bx
  21:	66 09 db             	or     bx,bx
  24:	66 09 db             	or     bx,bx
  27:	66 09 db             	or     bx,bx
  2a:	66 44 89 c0          	mov    ax,r8w
  2e:	66 44 89 ca          	mov    dx,r9w

Init:

MOV R8, 133;
MOV R9, 0x343a;
MOV RCX, 0x75e6;
MOV BX, CX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 16.0
- Core cycles: 36.63
- Reference cycles: 33.84
- UOPS_RETIRED.ANY: 23.0

Latency operand 1 → 3: 17 ≤ lat ≤ 23

Experiment 1 (fast division)

Instruction: IDIV BX
Chain instructions: AND BX, DX; AND BX, CX; OR BX, CX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; ; MOV AX, R8W;MOV DX, R9W
Chain latency: 13

Code:

   0:	66 f7 fb             	idiv   bx
   3:	66 21 d3             	and    bx,dx
   6:	66 21 cb             	and    bx,cx
   9:	66 09 cb             	or     bx,cx
   c:	66 09 db             	or     bx,bx
   f:	66 09 db             	or     bx,bx
  12:	66 09 db             	or     bx,bx
  15:	66 09 db             	or     bx,bx
  18:	66 09 db             	or     bx,bx
  1b:	66 09 db             	or     bx,bx
  1e:	66 09 db             	or     bx,bx
  21:	66 09 db             	or     bx,bx
  24:	66 09 db             	or     bx,bx
  27:	66 09 db             	or     bx,bx
  2a:	66 44 89 c0          	mov    ax,r8w
  2e:	66 44 89 ca          	mov    dx,r9w

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV BX, CX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 16.0
- Core cycles: 30.76
- Reference cycles: 28.32
- UOPS_RETIRED.ANY: 23.0

Experiment 2 (slow division)

Instruction: IDIV BX
Chain instructions: AND BX, DX; AND BX, CX; OR BX, CX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; OR BX, BX; ; MOV AX, R8W;MOV DX, R9W
Chain latency: 13

Code:

   0:	66 f7 fb             	idiv   bx
   3:	66 21 d3             	and    bx,dx
   6:	66 21 cb             	and    bx,cx
   9:	66 09 cb             	or     bx,cx
   c:	66 09 db             	or     bx,bx
   f:	66 09 db             	or     bx,bx
  12:	66 09 db             	or     bx,bx
  15:	66 09 db             	or     bx,bx
  18:	66 09 db             	or     bx,bx
  1b:	66 09 db             	or     bx,bx
  1e:	66 09 db             	or     bx,bx
  21:	66 09 db             	or     bx,bx
  24:	66 09 db             	or     bx,bx
  27:	66 09 db             	or     bx,bx
  2a:	66 44 89 c0          	mov    ax,r8w
  2e:	66 44 89 ca          	mov    dx,r9w

Init:

MOV R8, 133;
MOV R9, 0x343a;
MOV RCX, 0x75e6;
MOV BX, CX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 16.0
- Core cycles: 36.76
- Reference cycles: 33.84
- UOPS_RETIRED.ANY: 23.0

Latency operand 2 → 2: 19 ≤ lat ≤ 25

Experiment 1 (fast division)

Instruction: IDIV BX
Chain instructions: AND AX, R8W; OR AX, R8W; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; ; MOV DX, R9W
Chain latency: 12

Code:

   0:	66 f7 fb             	idiv   bx
   3:	66 44 21 c0          	and    ax,r8w
   7:	66 44 09 c0          	or     ax,r8w
   b:	66 09 c0             	or     ax,ax
   e:	66 09 c0             	or     ax,ax
  11:	66 09 c0             	or     ax,ax
  14:	66 09 c0             	or     ax,ax
  17:	66 09 c0             	or     ax,ax
  1a:	66 09 c0             	or     ax,ax
  1d:	66 09 c0             	or     ax,ax
  20:	66 09 c0             	or     ax,ax
  23:	66 09 c0             	or     ax,ax
  26:	66 09 c0             	or     ax,ax
  29:	66 44 89 ca          	mov    dx,r9w

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV BX, CX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 14.0
- Core cycles: 30.82
- Reference cycles: 28.56
- UOPS_RETIRED.ANY: 21.0

Experiment 2 (slow division)

Instruction: IDIV BX
Chain instructions: AND AX, R8W; OR AX, R8W; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; ; MOV DX, R9W
Chain latency: 12

Code:

   0:	66 f7 fb             	idiv   bx
   3:	66 44 21 c0          	and    ax,r8w
   7:	66 44 09 c0          	or     ax,r8w
   b:	66 09 c0             	or     ax,ax
   e:	66 09 c0             	or     ax,ax
  11:	66 09 c0             	or     ax,ax
  14:	66 09 c0             	or     ax,ax
  17:	66 09 c0             	or     ax,ax
  1a:	66 09 c0             	or     ax,ax
  1d:	66 09 c0             	or     ax,ax
  20:	66 09 c0             	or     ax,ax
  23:	66 09 c0             	or     ax,ax
  26:	66 09 c0             	or     ax,ax
  29:	66 44 89 ca          	mov    dx,r9w

Init:

MOV R8, 133;
MOV R9, 0x343a;
MOV RCX, 0x75e6;
MOV BX, CX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 14.0
- Core cycles: 36.82
- Reference cycles: 34.0
- UOPS_RETIRED.ANY: 21.0

Latency operand 2 → 3: 19 ≤ lat ≤ 25

Experiment 1 (fast division)

Instruction: IDIV BX
Chain instructions: AND AX, DX; AND AX, R8W; OR AX, R8W; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; ; MOV DX, R9W
Chain latency: 13

Code:

   0:	66 f7 fb             	idiv   bx
   3:	66 21 d0             	and    ax,dx
   6:	66 44 21 c0          	and    ax,r8w
   a:	66 44 09 c0          	or     ax,r8w
   e:	66 09 c0             	or     ax,ax
  11:	66 09 c0             	or     ax,ax
  14:	66 09 c0             	or     ax,ax
  17:	66 09 c0             	or     ax,ax
  1a:	66 09 c0             	or     ax,ax
  1d:	66 09 c0             	or     ax,ax
  20:	66 09 c0             	or     ax,ax
  23:	66 09 c0             	or     ax,ax
  26:	66 09 c0             	or     ax,ax
  29:	66 09 c0             	or     ax,ax
  2c:	66 44 89 ca          	mov    dx,r9w

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV BX, CX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 15.0
- Core cycles: 32.0
- Reference cycles: 29.48
- UOPS_RETIRED.ANY: 22.0

Experiment 2 (slow division)

Instruction: IDIV BX
Chain instructions: AND AX, DX; AND AX, R8W; OR AX, R8W; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; OR AX, AX; ; MOV DX, R9W
Chain latency: 13

Code:

   0:	66 f7 fb             	idiv   bx
   3:	66 21 d0             	and    ax,dx
   6:	66 44 21 c0          	and    ax,r8w
   a:	66 44 09 c0          	or     ax,r8w
   e:	66 09 c0             	or     ax,ax
  11:	66 09 c0             	or     ax,ax
  14:	66 09 c0             	or     ax,ax
  17:	66 09 c0             	or     ax,ax
  1a:	66 09 c0             	or     ax,ax
  1d:	66 09 c0             	or     ax,ax
  20:	66 09 c0             	or     ax,ax
  23:	66 09 c0             	or     ax,ax
  26:	66 09 c0             	or     ax,ax
  29:	66 09 c0             	or     ax,ax
  2c:	66 44 89 ca          	mov    dx,r9w

Init:

MOV R8, 133;
MOV R9, 0x343a;
MOV RCX, 0x75e6;
MOV BX, CX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 15.0
- Core cycles: 38.0
- Reference cycles: 35.08
- UOPS_RETIRED.ANY: 22.0

Latency operand 3 → 2: 19 ≤ lat ≤ 25

Experiment 1 (fast division)

Instruction: IDIV BX
Chain instructions: AND DX, AX; AND DX, R9W; OR DX, R9W; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; ; MOV AX, R8W
Chain latency: 13

Code:

   0:	66 f7 fb             	idiv   bx
   3:	66 21 c2             	and    dx,ax
   6:	66 44 21 ca          	and    dx,r9w
   a:	66 44 09 ca          	or     dx,r9w
   e:	66 09 d2             	or     dx,dx
  11:	66 09 d2             	or     dx,dx
  14:	66 09 d2             	or     dx,dx
  17:	66 09 d2             	or     dx,dx
  1a:	66 09 d2             	or     dx,dx
  1d:	66 09 d2             	or     dx,dx
  20:	66 09 d2             	or     dx,dx
  23:	66 09 d2             	or     dx,dx
  26:	66 09 d2             	or     dx,dx
  29:	66 09 d2             	or     dx,dx
  2c:	66 44 89 c0          	mov    ax,r8w

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV BX, CX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 15.0
- Core cycles: 32.0
- Reference cycles: 29.56
- UOPS_RETIRED.ANY: 22.0

Experiment 2 (slow division)

Instruction: IDIV BX
Chain instructions: AND DX, AX; AND DX, R9W; OR DX, R9W; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; ; MOV AX, R8W
Chain latency: 13

