VGATHERQPD (ZMM, K, VSIB_ZMM) - 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:	0f 7e c0             	movd   eax,mm0
  20:	41 0f 7e c0          	movd   r8d,mm0
  24:	41 0f 7e c1          	movd   r9d,mm0
  28:	41 0f 7e c2          	movd   r10d,mm0
  2c:	41 0f 7e c3          	movd   r11d,mm0
  30:	41 0f 7e c4          	movd   r12d,mm0
  34:	0f 7e c3             	movd   ebx,mm0
  37:	0f 7e c1             	movd   ecx,mm0
  3a:	0f 7e c2             	movd   edx,mm0
  3d:	0f 7e c0             	movd   eax,mm0
  40:	41 0f 7e c0          	movd   r8d,mm0
  44:	41 0f 7e c1          	movd   r9d,mm0
  48:	41 0f 7e c2          	movd   r10d,mm0
  4c:	41 0f 7e c3          	movd   r11d,mm0
  50:	41 0f 7e c4          	movd   r12d,mm0
  54:	0f 7e c3             	movd   ebx,mm0
  57:	0f 7e c1             	movd   ecx,mm0
  5a:	0f 7e c2             	movd   edx,mm0
  5d:	0f 7e c0             	movd   eax,mm0
  60:	41 0f 7e c0          	movd   r8d,mm0
  64:	41 0f 7e c1          	movd   r9d,mm0
  68:	41 0f 7e c2          	movd   r10d,mm0
  6c:	41 0f 7e c3          	movd   r11d,mm0
  70:	41 0f 7e c4          	movd   r12d,mm0
  74:	0f 7e c3             	movd   ebx,mm0
  77:	0f 7e c1             	movd   ecx,mm0
  7a:	0f 7e c2             	movd   edx,mm0
  7d:	0f 7e c0             	movd   eax,mm0
  80:	41 0f 7e c0          	movd   r8d,mm0
  84:	41 0f 7e c1          	movd   r9d,mm0
  88:	41 0f 7e c2          	movd   r10d,mm0
  8c:	41 0f 7e c3          	movd   r11d,mm0
  90:	62 92 fd 49 93 04 36 	vgatherqpd zmm0{k1},QWORD PTR [r14+zmm14*1]

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
PXOR MM0, MM0;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VXORPS ZMM14, ZMM14, ZMM14

Show nanoBench command
Results:
- Instructions retired: 41.0
- Core cycles: 42.69
- Reference cycles: 22.19
- UOPS_PORT_0: 40.96

