INC_LOCK (M32) - 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 0f 50 c8          	movmskpd ecx,xmm0
  21:	66 0f 50 d0          	movmskpd edx,xmm0
  25:	66 44 0f 50 c0       	movmskpd r8d,xmm0
  2a:	66 44 0f 50 c8       	movmskpd r9d,xmm0
  2f:	66 44 0f 50 d0       	movmskpd r10d,xmm0
  34:	66 44 0f 50 d8       	movmskpd r11d,xmm0
  39:	66 44 0f 50 e0       	movmskpd r12d,xmm0
  3e:	66 0f 50 d8          	movmskpd ebx,xmm0
  42:	66 0f 50 c8          	movmskpd ecx,xmm0
  46:	66 0f 50 d0          	movmskpd edx,xmm0
  4a:	66 44 0f 50 c0       	movmskpd r8d,xmm0
  4f:	66 44 0f 50 c8       	movmskpd r9d,xmm0
  54:	66 44 0f 50 d0       	movmskpd r10d,xmm0
  59:	66 44 0f 50 d8       	movmskpd r11d,xmm0
  5e:	66 44 0f 50 e0       	movmskpd r12d,xmm0
  63:	66 0f 50 d8          	movmskpd ebx,xmm0
  67:	66 0f 50 c8          	movmskpd ecx,xmm0
  6b:	66 0f 50 d0          	movmskpd edx,xmm0
  6f:	66 44 0f 50 c0       	movmskpd r8d,xmm0
  74:	66 44 0f 50 c8       	movmskpd r9d,xmm0
  79:	66 44 0f 50 d0       	movmskpd r10d,xmm0
  7e:	66 44 0f 50 d8       	movmskpd r11d,xmm0
  83:	66 44 0f 50 e0       	movmskpd r12d,xmm0
  88:	66 0f 50 d8          	movmskpd ebx,xmm0
  8c:	66 0f 50 c8          	movmskpd ecx,xmm0
  90:	66 0f 50 d0          	movmskpd edx,xmm0
  94:	66 44 0f 50 c0       	movmskpd r8d,xmm0
  99:	66 44 0f 50 c8       	movmskpd r9d,xmm0
  9e:	66 44 0f 50 d0       	movmskpd r10d,xmm0
  a3:	66 44 0f 50 d8       	movmskpd r11d,xmm0
  a8:	66 44 0f 50 e0       	movmskpd r12d,xmm0
  ad:	66 0f 50 d8          	movmskpd ebx,xmm0
  b1:	66 0f 50 c8          	movmskpd ecx,xmm0
  b5:	66 0f 50 d0          	movmskpd edx,xmm0
  b9:	f0 41 ff 06          	lock inc DWORD PTR [r14]

Init:

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

Show nanoBench command
Results:
- Instructions retired: 41.0
- Core cycles: 40.48
- Reference cycles: 33.6
- UOPS_PORT_0: 40.0
- UOPS_PORT_1: 1.2
- UOPS_PORT_2: 1.0
- UOPS_PORT_3: 1.0
- UOPS_PORT_4: 2.0
- UOPS_PORT_5: 0.0
- UOPS_RETIRED.ANY: 45.0

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:	f0 41 ff 06          	lock inc DWORD PTR [r14]

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: 41.0
- Core cycles: 40.56
- Reference cycles: 33.87
- UOPS_PORT_0: 1.44
- UOPS_PORT_1: 39.88
- UOPS_PORT_2: 1.0
- UOPS_PORT_3: 1.0
- UOPS_PORT_4: 2.0
- UOPS_PORT_5: 0.0
- UOPS_RETIRED.ANY: 45.0

With blocking instructions for port '2':

Code:

