MOVSB_REPE - Port Usage

With blocking instructions for port '0':

Code:

   0:	66 45 8d 06          	lea    r8w,[r14]
   4:	66 45 8d 0e          	lea    r9w,[r14]
   8:	66 45 8d 16          	lea    r10w,[r14]
   c:	66 45 8d 1e          	lea    r11w,[r14]
  10:	66 45 8d 26          	lea    r12w,[r14]
  14:	66 41 8d 1e          	lea    bx,[r14]
  18:	66 41 8d 16          	lea    dx,[r14]
  1c:	66 45 8d 06          	lea    r8w,[r14]
  20:	66 45 8d 0e          	lea    r9w,[r14]
  24:	66 45 8d 16          	lea    r10w,[r14]
  28:	66 45 8d 1e          	lea    r11w,[r14]
  2c:	66 45 8d 26          	lea    r12w,[r14]
  30:	66 41 8d 1e          	lea    bx,[r14]
  34:	66 41 8d 16          	lea    dx,[r14]
  38:	66 45 8d 06          	lea    r8w,[r14]
  3c:	66 45 8d 0e          	lea    r9w,[r14]
  40:	66 45 8d 16          	lea    r10w,[r14]
  44:	66 45 8d 1e          	lea    r11w,[r14]
  48:	66 45 8d 26          	lea    r12w,[r14]
  4c:	66 41 8d 1e          	lea    bx,[r14]
  50:	66 41 8d 16          	lea    dx,[r14]
  54:	66 45 8d 06          	lea    r8w,[r14]
  58:	66 45 8d 0e          	lea    r9w,[r14]
  5c:	66 45 8d 16          	lea    r10w,[r14]
  60:	66 45 8d 1e          	lea    r11w,[r14]
  64:	66 45 8d 26          	lea    r12w,[r14]
  68:	66 41 8d 1e          	lea    bx,[r14]
  6c:	48 c7 c1 02 00 00 00 	mov    rcx,0x2
  73:	f3 a4                	rep movs BYTE PTR es:[rdi],BYTE PTR ds:[rsi]

Show nanoBench command
Results:
- Instructions retired: 29.0
- Core cycles: 27.14
- Reference cycles: 27.0
- UOPS_PORT_0: 27.05

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:	48 c7 c1 02 00 00 00 	mov    rcx,0x2
  7d:	f3 a4                	rep movs BYTE PTR es:[rdi],BYTE PTR ds:[rsi]

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: 29.0
- Core cycles: 34.14
- Reference cycles: 34.05
- UOPS_PORT_1: 32.0

⇨ 5 μops that can only use port '1'

With blocking instructions for port '2':

Code:

   0:	66 45 8b 46 40       	mov    r8w,WORD PTR [r14+0x40]
   5:	66 45 8b 4e 42       	mov    r9w,WORD PTR [r14+0x42]
   a:	66 45 8b 56 44       	mov    r10w,WORD PTR [r14+0x44]
   f:	66 45 8b 5e 46       	mov    r11w,WORD PTR [r14+0x46]
  14:	66 45 8b 66 48       	mov    r12w,WORD PTR [r14+0x48]
  19:	66 41 8b 5e 4a       	mov    bx,WORD PTR [r14+0x4a]
  1e:	66 41 8b 56 4c       	mov    dx,WORD PTR [r14+0x4c]
  23:	66 45 8b 46 40       	mov    r8w,WORD PTR [r14+0x40]
  28:	66 45 8b 4e 42       	mov    r9w,WORD PTR [r14+0x42]
  2d:	66 45 8b 56 44       	mov    r10w,WORD PTR [r14+0x44]
  32:	66 45 8b 5e 46       	mov    r11w,WORD PTR [r14+0x46]
  37:	66 45 8b 66 48       	mov    r12w,WORD PTR [r14+0x48]
  3c:	66 41 8b 5e 4a       	mov    bx,WORD PTR [r14+0x4a]
  41:	66 41 8b 56 4c       	mov    dx,WORD PTR [r14+0x4c]
  46:	66 45 8b 46 40       	mov    r8w,WORD PTR [r14+0x40]
  4b:	66 45 8b 4e 42       	mov    r9w,WORD PTR [r14+0x42]
  50:	66 45 8b 56 44       	mov    r10w,WORD PTR [r14+0x44]
  55:	66 45 8b 5e 46       	mov    r11w,WORD PTR [r14+0x46]
  5a:	66 45 8b 66 48       	mov    r12w,WORD PTR [r14+0x48]
  5f:	66 41 8b 5e 4a       	mov    bx,WORD PTR [r14+0x4a]
  64:	66 41 8b 56 4c       	mov    dx,WORD PTR [r14+0x4c]
  69:	66 45 8b 46 40       	mov    r8w,WORD PTR [r14+0x40]
  6e:	66 45 8b 4e 42       	mov    r9w,WORD PTR [r14+0x42]
  73:	66 45 8b 56 44       	mov    r10w,WORD PTR [r14+0x44]
  78:	66 45 8b 5e 46       	mov    r11w,WORD PTR [r14+0x46]
  7d:	66 45 8b 66 48       	mov    r12w,WORD PTR [r14+0x48]
  82:	66 41 8b 5e 4a       	mov    bx,WORD PTR [r14+0x4a]
  87:	48 c7 c1 02 00 00 00 	mov    rcx,0x2
  8e:	f3 a4                	rep movs BYTE PTR es:[rdi],BYTE PTR ds:[rsi]

