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:	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: 61.0
- Core cycles: 75.94
- Reference cycles: 70.25
- UOPS_PORT_0: 66.38
- UOPS_PORT_1: 8.75
- UOPS_PORT_2: 0.0
- UOPS_PORT_3: 0.0
- UOPS_PORT_4: 0.0
- UOPS_PORT_5: 0.0
- UOPS_RETIRED.ANY: 83.0

⇨ 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:	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: 61.0
- Core cycles: 96.19
- Reference cycles: 88.5
- UOPS_PORT_0: 6.06
- UOPS_PORT_1: 68.75
- UOPS_PORT_2: 0.0
- UOPS_PORT_3: 0.0
- UOPS_PORT_4: 0.0
- UOPS_PORT_5: 0.0
- UOPS_RETIRED.ANY: 83.0

⇨ 8 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:	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: 61.0
- Core cycles: 92.5
- Reference cycles: 85.25
- UOPS_PORT_0: 6.06
- UOPS_PORT_1: 8.75
- UOPS_PORT_2: 0.0
- UOPS_PORT_3: 0.0
- UOPS_PORT_4: 0.0
- UOPS_PORT_5: -0.13
- UOPS_RETIRED.ANY: 83.0

⇨ 8 μops that can only use port '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:	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:	bb 00 00 00 01       	mov    ebx,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:	bb 00 00 00 01       	mov    ebx,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:	bb 00 00 00 01       	mov    ebx,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:	bb 00 00 00 01       	mov    ebx,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:	bb 00 00 00 01       	mov    ebx,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:	bb 00 00 00 01       	mov    ebx,0x1000000
  f5:	41 b8 00 00 00 01    	mov    r8d,0x1000000
  fb:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 101:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 107:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 10d:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 113:	bb 00 00 00 01       	mov    ebx,0x1000000
 118:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 11e:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 124:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 12a:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 130:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 136:	bb 00 00 00 01       	mov    ebx,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:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 164:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 16a:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 170:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 176:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 17c:	bb 00 00 00 01       	mov    ebx,0x1000000
 181:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 187:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 18d:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 193:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 199:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 19f:	bb 00 00 00 01       	mov    ebx,0x1000000
 1a4:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 1aa:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 1b0:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 1b6:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 1bc:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 1c2:	bb 00 00 00 01       	mov    ebx,0x1000000
 1c7:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 1cd:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 1d3:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 1d9:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 1df:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 1e5:	bb 00 00 00 01       	mov    ebx,0x1000000
 1ea:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 1f0:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 1f6:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 1fc:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 202:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 208:	bb 00 00 00 01       	mov    ebx,0x1000000
 20d:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 213:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 219:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 21f:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 225:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 22b:	bb 00 00 00 01       	mov    ebx,0x1000000
 230:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 236:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 23c:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 242:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 248:	0f 01 f9             	rdtscp

Show nanoBench command
Results:
- Instructions retired: 101.0
- Core cycles: 69.4
- Reference cycles: 63.2
- UOPS_PORT_0: 39.5
- UOPS_PORT_1: 41.5
- UOPS_PORT_2: 0.0
- UOPS_PORT_3: 0.0
- UOPS_PORT_4: 0.0
- UOPS_PORT_5: 0.0
- UOPS_RETIRED.ANY: 123.0

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