RDTSCP - 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 d8          	movmskpd ebx,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 d8          	movmskpd ebx,xmm0
  3a:	66 44 0f 50 c0       	movmskpd r8d,xmm0
  3f:	66 44 0f 50 c8       	movmskpd r9d,xmm0
  44:	66 44 0f 50 d0       	movmskpd r10d,xmm0
  49:	66 44 0f 50 d8       	movmskpd r11d,xmm0
  4e:	66 44 0f 50 e0       	movmskpd r12d,xmm0
  53:	66 0f 50 d8          	movmskpd ebx,xmm0
  57:	66 44 0f 50 c0       	movmskpd r8d,xmm0
  5c:	66 44 0f 50 c8       	movmskpd r9d,xmm0
  61:	66 44 0f 50 d0       	movmskpd r10d,xmm0
  66:	66 44 0f 50 d8       	movmskpd r11d,xmm0
  6b:	66 44 0f 50 e0       	movmskpd r12d,xmm0
  70:	66 0f 50 d8          	movmskpd ebx,xmm0
  74:	66 44 0f 50 c0       	movmskpd r8d,xmm0
  79:	66 44 0f 50 c8       	movmskpd r9d,xmm0
  7e:	66 44 0f 50 d0       	movmskpd r10d,xmm0
  83:	66 44 0f 50 d8       	movmskpd r11d,xmm0
  88:	66 44 0f 50 e0       	movmskpd r12d,xmm0
  8d:	66 0f 50 d8          	movmskpd ebx,xmm0
  91:	66 44 0f 50 c0       	movmskpd r8d,xmm0
  96:	66 44 0f 50 c8       	movmskpd r9d,xmm0
  9b:	66 44 0f 50 d0       	movmskpd r10d,xmm0
  a0:	66 44 0f 50 d8       	movmskpd r11d,xmm0
  a5:	66 44 0f 50 e0       	movmskpd r12d,xmm0
  aa:	66 0f 50 d8          	movmskpd ebx,xmm0
  ae:	66 44 0f 50 c0       	movmskpd r8d,xmm0
  b3:	66 44 0f 50 c8       	movmskpd r9d,xmm0
  b8:	66 44 0f 50 d0       	movmskpd r10d,xmm0
  bd:	66 44 0f 50 d8       	movmskpd r11d,xmm0
  c2:	66 44 0f 50 e0       	movmskpd r12d,xmm0
  c7:	66 0f 50 d8          	movmskpd ebx,xmm0
  cb:	66 44 0f 50 c0       	movmskpd r8d,xmm0
  d0:	66 44 0f 50 c8       	movmskpd r9d,xmm0
  d5:	66 44 0f 50 d0       	movmskpd r10d,xmm0
  da:	66 44 0f 50 d8       	movmskpd r11d,xmm0
  df:	66 44 0f 50 e0       	movmskpd r12d,xmm0
  e4:	66 0f 50 d8          	movmskpd ebx,xmm0
  e8:	66 44 0f 50 c0       	movmskpd r8d,xmm0
  ed:	66 44 0f 50 c8       	movmskpd r9d,xmm0
  f2:	66 44 0f 50 d0       	movmskpd r10d,xmm0
  f7:	66 44 0f 50 d8       	movmskpd r11d,xmm0
  fc:	66 44 0f 50 e0       	movmskpd r12d,xmm0
 101:	66 0f 50 d8          	movmskpd ebx,xmm0
 105:	66 44 0f 50 c0       	movmskpd r8d,xmm0
 10a:	66 44 0f 50 c8       	movmskpd r9d,xmm0
 10f:	66 44 0f 50 d0       	movmskpd r10d,xmm0
 114:	66 44 0f 50 d8       	movmskpd r11d,xmm0
 119:	66 44 0f 50 e0       	movmskpd r12d,xmm0
 11e:	66 0f 50 d8          	movmskpd ebx,xmm0
 122:	66 44 0f 50 c0       	movmskpd r8d,xmm0
 127:	66 44 0f 50 c8       	movmskpd r9d,xmm0
 12c:	0f 01 f9             	rdtscp

Init:

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

Show nanoBench command
Results:
- Instructions retired: 63.0
- Core cycles: 77.5
- Reference cycles: 65.0
- UOPS_PORT_0: 68.13
- UOPS_PORT_1: 8.94
- UOPS_PORT_2: 0.0
- UOPS_PORT_3: 0.0
- UOPS_PORT_4: 0.0
- UOPS_PORT_5: 77.5
- UOPS_RETIRED.ANY: 87.0

