DIV (R32) - Port Usage

With blocking instructions for port '0':

Code:

   0:	41 0f 7e c0          	movd   r8d,mm0
   4:	41 0f 7e c1          	movd   r9d,mm0
   8:	41 0f 7e c2          	movd   r10d,mm0
   c:	41 0f 7e c3          	movd   r11d,mm0
  10:	41 0f 7e c4          	movd   r12d,mm0
  14:	0f 7e c1             	movd   ecx,mm0
  17:	41 0f 7e c0          	movd   r8d,mm0
  1b:	41 0f 7e c1          	movd   r9d,mm0
  1f:	41 0f 7e c2          	movd   r10d,mm0
  23:	41 0f 7e c3          	movd   r11d,mm0
  27:	41 0f 7e c4          	movd   r12d,mm0
  2b:	0f 7e c1             	movd   ecx,mm0
  2e:	b8 85 00 00 00       	mov    eax,0x85
  33:	ba d7 9e 3a 34       	mov    edx,0x343a9ed7
  38:	f7 f3                	div    ebx

Init:
```
PXOR MM0, MM0;
MOV EBX, 0x75e6e44f
```
Show nanoBench command
Results:
- Instructions retired: 15.0
- Core cycles: 12.07
- Reference cycles: 3.98
- UOPS_PORT_0: 11.99

With blocking instructions for port '1':

Code:

   0:	66 f2 45 0f 38 f1 c1 	crc32  r8d,r9w
   7:	66 f2 45 0f 38 f1 d1 	crc32  r10d,r9w
   e:	66 f2 45 0f 38 f1 d9 	crc32  r11d,r9w
  15:	66 f2 45 0f 38 f1 e1 	crc32  r12d,r9w
  1c:	66 f2 41 0f 38 f1 c9 	crc32  ecx,r9w
  23:	66 f2 45 0f 38 f1 c1 	crc32  r8d,r9w
  2a:	66 f2 45 0f 38 f1 d1 	crc32  r10d,r9w
  31:	66 f2 45 0f 38 f1 d9 	crc32  r11d,r9w
  38:	66 f2 45 0f 38 f1 e1 	crc32  r12d,r9w
  3f:	66 f2 41 0f 38 f1 c9 	crc32  ecx,r9w
  46:	66 f2 45 0f 38 f1 c1 	crc32  r8d,r9w
  4d:	66 f2 45 0f 38 f1 d1 	crc32  r10d,r9w
  54:	b8 85 00 00 00       	mov    eax,0x85
  59:	ba d7 9e 3a 34       	mov    edx,0x343a9ed7
  5e:	f7 f3                	div    ebx

Init:
```
VZEROALL;
MOV EBX, 0x75e6e44f
```
Show nanoBench command
Results:
- Instructions retired: 15.0
- Core cycles: 14.17
- Reference cycles: 5.23
- UOPS_PORT_1: 14.01

⇨ 2 μops that can only use port '1'

With blocking instructions for port '5':

Code:

   0:	66 0f 3a 21 c1 02    	insertps xmm0,xmm1,0x2
   6:	66 0f 3a 21 d1 02    	insertps xmm2,xmm1,0x2
   c:	66 0f 3a 21 d9 02    	insertps xmm3,xmm1,0x2
  12:	66 0f 3a 21 e1 02    	insertps xmm4,xmm1,0x2
  18:	66 0f 3a 21 e9 02    	insertps xmm5,xmm1,0x2
  1e:	66 0f 3a 21 f1 02    	insertps xmm6,xmm1,0x2
  24:	66 0f 3a 21 f9 02    	insertps xmm7,xmm1,0x2
  2a:	66 44 0f 3a 21 c1 02 	insertps xmm8,xmm1,0x2
  31:	66 44 0f 3a 21 c9 02 	insertps xmm9,xmm1,0x2
  38:	66 44 0f 3a 21 d1 02 	insertps xmm10,xmm1,0x2
  3f:	66 44 0f 3a 21 d9 02 	insertps xmm11,xmm1,0x2
  46:	66 44 0f 3a 21 e1 02 	insertps xmm12,xmm1,0x2
  4d:	b8 85 00 00 00       	mov    eax,0x85
  52:	ba d7 9e 3a 34       	mov    edx,0x343a9ed7
  57:	f7 f3                	div    ebx

