XCHG (M32, R32) - Port Usage

With blocking instructions for port '2':

Code:

   0:	66 45 8b 4e 40       	mov    r9w,WORD PTR [r14+0x40]
   5:	66 45 8b 56 42       	mov    r10w,WORD PTR [r14+0x42]
   a:	66 45 8b 5e 44       	mov    r11w,WORD PTR [r14+0x44]
   f:	66 45 8b 66 46       	mov    r12w,WORD PTR [r14+0x46]
  14:	66 41 8b 5e 48       	mov    bx,WORD PTR [r14+0x48]
  19:	66 41 8b 4e 4a       	mov    cx,WORD PTR [r14+0x4a]
  1e:	66 41 8b 56 4c       	mov    dx,WORD PTR [r14+0x4c]
  23:	66 45 8b 4e 40       	mov    r9w,WORD PTR [r14+0x40]
  28:	66 45 8b 56 42       	mov    r10w,WORD PTR [r14+0x42]
  2d:	66 45 8b 5e 44       	mov    r11w,WORD PTR [r14+0x44]
  32:	66 45 8b 66 46       	mov    r12w,WORD PTR [r14+0x46]
  37:	66 41 8b 5e 48       	mov    bx,WORD PTR [r14+0x48]
  3c:	66 41 8b 4e 4a       	mov    cx,WORD PTR [r14+0x4a]
  41:	66 41 8b 56 4c       	mov    dx,WORD PTR [r14+0x4c]
  46:	66 45 8b 4e 40       	mov    r9w,WORD PTR [r14+0x40]
  4b:	66 45 8b 56 42       	mov    r10w,WORD PTR [r14+0x42]
  50:	66 45 8b 5e 44       	mov    r11w,WORD PTR [r14+0x44]
  55:	66 45 8b 66 46       	mov    r12w,WORD PTR [r14+0x46]
  5a:	66 41 8b 5e 48       	mov    bx,WORD PTR [r14+0x48]
  5f:	66 41 8b 4e 4a       	mov    cx,WORD PTR [r14+0x4a]
  64:	66 41 8b 56 4c       	mov    dx,WORD PTR [r14+0x4c]
  69:	66 45 8b 4e 40       	mov    r9w,WORD PTR [r14+0x40]
  6e:	66 45 8b 56 42       	mov    r10w,WORD PTR [r14+0x42]
  73:	66 45 8b 5e 44       	mov    r11w,WORD PTR [r14+0x44]
  78:	66 45 8b 66 46       	mov    r12w,WORD PTR [r14+0x46]
  7d:	66 41 8b 5e 48       	mov    bx,WORD PTR [r14+0x48]
  82:	66 41 8b 4e 4a       	mov    cx,WORD PTR [r14+0x4a]
  87:	66 41 8b 56 4c       	mov    dx,WORD PTR [r14+0x4c]
  8c:	66 45 8b 4e 40       	mov    r9w,WORD PTR [r14+0x40]
  91:	66 45 8b 56 42       	mov    r10w,WORD PTR [r14+0x42]
  96:	66 45 8b 5e 44       	mov    r11w,WORD PTR [r14+0x44]
  9b:	66 45 8b 66 46       	mov    r12w,WORD PTR [r14+0x46]
  a0:	66 41 8b 5e 48       	mov    bx,WORD PTR [r14+0x48]
  a5:	66 41 8b 4e 4a       	mov    cx,WORD PTR [r14+0x4a]
  aa:	66 41 8b 56 4c       	mov    dx,WORD PTR [r14+0x4c]
  af:	66 45 8b 4e 40       	mov    r9w,WORD PTR [r14+0x40]
  b4:	45 87 06             	xchg   DWORD PTR [r14],r8d

Show nanoBench command
Results:
- Instructions retired: 37.0
- Core cycles: 58.74
- Reference cycles: 58.67
- UOPS_PORT_2: 37.0

⇨ One μop that can only use port '2'

With blocking instructions for port '3':

Code:

   0:	4d 89 4e 40          	mov    QWORD PTR [r14+0x40],r9
   4:	4d 89 4e 48          	mov    QWORD PTR [r14+0x48],r9
   8:	4d 89 4e 50          	mov    QWORD PTR [r14+0x50],r9
   c:	4d 89 4e 58          	mov    QWORD PTR [r14+0x58],r9
  10:	4d 89 4e 60          	mov    QWORD PTR [r14+0x60],r9
  14:	4d 89 4e 68          	mov    QWORD PTR [r14+0x68],r9
  18:	4d 89 4e 70          	mov    QWORD PTR [r14+0x70],r9
  1c:	4d 89 4e 78          	mov    QWORD PTR [r14+0x78],r9
  20:	4d 89 8e 80 00 00 00 	mov    QWORD PTR [r14+0x80],r9
  27:	4d 89 8e 88 00 00 00 	mov    QWORD PTR [r14+0x88],r9
  2e:	4d 89 8e 90 00 00 00 	mov    QWORD PTR [r14+0x90],r9
  35:	4d 89 8e 98 00 00 00 	mov    QWORD PTR [r14+0x98],r9
  3c:	4d 89 8e a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r9
  43:	4d 89 8e a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r9
  4a:	4d 89 8e b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r9
  51:	4d 89 8e b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r9
  58:	4d 89 4e 40          	mov    QWORD PTR [r14+0x40],r9
  5c:	4d 89 4e 48          	mov    QWORD PTR [r14+0x48],r9
  60:	4d 89 4e 50          	mov    QWORD PTR [r14+0x50],r9
  64:	4d 89 4e 58          	mov    QWORD PTR [r14+0x58],r9
  68:	4d 89 4e 60          	mov    QWORD PTR [r14+0x60],r9
  6c:	4d 89 4e 68          	mov    QWORD PTR [r14+0x68],r9
  70:	4d 89 4e 70          	mov    QWORD PTR [r14+0x70],r9
  74:	4d 89 4e 78          	mov    QWORD PTR [r14+0x78],r9
  78:	4d 89 8e 80 00 00 00 	mov    QWORD PTR [r14+0x80],r9
  7f:	4d 89 8e 88 00 00 00 	mov    QWORD PTR [r14+0x88],r9
  86:	4d 89 8e 90 00 00 00 	mov    QWORD PTR [r14+0x90],r9
  8d:	4d 89 8e 98 00 00 00 	mov    QWORD PTR [r14+0x98],r9
  94:	4d 89 8e a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r9
  9b:	4d 89 8e a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r9
  a2:	4d 89 8e b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r9
  a9:	4d 89 8e b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r9
  b0:	4d 89 4e 40          	mov    QWORD PTR [r14+0x40],r9
  b4:	4d 89 4e 48          	mov    QWORD PTR [r14+0x48],r9
  b8:	4d 89 4e 50          	mov    QWORD PTR [r14+0x50],r9
  bc:	4d 89 4e 58          	mov    QWORD PTR [r14+0x58],r9
  c0:	45 87 06             	xchg   DWORD PTR [r14],r8d

Show nanoBench command
Results:
- Instructions retired: 37.0
- Core cycles: 65.67
- Reference cycles: 65.67
- UOPS_PORT_3: 38.0

⇨ 2 μops that can only use port '3'

With blocking instructions for port '4':

Code:

   0:	4d 89 4e 40          	mov    QWORD PTR [r14+0x40],r9
   4:	4d 89 4e 48          	mov    QWORD PTR [r14+0x48],r9
   8:	4d 89 4e 50          	mov    QWORD PTR [r14+0x50],r9
   c:	4d 89 4e 58          	mov    QWORD PTR [r14+0x58],r9
  10:	4d 89 4e 60          	mov    QWORD PTR [r14+0x60],r9
  14:	4d 89 4e 68          	mov    QWORD PTR [r14+0x68],r9
  18:	4d 89 4e 70          	mov    QWORD PTR [r14+0x70],r9
  1c:	4d 89 4e 78          	mov    QWORD PTR [r14+0x78],r9
  20:	4d 89 8e 80 00 00 00 	mov    QWORD PTR [r14+0x80],r9
  27:	4d 89 8e 88 00 00 00 	mov    QWORD PTR [r14+0x88],r9
  2e:	4d 89 8e 90 00 00 00 	mov    QWORD PTR [r14+0x90],r9
  35:	4d 89 8e 98 00 00 00 	mov    QWORD PTR [r14+0x98],r9
  3c:	4d 89 8e a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r9
  43:	4d 89 8e a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r9
  4a:	4d 89 8e b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r9
  51:	4d 89 8e b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r9
  58:	4d 89 4e 40          	mov    QWORD PTR [r14+0x40],r9
  5c:	4d 89 4e 48          	mov    QWORD PTR [r14+0x48],r9
  60:	4d 89 4e 50          	mov    QWORD PTR [r14+0x50],r9
  64:	4d 89 4e 58          	mov    QWORD PTR [r14+0x58],r9
  68:	4d 89 4e 60          	mov    QWORD PTR [r14+0x60],r9
  6c:	4d 89 4e 68          	mov    QWORD PTR [r14+0x68],r9
  70:	4d 89 4e 70          	mov    QWORD PTR [r14+0x70],r9
  74:	4d 89 4e 78          	mov    QWORD PTR [r14+0x78],r9
  78:	4d 89 8e 80 00 00 00 	mov    QWORD PTR [r14+0x80],r9
  7f:	4d 89 8e 88 00 00 00 	mov    QWORD PTR [r14+0x88],r9
  86:	4d 89 8e 90 00 00 00 	mov    QWORD PTR [r14+0x90],r9
  8d:	4d 89 8e 98 00 00 00 	mov    QWORD PTR [r14+0x98],r9
  94:	4d 89 8e a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r9
  9b:	4d 89 8e a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r9
  a2:	4d 89 8e b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r9
  a9:	4d 89 8e b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r9
  b0:	4d 89 4e 40          	mov    QWORD PTR [r14+0x40],r9
  b4:	4d 89 4e 48          	mov    QWORD PTR [r14+0x48],r9
  b8:	4d 89 4e 50          	mov    QWORD PTR [r14+0x50],r9
  bc:	4d 89 4e 58          	mov    QWORD PTR [r14+0x58],r9
  c0:	45 87 06             	xchg   DWORD PTR [r14],r8d