Show nanoBench command
Results:
- Instructions retired: 29.0
- Core cycles: 30.24
- Reference cycles: 30.16
- UOPS_PORT_2: 30.0

⇨ 3 μops that can only use port '2'

With blocking instructions for port '3':

Code:

   0:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
   4:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
   8:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
   c:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
  10:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
  14:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
  18:	4d 89 46 70          	mov    QWORD PTR [r14+0x70],r8
  1c:	4d 89 46 78          	mov    QWORD PTR [r14+0x78],r8
  20:	4d 89 86 80 00 00 00 	mov    QWORD PTR [r14+0x80],r8
  27:	4d 89 86 88 00 00 00 	mov    QWORD PTR [r14+0x88],r8
  2e:	4d 89 86 90 00 00 00 	mov    QWORD PTR [r14+0x90],r8
  35:	4d 89 86 98 00 00 00 	mov    QWORD PTR [r14+0x98],r8
  3c:	4d 89 86 a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r8
  43:	4d 89 86 a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r8
  4a:	4d 89 86 b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r8
  51:	4d 89 86 b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r8
  58:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
  5c:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
  60:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
  64:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
  68:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
  6c:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
  70:	4d 89 46 70          	mov    QWORD PTR [r14+0x70],r8
  74:	4d 89 46 78          	mov    QWORD PTR [r14+0x78],r8
  78:	4d 89 86 80 00 00 00 	mov    QWORD PTR [r14+0x80],r8
  7f:	4d 89 86 88 00 00 00 	mov    QWORD PTR [r14+0x88],r8
  86:	4d 89 86 90 00 00 00 	mov    QWORD PTR [r14+0x90],r8
  8d:	48 c7 c1 02 00 00 00 	mov    rcx,0x2
  94:	f3 a4                	rep movs BYTE PTR es:[rdi],BYTE PTR ds:[rsi]

Show nanoBench command
Results:
- Instructions retired: 29.0
- Core cycles: 32.54
- Reference cycles: 32.35
- UOPS_PORT_3: 30.0

⇨ 3 μops that can only use port '3'

With blocking instructions for port '4':

Code:

   0:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
   4:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
   8:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
   c:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
  10:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
  14:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
  18:	4d 89 46 70          	mov    QWORD PTR [r14+0x70],r8
  1c:	4d 89 46 78          	mov    QWORD PTR [r14+0x78],r8
  20:	4d 89 86 80 00 00 00 	mov    QWORD PTR [r14+0x80],r8
  27:	4d 89 86 88 00 00 00 	mov    QWORD PTR [r14+0x88],r8
  2e:	4d 89 86 90 00 00 00 	mov    QWORD PTR [r14+0x90],r8
  35:	4d 89 86 98 00 00 00 	mov    QWORD PTR [r14+0x98],r8
  3c:	4d 89 86 a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r8
  43:	4d 89 86 a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r8
  4a:	4d 89 86 b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r8
  51:	4d 89 86 b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r8
  58:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
  5c:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
  60:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
  64:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
  68:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
  6c:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
  70:	4d 89 46 70          	mov    QWORD PTR [r14+0x70],r8
  74:	4d 89 46 78          	mov    QWORD PTR [r14+0x78],r8
  78:	4d 89 86 80 00 00 00 	mov    QWORD PTR [r14+0x80],r8
  7f:	4d 89 86 88 00 00 00 	mov    QWORD PTR [r14+0x88],r8
  86:	4d 89 86 90 00 00 00 	mov    QWORD PTR [r14+0x90],r8
  8d:	48 c7 c1 02 00 00 00 	mov    rcx,0x2
  94:	f3 a4                	rep movs BYTE PTR es:[rdi],BYTE PTR ds:[rsi]

Show nanoBench command
Results:
- Instructions retired: 29.0
- Core cycles: 32.54
- Reference cycles: 32.35
- UOPS_PORT_4: 30.0

