DIV (R32) - Port Usage

With blocking instructions for port '0':

Code:

   0:	66 44 0f 50 c0       	movmskpd r8d,xmm0
   5:	66 44 0f 50 c8       	movmskpd r9d,xmm0
   a:	66 44 0f 50 d0       	movmskpd r10d,xmm0
   f:	66 44 0f 50 d8       	movmskpd r11d,xmm0
  14:	66 44 0f 50 e0       	movmskpd r12d,xmm0
  19:	66 0f 50 c8          	movmskpd ecx,xmm0
  1d:	66 44 0f 50 c0       	movmskpd r8d,xmm0
  22:	66 44 0f 50 c8       	movmskpd r9d,xmm0
  27:	66 44 0f 50 d0       	movmskpd r10d,xmm0
  2c:	66 44 0f 50 d8       	movmskpd r11d,xmm0
  31:	66 44 0f 50 e0       	movmskpd r12d,xmm0
  36:	66 0f 50 c8          	movmskpd ecx,xmm0
  3a:	66 44 0f 50 c0       	movmskpd r8d,xmm0
  3f:	66 44 0f 50 c8       	movmskpd r9d,xmm0
  44:	48 c7 c0 00 00 00 00 	mov    rax,0x0
  4b:	48 c7 c2 00 00 00 00 	mov    rdx,0x0
  52:	f7 f3                	div    ebx

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14];
MOV EBX, 1;
MOV RAX, 0;
MOV RDX, 0

Show nanoBench command
Results:
- Instructions retired: 17.0
- Core cycles: 16.08
- Reference cycles: 14.87
- UOPS_PORT_0: 15.03
- UOPS_PORT_1: 4.28
- UOPS_PORT_2: 0.0
- UOPS_PORT_3: 0.0
- UOPS_PORT_4: 0.0
- UOPS_PORT_5: 0.0
- UOPS_RETIRED.ANY: 22.0

⇨ One μop that can only use port '0'

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:	66 0f 58 c1          	addpd  xmm0,xmm1
  39:	66 0f 58 d1          	addpd  xmm2,xmm1
  3d:	48 c7 c0 00 00 00 00 	mov    rax,0x0
  44:	48 c7 c2 00 00 00 00 	mov    rdx,0x0
  4b:	f7 f3                	div    ebx

Init:

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, 1;
MOV RAX, 0;
MOV RDX, 0

Show nanoBench command
Results:
- Instructions retired: 17.0
- Core cycles: 16.14
- Reference cycles: 15.04
- UOPS_PORT_0: 3.94
- UOPS_PORT_1: 15.93
- UOPS_PORT_2: 0.0
- UOPS_PORT_3: 0.0
- UOPS_PORT_4: 0.0
- UOPS_PORT_5: 0.0
- UOPS_RETIRED.ANY: 22.0

⇨ 2 μops 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:	66 0f 55 c1          	andnpd xmm0,xmm1
  39:	66 0f 55 d1          	andnpd xmm2,xmm1
  3d:	48 c7 c0 00 00 00 00 	mov    rax,0x0
  44:	48 c7 c2 00 00 00 00 	mov    rdx,0x0
  4b:	f7 f3                	div    ebx

Init:

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, 1;
MOV RAX, 0;
MOV RDX, 0

Show nanoBench command
Results:
- Instructions retired: 17.0
- Core cycles: 14.01
- Reference cycles: 12.96
- UOPS_PORT_0: 3.51
- UOPS_PORT_1: 4.45
- UOPS_PORT_2: 0.0
- UOPS_PORT_3: 0.0
- UOPS_PORT_4: 0.0
- UOPS_PORT_5: 0.02
- UOPS_RETIRED.ANY: 22.0

With blocking instructions for ports {'0', '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:	0f 38 1c e1          	pabsb  mm4,mm1
  64:	0f 38 1c e9          	pabsb  mm5,mm1
  68:	0f 38 1c f1          	pabsb  mm6,mm1
  6c:	0f 38 1c f9          	pabsb  mm7,mm1
  70:	48 c7 c0 00 00 00 00 	mov    rax,0x0
  77:	48 c7 c2 00 00 00 00 	mov    rdx,0x0
  7e:	f7 f3                	div    ebx

Init:

PXOR MM1, MM1;
MOV EBX, 1;
MOV RAX, 0;
MOV RDX, 0

Show nanoBench command
Results:
- Instructions retired: 31.0
- Core cycles: 16.34
- Reference cycles: 15.2
- UOPS_PORT_0: 15.14
- UOPS_PORT_1: 4.89
- UOPS_PORT_2: 0.0
- UOPS_PORT_3: 0.0
- UOPS_PORT_4: 0.0
- UOPS_PORT_5: 16.66
- UOPS_RETIRED.ANY: 36.0

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

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

Code:

   0:	41 b8 00 00 00 01    	mov    r8d,0x1000000
   6:	41 b9 00 00 00 01    	mov    r9d,0x1000000
   c:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  12:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  18:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  1e:	b9 00 00 00 01       	mov    ecx,0x1000000
  23:	41 b8 00 00 00 01    	mov    r8d,0x1000000
  29:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  2f:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  35:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  3b:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  41:	b9 00 00 00 01       	mov    ecx,0x1000000
  46:	41 b8 00 00 00 01    	mov    r8d,0x1000000
  4c:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  52:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  58:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  5e:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  64:	b9 00 00 00 01       	mov    ecx,0x1000000
  69:	41 b8 00 00 00 01    	mov    r8d,0x1000000
  6f:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  75:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  7b:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  81:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  87:	b9 00 00 00 01       	mov    ecx,0x1000000
  8c:	41 b8 00 00 00 01    	mov    r8d,0x1000000
  92:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  98:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  9e:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  a4:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  aa:	b9 00 00 00 01       	mov    ecx,0x1000000
  af:	41 b8 00 00 00 01    	mov    r8d,0x1000000
  b5:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  bb:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  c1:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  c7:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  cd:	b9 00 00 00 01       	mov    ecx,0x1000000
  d2:	41 b8 00 00 00 01    	mov    r8d,0x1000000
  d8:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  de:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  e4:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  ea:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  f0:	b9 00 00 00 01       	mov    ecx,0x1000000
  f5:	48 c7 c0 00 00 00 00 	mov    rax,0x0
  fc:	48 c7 c2 00 00 00 00 	mov    rdx,0x0
 103:	f7 f3                	div    ebx

Init:
```
MOV EBX, 1;
MOV RAX, 0;
MOV RDX, 0
```
Show nanoBench command
Results:
- Instructions retired: 45.0
- Core cycles: 19.87
- Reference cycles: 18.09
- UOPS_PORT_0: 16.43
- UOPS_PORT_1: 16.22
- UOPS_PORT_2: 0.0
- UOPS_PORT_3: 0.0
- UOPS_PORT_4: 0.0
- UOPS_PORT_5: 0.0
- UOPS_RETIRED.ANY: 50.0

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