⇨ 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:	8d 05 80 00 00 00    	lea    eax,[rip+0x80]        # 0xbb
  3b:	44 8d 05 80 00 00 00 	lea    r8d,[rip+0x80]        # 0xc2
  42:	44 8d 0d 80 00 00 00 	lea    r9d,[rip+0x80]        # 0xc9
  49:	44 8d 15 80 00 00 00 	lea    r10d,[rip+0x80]        # 0xd0
  50:	44 8d 1d 80 00 00 00 	lea    r11d,[rip+0x80]        # 0xd7
  57:	44 8d 25 80 00 00 00 	lea    r12d,[rip+0x80]        # 0xde
  5e:	8d 1d 80 00 00 00    	lea    ebx,[rip+0x80]        # 0xe4
  64:	8d 0d 80 00 00 00    	lea    ecx,[rip+0x80]        # 0xea
  6a:	8d 15 80 00 00 00    	lea    edx,[rip+0x80]        # 0xf0
  70:	8d 05 80 00 00 00    	lea    eax,[rip+0x80]        # 0xf6
  76:	44 8d 05 80 00 00 00 	lea    r8d,[rip+0x80]        # 0xfd
  7d:	44 8d 0d 80 00 00 00 	lea    r9d,[rip+0x80]        # 0x104
  84:	44 8d 15 80 00 00 00 	lea    r10d,[rip+0x80]        # 0x10b
  8b:	44 8d 1d 80 00 00 00 	lea    r11d,[rip+0x80]        # 0x112
  92:	44 8d 25 80 00 00 00 	lea    r12d,[rip+0x80]        # 0x119
  99:	8d 1d 80 00 00 00    	lea    ebx,[rip+0x80]        # 0x11f
  9f:	8d 0d 80 00 00 00    	lea    ecx,[rip+0x80]        # 0x125
  a5:	8d 15 80 00 00 00    	lea    edx,[rip+0x80]        # 0x12b
  ab:	8d 05 80 00 00 00    	lea    eax,[rip+0x80]        # 0x131
  b1:	44 8d 05 80 00 00 00 	lea    r8d,[rip+0x80]        # 0x138
  b8:	44 8d 0d 80 00 00 00 	lea    r9d,[rip+0x80]        # 0x13f
  bf:	44 8d 15 80 00 00 00 	lea    r10d,[rip+0x80]        # 0x146
  c6:	44 8d 1d 80 00 00 00 	lea    r11d,[rip+0x80]        # 0x14d
  cd:	44 8d 25 80 00 00 00 	lea    r12d,[rip+0x80]        # 0x154
  d4:	8d 1d 80 00 00 00    	lea    ebx,[rip+0x80]        # 0x15a
  da:	8d 0d 80 00 00 00    	lea    ecx,[rip+0x80]        # 0x160
  e0:	8d 15 80 00 00 00    	lea    edx,[rip+0x80]        # 0x166
  e6:	8d 05 80 00 00 00    	lea    eax,[rip+0x80]        # 0x16c
  ec:	44 8d 05 80 00 00 00 	lea    r8d,[rip+0x80]        # 0x173
  f3:	44 8d 0d 80 00 00 00 	lea    r9d,[rip+0x80]        # 0x17a
  fa:	44 8d 15 80 00 00 00 	lea    r10d,[rip+0x80]        # 0x181
 101:	44 8d 1d 80 00 00 00 	lea    r11d,[rip+0x80]        # 0x188
 108:	62 92 fd 49 93 04 36 	vgatherqpd zmm0{k1},QWORD PTR [r14+zmm14*1]

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VXORPS ZMM14, ZMM14, ZMM14

Show nanoBench command
Results:
- Instructions retired: 41.0
- Core cycles: 41.03
- Reference cycles: 21.49
- UOPS_PORT_1: 40.04

With blocking instructions for port '23':

Code:

   0:	45 8b 46 40          	mov    r8d,DWORD PTR [r14+0x40]
   4:	45 8b 4e 44          	mov    r9d,DWORD PTR [r14+0x44]
   8:	45 8b 56 48          	mov    r10d,DWORD PTR [r14+0x48]
   c:	45 8b 5e 4c          	mov    r11d,DWORD PTR [r14+0x4c]
  10:	45 8b 66 50          	mov    r12d,DWORD PTR [r14+0x50]
  14:	41 8b 5e 54          	mov    ebx,DWORD PTR [r14+0x54]
  18:	41 8b 4e 58          	mov    ecx,DWORD PTR [r14+0x58]
  1c:	41 8b 56 5c          	mov    edx,DWORD PTR [r14+0x5c]
  20:	41 8b 46 60          	mov    eax,DWORD PTR [r14+0x60]
  24:	45 8b 46 40          	mov    r8d,DWORD PTR [r14+0x40]
  28:	45 8b 4e 44          	mov    r9d,DWORD PTR [r14+0x44]
  2c:	45 8b 56 48          	mov    r10d,DWORD PTR [r14+0x48]
  30:	45 8b 5e 4c          	mov    r11d,DWORD PTR [r14+0x4c]
  34:	45 8b 66 50          	mov    r12d,DWORD PTR [r14+0x50]
  38:	41 8b 5e 54          	mov    ebx,DWORD PTR [r14+0x54]
  3c:	41 8b 4e 58          	mov    ecx,DWORD PTR [r14+0x58]
  40:	41 8b 56 5c          	mov    edx,DWORD PTR [r14+0x5c]
  44:	41 8b 46 60          	mov    eax,DWORD PTR [r14+0x60]
  48:	45 8b 46 40          	mov    r8d,DWORD PTR [r14+0x40]
  4c:	45 8b 4e 44          	mov    r9d,DWORD PTR [r14+0x44]
  50:	45 8b 56 48          	mov    r10d,DWORD PTR [r14+0x48]
  54:	45 8b 5e 4c          	mov    r11d,DWORD PTR [r14+0x4c]
  58:	45 8b 66 50          	mov    r12d,DWORD PTR [r14+0x50]
  5c:	41 8b 5e 54          	mov    ebx,DWORD PTR [r14+0x54]
  60:	41 8b 4e 58          	mov    ecx,DWORD PTR [r14+0x58]
  64:	41 8b 56 5c          	mov    edx,DWORD PTR [r14+0x5c]
  68:	41 8b 46 60          	mov    eax,DWORD PTR [r14+0x60]
  6c:	45 8b 46 40          	mov    r8d,DWORD PTR [r14+0x40]
  70:	45 8b 4e 44          	mov    r9d,DWORD PTR [r14+0x44]
  74:	45 8b 56 48          	mov    r10d,DWORD PTR [r14+0x48]
  78:	45 8b 5e 4c          	mov    r11d,DWORD PTR [r14+0x4c]
  7c:	45 8b 66 50          	mov    r12d,DWORD PTR [r14+0x50]
  80:	41 8b 5e 54          	mov    ebx,DWORD PTR [r14+0x54]
  84:	41 8b 4e 58          	mov    ecx,DWORD PTR [r14+0x58]
  88:	41 8b 56 5c          	mov    edx,DWORD PTR [r14+0x5c]
  8c:	41 8b 46 60          	mov    eax,DWORD PTR [r14+0x60]
  90:	45 8b 46 40          	mov    r8d,DWORD PTR [r14+0x40]
  94:	45 8b 4e 44          	mov    r9d,DWORD PTR [r14+0x44]
  98:	45 8b 56 48          	mov    r10d,DWORD PTR [r14+0x48]
  9c:	45 8b 5e 4c          	mov    r11d,DWORD PTR [r14+0x4c]
  a0:	45 8b 66 50          	mov    r12d,DWORD PTR [r14+0x50]
