VP2INTERSECTD (R64, YMM, YMM) - Port Usage

With blocking instructions for port '0':

Code:

   0:	41 0f 7e c0          	movd   r8d,mm0
   4:	41 0f 7e c1          	movd   r9d,mm0
   8:	41 0f 7e c2          	movd   r10d,mm0
   c:	41 0f 7e c3          	movd   r11d,mm0
  10:	41 0f 7e c4          	movd   r12d,mm0
  14:	0f 7e c3             	movd   ebx,mm0
  17:	0f 7e c1             	movd   ecx,mm0
  1a:	0f 7e c2             	movd   edx,mm0
  1d:	41 0f 7e c0          	movd   r8d,mm0
  21:	41 0f 7e c1          	movd   r9d,mm0
  25:	41 0f 7e c2          	movd   r10d,mm0
  29:	41 0f 7e c3          	movd   r11d,mm0
  2d:	41 0f 7e c4          	movd   r12d,mm0
  31:	0f 7e c3             	movd   ebx,mm0
  34:	0f 7e c1             	movd   ecx,mm0
  37:	0f 7e c2             	movd   edx,mm0
  3a:	41 0f 7e c0          	movd   r8d,mm0
  3e:	41 0f 7e c1          	movd   r9d,mm0
  42:	41 0f 7e c2          	movd   r10d,mm0
  46:	41 0f 7e c3          	movd   r11d,mm0
  4a:	41 0f 7e c4          	movd   r12d,mm0
  4e:	0f 7e c3             	movd   ebx,mm0
  51:	0f 7e c1             	movd   ecx,mm0
  54:	0f 7e c2             	movd   edx,mm0
  57:	41 0f 7e c0          	movd   r8d,mm0
  5b:	41 0f 7e c1          	movd   r9d,mm0
  5f:	41 0f 7e c2          	movd   r10d,mm0
  63:	41 0f 7e c3          	movd   r11d,mm0
  67:	41 0f 7e c4          	movd   r12d,mm0
  6b:	0f 7e c3             	movd   ebx,mm0
  6e:	62 f2 7f 28 68 d1    	vp2intersectd k2,ymm0,ymm1

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
PXOR MM0, MM0;
VZEROALL;
VXORPS YMM0, YMM0, YMM0;
VXORPS YMM1, YMM1, YMM1

Show nanoBench command
Results:
- Instructions retired: 31.0
- Core cycles: 31.13
- Reference cycles: 23.27
- UOPS_PORT_0: 31.0

⇨ One μop that can only use port '0'

With blocking instructions for port '1':

Code:

   0:	44 8d 05 80 00 00 00 	lea    r8d,[rip+0x80]        # 0x87
   7:	44 8d 0d 80 00 00 00 	lea    r9d,[rip+0x80]        # 0x8e
   e:	44 8d 15 80 00 00 00 	lea    r10d,[rip+0x80]        # 0x95
  15:	44 8d 1d 80 00 00 00 	lea    r11d,[rip+0x80]        # 0x9c
  1c:	44 8d 25 80 00 00 00 	lea    r12d,[rip+0x80]        # 0xa3
  23:	8d 1d 80 00 00 00    	lea    ebx,[rip+0x80]        # 0xa9
  29:	8d 0d 80 00 00 00    	lea    ecx,[rip+0x80]        # 0xaf
  2f:	8d 15 80 00 00 00    	lea    edx,[rip+0x80]        # 0xb5
  35:	44 8d 05 80 00 00 00 	lea    r8d,[rip+0x80]        # 0xbc
  3c:	44 8d 0d 80 00 00 00 	lea    r9d,[rip+0x80]        # 0xc3
  43:	44 8d 15 80 00 00 00 	lea    r10d,[rip+0x80]        # 0xca
  4a:	44 8d 1d 80 00 00 00 	lea    r11d,[rip+0x80]        # 0xd1
  51:	44 8d 25 80 00 00 00 	lea    r12d,[rip+0x80]        # 0xd8
  58:	8d 1d 80 00 00 00    	lea    ebx,[rip+0x80]        # 0xde
  5e:	8d 0d 80 00 00 00    	lea    ecx,[rip+0x80]        # 0xe4
  64:	8d 15 80 00 00 00    	lea    edx,[rip+0x80]        # 0xea
  6a:	44 8d 05 80 00 00 00 	lea    r8d,[rip+0x80]        # 0xf1
  71:	44 8d 0d 80 00 00 00 	lea    r9d,[rip+0x80]        # 0xf8
  78:	44 8d 15 80 00 00 00 	lea    r10d,[rip+0x80]        # 0xff
  7f:	44 8d 1d 80 00 00 00 	lea    r11d,[rip+0x80]        # 0x106
  86:	44 8d 25 80 00 00 00 	lea    r12d,[rip+0x80]        # 0x10d
  8d:	8d 1d 80 00 00 00    	lea    ebx,[rip+0x80]        # 0x113
  93:	8d 0d 80 00 00 00    	lea    ecx,[rip+0x80]        # 0x119
  99:	8d 15 80 00 00 00    	lea    edx,[rip+0x80]        # 0x11f
  9f:	44 8d 05 80 00 00 00 	lea    r8d,[rip+0x80]        # 0x126
  a6:	44 8d 0d 80 00 00 00 	lea    r9d,[rip+0x80]        # 0x12d
  ad:	44 8d 15 80 00 00 00 	lea    r10d,[rip+0x80]        # 0x134
  b4:	44 8d 1d 80 00 00 00 	lea    r11d,[rip+0x80]        # 0x13b
  bb:	44 8d 25 80 00 00 00 	lea    r12d,[rip+0x80]        # 0x142
  c2:	8d 1d 80 00 00 00    	lea    ebx,[rip+0x80]        # 0x148
  c8:	62 f2 7f 28 68 d1    	vp2intersectd k2,ymm0,ymm1

