PCLMULQDQ (XMM, XMM, I8) - Port Usage

With blocking instructions for port '0':

Code:

   0:	66 44 0f 50 c2       	movmskpd r8d,xmm2
   5:	66 44 0f 50 ca       	movmskpd r9d,xmm2
   a:	66 44 0f 50 d2       	movmskpd r10d,xmm2
   f:	66 44 0f 50 da       	movmskpd r11d,xmm2
  14:	66 44 0f 50 e2       	movmskpd r12d,xmm2
  19:	66 0f 50 da          	movmskpd ebx,xmm2
  1d:	66 0f 50 ca          	movmskpd ecx,xmm2
  21:	66 0f 50 d2          	movmskpd edx,xmm2
  25:	66 44 0f 50 c2       	movmskpd r8d,xmm2
  2a:	66 44 0f 50 ca       	movmskpd r9d,xmm2
  2f:	66 44 0f 50 d2       	movmskpd r10d,xmm2
  34:	66 44 0f 50 da       	movmskpd r11d,xmm2
  39:	66 44 0f 50 e2       	movmskpd r12d,xmm2
  3e:	66 0f 50 da          	movmskpd ebx,xmm2
  42:	66 0f 50 ca          	movmskpd ecx,xmm2
  46:	66 0f 50 d2          	movmskpd edx,xmm2
  4a:	66 44 0f 50 c2       	movmskpd r8d,xmm2
  4f:	66 44 0f 50 ca       	movmskpd r9d,xmm2
  54:	66 44 0f 50 d2       	movmskpd r10d,xmm2
  59:	66 44 0f 50 da       	movmskpd r11d,xmm2
  5e:	66 44 0f 50 e2       	movmskpd r12d,xmm2
  63:	66 0f 50 da          	movmskpd ebx,xmm2
  67:	66 0f 50 ca          	movmskpd ecx,xmm2
  6b:	66 0f 50 d2          	movmskpd edx,xmm2
  6f:	66 44 0f 50 c2       	movmskpd r8d,xmm2
  74:	66 44 0f 50 ca       	movmskpd r9d,xmm2
  79:	66 0f 3a 44 c1 02    	pclmullqhqdq xmm0,xmm1

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM2, [R14];
PXOR XMM0, XMM0;
PXOR XMM1, XMM1

Show nanoBench command
Results:
- Instructions retired: 27.0
- Core cycles: 26.0
- Reference cycles: 23.79
- UOPS_PORT_0: 26.05
- UOPS_PORT_1: 5.92
- UOPS_PORT_2: 0.0
- UOPS_PORT_3: 0.0
- UOPS_PORT_4: 0.0
- UOPS_PORT_5: 10.45
- UOPS_RETIRED.ANY: 42.0

With blocking instructions for port '1':

Code:

   0:	66 0f 58 d3          	addpd  xmm2,xmm3
   4:	66 0f 58 e3          	addpd  xmm4,xmm3
   8:	66 0f 58 eb          	addpd  xmm5,xmm3
   c:	66 0f 58 f3          	addpd  xmm6,xmm3
  10:	66 0f 58 fb          	addpd  xmm7,xmm3
  14:	66 44 0f 58 c3       	addpd  xmm8,xmm3
  19:	66 44 0f 58 cb       	addpd  xmm9,xmm3
  1e:	66 44 0f 58 d3       	addpd  xmm10,xmm3
  23:	66 44 0f 58 db       	addpd  xmm11,xmm3
  28:	66 44 0f 58 e3       	addpd  xmm12,xmm3
  2d:	66 0f 58 d3          	addpd  xmm2,xmm3
  31:	66 0f 58 e3          	addpd  xmm4,xmm3
  35:	66 0f 58 eb          	addpd  xmm5,xmm3
  39:	66 0f 58 f3          	addpd  xmm6,xmm3
  3d:	66 0f 58 fb          	addpd  xmm7,xmm3
  41:	66 44 0f 58 c3       	addpd  xmm8,xmm3
  46:	66 44 0f 58 cb       	addpd  xmm9,xmm3
  4b:	66 44 0f 58 d3       	addpd  xmm10,xmm3
  50:	66 44 0f 58 db       	addpd  xmm11,xmm3
  55:	66 44 0f 58 e3       	addpd  xmm12,xmm3
  5a:	66 0f 58 d3          	addpd  xmm2,xmm3
  5e:	66 0f 58 e3          	addpd  xmm4,xmm3
  62:	66 0f 58 eb          	addpd  xmm5,xmm3
  66:	66 0f 58 f3          	addpd  xmm6,xmm3
  6a:	66 0f 58 fb          	addpd  xmm7,xmm3
  6e:	66 44 0f 58 c3       	addpd  xmm8,xmm3
  73:	66 0f 3a 44 c1 02    	pclmullqhqdq xmm0,xmm1