Show nanoBench command
Results:
- Instructions retired: 37.0
- Core cycles: 65.67
- Reference cycles: 65.67
- UOPS_PORT_4: 38.0

⇨ One μop that can only use port '4'

With blocking instructions for port '5':

Code:

   0:	66 0f 3a 0d c1 02    	blendpd xmm0,xmm1,0x2
   6:	66 0f 3a 0d d1 02    	blendpd xmm2,xmm1,0x2
   c:	66 0f 3a 0d d9 02    	blendpd xmm3,xmm1,0x2
  12:	66 0f 3a 0d e1 02    	blendpd xmm4,xmm1,0x2
  18:	66 0f 3a 0d e9 02    	blendpd xmm5,xmm1,0x2
  1e:	66 0f 3a 0d f1 02    	blendpd xmm6,xmm1,0x2
  24:	66 0f 3a 0d f9 02    	blendpd xmm7,xmm1,0x2
  2a:	66 44 0f 3a 0d c1 02 	blendpd xmm8,xmm1,0x2
  31:	66 44 0f 3a 0d c9 02 	blendpd xmm9,xmm1,0x2
  38:	66 44 0f 3a 0d d1 02 	blendpd xmm10,xmm1,0x2
  3f:	66 44 0f 3a 0d d9 02 	blendpd xmm11,xmm1,0x2
  46:	66 44 0f 3a 0d e1 02 	blendpd xmm12,xmm1,0x2
  4d:	66 0f 3a 0d c1 02    	blendpd xmm0,xmm1,0x2
  53:	66 0f 3a 0d d1 02    	blendpd xmm2,xmm1,0x2
  59:	66 0f 3a 0d d9 02    	blendpd xmm3,xmm1,0x2
  5f:	66 0f 3a 0d e1 02    	blendpd xmm4,xmm1,0x2
  65:	66 0f 3a 0d e9 02    	blendpd xmm5,xmm1,0x2
  6b:	66 0f 3a 0d f1 02    	blendpd xmm6,xmm1,0x2
  71:	66 0f 3a 0d f9 02    	blendpd xmm7,xmm1,0x2
  77:	66 44 0f 3a 0d c1 02 	blendpd xmm8,xmm1,0x2
  7e:	66 44 0f 3a 0d c9 02 	blendpd xmm9,xmm1,0x2
  85:	66 44 0f 3a 0d d1 02 	blendpd xmm10,xmm1,0x2
  8c:	66 44 0f 3a 0d d9 02 	blendpd xmm11,xmm1,0x2
  93:	66 44 0f 3a 0d e1 02 	blendpd xmm12,xmm1,0x2
  9a:	66 0f 3a 0d c1 02    	blendpd xmm0,xmm1,0x2
  a0:	66 0f 3a 0d d1 02    	blendpd xmm2,xmm1,0x2
  a6:	66 0f 3a 0d d9 02    	blendpd xmm3,xmm1,0x2
  ac:	66 0f 3a 0d e1 02    	blendpd xmm4,xmm1,0x2
  b2:	66 0f 3a 0d e9 02    	blendpd xmm5,xmm1,0x2
  b8:	66 0f 3a 0d f1 02    	blendpd xmm6,xmm1,0x2
  be:	66 0f 3a 0d f9 02    	blendpd xmm7,xmm1,0x2
  c4:	66 44 0f 3a 0d c1 02 	blendpd xmm8,xmm1,0x2
  cb:	66 44 0f 3a 0d c9 02 	blendpd xmm9,xmm1,0x2
  d2:	66 44 0f 3a 0d d1 02 	blendpd xmm10,xmm1,0x2
  d9:	66 44 0f 3a 0d d9 02 	blendpd xmm11,xmm1,0x2
  e0:	66 44 0f 3a 0d e1 02 	blendpd xmm12,xmm1,0x2
  e7:	45 87 06             	xchg   DWORD PTR [r14],r8d