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS YMM0, YMM0, YMM0;
VXORPS YMM1, YMM1, YMM1

Show nanoBench command
Results:
- Instructions retired: 31.0
- Core cycles: 30.08
- Reference cycles: 22.79
- UOPS_PORT_1: 30.0

With blocking instructions for port '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:	62 f2 7f 28 68 d1    	vp2intersectd k2,ymm0,ymm1

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS YMM0, YMM0, YMM0;
VXORPS YMM1, YMM1, YMM1

Show nanoBench command
Results:
- Instructions retired: 31.0
- Core cycles: 41.52
- Reference cycles: 31.52
- UOPS_PORT_5B: 41.0
- UOPS_PORT_5B>=2: 0.0

⇨ 11 μops that can only use port '5'

With blocking instructions for ports {'0', '1'}:

Code:

   0:	c4 e2 61 de d4       	vaesdec xmm2,xmm3,xmm4
   5:	c4 e2 61 de ec       	vaesdec xmm5,xmm3,xmm4
   a:	c4 e2 61 de f4       	vaesdec xmm6,xmm3,xmm4
   f:	c4 e2 61 de fc       	vaesdec xmm7,xmm3,xmm4
  14:	c4 62 61 de c4       	vaesdec xmm8,xmm3,xmm4
  19:	c4 62 61 de cc       	vaesdec xmm9,xmm3,xmm4
  1e:	c4 62 61 de d4       	vaesdec xmm10,xmm3,xmm4
  23:	c4 62 61 de dc       	vaesdec xmm11,xmm3,xmm4
  28:	c4 62 61 de e4       	vaesdec xmm12,xmm3,xmm4
  2d:	c4 e2 61 de d4       	vaesdec xmm2,xmm3,xmm4
  32:	c4 e2 61 de ec       	vaesdec xmm5,xmm3,xmm4
  37:	c4 e2 61 de f4       	vaesdec xmm6,xmm3,xmm4
  3c:	c4 e2 61 de fc       	vaesdec xmm7,xmm3,xmm4
  41:	c4 62 61 de c4       	vaesdec xmm8,xmm3,xmm4
  46:	c4 62 61 de cc       	vaesdec xmm9,xmm3,xmm4
  4b:	c4 62 61 de d4       	vaesdec xmm10,xmm3,xmm4
  50:	c4 62 61 de dc       	vaesdec xmm11,xmm3,xmm4
  55:	c4 62 61 de e4       	vaesdec xmm12,xmm3,xmm4
  5a:	c4 e2 61 de d4       	vaesdec xmm2,xmm3,xmm4
  5f:	c4 e2 61 de ec       	vaesdec xmm5,xmm3,xmm4
  64:	c4 e2 61 de f4       	vaesdec xmm6,xmm3,xmm4
  69:	c4 e2 61 de fc       	vaesdec xmm7,xmm3,xmm4
  6e:	c4 62 61 de c4       	vaesdec xmm8,xmm3,xmm4
  73:	c4 62 61 de cc       	vaesdec xmm9,xmm3,xmm4
  78:	c4 62 61 de d4       	vaesdec xmm10,xmm3,xmm4
  7d:	c4 62 61 de dc       	vaesdec xmm11,xmm3,xmm4
  82:	c4 62 61 de e4       	vaesdec xmm12,xmm3,xmm4
  87:	c4 e2 61 de d4       	vaesdec xmm2,xmm3,xmm4