Code:

   0:	66 f7 fb             	idiv   bx
   3:	66 21 c2             	and    dx,ax
   6:	66 44 21 ca          	and    dx,r9w
   a:	66 44 09 ca          	or     dx,r9w
   e:	66 09 d2             	or     dx,dx
  11:	66 09 d2             	or     dx,dx
  14:	66 09 d2             	or     dx,dx
  17:	66 09 d2             	or     dx,dx
  1a:	66 09 d2             	or     dx,dx
  1d:	66 09 d2             	or     dx,dx
  20:	66 09 d2             	or     dx,dx
  23:	66 09 d2             	or     dx,dx
  26:	66 09 d2             	or     dx,dx
  29:	66 09 d2             	or     dx,dx
  2c:	66 44 89 c0          	mov    ax,r8w

Init:

MOV R8, 133;
MOV R9, 0x343a;
MOV RCX, 0x75e6;
MOV BX, CX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 15.0
- Core cycles: 38.0
- Reference cycles: 35.08
- UOPS_RETIRED.ANY: 22.0

Latency operand 3 → 3: 19 ≤ lat ≤ 25

Experiment 1 (fast division)

Instruction: IDIV BX
Chain instructions: AND DX, R9W; OR DX, R9W; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; ; MOV AX, R8W
Chain latency: 12

Code:

   0:	66 f7 fb             	idiv   bx
   3:	66 44 21 ca          	and    dx,r9w
   7:	66 44 09 ca          	or     dx,r9w
   b:	66 09 d2             	or     dx,dx
   e:	66 09 d2             	or     dx,dx
  11:	66 09 d2             	or     dx,dx
  14:	66 09 d2             	or     dx,dx
  17:	66 09 d2             	or     dx,dx
  1a:	66 09 d2             	or     dx,dx
  1d:	66 09 d2             	or     dx,dx
  20:	66 09 d2             	or     dx,dx
  23:	66 09 d2             	or     dx,dx
  26:	66 09 d2             	or     dx,dx
  29:	66 44 89 c0          	mov    ax,r8w

Init:

MOV R8, 0;
MOV R9, 0;
MOV RCX, 1;
MOV BX, CX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 14.0
- Core cycles: 30.88
- Reference cycles: 28.56
- UOPS_RETIRED.ANY: 21.0

Experiment 2 (slow division)

Instruction: IDIV BX
Chain instructions: AND DX, R9W; OR DX, R9W; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; OR DX, DX; ; MOV AX, R8W
Chain latency: 12

Code:

   0:	66 f7 fb             	idiv   bx
   3:	66 44 21 ca          	and    dx,r9w
   7:	66 44 09 ca          	or     dx,r9w
   b:	66 09 d2             	or     dx,dx
   e:	66 09 d2             	or     dx,dx
  11:	66 09 d2             	or     dx,dx
  14:	66 09 d2             	or     dx,dx
  17:	66 09 d2             	or     dx,dx
  1a:	66 09 d2             	or     dx,dx
  1d:	66 09 d2             	or     dx,dx
  20:	66 09 d2             	or     dx,dx
  23:	66 09 d2             	or     dx,dx
  26:	66 09 d2             	or     dx,dx
  29:	66 44 89 c0          	mov    ax,r8w

Init:

MOV R8, 133;
MOV R9, 0x343a;
MOV RCX, 0x75e6;
MOV BX, CX;
MOV RAX, R8;
MOV RDX, R9

Show nanoBench command
Results:
- Instructions retired: 14.0
- Core cycles: 36.88
- Reference cycles: 34.08
- UOPS_RETIRED.ANY: 21.0

IDIV (R16) - Latency

Operands

Latency operand 1 → 2: 17 ≤ lat ≤ 23

Latency operand 1 → 3: 17 ≤ lat ≤ 23

Latency operand 2 → 2: 19 ≤ lat ≤ 25

Latency operand 2 → 3: 19 ≤ lat ≤ 25

Latency operand 3 → 2: 19 ≤ lat ≤ 25

Latency operand 3 → 3: 19 ≤ lat ≤ 25

Latency operand 1 → 2: 17 ≤ lat ≤ 23

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 1 → 3: 17 ≤ lat ≤ 23

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 2 → 2: 19 ≤ lat ≤ 25

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 2 → 3: 19 ≤ lat ≤ 25

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 3 → 2: 19 ≤ lat ≤ 25

Experiment 1 (fast division)

Experiment 2 (slow division)

Latency operand 3 → 3: 19 ≤ lat ≤ 25

Experiment 1 (fast division)

Experiment 2 (slow division)