RCL (R64, CL) - Port Usage

With blocking instructions for port '0':

Code:

   0:	66 44 0f 50 c8       	movmskpd r9d,xmm0
   5:	66 44 0f 50 d0       	movmskpd r10d,xmm0
   a:	66 44 0f 50 d8       	movmskpd r11d,xmm0
   f:	66 44 0f 50 e0       	movmskpd r12d,xmm0
  14:	66 0f 50 d8          	movmskpd ebx,xmm0
  18:	66 0f 50 d0          	movmskpd edx,xmm0
  1c:	66 44 0f 50 c8       	movmskpd r9d,xmm0
  21:	66 44 0f 50 d0       	movmskpd r10d,xmm0
  26:	66 44 0f 50 d8       	movmskpd r11d,xmm0
  2b:	66 44 0f 50 e0       	movmskpd r12d,xmm0
  30:	66 0f 50 d8          	movmskpd ebx,xmm0
  34:	66 0f 50 d0          	movmskpd edx,xmm0
  38:	66 44 0f 50 c8       	movmskpd r9d,xmm0
  3d:	66 44 0f 50 d0       	movmskpd r10d,xmm0
  42:	66 44 0f 50 d8       	movmskpd r11d,xmm0
  47:	66 44 0f 50 e0       	movmskpd r12d,xmm0
  4c:	66 0f 50 d8          	movmskpd ebx,xmm0
  50:	66 0f 50 d0          	movmskpd edx,xmm0
  54:	66 44 0f 50 c8       	movmskpd r9d,xmm0
  59:	66 44 0f 50 d0       	movmskpd r10d,xmm0
  5e:	66 44 0f 50 d8       	movmskpd r11d,xmm0
  63:	66 44 0f 50 e0       	movmskpd r12d,xmm0
  68:	66 0f 50 d8          	movmskpd ebx,xmm0
  6c:	66 0f 50 d0          	movmskpd edx,xmm0
  70:	66 44 0f 50 c8       	movmskpd r9d,xmm0
  75:	66 44 0f 50 d0       	movmskpd r10d,xmm0
  7a:	49 d3 d0             	rcl    r8,cl

Init:

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

Show nanoBench command
Results:
- Instructions retired: 27.0
- Core cycles: 25.95
- Reference cycles: 21.58
- UOPS_PORT_0: 26.05
- UOPS_PORT_1: 2.95
- UOPS_PORT_2: 0.0
- UOPS_PORT_3: 0.0
- UOPS_PORT_4: 0.0
- UOPS_PORT_5: 0.0
- UOPS_RETIRED.ANY: 32.0

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:	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:	66 0f 58 c1          	addpd  xmm0,xmm1
  6e:	66 0f 58 d1          	addpd  xmm2,xmm1
  72:	49 d3 d0             	rcl    r8,cl

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]

Show nanoBench command
Results:
- Instructions retired: 27.0
- Core cycles: 34.16
- Reference cycles: 28.68
- UOPS_PORT_0: 1.58
- UOPS_PORT_1: 27.92
- UOPS_PORT_2: 0.0
- UOPS_PORT_3: 0.0
- UOPS_PORT_4: 0.0
- UOPS_PORT_5: 0.0
- UOPS_RETIRED.ANY: 32.0

⇨ 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:	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:	49 d3 d0             	rcl    r8,cl

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

Show nanoBench command
Results:
- Instructions retired: 27.0
- Core cycles: 25.97
- Reference cycles: 21.58
- UOPS_PORT_0: 2.97
- UOPS_PORT_1: 3.08
- UOPS_PORT_2: 0.0
- UOPS_PORT_3: 0.0
- UOPS_PORT_4: 0.0
- UOPS_PORT_5: 0.2
- UOPS_RETIRED.ANY: 32.0

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:	49 d3 d0             	rcl    r8,cl

Init:
```
PXOR MM1, MM1
```
Show nanoBench command
Results:
- Instructions retired: 53.0
- Core cycles: 26.63
- Reference cycles: 22.11
- UOPS_PORT_0: 26.58
- UOPS_PORT_1: 5.0
- UOPS_PORT_2: 0.0
- UOPS_PORT_3: 0.0
- UOPS_PORT_4: 0.0
- UOPS_PORT_5: 28.25
- UOPS_RETIRED.ANY: 58.0

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

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

Code:

   0:	41 b9 00 00 00 01    	mov    r9d,0x1000000
   6:	41 ba 00 00 00 01    	mov    r10d,0x1000000
   c:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  12:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  18:	bb 00 00 00 01       	mov    ebx,0x1000000
  1d:	ba 00 00 00 01       	mov    edx,0x1000000
  22:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  28:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  2e:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  34:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  3a:	bb 00 00 00 01       	mov    ebx,0x1000000
  3f:	ba 00 00 00 01       	mov    edx,0x1000000
  44:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  4a:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  50:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  56:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  5c:	bb 00 00 00 01       	mov    ebx,0x1000000
  61:	ba 00 00 00 01       	mov    edx,0x1000000
  66:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  6c:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  72:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  78:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  7e:	bb 00 00 00 01       	mov    ebx,0x1000000
  83:	ba 00 00 00 01       	mov    edx,0x1000000
  88:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  8e:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  94:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  9a:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  a0:	bb 00 00 00 01       	mov    ebx,0x1000000
  a5:	ba 00 00 00 01       	mov    edx,0x1000000
  aa:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  b0:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  b6:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  bc:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  c2:	bb 00 00 00 01       	mov    ebx,0x1000000
  c7:	ba 00 00 00 01       	mov    edx,0x1000000
  cc:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  d2:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  d8:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  de:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  e4:	bb 00 00 00 01       	mov    ebx,0x1000000
  e9:	ba 00 00 00 01       	mov    edx,0x1000000
  ee:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  f4:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  fa:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 100:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 106:	bb 00 00 00 01       	mov    ebx,0x1000000
 10b:	ba 00 00 00 01       	mov    edx,0x1000000
 110:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 116:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 11c:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 122:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 128:	bb 00 00 00 01       	mov    ebx,0x1000000
 12d:	ba 00 00 00 01       	mov    edx,0x1000000
 132:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 138:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 13e:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 144:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 14a:	bb 00 00 00 01       	mov    ebx,0x1000000
 14f:	ba 00 00 00 01       	mov    edx,0x1000000
 154:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 15a:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 160:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 166:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 16c:	bb 00 00 00 01       	mov    ebx,0x1000000
 171:	ba 00 00 00 01       	mov    edx,0x1000000
 176:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 17c:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 182:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 188:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 18e:	bb 00 00 00 01       	mov    ebx,0x1000000
 193:	ba 00 00 00 01       	mov    edx,0x1000000
 198:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 19e:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 1a4:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 1aa:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 1b0:	bb 00 00 00 01       	mov    ebx,0x1000000
 1b5:	ba 00 00 00 01       	mov    edx,0x1000000
 1ba:	49 d3 d0             	rcl    r8,cl

Show nanoBench command
Results:
- Instructions retired: 79.0
- Core cycles: 31.92
- Reference cycles: 26.67
- UOPS_PORT_0: 28.08
- UOPS_PORT_1: 27.25
- UOPS_PORT_2: 0.0
- UOPS_PORT_3: 0.0
- UOPS_PORT_4: 0.0
- UOPS_PORT_5: 31.92
- UOPS_RETIRED.ANY: 84.0

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