  8c:	c4 e2 61 de ec       	vaesdec xmm5,xmm3,xmm4
  91:	c4 e2 61 de f4       	vaesdec xmm6,xmm3,xmm4
  96:	c4 e2 61 de fc       	vaesdec xmm7,xmm3,xmm4
  9b:	c4 62 61 de c4       	vaesdec xmm8,xmm3,xmm4
  a0:	c4 62 61 de cc       	vaesdec xmm9,xmm3,xmm4
  a5:	c4 62 61 de d4       	vaesdec xmm10,xmm3,xmm4
  aa:	c4 62 61 de dc       	vaesdec xmm11,xmm3,xmm4
  af:	c4 62 61 de e4       	vaesdec xmm12,xmm3,xmm4
  b4:	c4 e2 61 de d4       	vaesdec xmm2,xmm3,xmm4
  b9:	c4 e2 61 de ec       	vaesdec xmm5,xmm3,xmm4
  be:	c4 e2 61 de f4       	vaesdec xmm6,xmm3,xmm4
  c3:	c4 e2 61 de fc       	vaesdec xmm7,xmm3,xmm4
  c8:	c4 62 61 de c4       	vaesdec xmm8,xmm3,xmm4
  cd:	c4 62 61 de cc       	vaesdec xmm9,xmm3,xmm4
  d2:	c4 62 61 de d4       	vaesdec xmm10,xmm3,xmm4
  d7:	c4 62 61 de dc       	vaesdec xmm11,xmm3,xmm4
  dc:	c4 62 61 de e4       	vaesdec xmm12,xmm3,xmm4
  e1:	c4 e2 61 de d4       	vaesdec xmm2,xmm3,xmm4
  e6:	c4 e2 61 de ec       	vaesdec xmm5,xmm3,xmm4
  eb:	c4 e2 61 de f4       	vaesdec xmm6,xmm3,xmm4
  f0:	c4 e2 61 de fc       	vaesdec xmm7,xmm3,xmm4
  f5:	c4 62 61 de c4       	vaesdec xmm8,xmm3,xmm4
  fa:	c4 62 61 de cc       	vaesdec xmm9,xmm3,xmm4
  ff:	c4 62 61 de d4       	vaesdec xmm10,xmm3,xmm4
 104:	c4 62 61 de dc       	vaesdec xmm11,xmm3,xmm4
 109:	c4 62 61 de e4       	vaesdec xmm12,xmm3,xmm4
 10e:	c4 e2 61 de d4       	vaesdec xmm2,xmm3,xmm4
 113:	c4 e2 61 de ec       	vaesdec xmm5,xmm3,xmm4
 118:	c4 e2 61 de f4       	vaesdec xmm6,xmm3,xmm4
 11d:	c4 e2 61 de fc       	vaesdec xmm7,xmm3,xmm4
 122:	c4 62 61 de c4       	vaesdec xmm8,xmm3,xmm4
 127:	c4 62 61 de cc       	vaesdec xmm9,xmm3,xmm4
 12c:	62 f2 7f 28 68 d1    	vp2intersectd k2,ymm0,ymm1

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS XMM3, XMM3, XMM3;
VXORPS XMM4, XMM4, XMM4;
VXORPS YMM0, YMM0, YMM0;
VXORPS YMM1, YMM1, YMM1

Show nanoBench command
Results:
- Instructions retired: 61.0
- Core cycles: 35.51
- Reference cycles: 26.0
- UOPS_PORT_0: 34.5
- UOPS_PORT_1: 34.5

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

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

Code:

   0:	0f 6f c1             	movq   mm0,mm1
   3:	0f 6f d1             	movq   mm2,mm1
   6:	0f 6f d9             	movq   mm3,mm1
   9:	0f 6f e1             	movq   mm4,mm1
   c:	0f 6f e9             	movq   mm5,mm1
   f:	0f 6f f1             	movq   mm6,mm1
  12:	0f 6f f9             	movq   mm7,mm1
  15:	0f 6f c1             	movq   mm0,mm1
  18:	0f 6f d1             	movq   mm2,mm1
  1b:	0f 6f d9             	movq   mm3,mm1
  1e:	0f 6f e1             	movq   mm4,mm1
  21:	0f 6f e9             	movq   mm5,mm1
  24:	0f 6f f1             	movq   mm6,mm1
  27:	0f 6f f9             	movq   mm7,mm1
  2a:	0f 6f c1             	movq   mm0,mm1
  2d:	0f 6f d1             	movq   mm2,mm1
  30:	0f 6f d9             	movq   mm3,mm1
  33:	0f 6f e1             	movq   mm4,mm1
  36:	0f 6f e9             	movq   mm5,mm1
  39:	0f 6f f1             	movq   mm6,mm1
  3c:	0f 6f f9             	movq   mm7,mm1
  3f:	0f 6f c1             	movq   mm0,mm1
  42:	0f 6f d1             	movq   mm2,mm1
  45:	0f 6f d9             	movq   mm3,mm1
  48:	0f 6f e1             	movq   mm4,mm1
  4b:	0f 6f e9             	movq   mm5,mm1
  4e:	0f 6f f1             	movq   mm6,mm1
  51:	0f 6f f9             	movq   mm7,mm1
  54:	0f 6f c1             	movq   mm0,mm1
  57:	0f 6f d1             	movq   mm2,mm1
  5a:	0f 6f d9             	movq   mm3,mm1
  5d:	0f 6f e1             	movq   mm4,mm1
  60:	0f 6f e9             	movq   mm5,mm1
  63:	0f 6f f1             	movq   mm6,mm1
  66:	0f 6f f9             	movq   mm7,mm1
  69:	0f 6f c1             	movq   mm0,mm1
  6c:	0f 6f d1             	movq   mm2,mm1
  6f:	0f 6f d9             	movq   mm3,mm1
  72:	0f 6f e1             	movq   mm4,mm1
  75:	0f 6f e9             	movq   mm5,mm1
  78:	0f 6f f1             	movq   mm6,mm1
  7b:	0f 6f f9             	movq   mm7,mm1
  7e:	0f 6f c1             	movq   mm0,mm1
  81:	0f 6f d1             	movq   mm2,mm1
  84:	0f 6f d9             	movq   mm3,mm1
  87:	0f 6f e1             	movq   mm4,mm1
  8a:	0f 6f e9             	movq   mm5,mm1
  8d:	0f 6f f1             	movq   mm6,mm1
  90:	0f 6f f9             	movq   mm7,mm1
  93:	0f 6f c1             	movq   mm0,mm1
  96:	0f 6f d1             	movq   mm2,mm1
  99:	0f 6f d9             	movq   mm3,mm1
  9c:	0f 6f e1             	movq   mm4,mm1
  9f:	0f 6f e9             	movq   mm5,mm1
  a2:	0f 6f f1             	movq   mm6,mm1
  a5:	0f 6f f9             	movq   mm7,mm1
  a8:	0f 6f c1             	movq   mm0,mm1
  ab:	0f 6f d1             	movq   mm2,mm1
  ae:	0f 6f d9             	movq   mm3,mm1
  b1:	0f 6f e1             	movq   mm4,mm1
  b4:	62 f2 7f 28 68 d1    	vp2intersectd k2,ymm0,ymm1

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
PXOR MM1, MM1;
VZEROALL;
VXORPS YMM0, YMM0, YMM0;
VXORPS YMM1, YMM1, YMM1

Show nanoBench command
Results:
- Instructions retired: 61.0
- Core cycles: 37.54
- Reference cycles: 26.0
- UOPS_PORT_0: 35.75
- UOPS_PORT_5B: 36.25
- UOPS_PORT_5B>=2: 0.0

With blocking instructions for ports {'0', '6'}:

Code:

   0:	66 41 c1 c0 00       	rol    r8w,0x0
   5:	66 41 c1 c1 00       	rol    r9w,0x0
   a:	66 41 c1 c2 00       	rol    r10w,0x0
   f:	66 41 c1 c3 00       	rol    r11w,0x0
  14:	66 41 c1 c4 00       	rol    r12w,0x0
  19:	66 c1 c3 00          	rol    bx,0x0
  1d:	66 c1 c1 00          	rol    cx,0x0
  21:	66 c1 c2 00          	rol    dx,0x0
  25:	66 41 c1 c0 00       	rol    r8w,0x0
  2a:	66 41 c1 c1 00       	rol    r9w,0x0
  2f:	66 41 c1 c2 00       	rol    r10w,0x0
  34:	66 41 c1 c3 00       	rol    r11w,0x0
  39:	66 41 c1 c4 00       	rol    r12w,0x0
  3e:	66 c1 c3 00          	rol    bx,0x0
  42:	66 c1 c1 00          	rol    cx,0x0
  46:	66 c1 c2 00          	rol    dx,0x0
  4a:	66 41 c1 c0 00       	rol    r8w,0x0
  4f:	66 41 c1 c1 00       	rol    r9w,0x0
  54:	66 41 c1 c2 00       	rol    r10w,0x0
  59:	66 41 c1 c3 00       	rol    r11w,0x0
  5e:	66 41 c1 c4 00       	rol    r12w,0x0
  63:	66 c1 c3 00          	rol    bx,0x0
  67:	66 c1 c1 00          	rol    cx,0x0
  6b:	66 c1 c2 00          	rol    dx,0x0
  6f:	66 41 c1 c0 00       	rol    r8w,0x0
  74:	66 41 c1 c1 00       	rol    r9w,0x0
  79:	66 41 c1 c2 00       	rol    r10w,0x0
  7e:	66 41 c1 c3 00       	rol    r11w,0x0
  83:	66 41 c1 c4 00       	rol    r12w,0x0
  88:	66 c1 c3 00          	rol    bx,0x0
  8c:	66 c1 c1 00          	rol    cx,0x0
  90:	66 c1 c2 00          	rol    dx,0x0
  94:	66 41 c1 c0 00       	rol    r8w,0x0
  99:	66 41 c1 c1 00       	rol    r9w,0x0
  9e:	66 41 c1 c2 00       	rol    r10w,0x0
  a3:	66 41 c1 c3 00       	rol    r11w,0x0
  a8:	66 41 c1 c4 00       	rol    r12w,0x0
  ad:	66 c1 c3 00          	rol    bx,0x0
  b1:	66 c1 c1 00          	rol    cx,0x0
  b5:	66 c1 c2 00          	rol    dx,0x0
  b9:	66 41 c1 c0 00       	rol    r8w,0x0
  be:	66 41 c1 c1 00       	rol    r9w,0x0
  c3:	66 41 c1 c2 00       	rol    r10w,0x0
  c8:	66 41 c1 c3 00       	rol    r11w,0x0
  cd:	66 41 c1 c4 00       	rol    r12w,0x0
  d2:	66 c1 c3 00          	rol    bx,0x0
  d6:	66 c1 c1 00          	rol    cx,0x0
  da:	66 c1 c2 00          	rol    dx,0x0
  de:	66 41 c1 c0 00       	rol    r8w,0x0
  e3:	66 41 c1 c1 00       	rol    r9w,0x0
  e8:	66 41 c1 c2 00       	rol    r10w,0x0
  ed:	66 41 c1 c3 00       	rol    r11w,0x0
  f2:	66 41 c1 c4 00       	rol    r12w,0x0
  f7:	66 c1 c3 00          	rol    bx,0x0
  fb:	66 c1 c1 00          	rol    cx,0x0
  ff:	66 c1 c2 00          	rol    dx,0x0
 103:	66 41 c1 c0 00       	rol    r8w,0x0
 108:	66 41 c1 c1 00       	rol    r9w,0x0
 10d:	66 41 c1 c2 00       	rol    r10w,0x0
 112:	66 41 c1 c3 00       	rol    r11w,0x0
 117:	62 f2 7f 28 68 d1    	vp2intersectd k2,ymm0,ymm1

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS YMM0, YMM0, YMM0;
VXORPS YMM1, YMM1, YMM1

Show nanoBench command
Results:
- Instructions retired: 61.0
- Core cycles: 31.52
- Reference cycles: 23.0
- UOPS_PORT_6: 30.74
- UOPS_PORT_0: 30.25

With blocking instructions for ports {'1', '5'}:

Code:

   0:	c5 e1 58 d4          	vaddpd xmm2,xmm3,xmm4
   4:	c5 e1 58 ec          	vaddpd xmm5,xmm3,xmm4
   8:	c5 e1 58 f4          	vaddpd xmm6,xmm3,xmm4
   c:	c5 e1 58 fc          	vaddpd xmm7,xmm3,xmm4
  10:	c5 61 58 c4          	vaddpd xmm8,xmm3,xmm4
  14:	c5 61 58 cc          	vaddpd xmm9,xmm3,xmm4
  18:	c5 61 58 d4          	vaddpd xmm10,xmm3,xmm4
  1c:	c5 61 58 dc          	vaddpd xmm11,xmm3,xmm4
  20:	c5 61 58 e4          	vaddpd xmm12,xmm3,xmm4
  24:	c5 e1 58 d4          	vaddpd xmm2,xmm3,xmm4
  28:	c5 e1 58 ec          	vaddpd xmm5,xmm3,xmm4
  2c:	c5 e1 58 f4          	vaddpd xmm6,xmm3,xmm4
  30:	c5 e1 58 fc          	vaddpd xmm7,xmm3,xmm4
  34:	c5 61 58 c4          	vaddpd xmm8,xmm3,xmm4
  38:	c5 61 58 cc          	vaddpd xmm9,xmm3,xmm4
  3c:	c5 61 58 d4          	vaddpd xmm10,xmm3,xmm4
  40:	c5 61 58 dc          	vaddpd xmm11,xmm3,xmm4
  44:	c5 61 58 e4          	vaddpd xmm12,xmm3,xmm4
  48:	c5 e1 58 d4          	vaddpd xmm2,xmm3,xmm4
  4c:	c5 e1 58 ec          	vaddpd xmm5,xmm3,xmm4
  50:	c5 e1 58 f4          	vaddpd xmm6,xmm3,xmm4
  54:	c5 e1 58 fc          	vaddpd xmm7,xmm3,xmm4
  58:	c5 61 58 c4          	vaddpd xmm8,xmm3,xmm4
  5c:	c5 61 58 cc          	vaddpd xmm9,xmm3,xmm4
  60:	c5 61 58 d4          	vaddpd xmm10,xmm3,xmm4
  64:	c5 61 58 dc          	vaddpd xmm11,xmm3,xmm4
  68:	c5 61 58 e4          	vaddpd xmm12,xmm3,xmm4
  6c:	c5 e1 58 d4          	vaddpd xmm2,xmm3,xmm4
  70:	c5 e1 58 ec          	vaddpd xmm5,xmm3,xmm4
  74:	c5 e1 58 f4          	vaddpd xmm6,xmm3,xmm4
  78:	c5 e1 58 fc          	vaddpd xmm7,xmm3,xmm4
  7c:	c5 61 58 c4          	vaddpd xmm8,xmm3,xmm4
  80:	c5 61 58 cc          	vaddpd xmm9,xmm3,xmm4
  84:	c5 61 58 d4          	vaddpd xmm10,xmm3,xmm4
  88:	c5 61 58 dc          	vaddpd xmm11,xmm3,xmm4
  8c:	c5 61 58 e4          	vaddpd xmm12,xmm3,xmm4
  90:	c5 e1 58 d4          	vaddpd xmm2,xmm3,xmm4
  94:	c5 e1 58 ec          	vaddpd xmm5,xmm3,xmm4
  98:	c5 e1 58 f4          	vaddpd xmm6,xmm3,xmm4
  9c:	c5 e1 58 fc          	vaddpd xmm7,xmm3,xmm4
  a0:	c5 61 58 c4          	vaddpd xmm8,xmm3,xmm4
  a4:	c5 61 58 cc          	vaddpd xmm9,xmm3,xmm4
  a8:	c5 61 58 d4          	vaddpd xmm10,xmm3,xmm4
  ac:	c5 61 58 dc          	vaddpd xmm11,xmm3,xmm4
  b0:	c5 61 58 e4          	vaddpd xmm12,xmm3,xmm4
  b4:	c5 e1 58 d4          	vaddpd xmm2,xmm3,xmm4
  b8:	c5 e1 58 ec          	vaddpd xmm5,xmm3,xmm4
  bc:	c5 e1 58 f4          	vaddpd xmm6,xmm3,xmm4
  c0:	c5 e1 58 fc          	vaddpd xmm7,xmm3,xmm4
  c4:	c5 61 58 c4          	vaddpd xmm8,xmm3,xmm4
  c8:	c5 61 58 cc          	vaddpd xmm9,xmm3,xmm4
  cc:	c5 61 58 d4          	vaddpd xmm10,xmm3,xmm4
  d0:	c5 61 58 dc          	vaddpd xmm11,xmm3,xmm4
  d4:	c5 61 58 e4          	vaddpd xmm12,xmm3,xmm4
  d8:	c5 e1 58 d4          	vaddpd xmm2,xmm3,xmm4
  dc:	c5 e1 58 ec          	vaddpd xmm5,xmm3,xmm4
  e0:	c5 e1 58 f4          	vaddpd xmm6,xmm3,xmm4
  e4:	c5 e1 58 fc          	vaddpd xmm7,xmm3,xmm4
  e8:	c5 61 58 c4          	vaddpd xmm8,xmm3,xmm4
  ec:	c5 61 58 cc          	vaddpd xmm9,xmm3,xmm4
  f0:	62 f2 7f 28 68 d1    	vp2intersectd k2,ymm0,ymm1

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
VMOVUPD XMM3, [R14];
VMOVUPD XMM4, [R14];
VXORPS YMM0, YMM0, YMM0;
VXORPS YMM1, YMM1, YMM1