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
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];
PXOR XMM0, XMM0;
PXOR XMM1, XMM1

Show nanoBench command
Results:
- Instructions retired: 27.0
- Core cycles: 30.08
- Reference cycles: 27.89
- UOPS_PORT_0: 6.11
- UOPS_PORT_1: 29.84
- UOPS_PORT_2: 0.0
- UOPS_PORT_3: 0.0
- UOPS_PORT_4: 0.0
- UOPS_PORT_5: 6.43
- UOPS_RETIRED.ANY: 42.0

⇨ 4 μops that can only use port '1'

With blocking instructions for port '5':

Code:

   0:	66 0f 55 d3          	andnpd xmm2,xmm3
   4:	66 0f 55 e3          	andnpd xmm4,xmm3
   8:	66 0f 55 eb          	andnpd xmm5,xmm3
   c:	66 0f 55 f3          	andnpd xmm6,xmm3
  10:	66 0f 55 fb          	andnpd xmm7,xmm3
  14:	66 44 0f 55 c3       	andnpd xmm8,xmm3
  19:	66 44 0f 55 cb       	andnpd xmm9,xmm3
  1e:	66 44 0f 55 d3       	andnpd xmm10,xmm3
  23:	66 44 0f 55 db       	andnpd xmm11,xmm3
  28:	66 44 0f 55 e3       	andnpd xmm12,xmm3
  2d:	66 0f 55 d3          	andnpd xmm2,xmm3
  31:	66 0f 55 e3          	andnpd xmm4,xmm3
  35:	66 0f 55 eb          	andnpd xmm5,xmm3
  39:	66 0f 55 f3          	andnpd xmm6,xmm3
  3d:	66 0f 55 fb          	andnpd xmm7,xmm3
  41:	66 44 0f 55 c3       	andnpd xmm8,xmm3
  46:	66 44 0f 55 cb       	andnpd xmm9,xmm3
  4b:	66 44 0f 55 d3       	andnpd xmm10,xmm3
  50:	66 44 0f 55 db       	andnpd xmm11,xmm3
  55:	66 44 0f 55 e3       	andnpd xmm12,xmm3
  5a:	66 0f 55 d3          	andnpd xmm2,xmm3
  5e:	66 0f 55 e3          	andnpd xmm4,xmm3
  62:	66 0f 55 eb          	andnpd xmm5,xmm3
  66:	66 0f 55 f3          	andnpd xmm6,xmm3
  6a:	66 0f 55 fb          	andnpd xmm7,xmm3
  6e:	66 44 0f 55 c3       	andnpd xmm8,xmm3
  73:	66 0f 3a 44 c1 02    	pclmullqhqdq xmm0,xmm1

Init:

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;
PXOR XMM0, XMM0;
PXOR XMM1, XMM1

Show nanoBench command
Results:
- Instructions retired: 27.0
- Core cycles: 26.05
- Reference cycles: 23.89
- UOPS_PORT_0: 9.5
- UOPS_PORT_1: 6.45
- UOPS_PORT_2: 0.0
- UOPS_PORT_3: 0.0
- UOPS_PORT_4: 0.0
- UOPS_PORT_5: 27.44
- UOPS_RETIRED.ANY: 42.0

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:	0f 38 1c c1          	pabsb  mm0,mm1
  74:	0f 38 1c d1          	pabsb  mm2,mm1
  78:	0f 38 1c d9          	pabsb  mm3,mm1
  7c:	0f 38 1c e1          	pabsb  mm4,mm1
  80:	0f 38 1c e9          	pabsb  mm5,mm1
  84:	0f 38 1c f1          	pabsb  mm6,mm1
  88:	0f 38 1c f9          	pabsb  mm7,mm1
  8c:	0f 38 1c c1          	pabsb  mm0,mm1
  90:	0f 38 1c d1          	pabsb  mm2,mm1
  94:	0f 38 1c d9          	pabsb  mm3,mm1
  98:	0f 38 1c e1          	pabsb  mm4,mm1
  9c:	0f 38 1c e9          	pabsb  mm5,mm1
  a0:	0f 38 1c f1          	pabsb  mm6,mm1
  a4:	0f 38 1c f9          	pabsb  mm7,mm1
  a8:	0f 38 1c c1          	pabsb  mm0,mm1
  ac:	0f 38 1c d1          	pabsb  mm2,mm1
  b0:	0f 38 1c d9          	pabsb  mm3,mm1
  b4:	0f 38 1c e1          	pabsb  mm4,mm1
  b8:	0f 38 1c e9          	pabsb  mm5,mm1
  bc:	0f 38 1c f1          	pabsb  mm6,mm1
  c0:	0f 38 1c f9          	pabsb  mm7,mm1
  c4:	0f 38 1c c1          	pabsb  mm0,mm1
  c8:	0f 38 1c d1          	pabsb  mm2,mm1
  cc:	0f 38 1c d9          	pabsb  mm3,mm1
  d0:	66 0f 3a 44 c1 02    	pclmullqhqdq xmm0,xmm1

