LOOPNE (Rel8) - 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 c3             	movd   ebx,mm0
  17:	0f 7e c2             	movd   edx,mm0
  1a:	41 0f 7e c0          	movd   r8d,mm0
  1e:	41 0f 7e c1          	movd   r9d,mm0
  22:	41 0f 7e c2          	movd   r10d,mm0
  26:	41 0f 7e c3          	movd   r11d,mm0
  2a:	41 0f 7e c4          	movd   r12d,mm0
  2e:	48 c7 c1 00 00 00 00 	mov    rcx,0x0
  35:	e0 00                	loopne 0x37

Init:
```
PXOR MM0, MM0
```
Show nanoBench command
Results:
- Instructions retired: 14.0
- Core cycles: 12.11
- Reference cycles: 11.89
- UOPS_PORT_0: 11.99

With blocking instructions for port '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:	48 c7 c1 00 00 00 00 	mov    rcx,0x0
  3c:	e0 00                	loopne 0x3e

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]

Show nanoBench command
Results:
- Instructions retired: 14.0
- Core cycles: 13.12
- Reference cycles: 12.72
- UOPS_PORT_1: 12.99

⇨ One μop that can only use port '1'

With blocking instructions for port '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:	48 c7 c1 00 00 00 00 	mov    rcx,0x0
  3c:	e0 00                	loopne 0x3e

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

Show nanoBench command
Results:
- Instructions retired: 14.0
- Core cycles: 15.05
- Reference cycles: 16.58
- UOPS_PORT_5: 15.0

⇨ 3 μops that can only use port '5'

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

Code:

   0:	45 8d 06             	lea    r8d,[r14]
   3:	45 8d 0e             	lea    r9d,[r14]
   6:	45 8d 16             	lea    r10d,[r14]
   9:	45 8d 1e             	lea    r11d,[r14]
   c:	45 8d 26             	lea    r12d,[r14]
   f:	41 8d 1e             	lea    ebx,[r14]
  12:	41 8d 16             	lea    edx,[r14]
  15:	45 8d 06             	lea    r8d,[r14]
  18:	45 8d 0e             	lea    r9d,[r14]
  1b:	45 8d 16             	lea    r10d,[r14]
  1e:	45 8d 1e             	lea    r11d,[r14]
  21:	45 8d 26             	lea    r12d,[r14]
  24:	41 8d 1e             	lea    ebx,[r14]
  27:	41 8d 16             	lea    edx,[r14]
  2a:	45 8d 06             	lea    r8d,[r14]
  2d:	45 8d 0e             	lea    r9d,[r14]
  30:	45 8d 16             	lea    r10d,[r14]
  33:	45 8d 1e             	lea    r11d,[r14]
  36:	45 8d 26             	lea    r12d,[r14]
  39:	41 8d 1e             	lea    ebx,[r14]
  3c:	41 8d 16             	lea    edx,[r14]
  3f:	45 8d 06             	lea    r8d,[r14]
  42:	45 8d 0e             	lea    r9d,[r14]
  45:	45 8d 16             	lea    r10d,[r14]
  48:	48 c7 c1 00 00 00 00 	mov    rcx,0x0
  4f:	e0 00                	loopne 0x51

Show nanoBench command
Results:
- Instructions retired: 26.0
- Core cycles: 13.02
- Reference cycles: 14.31
- UOPS_PORT_0: 12.76
- UOPS_PORT_1: 12.29

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

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 c3 00          	rol    bx,0x0
  1d:	66 c1 c2 00          	rol    dx,0x0
  21:	66 41 c1 c0 00       	rol    r8w,0x0
  26:	66 41 c1 c1 00       	rol    r9w,0x0
  2b:	66 41 c1 c2 00       	rol    r10w,0x0
  30:	66 41 c1 c3 00       	rol    r11w,0x0
  35:	66 41 c1 c4 00       	rol    r12w,0x0
  3a:	66 c1 c3 00          	rol    bx,0x0
  3e:	66 c1 c2 00          	rol    dx,0x0
  42:	66 41 c1 c0 00       	rol    r8w,0x0
  47:	66 41 c1 c1 00       	rol    r9w,0x0
  4c:	66 41 c1 c2 00       	rol    r10w,0x0
  51:	66 41 c1 c3 00       	rol    r11w,0x0
  56:	66 41 c1 c4 00       	rol    r12w,0x0
  5b:	66 c1 c3 00          	rol    bx,0x0
  5f:	66 c1 c2 00          	rol    dx,0x0
  63:	66 41 c1 c0 00       	rol    r8w,0x0
  68:	66 41 c1 c1 00       	rol    r9w,0x0
  6d:	66 41 c1 c2 00       	rol    r10w,0x0
  72:	48 c7 c1 00 00 00 00 	mov    rcx,0x0
  79:	e0 00                	loopne 0x7b