Show nanoBench command
Results:
- Instructions retired: 61.0
- Core cycles: 37.99
- Reference cycles: 28.0
- UOPS_PORT_1: 36.21
- UOPS_PORT_5B: 36.81
- UOPS_PORT_5B>=2: 0.0

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

With blocking instructions for ports {'0', '1', '5'}:

Code:

   0:	c5 e1 55 d4          	vandnpd xmm2,xmm3,xmm4
   4:	c5 e1 55 ec          	vandnpd xmm5,xmm3,xmm4
   8:	c5 e1 55 f4          	vandnpd xmm6,xmm3,xmm4
   c:	c5 e1 55 fc          	vandnpd xmm7,xmm3,xmm4
  10:	c5 61 55 c4          	vandnpd xmm8,xmm3,xmm4
  14:	c5 61 55 cc          	vandnpd xmm9,xmm3,xmm4
  18:	c5 61 55 d4          	vandnpd xmm10,xmm3,xmm4
  1c:	c5 61 55 dc          	vandnpd xmm11,xmm3,xmm4
  20:	c5 61 55 e4          	vandnpd xmm12,xmm3,xmm4
  24:	c5 e1 55 d4          	vandnpd xmm2,xmm3,xmm4
  28:	c5 e1 55 ec          	vandnpd xmm5,xmm3,xmm4
  2c:	c5 e1 55 f4          	vandnpd xmm6,xmm3,xmm4
  30:	c5 e1 55 fc          	vandnpd xmm7,xmm3,xmm4
  34:	c5 61 55 c4          	vandnpd xmm8,xmm3,xmm4
  38:	c5 61 55 cc          	vandnpd xmm9,xmm3,xmm4
  3c:	c5 61 55 d4          	vandnpd xmm10,xmm3,xmm4
  40:	c5 61 55 dc          	vandnpd xmm11,xmm3,xmm4
  44:	c5 61 55 e4          	vandnpd xmm12,xmm3,xmm4
  48:	c5 e1 55 d4          	vandnpd xmm2,xmm3,xmm4
  4c:	c5 e1 55 ec          	vandnpd xmm5,xmm3,xmm4
  50:	c5 e1 55 f4          	vandnpd xmm6,xmm3,xmm4
  54:	c5 e1 55 fc          	vandnpd xmm7,xmm3,xmm4
  58:	c5 61 55 c4          	vandnpd xmm8,xmm3,xmm4
  5c:	c5 61 55 cc          	vandnpd xmm9,xmm3,xmm4
  60:	c5 61 55 d4          	vandnpd xmm10,xmm3,xmm4
  64:	c5 61 55 dc          	vandnpd xmm11,xmm3,xmm4
  68:	c5 61 55 e4          	vandnpd xmm12,xmm3,xmm4
  6c:	c5 e1 55 d4          	vandnpd xmm2,xmm3,xmm4
  70:	c5 e1 55 ec          	vandnpd xmm5,xmm3,xmm4
  74:	c5 e1 55 f4          	vandnpd xmm6,xmm3,xmm4
  78:	c5 e1 55 fc          	vandnpd xmm7,xmm3,xmm4
  7c:	c5 61 55 c4          	vandnpd xmm8,xmm3,xmm4
  80:	c5 61 55 cc          	vandnpd xmm9,xmm3,xmm4
  84:	c5 61 55 d4          	vandnpd xmm10,xmm3,xmm4
  88:	c5 61 55 dc          	vandnpd xmm11,xmm3,xmm4
  8c:	c5 61 55 e4          	vandnpd xmm12,xmm3,xmm4
  90:	c5 e1 55 d4          	vandnpd xmm2,xmm3,xmm4
  94:	c5 e1 55 ec          	vandnpd xmm5,xmm3,xmm4
  98:	c5 e1 55 f4          	vandnpd xmm6,xmm3,xmm4
  9c:	c5 e1 55 fc          	vandnpd xmm7,xmm3,xmm4
  a0:	c5 61 55 c4          	vandnpd xmm8,xmm3,xmm4
  a4:	c5 61 55 cc          	vandnpd xmm9,xmm3,xmm4
  a8:	c5 61 55 d4          	vandnpd xmm10,xmm3,xmm4
  ac:	c5 61 55 dc          	vandnpd xmm11,xmm3,xmm4
  b0:	c5 61 55 e4          	vandnpd xmm12,xmm3,xmm4
  b4:	c5 e1 55 d4          	vandnpd xmm2,xmm3,xmm4
  b8:	c5 e1 55 ec          	vandnpd xmm5,xmm3,xmm4