Init:

PXOR MM1, MM1;
PXOR XMM0, XMM0;
PXOR XMM1, XMM1

Show nanoBench command
Results:
- Instructions retired: 53.0
- Core cycles: 29.53
- Reference cycles: 27.16
- UOPS_PORT_0: 29.16
- UOPS_PORT_1: 9.79
- UOPS_PORT_2: 0.0
- UOPS_PORT_3: 0.0
- UOPS_PORT_4: 0.0
- UOPS_PORT_5: 30.27
- UOPS_RETIRED.ANY: 68.0

⇨ 6 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:	bb 00 00 00 01       	mov    ebx,0x1000000
  23:	b9 00 00 00 01       	mov    ecx,0x1000000
  28:	ba 00 00 00 01       	mov    edx,0x1000000
  2d:	41 b8 00 00 00 01    	mov    r8d,0x1000000
  33:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  39:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  3f:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  45:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  4b:	bb 00 00 00 01       	mov    ebx,0x1000000
  50:	b9 00 00 00 01       	mov    ecx,0x1000000
  55:	ba 00 00 00 01       	mov    edx,0x1000000
  5a:	41 b8 00 00 00 01    	mov    r8d,0x1000000
  60:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  66:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  6c:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  72:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  78:	bb 00 00 00 01       	mov    ebx,0x1000000
  7d:	b9 00 00 00 01       	mov    ecx,0x1000000
  82:	ba 00 00 00 01       	mov    edx,0x1000000
  87:	41 b8 00 00 00 01    	mov    r8d,0x1000000
  8d:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  93:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  99:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  9f:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  a5:	bb 00 00 00 01       	mov    ebx,0x1000000
  aa:	b9 00 00 00 01       	mov    ecx,0x1000000
  af:	ba 00 00 00 01       	mov    edx,0x1000000
  b4:	41 b8 00 00 00 01    	mov    r8d,0x1000000
  ba:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  c0:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  c6:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  cc:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  d2:	bb 00 00 00 01       	mov    ebx,0x1000000
  d7:	b9 00 00 00 01       	mov    ecx,0x1000000
  dc:	ba 00 00 00 01       	mov    edx,0x1000000
  e1:	41 b8 00 00 00 01    	mov    r8d,0x1000000
  e7:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  ed:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  f3:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  f9:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  ff:	bb 00 00 00 01       	mov    ebx,0x1000000
 104:	b9 00 00 00 01       	mov    ecx,0x1000000
 109:	ba 00 00 00 01       	mov    edx,0x1000000
 10e:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 114:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 11a:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 120:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 126:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 12c:	bb 00 00 00 01       	mov    ebx,0x1000000
 131:	b9 00 00 00 01       	mov    ecx,0x1000000
 136:	ba 00 00 00 01       	mov    edx,0x1000000
 13b:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 141:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 147:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 14d:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 153:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 159:	bb 00 00 00 01       	mov    ebx,0x1000000
 15e:	b9 00 00 00 01       	mov    ecx,0x1000000
 163:	ba 00 00 00 01       	mov    edx,0x1000000
 168:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 16e:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 174:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 17a:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 180:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 186:	bb 00 00 00 01       	mov    ebx,0x1000000
 18b:	b9 00 00 00 01       	mov    ecx,0x1000000
 190:	ba 00 00 00 01       	mov    edx,0x1000000
 195:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 19b:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 1a1:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 1a7:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 1ad:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 1b3:	bb 00 00 00 01       	mov    ebx,0x1000000
 1b8:	66 0f 3a 44 c1 02    	pclmullqhqdq xmm0,xmm1

Init:
```
PXOR XMM0, XMM0;
PXOR XMM1, XMM1
```
Show nanoBench command
Results:
- Instructions retired: 79.0
- Core cycles: 35.33
- Reference cycles: 33.0
- UOPS_PORT_0: 32.0
- UOPS_PORT_1: 29.83
- UOPS_PORT_2: 0.0
- UOPS_PORT_3: 0.0
- UOPS_PORT_4: 0.0
- UOPS_PORT_5: 31.76
- UOPS_RETIRED.ANY: 94.0

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