  a4:	41 8b 5e 54          	mov    ebx,DWORD PTR [r14+0x54]
  a8:	41 8b 4e 58          	mov    ecx,DWORD PTR [r14+0x58]
  ac:	41 8b 56 5c          	mov    edx,DWORD PTR [r14+0x5c]
  b0:	41 8b 46 60          	mov    eax,DWORD PTR [r14+0x60]
  b4:	45 8b 46 40          	mov    r8d,DWORD PTR [r14+0x40]
  b8:	45 8b 4e 44          	mov    r9d,DWORD PTR [r14+0x44]
  bc:	45 8b 56 48          	mov    r10d,DWORD PTR [r14+0x48]
  c0:	45 8b 5e 4c          	mov    r11d,DWORD PTR [r14+0x4c]
  c4:	45 8b 66 50          	mov    r12d,DWORD PTR [r14+0x50]
  c8:	41 8b 5e 54          	mov    ebx,DWORD PTR [r14+0x54]
  cc:	41 8b 4e 58          	mov    ecx,DWORD PTR [r14+0x58]
  d0:	41 8b 56 5c          	mov    edx,DWORD PTR [r14+0x5c]
  d4:	41 8b 46 60          	mov    eax,DWORD PTR [r14+0x60]
  d8:	45 8b 46 40          	mov    r8d,DWORD PTR [r14+0x40]
  dc:	45 8b 4e 44          	mov    r9d,DWORD PTR [r14+0x44]
  e0:	45 8b 56 48          	mov    r10d,DWORD PTR [r14+0x48]
  e4:	45 8b 5e 4c          	mov    r11d,DWORD PTR [r14+0x4c]
  e8:	45 8b 66 50          	mov    r12d,DWORD PTR [r14+0x50]
  ec:	41 8b 5e 54          	mov    ebx,DWORD PTR [r14+0x54]
  f0:	41 8b 4e 58          	mov    ecx,DWORD PTR [r14+0x58]
  f4:	41 8b 56 5c          	mov    edx,DWORD PTR [r14+0x5c]
  f8:	41 8b 46 60          	mov    eax,DWORD PTR [r14+0x60]
  fc:	45 8b 46 40          	mov    r8d,DWORD PTR [r14+0x40]
 100:	45 8b 4e 44          	mov    r9d,DWORD PTR [r14+0x44]
 104:	45 8b 56 48          	mov    r10d,DWORD PTR [r14+0x48]
 108:	45 8b 5e 4c          	mov    r11d,DWORD PTR [r14+0x4c]
 10c:	45 8b 66 50          	mov    r12d,DWORD PTR [r14+0x50]
 110:	41 8b 5e 54          	mov    ebx,DWORD PTR [r14+0x54]
 114:	41 8b 4e 58          	mov    ecx,DWORD PTR [r14+0x58]
 118:	41 8b 56 5c          	mov    edx,DWORD PTR [r14+0x5c]
 11c:	41 8b 46 60          	mov    eax,DWORD PTR [r14+0x60]
 120:	45 8b 46 40          	mov    r8d,DWORD PTR [r14+0x40]
 124:	45 8b 4e 44          	mov    r9d,DWORD PTR [r14+0x44]
 128:	45 8b 56 48          	mov    r10d,DWORD PTR [r14+0x48]
 12c:	45 8b 5e 4c          	mov    r11d,DWORD PTR [r14+0x4c]
 130:	45 8b 66 50          	mov    r12d,DWORD PTR [r14+0x50]
 134:	41 8b 5e 54          	mov    ebx,DWORD PTR [r14+0x54]
 138:	41 8b 4e 58          	mov    ecx,DWORD PTR [r14+0x58]
 13c:	41 8b 56 5c          	mov    edx,DWORD PTR [r14+0x5c]
 140:	62 92 fd 49 93 04 36 	vgatherqpd zmm0{k1},QWORD PTR [r14+zmm14*1]