Init:

VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14];
MOVUPD XMM1, [R14];
MOVUPD XMM2, [R14];
MOVUPD XMM3, [R14];
MOVUPD XMM4, [R14];
MOVUPD XMM5, [R14];
MOVUPD XMM6, [R14];
MOVUPD XMM7, [R14];
MOVUPD XMM8, [R14];
MOVUPD XMM9, [R14];
MOVUPD XMM10, [R14];
MOVUPD XMM11, [R14];
MOVUPD XMM12, [R14];
MOV EBX, 0x75e6e44f

Show nanoBench command
Results:
- Instructions retired: 15.0
- Core cycles: 12.06
- Reference cycles: 4.42
- UOPS_PORT_5: 11.99

With blocking instructions for ports {'0', '1'}:

Code:

   0:	66 0f 58 c1          	addpd  xmm0,xmm1
   4:	66 0f 58 d1          	addpd  xmm2,xmm1
   8:	66 0f 58 d9          	addpd  xmm3,xmm1
   c:	66 0f 58 e1          	addpd  xmm4,xmm1
  10:	66 0f 58 e9          	addpd  xmm5,xmm1
  14:	66 0f 58 f1          	addpd  xmm6,xmm1
  18:	66 0f 58 f9          	addpd  xmm7,xmm1
  1c:	66 44 0f 58 c1       	addpd  xmm8,xmm1
  21:	66 44 0f 58 c9       	addpd  xmm9,xmm1
  26:	66 44 0f 58 d1       	addpd  xmm10,xmm1
  2b:	66 44 0f 58 d9       	addpd  xmm11,xmm1
  30:	66 44 0f 58 e1       	addpd  xmm12,xmm1
  35:	66 0f 58 c1          	addpd  xmm0,xmm1
  39:	66 0f 58 d1          	addpd  xmm2,xmm1
  3d:	66 0f 58 d9          	addpd  xmm3,xmm1
  41:	66 0f 58 e1          	addpd  xmm4,xmm1
  45:	66 0f 58 e9          	addpd  xmm5,xmm1
  49:	66 0f 58 f1          	addpd  xmm6,xmm1
  4d:	66 0f 58 f9          	addpd  xmm7,xmm1
  51:	66 44 0f 58 c1       	addpd  xmm8,xmm1
  56:	66 44 0f 58 c9       	addpd  xmm9,xmm1
  5b:	66 44 0f 58 d1       	addpd  xmm10,xmm1
  60:	66 44 0f 58 d9       	addpd  xmm11,xmm1
  65:	66 44 0f 58 e1       	addpd  xmm12,xmm1
  6a:	b8 85 00 00 00       	mov    eax,0x85
  6f:	ba d7 9e 3a 34       	mov    edx,0x343a9ed7
  74:	f7 f3                	div    ebx

Init:

VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14];
MOVUPD XMM1, [R14];
MOVUPD XMM2, [R14];
MOVUPD XMM3, [R14];
MOVUPD XMM4, [R14];
MOVUPD XMM5, [R14];
MOVUPD XMM6, [R14];
MOVUPD XMM7, [R14];
MOVUPD XMM8, [R14];
MOVUPD XMM9, [R14];
MOVUPD XMM10, [R14];
MOVUPD XMM11, [R14];
MOVUPD XMM12, [R14];
MOV EBX, 0x75e6e44f

Show nanoBench command
Results:
- Instructions retired: 27.0
- Core cycles: 13.39
- Reference cycles: 4.03
- UOPS_PORT_0: 12.95
- UOPS_PORT_1: 13.05

With blocking instructions for ports {'0', '5'}:

Code:

   0:	0f 6f c1             	movq   mm0,mm1
   3:	0f 6f d1             	movq   mm2,mm1
   6:	0f 6f d9             	movq   mm3,mm1
   9:	0f 6f e1             	movq   mm4,mm1
   c:	0f 6f e9             	movq   mm5,mm1
   f:	0f 6f f1             	movq   mm6,mm1
  12:	0f 6f f9             	movq   mm7,mm1
  15:	0f 6f c1             	movq   mm0,mm1
  18:	0f 6f d1             	movq   mm2,mm1
  1b:	0f 6f d9             	movq   mm3,mm1
  1e:	0f 6f e1             	movq   mm4,mm1
  21:	0f 6f e9             	movq   mm5,mm1
  24:	0f 6f f1             	movq   mm6,mm1
  27:	0f 6f f9             	movq   mm7,mm1
  2a:	0f 6f c1             	movq   mm0,mm1
  2d:	0f 6f d1             	movq   mm2,mm1
  30:	0f 6f d9             	movq   mm3,mm1
  33:	0f 6f e1             	movq   mm4,mm1
  36:	0f 6f e9             	movq   mm5,mm1
  39:	0f 6f f1             	movq   mm6,mm1
  3c:	0f 6f f9             	movq   mm7,mm1
  3f:	0f 6f c1             	movq   mm0,mm1
  42:	0f 6f d1             	movq   mm2,mm1
  45:	0f 6f d9             	movq   mm3,mm1
  48:	b8 85 00 00 00       	mov    eax,0x85
  4d:	ba d7 9e 3a 34       	mov    edx,0x343a9ed7
  52:	f7 f3                	div    ebx

Init:
```
PXOR MM1, MM1;
MOV EBX, 0x75e6e44f
```
Show nanoBench command
Results:
- Instructions retired: 27.0
- Core cycles: 12.2
- Reference cycles: 3.78
- UOPS_PORT_0: 11.98
- UOPS_PORT_5: 11.98

With blocking instructions for ports {'0', '6'}:

Code:

   0:	66 41 c1 c0 00       	rol    r8w,0x0
   5:	66 41 c1 c1 00       	rol    r9w,0x0
   a:	66 41 c1 c2 00       	rol    r10w,0x0
   f:	66 41 c1 c3 00       	rol    r11w,0x0
  14:	66 41 c1 c4 00       	rol    r12w,0x0
  19:	66 c1 c1 00          	rol    cx,0x0
  1d:	66 41 c1 c0 00       	rol    r8w,0x0
  22:	66 41 c1 c1 00       	rol    r9w,0x0
  27:	66 41 c1 c2 00       	rol    r10w,0x0
  2c:	66 41 c1 c3 00       	rol    r11w,0x0
  31:	66 41 c1 c4 00       	rol    r12w,0x0
  36:	66 c1 c1 00          	rol    cx,0x0
  3a:	66 41 c1 c0 00       	rol    r8w,0x0
  3f:	66 41 c1 c1 00       	rol    r9w,0x0
  44:	66 41 c1 c2 00       	rol    r10w,0x0
  49:	66 41 c1 c3 00       	rol    r11w,0x0
  4e:	66 41 c1 c4 00       	rol    r12w,0x0
  53:	66 c1 c1 00          	rol    cx,0x0
  57:	66 41 c1 c0 00       	rol    r8w,0x0
  5c:	66 41 c1 c1 00       	rol    r9w,0x0
  61:	66 41 c1 c2 00       	rol    r10w,0x0
  66:	66 41 c1 c3 00       	rol    r11w,0x0
  6b:	66 41 c1 c4 00       	rol    r12w,0x0
  70:	66 c1 c1 00          	rol    cx,0x0
  74:	b8 85 00 00 00       	mov    eax,0x85
  79:	ba d7 9e 3a 34       	mov    edx,0x343a9ed7
  7e:	f7 f3                	div    ebx

Init:
```
MOV EBX, 0x75e6e44f
```
Show nanoBench command
Results:
- Instructions retired: 27.0
- Core cycles: 12.11
- Reference cycles: 3.91
- UOPS_PORT_0: 11.96
- UOPS_PORT_6: 11.98

With blocking instructions for ports {'1', '5'}:

Code:

   0:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
   4:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
   8:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
   c:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
  10:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
  14:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
  18:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
  1c:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
  20:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
  24:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
  28:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
  2c:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
  30:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
  34:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
  38:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
  3c:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
  40:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
  44:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
  48:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
  4c:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
  50:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
  54:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
  58:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
  5c:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
  60:	b8 85 00 00 00       	mov    eax,0x85
  65:	ba d7 9e 3a 34       	mov    edx,0x343a9ed7
  6a:	f7 f3                	div    ebx