⇨ 6 μops 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:	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:	66 0f 58 d9          	addpd  xmm3,xmm1
  76:	66 0f 58 e1          	addpd  xmm4,xmm1
  7a:	66 0f 58 e9          	addpd  xmm5,xmm1
  7e:	66 0f 58 f1          	addpd  xmm6,xmm1
  82:	66 0f 58 f9          	addpd  xmm7,xmm1
  86:	66 44 0f 58 c1       	addpd  xmm8,xmm1
  8b:	66 44 0f 58 c9       	addpd  xmm9,xmm1
  90:	66 44 0f 58 d1       	addpd  xmm10,xmm1
  95:	66 44 0f 58 d9       	addpd  xmm11,xmm1
  9a:	66 44 0f 58 e1       	addpd  xmm12,xmm1
  9f:	66 0f 58 c1          	addpd  xmm0,xmm1
  a3:	66 0f 58 d1          	addpd  xmm2,xmm1
  a7:	66 0f 58 d9          	addpd  xmm3,xmm1
  ab:	66 0f 58 e1          	addpd  xmm4,xmm1
  af:	66 0f 58 e9          	addpd  xmm5,xmm1
  b3:	66 0f 58 f1          	addpd  xmm6,xmm1
  b7:	66 0f 58 f9          	addpd  xmm7,xmm1
  bb:	66 44 0f 58 c1       	addpd  xmm8,xmm1
  c0:	66 44 0f 58 c9       	addpd  xmm9,xmm1
  c5:	66 44 0f 58 d1       	addpd  xmm10,xmm1
  ca:	66 44 0f 58 d9       	addpd  xmm11,xmm1
  cf:	66 44 0f 58 e1       	addpd  xmm12,xmm1
  d4:	66 0f 58 c1          	addpd  xmm0,xmm1
  d8:	66 0f 58 d1          	addpd  xmm2,xmm1
  dc:	66 0f 58 d9          	addpd  xmm3,xmm1
  e0:	66 0f 58 e1          	addpd  xmm4,xmm1
  e4:	66 0f 58 e9          	addpd  xmm5,xmm1
  e8:	66 0f 58 f1          	addpd  xmm6,xmm1
  ec:	66 0f 58 f9          	addpd  xmm7,xmm1
  f0:	66 44 0f 58 c1       	addpd  xmm8,xmm1
  f5:	66 44 0f 58 c9       	addpd  xmm9,xmm1
  fa:	66 44 0f 58 d1       	addpd  xmm10,xmm1
  ff:	66 44 0f 58 d9       	addpd  xmm11,xmm1
 104:	66 44 0f 58 e1       	addpd  xmm12,xmm1
 109:	66 0f 58 c1          	addpd  xmm0,xmm1
 10d:	66 0f 58 d1          	addpd  xmm2,xmm1
 111:	0f 01 f9             	rdtscp

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: 63.0
- Core cycles: 93.94
- Reference cycles: 78.33
- UOPS_PORT_0: 6.69
- UOPS_PORT_1: 70.94
- UOPS_PORT_2: 0.0
- UOPS_PORT_3: 0.0
- UOPS_PORT_4: 0.0
- UOPS_PORT_5: 0.0
- UOPS_RETIRED.ANY: 87.0

⇨ 9 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:	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:	66 0f 55 c1          	andnpd xmm0,xmm1
  a3:	66 0f 55 d1          	andnpd xmm2,xmm1
  a7:	66 0f 55 d9          	andnpd xmm3,xmm1
  ab:	66 0f 55 e1          	andnpd xmm4,xmm1
  af:	66 0f 55 e9          	andnpd xmm5,xmm1
  b3:	66 0f 55 f1          	andnpd xmm6,xmm1
  b7:	66 0f 55 f9          	andnpd xmm7,xmm1
  bb:	66 44 0f 55 c1       	andnpd xmm8,xmm1
  c0:	66 44 0f 55 c9       	andnpd xmm9,xmm1
  c5:	66 44 0f 55 d1       	andnpd xmm10,xmm1
  ca:	66 44 0f 55 d9       	andnpd xmm11,xmm1
  cf:	66 44 0f 55 e1       	andnpd xmm12,xmm1
  d4:	66 0f 55 c1          	andnpd xmm0,xmm1
  d8:	66 0f 55 d1          	andnpd xmm2,xmm1
  dc:	66 0f 55 d9          	andnpd xmm3,xmm1
  e0:	66 0f 55 e1          	andnpd xmm4,xmm1
  e4:	66 0f 55 e9          	andnpd xmm5,xmm1
  e8:	66 0f 55 f1          	andnpd xmm6,xmm1
  ec:	66 0f 55 f9          	andnpd xmm7,xmm1
  f0:	66 44 0f 55 c1       	andnpd xmm8,xmm1
  f5:	66 44 0f 55 c9       	andnpd xmm9,xmm1
  fa:	66 44 0f 55 d1       	andnpd xmm10,xmm1
  ff:	66 44 0f 55 d9       	andnpd xmm11,xmm1
 104:	66 44 0f 55 e1       	andnpd xmm12,xmm1
 109:	66 0f 55 c1          	andnpd xmm0,xmm1
 10d:	66 0f 55 d1          	andnpd xmm2,xmm1
 111:	0f 01 f9             	rdtscp

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: 63.0
- Core cycles: 96.06
- Reference cycles: 80.0
- UOPS_PORT_0: 6.44
- UOPS_PORT_1: 8.75
- UOPS_PORT_2: 0.0
- UOPS_PORT_3: 0.0
- UOPS_PORT_4: 0.0
- UOPS_PORT_5: 0.17
- UOPS_RETIRED.ANY: 87.0

⇨ 10 μops that can only use port '5'