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: 37.0
- Core cycles: 38.04
- Reference cycles: 38.0
- UOPS_PORT_5: 36.85

⇨ One μop that can only use port '5'

With blocking instructions for ports {'0', '1', '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:	66 0f 55 d9          	andnpd xmm3,xmm1
 115:	66 0f 55 e1          	andnpd xmm4,xmm1
 119:	66 0f 55 e9          	andnpd xmm5,xmm1
 11d:	66 0f 55 f1          	andnpd xmm6,xmm1
 121:	66 0f 55 f9          	andnpd xmm7,xmm1
 125:	66 44 0f 55 c1       	andnpd xmm8,xmm1
 12a:	66 44 0f 55 c9       	andnpd xmm9,xmm1
 12f:	66 44 0f 55 d1       	andnpd xmm10,xmm1
 134:	66 44 0f 55 d9       	andnpd xmm11,xmm1
 139:	66 44 0f 55 e1       	andnpd xmm12,xmm1
 13e:	66 0f 55 c1          	andnpd xmm0,xmm1
 142:	66 0f 55 d1          	andnpd xmm2,xmm1
 146:	66 0f 55 d9          	andnpd xmm3,xmm1
 14a:	66 0f 55 e1          	andnpd xmm4,xmm1
 14e:	66 0f 55 e9          	andnpd xmm5,xmm1
 152:	66 0f 55 f1          	andnpd xmm6,xmm1
 156:	66 0f 55 f9          	andnpd xmm7,xmm1
 15a:	66 44 0f 55 c1       	andnpd xmm8,xmm1
 15f:	66 44 0f 55 c9       	andnpd xmm9,xmm1
 164:	66 44 0f 55 d1       	andnpd xmm10,xmm1
 169:	66 44 0f 55 d9       	andnpd xmm11,xmm1
 16e:	66 44 0f 55 e1       	andnpd xmm12,xmm1
 173:	66 0f 55 c1          	andnpd xmm0,xmm1
 177:	66 0f 55 d1          	andnpd xmm2,xmm1
 17b:	66 0f 55 d9          	andnpd xmm3,xmm1
 17f:	66 0f 55 e1          	andnpd xmm4,xmm1
 183:	66 0f 55 e9          	andnpd xmm5,xmm1
 187:	66 0f 55 f1          	andnpd xmm6,xmm1
 18b:	66 0f 55 f9          	andnpd xmm7,xmm1
 18f:	66 44 0f 55 c1       	andnpd xmm8,xmm1
 194:	66 44 0f 55 c9       	andnpd xmm9,xmm1
 199:	66 44 0f 55 d1       	andnpd xmm10,xmm1
 19e:	66 44 0f 55 d9       	andnpd xmm11,xmm1
 1a3:	66 44 0f 55 e1       	andnpd xmm12,xmm1
 1a8:	66 0f 55 c1          	andnpd xmm0,xmm1
 1ac:	66 0f 55 d1          	andnpd xmm2,xmm1
 1b0:	66 0f 55 d9          	andnpd xmm3,xmm1
 1b4:	66 0f 55 e1          	andnpd xmm4,xmm1
 1b8:	45 87 06             	xchg   DWORD PTR [r14],r8d

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: 101.0
- Core cycles: 101.4
- Reference cycles: 101.7
- UOPS_PORT_0: 12.7
- UOPS_PORT_1: 43.9
- UOPS_PORT_5: 45.4

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

With an indexed addressing mode

With blocking instructions for port '2':

Code:

   0:	66 45 8b 4e 40       	mov    r9w,WORD PTR [r14+0x40]
   5:	66 45 8b 56 42       	mov    r10w,WORD PTR [r14+0x42]
   a:	66 45 8b 5e 44       	mov    r11w,WORD PTR [r14+0x44]
   f:	66 45 8b 66 46       	mov    r12w,WORD PTR [r14+0x46]
  14:	66 41 8b 5e 48       	mov    bx,WORD PTR [r14+0x48]
  19:	66 41 8b 4e 4a       	mov    cx,WORD PTR [r14+0x4a]
  1e:	66 41 8b 56 4c       	mov    dx,WORD PTR [r14+0x4c]
  23:	66 45 8b 4e 40       	mov    r9w,WORD PTR [r14+0x40]
  28:	66 45 8b 56 42       	mov    r10w,WORD PTR [r14+0x42]
  2d:	66 45 8b 5e 44       	mov    r11w,WORD PTR [r14+0x44]
  32:	66 45 8b 66 46       	mov    r12w,WORD PTR [r14+0x46]
  37:	66 41 8b 5e 48       	mov    bx,WORD PTR [r14+0x48]
  3c:	66 41 8b 4e 4a       	mov    cx,WORD PTR [r14+0x4a]
  41:	66 41 8b 56 4c       	mov    dx,WORD PTR [r14+0x4c]
  46:	66 45 8b 4e 40       	mov    r9w,WORD PTR [r14+0x40]
  4b:	66 45 8b 56 42       	mov    r10w,WORD PTR [r14+0x42]
  50:	66 45 8b 5e 44       	mov    r11w,WORD PTR [r14+0x44]
  55:	66 45 8b 66 46       	mov    r12w,WORD PTR [r14+0x46]
  5a:	66 41 8b 5e 48       	mov    bx,WORD PTR [r14+0x48]
  5f:	66 41 8b 4e 4a       	mov    cx,WORD PTR [r14+0x4a]
  64:	66 41 8b 56 4c       	mov    dx,WORD PTR [r14+0x4c]
  69:	66 45 8b 4e 40       	mov    r9w,WORD PTR [r14+0x40]
  6e:	66 45 8b 56 42       	mov    r10w,WORD PTR [r14+0x42]
  73:	66 45 8b 5e 44       	mov    r11w,WORD PTR [r14+0x44]
  78:	66 45 8b 66 46       	mov    r12w,WORD PTR [r14+0x46]
  7d:	66 41 8b 5e 48       	mov    bx,WORD PTR [r14+0x48]
  82:	66 41 8b 4e 4a       	mov    cx,WORD PTR [r14+0x4a]
  87:	66 41 8b 56 4c       	mov    dx,WORD PTR [r14+0x4c]
  8c:	66 45 8b 4e 40       	mov    r9w,WORD PTR [r14+0x40]
  91:	66 45 8b 56 42       	mov    r10w,WORD PTR [r14+0x42]
  96:	66 45 8b 5e 44       	mov    r11w,WORD PTR [r14+0x44]
  9b:	66 45 8b 66 46       	mov    r12w,WORD PTR [r14+0x46]
  a0:	66 41 8b 5e 48       	mov    bx,WORD PTR [r14+0x48]
  a5:	66 41 8b 4e 4a       	mov    cx,WORD PTR [r14+0x4a]
  aa:	66 41 8b 56 4c       	mov    dx,WORD PTR [r14+0x4c]
  af:	66 45 8b 4e 40       	mov    r9w,WORD PTR [r14+0x40]
  b4:	47 87 04 2e          	xchg   DWORD PTR [r14+r13*1],r8d

Init:
```
XOR R13, R13
```
Show nanoBench command
Results:
- Instructions retired: 37.0
- Core cycles: 58.74
- Reference cycles: 58.67
- UOPS_PORT_2: 37.0

⇨ One μop that can only use port '2'

With blocking instructions for port '3':

Code:

   0:	4d 89 4e 40          	mov    QWORD PTR [r14+0x40],r9
   4:	4d 89 4e 48          	mov    QWORD PTR [r14+0x48],r9
   8:	4d 89 4e 50          	mov    QWORD PTR [r14+0x50],r9
   c:	4d 89 4e 58          	mov    QWORD PTR [r14+0x58],r9
  10:	4d 89 4e 60          	mov    QWORD PTR [r14+0x60],r9
  14:	4d 89 4e 68          	mov    QWORD PTR [r14+0x68],r9
  18:	4d 89 4e 70          	mov    QWORD PTR [r14+0x70],r9
  1c:	4d 89 4e 78          	mov    QWORD PTR [r14+0x78],r9
  20:	4d 89 8e 80 00 00 00 	mov    QWORD PTR [r14+0x80],r9
  27:	4d 89 8e 88 00 00 00 	mov    QWORD PTR [r14+0x88],r9
  2e:	4d 89 8e 90 00 00 00 	mov    QWORD PTR [r14+0x90],r9
  35:	4d 89 8e 98 00 00 00 	mov    QWORD PTR [r14+0x98],r9
  3c:	4d 89 8e a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r9
  43:	4d 89 8e a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r9
  4a:	4d 89 8e b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r9
  51:	4d 89 8e b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r9
  58:	4d 89 4e 40          	mov    QWORD PTR [r14+0x40],r9
  5c:	4d 89 4e 48          	mov    QWORD PTR [r14+0x48],r9
  60:	4d 89 4e 50          	mov    QWORD PTR [r14+0x50],r9
  64:	4d 89 4e 58          	mov    QWORD PTR [r14+0x58],r9
  68:	4d 89 4e 60          	mov    QWORD PTR [r14+0x60],r9
  6c:	4d 89 4e 68          	mov    QWORD PTR [r14+0x68],r9
  70:	4d 89 4e 70          	mov    QWORD PTR [r14+0x70],r9
  74:	4d 89 4e 78          	mov    QWORD PTR [r14+0x78],r9
  78:	4d 89 8e 80 00 00 00 	mov    QWORD PTR [r14+0x80],r9
  7f:	4d 89 8e 88 00 00 00 	mov    QWORD PTR [r14+0x88],r9
  86:	4d 89 8e 90 00 00 00 	mov    QWORD PTR [r14+0x90],r9
  8d:	4d 89 8e 98 00 00 00 	mov    QWORD PTR [r14+0x98],r9
  94:	4d 89 8e a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r9
  9b:	4d 89 8e a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r9
  a2:	4d 89 8e b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r9
  a9:	4d 89 8e b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r9
  b0:	4d 89 4e 40          	mov    QWORD PTR [r14+0x40],r9
  b4:	4d 89 4e 48          	mov    QWORD PTR [r14+0x48],r9
  b8:	4d 89 4e 50          	mov    QWORD PTR [r14+0x50],r9
  bc:	4d 89 4e 58          	mov    QWORD PTR [r14+0x58],r9
  c0:	47 87 04 2e          	xchg   DWORD PTR [r14+r13*1],r8d

Init:
```
XOR R13, R13
```
Show nanoBench command
Results:
- Instructions retired: 37.0
- Core cycles: 65.67
- Reference cycles: 65.67
- UOPS_PORT_3: 38.0

⇨ 2 μops that can only use port '3'

With blocking instructions for port '4':

Code:

   0:	4d 89 4e 40          	mov    QWORD PTR [r14+0x40],r9
   4:	4d 89 4e 48          	mov    QWORD PTR [r14+0x48],r9
   8:	4d 89 4e 50          	mov    QWORD PTR [r14+0x50],r9
   c:	4d 89 4e 58          	mov    QWORD PTR [r14+0x58],r9
  10:	4d 89 4e 60          	mov    QWORD PTR [r14+0x60],r9
  14:	4d 89 4e 68          	mov    QWORD PTR [r14+0x68],r9
  18:	4d 89 4e 70          	mov    QWORD PTR [r14+0x70],r9
  1c:	4d 89 4e 78          	mov    QWORD PTR [r14+0x78],r9
  20:	4d 89 8e 80 00 00 00 	mov    QWORD PTR [r14+0x80],r9
  27:	4d 89 8e 88 00 00 00 	mov    QWORD PTR [r14+0x88],r9
  2e:	4d 89 8e 90 00 00 00 	mov    QWORD PTR [r14+0x90],r9
  35:	4d 89 8e 98 00 00 00 	mov    QWORD PTR [r14+0x98],r9
  3c:	4d 89 8e a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r9
  43:	4d 89 8e a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r9
  4a:	4d 89 8e b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r9
  51:	4d 89 8e b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r9
  58:	4d 89 4e 40          	mov    QWORD PTR [r14+0x40],r9
  5c:	4d 89 4e 48          	mov    QWORD PTR [r14+0x48],r9
  60:	4d 89 4e 50          	mov    QWORD PTR [r14+0x50],r9
  64:	4d 89 4e 58          	mov    QWORD PTR [r14+0x58],r9
  68:	4d 89 4e 60          	mov    QWORD PTR [r14+0x60],r9
  6c:	4d 89 4e 68          	mov    QWORD PTR [r14+0x68],r9
  70:	4d 89 4e 70          	mov    QWORD PTR [r14+0x70],r9
  74:	4d 89 4e 78          	mov    QWORD PTR [r14+0x78],r9
  78:	4d 89 8e 80 00 00 00 	mov    QWORD PTR [r14+0x80],r9
  7f:	4d 89 8e 88 00 00 00 	mov    QWORD PTR [r14+0x88],r9
  86:	4d 89 8e 90 00 00 00 	mov    QWORD PTR [r14+0x90],r9
  8d:	4d 89 8e 98 00 00 00 	mov    QWORD PTR [r14+0x98],r9
  94:	4d 89 8e a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r9
  9b:	4d 89 8e a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r9
  a2:	4d 89 8e b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r9
  a9:	4d 89 8e b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r9
  b0:	4d 89 4e 40          	mov    QWORD PTR [r14+0x40],r9
  b4:	4d 89 4e 48          	mov    QWORD PTR [r14+0x48],r9
  b8:	4d 89 4e 50          	mov    QWORD PTR [r14+0x50],r9
  bc:	4d 89 4e 58          	mov    QWORD PTR [r14+0x58],r9
  c0:	47 87 04 2e          	xchg   DWORD PTR [r14+r13*1],r8d