Init:
```
MOV EBX, 0x75e6e44f
```
Show nanoBench command
Results:
- Instructions retired: 27.0
- Core cycles: 14.65
- Reference cycles: 4.54
- UOPS_PORT_1: 12.83
- UOPS_PORT_5: 14.17

⇨ One μop that can only use ports {'1', '5'}

With blocking instructions for ports {'0', '1', '5'}:

Code:

   0:	66 0f 55 c1          	andnpd xmm0,xmm1
   4:	66 0f 55 d1          	andnpd xmm2,xmm1
   8:	66 0f 55 d9          	andnpd xmm3,xmm1
   c:	66 0f 55 e1          	andnpd xmm4,xmm1
  10:	66 0f 55 e9          	andnpd xmm5,xmm1
  14:	66 0f 55 f1          	andnpd xmm6,xmm1
  18:	66 0f 55 f9          	andnpd xmm7,xmm1
  1c:	66 44 0f 55 c1       	andnpd xmm8,xmm1
  21:	66 44 0f 55 c9       	andnpd xmm9,xmm1
  26:	66 44 0f 55 d1       	andnpd xmm10,xmm1
  2b:	66 44 0f 55 d9       	andnpd xmm11,xmm1
  30:	66 44 0f 55 e1       	andnpd xmm12,xmm1
  35:	66 0f 55 c1          	andnpd xmm0,xmm1
  39:	66 0f 55 d1          	andnpd xmm2,xmm1
  3d:	66 0f 55 d9          	andnpd xmm3,xmm1
  41:	66 0f 55 e1          	andnpd xmm4,xmm1
  45:	66 0f 55 e9          	andnpd xmm5,xmm1
  49:	66 0f 55 f1          	andnpd xmm6,xmm1
  4d:	66 0f 55 f9          	andnpd xmm7,xmm1
  51:	66 44 0f 55 c1       	andnpd xmm8,xmm1
  56:	66 44 0f 55 c9       	andnpd xmm9,xmm1
  5b:	66 44 0f 55 d1       	andnpd xmm10,xmm1
  60:	66 44 0f 55 d9       	andnpd xmm11,xmm1
  65:	66 44 0f 55 e1       	andnpd xmm12,xmm1
  6a:	66 0f 55 c1          	andnpd xmm0,xmm1
  6e:	66 0f 55 d1          	andnpd xmm2,xmm1
  72:	66 0f 55 d9          	andnpd xmm3,xmm1
  76:	66 0f 55 e1          	andnpd xmm4,xmm1
  7a:	66 0f 55 e9          	andnpd xmm5,xmm1
  7e:	66 0f 55 f1          	andnpd xmm6,xmm1
  82:	66 0f 55 f9          	andnpd xmm7,xmm1
  86:	66 44 0f 55 c1       	andnpd xmm8,xmm1
  8b:	66 44 0f 55 c9       	andnpd xmm9,xmm1
  90:	66 44 0f 55 d1       	andnpd xmm10,xmm1
  95:	66 44 0f 55 d9       	andnpd xmm11,xmm1
  9a:	66 44 0f 55 e1       	andnpd xmm12,xmm1
  9f:	b8 85 00 00 00       	mov    eax,0x85
  a4:	ba d7 9e 3a 34       	mov    edx,0x343a9ed7
  a9:	f7 f3                	div    ebx

Init:

VZEROALL;
PXOR XMM0, XMM0;
PXOR XMM1, XMM1;
PXOR XMM2, XMM2;
PXOR XMM3, XMM3;
PXOR XMM4, XMM4;
PXOR XMM5, XMM5;
PXOR XMM6, XMM6;
PXOR XMM7, XMM7;
PXOR XMM8, XMM8;
PXOR XMM9, XMM9;
PXOR XMM10, XMM10;
PXOR XMM11, XMM11;
PXOR XMM12, XMM12;
MOV EBX, 0x75e6e44f

Show nanoBench command
Results:
- Instructions retired: 39.0
- Core cycles: 13.89
- Reference cycles: 4.59
- UOPS_PORT_0: 12.93
- UOPS_PORT_1: 13.0
- UOPS_PORT_5: 13.04

With blocking instructions for ports {'0', '1', '5', '6'}:

Code:

   0:	45 8d 46 08          	lea    r8d,[r14+0x8]
   4:	45 8d 4e 08          	lea    r9d,[r14+0x8]
   8:	45 8d 56 08          	lea    r10d,[r14+0x8]
   c:	45 8d 5e 08          	lea    r11d,[r14+0x8]
  10:	45 8d 66 08          	lea    r12d,[r14+0x8]
  14:	41 8d 4e 08          	lea    ecx,[r14+0x8]
  18:	45 8d 46 08          	lea    r8d,[r14+0x8]
  1c:	45 8d 4e 08          	lea    r9d,[r14+0x8]
  20:	45 8d 56 08          	lea    r10d,[r14+0x8]
  24:	45 8d 5e 08          	lea    r11d,[r14+0x8]
  28:	45 8d 66 08          	lea    r12d,[r14+0x8]
  2c:	41 8d 4e 08          	lea    ecx,[r14+0x8]
  30:	45 8d 46 08          	lea    r8d,[r14+0x8]
  34:	45 8d 4e 08          	lea    r9d,[r14+0x8]
  38:	45 8d 56 08          	lea    r10d,[r14+0x8]
  3c:	45 8d 5e 08          	lea    r11d,[r14+0x8]
  40:	45 8d 66 08          	lea    r12d,[r14+0x8]
  44:	41 8d 4e 08          	lea    ecx,[r14+0x8]
  48:	45 8d 46 08          	lea    r8d,[r14+0x8]
  4c:	45 8d 4e 08          	lea    r9d,[r14+0x8]
  50:	45 8d 56 08          	lea    r10d,[r14+0x8]
  54:	45 8d 5e 08          	lea    r11d,[r14+0x8]
  58:	45 8d 66 08          	lea    r12d,[r14+0x8]
  5c:	41 8d 4e 08          	lea    ecx,[r14+0x8]
  60:	45 8d 46 08          	lea    r8d,[r14+0x8]
  64:	45 8d 4e 08          	lea    r9d,[r14+0x8]
  68:	45 8d 56 08          	lea    r10d,[r14+0x8]
  6c:	45 8d 5e 08          	lea    r11d,[r14+0x8]
  70:	45 8d 66 08          	lea    r12d,[r14+0x8]
  74:	41 8d 4e 08          	lea    ecx,[r14+0x8]
  78:	45 8d 46 08          	lea    r8d,[r14+0x8]
  7c:	45 8d 4e 08          	lea    r9d,[r14+0x8]
  80:	45 8d 56 08          	lea    r10d,[r14+0x8]
  84:	45 8d 5e 08          	lea    r11d,[r14+0x8]
  88:	45 8d 66 08          	lea    r12d,[r14+0x8]
  8c:	41 8d 4e 08          	lea    ecx,[r14+0x8]
  90:	45 8d 46 08          	lea    r8d,[r14+0x8]
  94:	45 8d 4e 08          	lea    r9d,[r14+0x8]
  98:	45 8d 56 08          	lea    r10d,[r14+0x8]
  9c:	45 8d 5e 08          	lea    r11d,[r14+0x8]
  a0:	45 8d 66 08          	lea    r12d,[r14+0x8]
  a4:	41 8d 4e 08          	lea    ecx,[r14+0x8]
  a8:	45 8d 46 08          	lea    r8d,[r14+0x8]
  ac:	45 8d 4e 08          	lea    r9d,[r14+0x8]
  b0:	45 8d 56 08          	lea    r10d,[r14+0x8]
  b4:	45 8d 5e 08          	lea    r11d,[r14+0x8]
  b8:	45 8d 66 08          	lea    r12d,[r14+0x8]
  bc:	41 8d 4e 08          	lea    ecx,[r14+0x8]
  c0:	b8 85 00 00 00       	mov    eax,0x85
  c5:	ba d7 9e 3a 34       	mov    edx,0x343a9ed7
  ca:	f7 f3                	div    ebx

Init:
```
MOV EBX, 0x75e6e44f
```
Show nanoBench command
Results:
- Instructions retired: 51.0
- Core cycles: 15.0
- Reference cycles: 4.65
- UOPS_PORT_0: 13.85
- UOPS_PORT_1: 12.4
- UOPS_PORT_6: 13.85
- UOPS_PORT_5: 13.9

⇨ One μop that can only use ports {'0', '1', '5', '6'}