   0:	f2 41 0f f0 46 40    	lddqu  xmm0,[r14+0x40]
   6:	f2 41 0f f0 4e 50    	lddqu  xmm1,[r14+0x50]
   c:	f2 41 0f f0 56 60    	lddqu  xmm2,[r14+0x60]
  12:	f2 41 0f f0 5e 70    	lddqu  xmm3,[r14+0x70]
  18:	f2 41 0f f0 a6 80 00 	lddqu  xmm4,[r14+0x80]
  1f:	00 00 
  21:	f2 41 0f f0 ae 90 00 	lddqu  xmm5,[r14+0x90]
  28:	00 00 
  2a:	f2 41 0f f0 b6 a0 00 	lddqu  xmm6,[r14+0xa0]
  31:	00 00 
  33:	f2 41 0f f0 be b0 00 	lddqu  xmm7,[r14+0xb0]
  3a:	00 00 
  3c:	f2 45 0f f0 86 c0 00 	lddqu  xmm8,[r14+0xc0]
  43:	00 00 
  45:	f2 45 0f f0 8e d0 00 	lddqu  xmm9,[r14+0xd0]
  4c:	00 00 
  4e:	f2 45 0f f0 96 e0 00 	lddqu  xmm10,[r14+0xe0]
  55:	00 00 
  57:	f2 45 0f f0 9e f0 00 	lddqu  xmm11,[r14+0xf0]
  5e:	00 00 
  60:	f2 45 0f f0 a6 00 01 	lddqu  xmm12,[r14+0x100]
  67:	00 00 
  69:	f2 41 0f f0 46 40    	lddqu  xmm0,[r14+0x40]
  6f:	f2 41 0f f0 4e 50    	lddqu  xmm1,[r14+0x50]
  75:	f2 41 0f f0 56 60    	lddqu  xmm2,[r14+0x60]
  7b:	f2 41 0f f0 5e 70    	lddqu  xmm3,[r14+0x70]
  81:	f2 41 0f f0 a6 80 00 	lddqu  xmm4,[r14+0x80]
  88:	00 00 
  8a:	f2 41 0f f0 ae 90 00 	lddqu  xmm5,[r14+0x90]
  91:	00 00 
  93:	f2 41 0f f0 b6 a0 00 	lddqu  xmm6,[r14+0xa0]
  9a:	00 00 
  9c:	f2 41 0f f0 be b0 00 	lddqu  xmm7,[r14+0xb0]
  a3:	00 00 
  a5:	f2 45 0f f0 86 c0 00 	lddqu  xmm8,[r14+0xc0]
  ac:	00 00 
  ae:	f2 45 0f f0 8e d0 00 	lddqu  xmm9,[r14+0xd0]
  b5:	00 00 
  b7:	f2 45 0f f0 96 e0 00 	lddqu  xmm10,[r14+0xe0]
  be:	00 00 
  c0:	f2 45 0f f0 9e f0 00 	lddqu  xmm11,[r14+0xf0]
  c7:	00 00 
  c9:	f2 45 0f f0 a6 00 01 	lddqu  xmm12,[r14+0x100]
  d0:	00 00 
  d2:	f2 41 0f f0 46 40    	lddqu  xmm0,[r14+0x40]
  d8:	f2 41 0f f0 4e 50    	lddqu  xmm1,[r14+0x50]
  de:	f2 41 0f f0 56 60    	lddqu  xmm2,[r14+0x60]
  e4:	f2 41 0f f0 5e 70    	lddqu  xmm3,[r14+0x70]
  ea:	f2 41 0f f0 a6 80 00 	lddqu  xmm4,[r14+0x80]
  f1:	00 00 
  f3:	f2 41 0f f0 ae 90 00 	lddqu  xmm5,[r14+0x90]
  fa:	00 00 
  fc:	f2 41 0f f0 b6 a0 00 	lddqu  xmm6,[r14+0xa0]
 103:	00 00 
 105:	f2 41 0f f0 be b0 00 	lddqu  xmm7,[r14+0xb0]
 10c:	00 00 
 10e:	f2 45 0f f0 86 c0 00 	lddqu  xmm8,[r14+0xc0]
 115:	00 00 
 117:	f2 45 0f f0 8e d0 00 	lddqu  xmm9,[r14+0xd0]
 11e:	00 00 
 120:	f2 45 0f f0 96 e0 00 	lddqu  xmm10,[r14+0xe0]
 127:	00 00 
 129:	f2 45 0f f0 9e f0 00 	lddqu  xmm11,[r14+0xf0]
 130:	00 00 
 132:	f2 45 0f f0 a6 00 01 	lddqu  xmm12,[r14+0x100]
 139:	00 00 
 13b:	f2 41 0f f0 46 40    	lddqu  xmm0,[r14+0x40]
 141:	f0 41 ff 06          	lock inc DWORD PTR [r14]

Show nanoBench command
Results:
- Instructions retired: 41.0
- Core cycles: 41.72
- Reference cycles: 34.93
- UOPS_PORT_0: 0.28
- UOPS_PORT_1: 0.72
- UOPS_PORT_2: 41.0
- UOPS_PORT_3: 1.0
- UOPS_PORT_4: 1.16
- UOPS_PORT_5: 41.76
- UOPS_RETIRED.ANY: 45.0