Init:
```
XOR R13, R13
```
Show nanoBench command
Results:
- Instructions retired: 37.0
- Core cycles: 65.67
- Reference cycles: 65.67
- UOPS_PORT_4: 38.0

⇨ One μop that can only use port '4'

With blocking instructions for port '5':

Code:

   0:	66 0f 3a 0d c1 02    	blendpd xmm0,xmm1,0x2
   6:	66 0f 3a 0d d1 02    	blendpd xmm2,xmm1,0x2
   c:	66 0f 3a 0d d9 02    	blendpd xmm3,xmm1,0x2
  12:	66 0f 3a 0d e1 02    	blendpd xmm4,xmm1,0x2
  18:	66 0f 3a 0d e9 02    	blendpd xmm5,xmm1,0x2
  1e:	66 0f 3a 0d f1 02    	blendpd xmm6,xmm1,0x2
  24:	66 0f 3a 0d f9 02    	blendpd xmm7,xmm1,0x2
  2a:	66 44 0f 3a 0d c1 02 	blendpd xmm8,xmm1,0x2
  31:	66 44 0f 3a 0d c9 02 	blendpd xmm9,xmm1,0x2
  38:	66 44 0f 3a 0d d1 02 	blendpd xmm10,xmm1,0x2
  3f:	66 44 0f 3a 0d d9 02 	blendpd xmm11,xmm1,0x2
  46:	66 44 0f 3a 0d e1 02 	blendpd xmm12,xmm1,0x2
  4d:	66 0f 3a 0d c1 02    	blendpd xmm0,xmm1,0x2
  53:	66 0f 3a 0d d1 02    	blendpd xmm2,xmm1,0x2
  59:	66 0f 3a 0d d9 02    	blendpd xmm3,xmm1,0x2
  5f:	66 0f 3a 0d e1 02    	blendpd xmm4,xmm1,0x2
  65:	66 0f 3a 0d e9 02    	blendpd xmm5,xmm1,0x2
  6b:	66 0f 3a 0d f1 02    	blendpd xmm6,xmm1,0x2
  71:	66 0f 3a 0d f9 02    	blendpd xmm7,xmm1,0x2
  77:	66 44 0f 3a 0d c1 02 	blendpd xmm8,xmm1,0x2
  7e:	66 44 0f 3a 0d c9 02 	blendpd xmm9,xmm1,0x2
  85:	66 44 0f 3a 0d d1 02 	blendpd xmm10,xmm1,0x2
  8c:	66 44 0f 3a 0d d9 02 	blendpd xmm11,xmm1,0x2
  93:	66 44 0f 3a 0d e1 02 	blendpd xmm12,xmm1,0x2
  9a:	66 0f 3a 0d c1 02    	blendpd xmm0,xmm1,0x2
  a0:	66 0f 3a 0d d1 02    	blendpd xmm2,xmm1,0x2
  a6:	66 0f 3a 0d d9 02    	blendpd xmm3,xmm1,0x2
  ac:	66 0f 3a 0d e1 02    	blendpd xmm4,xmm1,0x2
  b2:	66 0f 3a 0d e9 02    	blendpd xmm5,xmm1,0x2
  b8:	66 0f 3a 0d f1 02    	blendpd xmm6,xmm1,0x2
  be:	66 0f 3a 0d f9 02    	blendpd xmm7,xmm1,0x2
  c4:	66 44 0f 3a 0d c1 02 	blendpd xmm8,xmm1,0x2
  cb:	66 44 0f 3a 0d c9 02 	blendpd xmm9,xmm1,0x2
  d2:	66 44 0f 3a 0d d1 02 	blendpd xmm10,xmm1,0x2
  d9:	66 44 0f 3a 0d d9 02 	blendpd xmm11,xmm1,0x2
  e0:	66 44 0f 3a 0d e1 02 	blendpd xmm12,xmm1,0x2
  e7:	47 87 04 2e          	xchg   DWORD PTR [r14+r13*1],r8d