⇨ 3 μops 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:	48 c7 c1 02 00 00 00 	mov    rcx,0x2
  b3:	f3 a4                	rep movs BYTE PTR es:[rdi],BYTE PTR ds:[rsi]

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: 29.0
- Core cycles: 34.14
- Reference cycles: 34.05
- UOPS_PORT_5: 31.73

⇨ 4 μops that can only use port '5'

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

Code:

   0:	41 0f 6e c0          	movd   mm0,r8d
   4:	41 0f 6e c8          	movd   mm1,r8d
   8:	41 0f 6e d0          	movd   mm2,r8d
   c:	41 0f 6e d8          	movd   mm3,r8d
  10:	41 0f 6e e0          	movd   mm4,r8d
  14:	41 0f 6e e8          	movd   mm5,r8d
  18:	41 0f 6e f0          	movd   mm6,r8d
  1c:	41 0f 6e f8          	movd   mm7,r8d
  20:	41 0f 6e c0          	movd   mm0,r8d
  24:	41 0f 6e c8          	movd   mm1,r8d
  28:	41 0f 6e d0          	movd   mm2,r8d
  2c:	41 0f 6e d8          	movd   mm3,r8d
  30:	41 0f 6e e0          	movd   mm4,r8d
  34:	41 0f 6e e8          	movd   mm5,r8d
  38:	41 0f 6e f0          	movd   mm6,r8d
  3c:	41 0f 6e f8          	movd   mm7,r8d
  40:	41 0f 6e c0          	movd   mm0,r8d
  44:	41 0f 6e c8          	movd   mm1,r8d
  48:	41 0f 6e d0          	movd   mm2,r8d
  4c:	41 0f 6e d8          	movd   mm3,r8d
  50:	41 0f 6e e0          	movd   mm4,r8d
  54:	41 0f 6e e8          	movd   mm5,r8d
  58:	41 0f 6e f0          	movd   mm6,r8d
  5c:	41 0f 6e f8          	movd   mm7,r8d
  60:	41 0f 6e c0          	movd   mm0,r8d
  64:	41 0f 6e c8          	movd   mm1,r8d
  68:	41 0f 6e d0          	movd   mm2,r8d
  6c:	41 0f 6e d8          	movd   mm3,r8d
  70:	41 0f 6e e0          	movd   mm4,r8d
  74:	41 0f 6e e8          	movd   mm5,r8d
  78:	41 0f 6e f0          	movd   mm6,r8d
  7c:	41 0f 6e f8          	movd   mm7,r8d
  80:	41 0f 6e c0          	movd   mm0,r8d
  84:	41 0f 6e c8          	movd   mm1,r8d
  88:	41 0f 6e d0          	movd   mm2,r8d
  8c:	41 0f 6e d8          	movd   mm3,r8d
  90:	41 0f 6e e0          	movd   mm4,r8d
  94:	41 0f 6e e8          	movd   mm5,r8d
  98:	41 0f 6e f0          	movd   mm6,r8d
  9c:	41 0f 6e f8          	movd   mm7,r8d
  a0:	41 0f 6e c0          	movd   mm0,r8d
  a4:	41 0f 6e c8          	movd   mm1,r8d
  a8:	41 0f 6e d0          	movd   mm2,r8d
  ac:	41 0f 6e d8          	movd   mm3,r8d
  b0:	41 0f 6e e0          	movd   mm4,r8d
  b4:	41 0f 6e e8          	movd   mm5,r8d
  b8:	41 0f 6e f0          	movd   mm6,r8d
  bc:	41 0f 6e f8          	movd   mm7,r8d
  c0:	41 0f 6e c0          	movd   mm0,r8d
  c4:	41 0f 6e c8          	movd   mm1,r8d
  c8:	41 0f 6e d0          	movd   mm2,r8d
  cc:	41 0f 6e d8          	movd   mm3,r8d
  d0:	41 0f 6e e0          	movd   mm4,r8d
  d4:	41 0f 6e e8          	movd   mm5,r8d
  d8:	48 c7 c1 02 00 00 00 	mov    rcx,0x2
  df:	f3 a4                	rep movs BYTE PTR es:[rdi],BYTE PTR ds:[rsi]

Show nanoBench command
Results:
- Instructions retired: 56.0
- Core cycles: 29.33
- Reference cycles: 29.08
- UOPS_PORT_0: 29.06
- UOPS_PORT_5: 29.06

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:	48 c7 c1 02 00 00 00 	mov    rcx,0x2
 16b:	f3 a4                	rep movs BYTE PTR es:[rdi],BYTE PTR ds:[rsi]

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: 83.0
- Core cycles: 88.33
- Reference cycles: 88.38
- UOPS_PORT_0: 10.67
- UOPS_PORT_1: 42.42
- UOPS_PORT_5: 45.92

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