⇨ One μop 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:	4d 89 86 98 00 00 00 	mov    QWORD PTR [r14+0x98],r8
  94:	4d 89 86 a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r8
  9b:	4d 89 86 a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r8
  a2:	4d 89 86 b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r8
  a9:	4d 89 86 b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r8
  b0:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
  b4:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
  b8:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
  bc:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
  c0:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
  c4:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
  c8:	4d 89 46 70          	mov    QWORD PTR [r14+0x70],r8
  cc:	4d 89 46 78          	mov    QWORD PTR [r14+0x78],r8
  d0:	f0 41 ff 06          	lock inc DWORD PTR [r14]

Show nanoBench command
Results:
- Instructions retired: 41.0
- Core cycles: 59.16
- Reference cycles: 49.33
- UOPS_PORT_0: 0.0
- UOPS_PORT_1: 1.44
- UOPS_PORT_2: 1.0
- UOPS_PORT_3: 41.0
- UOPS_PORT_4: 42.96
- UOPS_PORT_5: 0.0
- UOPS_RETIRED.ANY: 85.0

⇨ One μop 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:	4d 89 86 98 00 00 00 	mov    QWORD PTR [r14+0x98],r8
  94:	4d 89 86 a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r8
  9b:	4d 89 86 a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r8
  a2:	4d 89 86 b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r8
  a9:	4d 89 86 b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r8
  b0:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
  b4:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
  b8:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
  bc:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
  c0:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
  c4:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
  c8:	4d 89 46 70          	mov    QWORD PTR [r14+0x70],r8
  cc:	4d 89 46 78          	mov    QWORD PTR [r14+0x78],r8
  d0:	f0 41 ff 06          	lock inc DWORD PTR [r14]

Show nanoBench command
Results:
- Instructions retired: 41.0
- Core cycles: 59.16
- Reference cycles: 49.6
- UOPS_PORT_0: 0.0
- UOPS_PORT_1: 1.44
- UOPS_PORT_2: 1.0
- UOPS_PORT_3: 41.0
- UOPS_PORT_4: 42.96
- UOPS_PORT_5: 0.0
- UOPS_RETIRED.ANY: 85.0

⇨ One μop that can only use port '4'

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:	0f 38 1c e1          	pabsb  mm4,mm1
  d4:	0f 38 1c e9          	pabsb  mm5,mm1
  d8:	0f 38 1c f1          	pabsb  mm6,mm1
  dc:	0f 38 1c f9          	pabsb  mm7,mm1
  e0:	0f 38 1c c1          	pabsb  mm0,mm1
  e4:	0f 38 1c d1          	pabsb  mm2,mm1
  e8:	0f 38 1c d9          	pabsb  mm3,mm1
  ec:	0f 38 1c e1          	pabsb  mm4,mm1
  f0:	0f 38 1c e9          	pabsb  mm5,mm1
  f4:	0f 38 1c f1          	pabsb  mm6,mm1
  f8:	0f 38 1c f9          	pabsb  mm7,mm1
  fc:	0f 38 1c c1          	pabsb  mm0,mm1
 100:	0f 38 1c d1          	pabsb  mm2,mm1
 104:	0f 38 1c d9          	pabsb  mm3,mm1
 108:	0f 38 1c e1          	pabsb  mm4,mm1
 10c:	0f 38 1c e9          	pabsb  mm5,mm1
 110:	0f 38 1c f1          	pabsb  mm6,mm1
 114:	0f 38 1c f9          	pabsb  mm7,mm1
 118:	0f 38 1c c1          	pabsb  mm0,mm1
 11c:	0f 38 1c d1          	pabsb  mm2,mm1
 120:	0f 38 1c d9          	pabsb  mm3,mm1
 124:	0f 38 1c e1          	pabsb  mm4,mm1
 128:	0f 38 1c e9          	pabsb  mm5,mm1
 12c:	0f 38 1c f1          	pabsb  mm6,mm1
 130:	0f 38 1c f9          	pabsb  mm7,mm1
 134:	0f 38 1c c1          	pabsb  mm0,mm1
 138:	0f 38 1c d1          	pabsb  mm2,mm1
 13c:	0f 38 1c d9          	pabsb  mm3,mm1
 140:	f0 41 ff 06          	lock inc DWORD PTR [r14]

Init:
```
PXOR MM1, MM1
```
Show nanoBench command
Results:
- Instructions retired: 81.0
- Core cycles: 41.08
- Reference cycles: 34.44
- UOPS_PORT_0: 40.17
- UOPS_PORT_1: 3.0
- UOPS_PORT_2: 1.0
- UOPS_PORT_3: 1.0
- UOPS_PORT_4: 2.0
- UOPS_PORT_5: 42.5
- UOPS_RETIRED.ANY: 85.0