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];
XOR R13, R13

Show nanoBench command
Results:
- Instructions retired: 37.0
- Core cycles: 39.52
- Reference cycles: 39.67
- UOPS_PORT_5: 36.85

⇨ One μop that can only use port '5'

With blocking instructions for ports {'0', '1', '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:	66 0f 55 d9          	andnpd xmm3,xmm1
 115:	66 0f 55 e1          	andnpd xmm4,xmm1
 119:	66 0f 55 e9          	andnpd xmm5,xmm1
 11d:	66 0f 55 f1          	andnpd xmm6,xmm1
 121:	66 0f 55 f9          	andnpd xmm7,xmm1
 125:	66 44 0f 55 c1       	andnpd xmm8,xmm1
 12a:	66 44 0f 55 c9       	andnpd xmm9,xmm1
 12f:	66 44 0f 55 d1       	andnpd xmm10,xmm1
 134:	66 44 0f 55 d9       	andnpd xmm11,xmm1
 139:	66 44 0f 55 e1       	andnpd xmm12,xmm1
 13e:	66 0f 55 c1          	andnpd xmm0,xmm1
 142:	66 0f 55 d1          	andnpd xmm2,xmm1
 146:	66 0f 55 d9          	andnpd xmm3,xmm1
 14a:	66 0f 55 e1          	andnpd xmm4,xmm1
 14e:	66 0f 55 e9          	andnpd xmm5,xmm1
 152:	66 0f 55 f1          	andnpd xmm6,xmm1
 156:	66 0f 55 f9          	andnpd xmm7,xmm1
 15a:	66 44 0f 55 c1       	andnpd xmm8,xmm1
 15f:	66 44 0f 55 c9       	andnpd xmm9,xmm1
 164:	66 44 0f 55 d1       	andnpd xmm10,xmm1
 169:	66 44 0f 55 d9       	andnpd xmm11,xmm1
 16e:	66 44 0f 55 e1       	andnpd xmm12,xmm1
 173:	66 0f 55 c1          	andnpd xmm0,xmm1
 177:	66 0f 55 d1          	andnpd xmm2,xmm1
 17b:	66 0f 55 d9          	andnpd xmm3,xmm1
 17f:	66 0f 55 e1          	andnpd xmm4,xmm1
 183:	66 0f 55 e9          	andnpd xmm5,xmm1
 187:	66 0f 55 f1          	andnpd xmm6,xmm1
 18b:	66 0f 55 f9          	andnpd xmm7,xmm1
 18f:	66 44 0f 55 c1       	andnpd xmm8,xmm1
 194:	66 44 0f 55 c9       	andnpd xmm9,xmm1
 199:	66 44 0f 55 d1       	andnpd xmm10,xmm1
 19e:	66 44 0f 55 d9       	andnpd xmm11,xmm1
 1a3:	66 44 0f 55 e1       	andnpd xmm12,xmm1
 1a8:	66 0f 55 c1          	andnpd xmm0,xmm1
 1ac:	66 0f 55 d1          	andnpd xmm2,xmm1
 1b0:	66 0f 55 d9          	andnpd xmm3,xmm1
 1b4:	66 0f 55 e1          	andnpd xmm4,xmm1
 1b8:	47 87 04 2e          	xchg   DWORD PTR [r14+r13*1],r8d

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;
XOR R13, R13

Show nanoBench command
Results:
- Instructions retired: 101.0
- Core cycles: 104.3
- Reference cycles: 104.4
- UOPS_PORT_0: 11.9
- UOPS_PORT_1: 44.2
- UOPS_PORT_5: 45.9

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