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VXORPS ZMM14, ZMM14, ZMM14

Show nanoBench command
Results:
- Instructions retired: 81.0
- Core cycles: 48.56
- Reference cycles: 30.33
- UOPS_PORT_23: 89.0

⇨ 9 μops that can only use port '23'

With blocking instructions for port '49':

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:	4d 89 86 80 00 00 00 	mov    QWORD PTR [r14+0x80],r8
  d7:	4d 89 86 88 00 00 00 	mov    QWORD PTR [r14+0x88],r8
  de:	4d 89 86 90 00 00 00 	mov    QWORD PTR [r14+0x90],r8
  e5:	4d 89 86 98 00 00 00 	mov    QWORD PTR [r14+0x98],r8
  ec:	4d 89 86 a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r8
  f3:	4d 89 86 a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r8
  fa:	4d 89 86 b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r8
 101:	4d 89 86 b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r8
 108:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
 10c:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
 110:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
 114:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
 118:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
 11c:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
 120:	4d 89 46 70          	mov    QWORD PTR [r14+0x70],r8
 124:	4d 89 46 78          	mov    QWORD PTR [r14+0x78],r8
 128:	4d 89 86 80 00 00 00 	mov    QWORD PTR [r14+0x80],r8
 12f:	4d 89 86 88 00 00 00 	mov    QWORD PTR [r14+0x88],r8
 136:	4d 89 86 90 00 00 00 	mov    QWORD PTR [r14+0x90],r8
 13d:	4d 89 86 98 00 00 00 	mov    QWORD PTR [r14+0x98],r8
 144:	4d 89 86 a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r8
 14b:	4d 89 86 a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r8
 152:	4d 89 86 b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r8
 159:	4d 89 86 b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r8
 160:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
 164:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
 168:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
 16c:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
 170:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
 174:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
 178:	4d 89 46 70          	mov    QWORD PTR [r14+0x70],r8
 17c:	4d 89 46 78          	mov    QWORD PTR [r14+0x78],r8
 180:	4d 89 86 80 00 00 00 	mov    QWORD PTR [r14+0x80],r8
 187:	4d 89 86 88 00 00 00 	mov    QWORD PTR [r14+0x88],r8
 18e:	4d 89 86 90 00 00 00 	mov    QWORD PTR [r14+0x90],r8
 195:	4d 89 86 98 00 00 00 	mov    QWORD PTR [r14+0x98],r8
 19c:	4d 89 86 a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r8
 1a3:	4d 89 86 a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r8
 1aa:	4d 89 86 b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r8
 1b1:	4d 89 86 b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r8
 1b8:	62 92 fd 49 93 04 36 	vgatherqpd zmm0{k1},QWORD PTR [r14+zmm14*1]

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VXORPS ZMM14, ZMM14, ZMM14

Show nanoBench command
Results:
- Instructions retired: 81.0
- Core cycles: 66.75
- Reference cycles: 39.0
- UOPS_PORT_49: 82.0

⇨ 2 μops that can only use port '49'

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:	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:	62 92 fd 49 93 04 36 	vgatherqpd zmm0{k1},QWORD PTR [r14+zmm14*1]

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VXORPS ZMM14, ZMM14, ZMM14

Show nanoBench command
Results:
- Instructions retired: 41.0
- Core cycles: 42.13
- Reference cycles: 22.19
- UOPS_PORT_5: 40.96

⇨ One μop that can only use port '5'

With blocking instructions for port '78':

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:	4d 89 86 80 00 00 00 	mov    QWORD PTR [r14+0x80],r8
  d7:	4d 89 86 88 00 00 00 	mov    QWORD PTR [r14+0x88],r8
  de:	4d 89 86 90 00 00 00 	mov    QWORD PTR [r14+0x90],r8
  e5:	4d 89 86 98 00 00 00 	mov    QWORD PTR [r14+0x98],r8
  ec:	4d 89 86 a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r8
  f3:	4d 89 86 a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r8
  fa:	4d 89 86 b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r8
 101:	4d 89 86 b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r8
 108:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
 10c:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
 110:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
 114:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
 118:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
 11c:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
 120:	4d 89 46 70          	mov    QWORD PTR [r14+0x70],r8
 124:	4d 89 46 78          	mov    QWORD PTR [r14+0x78],r8
 128:	4d 89 86 80 00 00 00 	mov    QWORD PTR [r14+0x80],r8
 12f:	4d 89 86 88 00 00 00 	mov    QWORD PTR [r14+0x88],r8
 136:	4d 89 86 90 00 00 00 	mov    QWORD PTR [r14+0x90],r8
 13d:	4d 89 86 98 00 00 00 	mov    QWORD PTR [r14+0x98],r8
 144:	4d 89 86 a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r8
 14b:	4d 89 86 a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r8
 152:	4d 89 86 b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r8
 159:	4d 89 86 b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r8
 160:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
 164:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
 168:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
 16c:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
 170:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
 174:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
 178:	4d 89 46 70          	mov    QWORD PTR [r14+0x70],r8
 17c:	4d 89 46 78          	mov    QWORD PTR [r14+0x78],r8
 180:	4d 89 86 80 00 00 00 	mov    QWORD PTR [r14+0x80],r8
 187:	4d 89 86 88 00 00 00 	mov    QWORD PTR [r14+0x88],r8
 18e:	4d 89 86 90 00 00 00 	mov    QWORD PTR [r14+0x90],r8
 195:	4d 89 86 98 00 00 00 	mov    QWORD PTR [r14+0x98],r8
 19c:	4d 89 86 a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r8
 1a3:	4d 89 86 a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r8
 1aa:	4d 89 86 b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r8
 1b1:	4d 89 86 b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r8
 1b8:	62 92 fd 49 93 04 36 	vgatherqpd zmm0{k1},QWORD PTR [r14+zmm14*1]