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:	b9 00 00 00 01       	mov    ecx,0x1000000
  28:	ba 00 00 00 01       	mov    edx,0x1000000
  2d:	41 b8 00 00 00 01    	mov    r8d,0x1000000
  33:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  39:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  3f:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  45:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  4b:	bb 00 00 00 01       	mov    ebx,0x1000000
  50:	b9 00 00 00 01       	mov    ecx,0x1000000
  55:	ba 00 00 00 01       	mov    edx,0x1000000
  5a:	41 b8 00 00 00 01    	mov    r8d,0x1000000
  60:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  66:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  6c:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  72:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  78:	bb 00 00 00 01       	mov    ebx,0x1000000
  7d:	b9 00 00 00 01       	mov    ecx,0x1000000
  82:	ba 00 00 00 01       	mov    edx,0x1000000
  87:	41 b8 00 00 00 01    	mov    r8d,0x1000000
  8d:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  93:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  99:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  9f:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  a5:	bb 00 00 00 01       	mov    ebx,0x1000000
  aa:	b9 00 00 00 01       	mov    ecx,0x1000000
  af:	ba 00 00 00 01       	mov    edx,0x1000000
  b4:	41 b8 00 00 00 01    	mov    r8d,0x1000000
  ba:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  c0:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  c6:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  cc:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  d2:	bb 00 00 00 01       	mov    ebx,0x1000000
  d7:	b9 00 00 00 01       	mov    ecx,0x1000000
  dc:	ba 00 00 00 01       	mov    edx,0x1000000
  e1:	41 b8 00 00 00 01    	mov    r8d,0x1000000
  e7:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  ed:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  f3:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  f9:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  ff:	bb 00 00 00 01       	mov    ebx,0x1000000
 104:	b9 00 00 00 01       	mov    ecx,0x1000000
 109:	ba 00 00 00 01       	mov    edx,0x1000000
 10e:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 114:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 11a:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 120:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 126:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 12c:	bb 00 00 00 01       	mov    ebx,0x1000000
 131:	b9 00 00 00 01       	mov    ecx,0x1000000
 136:	ba 00 00 00 01       	mov    edx,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:	b9 00 00 00 01       	mov    ecx,0x1000000
 163:	ba 00 00 00 01       	mov    edx,0x1000000
 168:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 16e:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 174:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 17a:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 180:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 186:	bb 00 00 00 01       	mov    ebx,0x1000000
 18b:	b9 00 00 00 01       	mov    ecx,0x1000000
 190:	ba 00 00 00 01       	mov    edx,0x1000000
 195:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 19b:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 1a1:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 1a7:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 1ad:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 1b3:	bb 00 00 00 01       	mov    ebx,0x1000000
 1b8:	b9 00 00 00 01       	mov    ecx,0x1000000
 1bd:	ba 00 00 00 01       	mov    edx,0x1000000
 1c2:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 1c8:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 1ce:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 1d4:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 1da:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 1e0:	bb 00 00 00 01       	mov    ebx,0x1000000
 1e5:	b9 00 00 00 01       	mov    ecx,0x1000000
 1ea:	ba 00 00 00 01       	mov    edx,0x1000000
 1ef:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 1f5:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 1fb:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 201:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 207:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 20d:	bb 00 00 00 01       	mov    ebx,0x1000000
 212:	b9 00 00 00 01       	mov    ecx,0x1000000
 217:	ba 00 00 00 01       	mov    edx,0x1000000
 21c:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 222:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 228:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 22e:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 234:	f0 41 ff 06          	lock inc DWORD PTR [r14]

Show nanoBench command
Results:
- Instructions retired: 101.0
- Core cycles: 40.3
- Reference cycles: 33.67
- UOPS_PORT_0: 33.9
- UOPS_PORT_1: 34.9
- UOPS_PORT_2: 1.0
- UOPS_PORT_3: 1.0
- UOPS_PORT_4: 2.0
- UOPS_PORT_5: 0.0
- UOPS_RETIRED.ANY: 105.0