  bc:	c5 e1 55 f4          	vandnpd xmm6,xmm3,xmm4
  c0:	c5 e1 55 fc          	vandnpd xmm7,xmm3,xmm4
  c4:	c5 61 55 c4          	vandnpd xmm8,xmm3,xmm4
  c8:	c5 61 55 cc          	vandnpd xmm9,xmm3,xmm4
  cc:	c5 61 55 d4          	vandnpd xmm10,xmm3,xmm4
  d0:	c5 61 55 dc          	vandnpd xmm11,xmm3,xmm4
  d4:	c5 61 55 e4          	vandnpd xmm12,xmm3,xmm4
  d8:	c5 e1 55 d4          	vandnpd xmm2,xmm3,xmm4
  dc:	c5 e1 55 ec          	vandnpd xmm5,xmm3,xmm4
  e0:	c5 e1 55 f4          	vandnpd xmm6,xmm3,xmm4
  e4:	c5 e1 55 fc          	vandnpd xmm7,xmm3,xmm4
  e8:	c5 61 55 c4          	vandnpd xmm8,xmm3,xmm4
  ec:	c5 61 55 cc          	vandnpd xmm9,xmm3,xmm4
  f0:	c5 61 55 d4          	vandnpd xmm10,xmm3,xmm4
  f4:	c5 61 55 dc          	vandnpd xmm11,xmm3,xmm4
  f8:	c5 61 55 e4          	vandnpd xmm12,xmm3,xmm4
  fc:	c5 e1 55 d4          	vandnpd xmm2,xmm3,xmm4
 100:	c5 e1 55 ec          	vandnpd xmm5,xmm3,xmm4
 104:	c5 e1 55 f4          	vandnpd xmm6,xmm3,xmm4
 108:	c5 e1 55 fc          	vandnpd xmm7,xmm3,xmm4
 10c:	c5 61 55 c4          	vandnpd xmm8,xmm3,xmm4
 110:	c5 61 55 cc          	vandnpd xmm9,xmm3,xmm4
 114:	c5 61 55 d4          	vandnpd xmm10,xmm3,xmm4
 118:	c5 61 55 dc          	vandnpd xmm11,xmm3,xmm4
 11c:	c5 61 55 e4          	vandnpd xmm12,xmm3,xmm4
 120:	c5 e1 55 d4          	vandnpd xmm2,xmm3,xmm4
 124:	c5 e1 55 ec          	vandnpd xmm5,xmm3,xmm4
 128:	c5 e1 55 f4          	vandnpd xmm6,xmm3,xmm4
 12c:	c5 e1 55 fc          	vandnpd xmm7,xmm3,xmm4
 130:	c5 61 55 c4          	vandnpd xmm8,xmm3,xmm4
 134:	c5 61 55 cc          	vandnpd xmm9,xmm3,xmm4
 138:	c5 61 55 d4          	vandnpd xmm10,xmm3,xmm4
 13c:	c5 61 55 dc          	vandnpd xmm11,xmm3,xmm4
 140:	c5 61 55 e4          	vandnpd xmm12,xmm3,xmm4
 144:	c5 e1 55 d4          	vandnpd xmm2,xmm3,xmm4
 148:	c5 e1 55 ec          	vandnpd xmm5,xmm3,xmm4
 14c:	c5 e1 55 f4          	vandnpd xmm6,xmm3,xmm4
 150:	c5 e1 55 fc          	vandnpd xmm7,xmm3,xmm4
 154:	c5 61 55 c4          	vandnpd xmm8,xmm3,xmm4
 158:	c5 61 55 cc          	vandnpd xmm9,xmm3,xmm4
 15c:	c5 61 55 d4          	vandnpd xmm10,xmm3,xmm4
 160:	c5 61 55 dc          	vandnpd xmm11,xmm3,xmm4
 164:	c5 61 55 e4          	vandnpd xmm12,xmm3,xmm4
 168:	62 f2 7f 28 68 d1    	vp2intersectd k2,ymm0,ymm1

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS XMM3, XMM3, XMM3;
VXORPS XMM4, XMM4, XMM4;
VXORPS YMM0, YMM0, YMM0;
VXORPS YMM1, YMM1, YMM1

Show nanoBench command
Results:
- Instructions retired: 91.0
- Core cycles: 42.03
- Reference cycles: 29.09
- UOPS_PORT_1: 40.03
- UOPS_PORT_0: 39.67
- UOPS_PORT_5B: 40.27
- UOPS_PORT_5B>=2: 0.0

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