Show nanoBench command
Results:
- Instructions retired: 26.0
- Core cycles: 14.64
- Reference cycles: 16.26
- UOPS_PORT_5: 14.54
- UOPS_PORT_0: 14.44

⇨ 2 μops that can only use ports {'0', '5'}

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

Code:

   0:	0f 38 1c c1          	pabsb  mm0,mm1
   4:	0f 38 1c d1          	pabsb  mm2,mm1
   8:	0f 38 1c d9          	pabsb  mm3,mm1
   c:	0f 38 1c e1          	pabsb  mm4,mm1
  10:	0f 38 1c e9          	pabsb  mm5,mm1
  14:	0f 38 1c f1          	pabsb  mm6,mm1
  18:	0f 38 1c f9          	pabsb  mm7,mm1
  1c:	0f 38 1c c1          	pabsb  mm0,mm1
  20:	0f 38 1c d1          	pabsb  mm2,mm1
  24:	0f 38 1c d9          	pabsb  mm3,mm1
  28:	0f 38 1c e1          	pabsb  mm4,mm1
  2c:	0f 38 1c e9          	pabsb  mm5,mm1
  30:	0f 38 1c f1          	pabsb  mm6,mm1
  34:	0f 38 1c f9          	pabsb  mm7,mm1
  38:	0f 38 1c c1          	pabsb  mm0,mm1
  3c:	0f 38 1c d1          	pabsb  mm2,mm1
  40:	0f 38 1c d9          	pabsb  mm3,mm1
  44:	0f 38 1c e1          	pabsb  mm4,mm1
  48:	0f 38 1c e9          	pabsb  mm5,mm1
  4c:	0f 38 1c f1          	pabsb  mm6,mm1
  50:	0f 38 1c f9          	pabsb  mm7,mm1
  54:	0f 38 1c c1          	pabsb  mm0,mm1
  58:	0f 38 1c d1          	pabsb  mm2,mm1
  5c:	0f 38 1c d9          	pabsb  mm3,mm1
  60:	48 c7 c1 00 00 00 00 	mov    rcx,0x0
  67:	e0 00                	loopne 0x69

Init:
```
VZEROALL;
PXOR MM1, MM1
```
Show nanoBench command
Results:
- Instructions retired: 26.0
- Core cycles: 14.22
- Reference cycles: 15.61
- UOPS_PORT_5: 14.05
- UOPS_PORT_1: 13.93

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

Code:

   0:	41 b0 00             	mov    r8b,0x0
   3:	41 b1 00             	mov    r9b,0x0
   6:	41 b2 00             	mov    r10b,0x0
   9:	41 b3 00             	mov    r11b,0x0
   c:	41 b4 00             	mov    r12b,0x0
   f:	b3 00                	mov    bl,0x0
  11:	b2 00                	mov    dl,0x0
  13:	41 b0 00             	mov    r8b,0x0
  16:	41 b1 00             	mov    r9b,0x0
  19:	41 b2 00             	mov    r10b,0x0
  1c:	41 b3 00             	mov    r11b,0x0
  1f:	41 b4 00             	mov    r12b,0x0
  22:	b3 00                	mov    bl,0x0
  24:	b2 00                	mov    dl,0x0
  26:	41 b0 00             	mov    r8b,0x0
  29:	41 b1 00             	mov    r9b,0x0
  2c:	41 b2 00             	mov    r10b,0x0
  2f:	41 b3 00             	mov    r11b,0x0
  32:	41 b4 00             	mov    r12b,0x0
  35:	b3 00                	mov    bl,0x0
  37:	b2 00                	mov    dl,0x0
  39:	41 b0 00             	mov    r8b,0x0
  3c:	41 b1 00             	mov    r9b,0x0
  3f:	41 b2 00             	mov    r10b,0x0
  42:	41 b3 00             	mov    r11b,0x0
  45:	41 b4 00             	mov    r12b,0x0
  48:	b3 00                	mov    bl,0x0
  4a:	b2 00                	mov    dl,0x0
  4c:	41 b0 00             	mov    r8b,0x0
  4f:	41 b1 00             	mov    r9b,0x0
  52:	41 b2 00             	mov    r10b,0x0
  55:	41 b3 00             	mov    r11b,0x0
  58:	41 b4 00             	mov    r12b,0x0
  5b:	b3 00                	mov    bl,0x0
  5d:	b2 00                	mov    dl,0x0
  5f:	41 b0 00             	mov    r8b,0x0
  62:	48 c7 c1 00 00 00 00 	mov    rcx,0x0
  69:	e0 00                	loopne 0x6b

Show nanoBench command
Results:
- Instructions retired: 38.0
- Core cycles: 16.58
- Reference cycles: 18.77
- UOPS_PORT_5: 16.35
- UOPS_PORT_0: 16.2
- UOPS_PORT_1: 15.46

⇨ 5 μops that can only use ports {'0', '1', '5'}