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

With an indexed addressing mode

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 0f 50 c8          	movmskpd ecx,xmm0
  21:	66 0f 50 d0          	movmskpd edx,xmm0
  25:	66 44 0f 50 c0       	movmskpd r8d,xmm0
  2a:	66 44 0f 50 c8       	movmskpd r9d,xmm0
  2f:	66 44 0f 50 d0       	movmskpd r10d,xmm0
  34:	66 44 0f 50 d8       	movmskpd r11d,xmm0
  39:	66 44 0f 50 e0       	movmskpd r12d,xmm0
  3e:	66 0f 50 d8          	movmskpd ebx,xmm0
  42:	66 0f 50 c8          	movmskpd ecx,xmm0
  46:	66 0f 50 d0          	movmskpd edx,xmm0
  4a:	66 44 0f 50 c0       	movmskpd r8d,xmm0
  4f:	66 44 0f 50 c8       	movmskpd r9d,xmm0
  54:	66 44 0f 50 d0       	movmskpd r10d,xmm0
  59:	66 44 0f 50 d8       	movmskpd r11d,xmm0
  5e:	66 44 0f 50 e0       	movmskpd r12d,xmm0
  63:	66 0f 50 d8          	movmskpd ebx,xmm0
  67:	66 0f 50 c8          	movmskpd ecx,xmm0
  6b:	66 0f 50 d0          	movmskpd edx,xmm0
  6f:	66 44 0f 50 c0       	movmskpd r8d,xmm0
  74:	66 44 0f 50 c8       	movmskpd r9d,xmm0
  79:	66 44 0f 50 d0       	movmskpd r10d,xmm0
  7e:	66 44 0f 50 d8       	movmskpd r11d,xmm0
  83:	66 44 0f 50 e0       	movmskpd r12d,xmm0
  88:	66 0f 50 d8          	movmskpd ebx,xmm0
  8c:	66 0f 50 c8          	movmskpd ecx,xmm0
  90:	66 0f 50 d0          	movmskpd edx,xmm0
  94:	66 44 0f 50 c0       	movmskpd r8d,xmm0
  99:	66 44 0f 50 c8       	movmskpd r9d,xmm0
  9e:	66 44 0f 50 d0       	movmskpd r10d,xmm0
  a3:	66 44 0f 50 d8       	movmskpd r11d,xmm0
  a8:	66 44 0f 50 e0       	movmskpd r12d,xmm0
  ad:	66 0f 50 d8          	movmskpd ebx,xmm0
  b1:	66 0f 50 c8          	movmskpd ecx,xmm0
  b5:	66 0f 50 d0          	movmskpd edx,xmm0
  b9:	f0 43 ff 04 2e       	lock inc DWORD PTR [r14+r13*1]

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14];
XOR R13, R13

Show nanoBench command
Results:
- Instructions retired: 41.0
- Core cycles: 40.48
- Reference cycles: 33.87
- UOPS_PORT_0: 40.0
- UOPS_PORT_1: 1.2
- UOPS_PORT_2: 1.0
- UOPS_PORT_3: 1.0
- UOPS_PORT_4: 2.0
- UOPS_PORT_5: 0.0
- UOPS_RETIRED.ANY: 45.0

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:	f0 43 ff 04 2e       	lock inc DWORD PTR [r14+r13*1]

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: 41.0
- Core cycles: 40.56
- Reference cycles: 33.6
- UOPS_PORT_0: 1.44
- UOPS_PORT_1: 39.88
- UOPS_PORT_2: 1.0
- UOPS_PORT_3: 1.0
- UOPS_PORT_4: 2.0
- UOPS_PORT_5: 0.0
- UOPS_RETIRED.ANY: 45.0

With blocking instructions for port '2':

Code:

   0:	f2 41 0f f0 46 40    	lddqu  xmm0,[r14+0x40]
   6:	f2 41 0f f0 4e 50    	lddqu  xmm1,[r14+0x50]
   c:	f2 41 0f f0 56 60    	lddqu  xmm2,[r14+0x60]
  12:	f2 41 0f f0 5e 70    	lddqu  xmm3,[r14+0x70]
  18:	f2 41 0f f0 a6 80 00 	lddqu  xmm4,[r14+0x80]
  1f:	00 00 
  21:	f2 41 0f f0 ae 90 00 	lddqu  xmm5,[r14+0x90]
  28:	00 00 
  2a:	f2 41 0f f0 b6 a0 00 	lddqu  xmm6,[r14+0xa0]
  31:	00 00 
  33:	f2 41 0f f0 be b0 00 	lddqu  xmm7,[r14+0xb0]
  3a:	00 00 
  3c:	f2 45 0f f0 86 c0 00 	lddqu  xmm8,[r14+0xc0]
  43:	00 00 
  45:	f2 45 0f f0 8e d0 00 	lddqu  xmm9,[r14+0xd0]
  4c:	00 00 
  4e:	f2 45 0f f0 96 e0 00 	lddqu  xmm10,[r14+0xe0]
  55:	00 00 
  57:	f2 45 0f f0 9e f0 00 	lddqu  xmm11,[r14+0xf0]
  5e:	00 00 
  60:	f2 45 0f f0 a6 00 01 	lddqu  xmm12,[r14+0x100]
  67:	00 00 
  69:	f2 41 0f f0 46 40    	lddqu  xmm0,[r14+0x40]
  6f:	f2 41 0f f0 4e 50    	lddqu  xmm1,[r14+0x50]
  75:	f2 41 0f f0 56 60    	lddqu  xmm2,[r14+0x60]
  7b:	f2 41 0f f0 5e 70    	lddqu  xmm3,[r14+0x70]
  81:	f2 41 0f f0 a6 80 00 	lddqu  xmm4,[r14+0x80]
  88:	00 00 
  8a:	f2 41 0f f0 ae 90 00 	lddqu  xmm5,[r14+0x90]
  91:	00 00 
  93:	f2 41 0f f0 b6 a0 00 	lddqu  xmm6,[r14+0xa0]
  9a:	00 00 
  9c:	f2 41 0f f0 be b0 00 	lddqu  xmm7,[r14+0xb0]
  a3:	00 00 
  a5:	f2 45 0f f0 86 c0 00 	lddqu  xmm8,[r14+0xc0]
  ac:	00 00 
  ae:	f2 45 0f f0 8e d0 00 	lddqu  xmm9,[r14+0xd0]
  b5:	00 00 
  b7:	f2 45 0f f0 96 e0 00 	lddqu  xmm10,[r14+0xe0]
  be:	00 00 
  c0:	f2 45 0f f0 9e f0 00 	lddqu  xmm11,[r14+0xf0]
  c7:	00 00 
  c9:	f2 45 0f f0 a6 00 01 	lddqu  xmm12,[r14+0x100]
  d0:	00 00 
  d2:	f2 41 0f f0 46 40    	lddqu  xmm0,[r14+0x40]
  d8:	f2 41 0f f0 4e 50    	lddqu  xmm1,[r14+0x50]
  de:	f2 41 0f f0 56 60    	lddqu  xmm2,[r14+0x60]
  e4:	f2 41 0f f0 5e 70    	lddqu  xmm3,[r14+0x70]
  ea:	f2 41 0f f0 a6 80 00 	lddqu  xmm4,[r14+0x80]
  f1:	00 00 
  f3:	f2 41 0f f0 ae 90 00 	lddqu  xmm5,[r14+0x90]
  fa:	00 00 
  fc:	f2 41 0f f0 b6 a0 00 	lddqu  xmm6,[r14+0xa0]
 103:	00 00 
 105:	f2 41 0f f0 be b0 00 	lddqu  xmm7,[r14+0xb0]
 10c:	00 00 
 10e:	f2 45 0f f0 86 c0 00 	lddqu  xmm8,[r14+0xc0]
 115:	00 00 
 117:	f2 45 0f f0 8e d0 00 	lddqu  xmm9,[r14+0xd0]
 11e:	00 00 
 120:	f2 45 0f f0 96 e0 00 	lddqu  xmm10,[r14+0xe0]
 127:	00 00 
 129:	f2 45 0f f0 9e f0 00 	lddqu  xmm11,[r14+0xf0]
 130:	00 00 
 132:	f2 45 0f f0 a6 00 01 	lddqu  xmm12,[r14+0x100]
 139:	00 00 
 13b:	f2 41 0f f0 46 40    	lddqu  xmm0,[r14+0x40]
 141:	f0 43 ff 04 2e       	lock inc DWORD PTR [r14+r13*1]

Init:
```
XOR R13, R13
```
Show nanoBench command
Results:
- Instructions retired: 41.0
- Core cycles: 41.72
- Reference cycles: 34.53
- UOPS_PORT_0: 0.4
- UOPS_PORT_1: 0.68
- UOPS_PORT_2: 41.0
- UOPS_PORT_3: 1.0
- UOPS_PORT_4: 1.16
- UOPS_PORT_5: 0.0
- UOPS_RETIRED.ANY: 45.0

⇨ One μop 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:	4d 89 86 98 00 00 00 	mov    QWORD PTR [r14+0x98],r8
  94:	4d 89 86 a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r8
  9b:	4d 89 86 a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r8
  a2:	4d 89 86 b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r8
  a9:	4d 89 86 b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r8
  b0:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
  b4:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
  b8:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
  bc:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
  c0:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
  c4:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
  c8:	4d 89 46 70          	mov    QWORD PTR [r14+0x70],r8
  cc:	4d 89 46 78          	mov    QWORD PTR [r14+0x78],r8
  d0:	f0 43 ff 04 2e       	lock inc DWORD PTR [r14+r13*1]

Init:
```
XOR R13, R13
```
Show nanoBench command
Results:
- Instructions retired: 41.0
- Core cycles: 59.16
- Reference cycles: 48.93
- UOPS_PORT_0: 0.0
- UOPS_PORT_1: 1.44
- UOPS_PORT_2: 1.0
- UOPS_PORT_3: 41.0
- UOPS_PORT_4: 42.96
- UOPS_PORT_5: 59.2
- UOPS_RETIRED.ANY: 85.0

⇨ One μop 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:	4d 89 86 98 00 00 00 	mov    QWORD PTR [r14+0x98],r8
  94:	4d 89 86 a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r8
  9b:	4d 89 86 a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r8
  a2:	4d 89 86 b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r8
  a9:	4d 89 86 b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r8
  b0:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
  b4:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
  b8:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
  bc:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
  c0:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
  c4:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
  c8:	4d 89 46 70          	mov    QWORD PTR [r14+0x70],r8
  cc:	4d 89 46 78          	mov    QWORD PTR [r14+0x78],r8
  d0:	f0 43 ff 04 2e       	lock inc DWORD PTR [r14+r13*1]

Init:
```
XOR R13, R13
```
Show nanoBench command
Results:
- Instructions retired: 41.0
- Core cycles: 59.16
- Reference cycles: 49.47
- UOPS_PORT_0: 0.0
- UOPS_PORT_1: 1.44
- UOPS_PORT_2: 1.0
- UOPS_PORT_3: 41.0
- UOPS_PORT_4: 42.96
- UOPS_PORT_5: 0.0
- UOPS_RETIRED.ANY: 85.0

⇨ One μop that can only use port '4'

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:	0f 38 1c e1          	pabsb  mm4,mm1
  d4:	0f 38 1c e9          	pabsb  mm5,mm1
  d8:	0f 38 1c f1          	pabsb  mm6,mm1
  dc:	0f 38 1c f9          	pabsb  mm7,mm1
  e0:	0f 38 1c c1          	pabsb  mm0,mm1
  e4:	0f 38 1c d1          	pabsb  mm2,mm1
  e8:	0f 38 1c d9          	pabsb  mm3,mm1
  ec:	0f 38 1c e1          	pabsb  mm4,mm1
  f0:	0f 38 1c e9          	pabsb  mm5,mm1
  f4:	0f 38 1c f1          	pabsb  mm6,mm1
  f8:	0f 38 1c f9          	pabsb  mm7,mm1
  fc:	0f 38 1c c1          	pabsb  mm0,mm1
 100:	0f 38 1c d1          	pabsb  mm2,mm1
 104:	0f 38 1c d9          	pabsb  mm3,mm1
 108:	0f 38 1c e1          	pabsb  mm4,mm1
 10c:	0f 38 1c e9          	pabsb  mm5,mm1
 110:	0f 38 1c f1          	pabsb  mm6,mm1
 114:	0f 38 1c f9          	pabsb  mm7,mm1
 118:	0f 38 1c c1          	pabsb  mm0,mm1
 11c:	0f 38 1c d1          	pabsb  mm2,mm1
 120:	0f 38 1c d9          	pabsb  mm3,mm1
 124:	0f 38 1c e1          	pabsb  mm4,mm1
 128:	0f 38 1c e9          	pabsb  mm5,mm1
 12c:	0f 38 1c f1          	pabsb  mm6,mm1
 130:	0f 38 1c f9          	pabsb  mm7,mm1
 134:	0f 38 1c c1          	pabsb  mm0,mm1
 138:	0f 38 1c d1          	pabsb  mm2,mm1
 13c:	0f 38 1c d9          	pabsb  mm3,mm1
 140:	f0 43 ff 04 2e       	lock inc DWORD PTR [r14+r13*1]

Init:
```
PXOR MM1, MM1;
XOR R13, R13
```
Show nanoBench command
Results:
- Instructions retired: 81.0
- Core cycles: 41.08
- Reference cycles: 34.17
- UOPS_PORT_0: 40.17
- UOPS_PORT_1: 3.0
- UOPS_PORT_2: 1.0
- UOPS_PORT_3: 1.0
- UOPS_PORT_4: 2.0
- UOPS_PORT_5: 41.61
- UOPS_RETIRED.ANY: 85.0

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:	b9 00 00 00 01       	mov    ecx,0x1000000
  28:	ba 00 00 00 01       	mov    edx,0x1000000
  2d:	41 b8 00 00 00 01    	mov    r8d,0x1000000
  33:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  39:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  3f:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  45:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  4b:	bb 00 00 00 01       	mov    ebx,0x1000000
  50:	b9 00 00 00 01       	mov    ecx,0x1000000
  55:	ba 00 00 00 01       	mov    edx,0x1000000
  5a:	41 b8 00 00 00 01    	mov    r8d,0x1000000
  60:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  66:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  6c:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  72:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  78:	bb 00 00 00 01       	mov    ebx,0x1000000
  7d:	b9 00 00 00 01       	mov    ecx,0x1000000
  82:	ba 00 00 00 01       	mov    edx,0x1000000
  87:	41 b8 00 00 00 01    	mov    r8d,0x1000000
  8d:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  93:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  99:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  9f:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  a5:	bb 00 00 00 01       	mov    ebx,0x1000000
  aa:	b9 00 00 00 01       	mov    ecx,0x1000000
  af:	ba 00 00 00 01       	mov    edx,0x1000000
  b4:	41 b8 00 00 00 01    	mov    r8d,0x1000000
  ba:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  c0:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  c6:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  cc:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  d2:	bb 00 00 00 01       	mov    ebx,0x1000000
  d7:	b9 00 00 00 01       	mov    ecx,0x1000000
  dc:	ba 00 00 00 01       	mov    edx,0x1000000
  e1:	41 b8 00 00 00 01    	mov    r8d,0x1000000
  e7:	41 b9 00 00 00 01    	mov    r9d,0x1000000
  ed:	41 ba 00 00 00 01    	mov    r10d,0x1000000
  f3:	41 bb 00 00 00 01    	mov    r11d,0x1000000
  f9:	41 bc 00 00 00 01    	mov    r12d,0x1000000
  ff:	bb 00 00 00 01       	mov    ebx,0x1000000
 104:	b9 00 00 00 01       	mov    ecx,0x1000000
 109:	ba 00 00 00 01       	mov    edx,0x1000000
 10e:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 114:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 11a:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 120:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 126:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 12c:	bb 00 00 00 01       	mov    ebx,0x1000000
 131:	b9 00 00 00 01       	mov    ecx,0x1000000
 136:	ba 00 00 00 01       	mov    edx,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:	b9 00 00 00 01       	mov    ecx,0x1000000
 163:	ba 00 00 00 01       	mov    edx,0x1000000
 168:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 16e:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 174:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 17a:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 180:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 186:	bb 00 00 00 01       	mov    ebx,0x1000000
 18b:	b9 00 00 00 01       	mov    ecx,0x1000000
 190:	ba 00 00 00 01       	mov    edx,0x1000000
 195:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 19b:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 1a1:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 1a7:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 1ad:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 1b3:	bb 00 00 00 01       	mov    ebx,0x1000000
 1b8:	b9 00 00 00 01       	mov    ecx,0x1000000
 1bd:	ba 00 00 00 01       	mov    edx,0x1000000
 1c2:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 1c8:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 1ce:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 1d4:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 1da:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 1e0:	bb 00 00 00 01       	mov    ebx,0x1000000
 1e5:	b9 00 00 00 01       	mov    ecx,0x1000000
 1ea:	ba 00 00 00 01       	mov    edx,0x1000000
 1ef:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 1f5:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 1fb:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 201:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 207:	41 bc 00 00 00 01    	mov    r12d,0x1000000
 20d:	bb 00 00 00 01       	mov    ebx,0x1000000
 212:	b9 00 00 00 01       	mov    ecx,0x1000000
 217:	ba 00 00 00 01       	mov    edx,0x1000000
 21c:	41 b8 00 00 00 01    	mov    r8d,0x1000000
 222:	41 b9 00 00 00 01    	mov    r9d,0x1000000
 228:	41 ba 00 00 00 01    	mov    r10d,0x1000000
 22e:	41 bb 00 00 00 01    	mov    r11d,0x1000000
 234:	f0 43 ff 04 2e       	lock inc DWORD PTR [r14+r13*1]

Init:
```
XOR R13, R13
```
Show nanoBench command
Results:
- Instructions retired: 101.0
- Core cycles: 40.4
- Reference cycles: 33.33
- UOPS_PORT_0: 33.8
- UOPS_PORT_1: 34.2
- UOPS_PORT_2: 1.0
- UOPS_PORT_3: 1.0
- UOPS_PORT_4: 2.0
- UOPS_PORT_5: 0.0
- UOPS_RETIRED.ANY: 105.0

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