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VXORPS ZMM14, ZMM14, ZMM14

Show nanoBench command
Results:
- Instructions retired: 81.0
- Core cycles: 66.82
- Reference cycles: 30.33
- UOPS_PORT_78: 81.0

⇨ One μop that can only use port '78'

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

Code:

   0:	c5 e9 58 cb          	vaddpd xmm1,xmm2,xmm3
   4:	c5 e9 58 e3          	vaddpd xmm4,xmm2,xmm3
   8:	c5 e9 58 eb          	vaddpd xmm5,xmm2,xmm3
   c:	c5 e9 58 f3          	vaddpd xmm6,xmm2,xmm3
  10:	c5 e9 58 fb          	vaddpd xmm7,xmm2,xmm3
  14:	c5 69 58 c3          	vaddpd xmm8,xmm2,xmm3
  18:	c5 69 58 cb          	vaddpd xmm9,xmm2,xmm3
  1c:	c5 69 58 d3          	vaddpd xmm10,xmm2,xmm3
  20:	c5 69 58 db          	vaddpd xmm11,xmm2,xmm3
  24:	c5 69 58 e3          	vaddpd xmm12,xmm2,xmm3
  28:	c5 e9 58 cb          	vaddpd xmm1,xmm2,xmm3
  2c:	c5 e9 58 e3          	vaddpd xmm4,xmm2,xmm3
  30:	c5 e9 58 eb          	vaddpd xmm5,xmm2,xmm3
  34:	c5 e9 58 f3          	vaddpd xmm6,xmm2,xmm3
  38:	c5 e9 58 fb          	vaddpd xmm7,xmm2,xmm3
  3c:	c5 69 58 c3          	vaddpd xmm8,xmm2,xmm3
  40:	c5 69 58 cb          	vaddpd xmm9,xmm2,xmm3
  44:	c5 69 58 d3          	vaddpd xmm10,xmm2,xmm3
  48:	c5 69 58 db          	vaddpd xmm11,xmm2,xmm3
  4c:	c5 69 58 e3          	vaddpd xmm12,xmm2,xmm3
  50:	c5 e9 58 cb          	vaddpd xmm1,xmm2,xmm3
  54:	c5 e9 58 e3          	vaddpd xmm4,xmm2,xmm3
  58:	c5 e9 58 eb          	vaddpd xmm5,xmm2,xmm3
  5c:	c5 e9 58 f3          	vaddpd xmm6,xmm2,xmm3
  60:	c5 e9 58 fb          	vaddpd xmm7,xmm2,xmm3
  64:	c5 69 58 c3          	vaddpd xmm8,xmm2,xmm3
  68:	c5 69 58 cb          	vaddpd xmm9,xmm2,xmm3
  6c:	c5 69 58 d3          	vaddpd xmm10,xmm2,xmm3
  70:	c5 69 58 db          	vaddpd xmm11,xmm2,xmm3
  74:	c5 69 58 e3          	vaddpd xmm12,xmm2,xmm3
  78:	c5 e9 58 cb          	vaddpd xmm1,xmm2,xmm3
  7c:	c5 e9 58 e3          	vaddpd xmm4,xmm2,xmm3
  80:	c5 e9 58 eb          	vaddpd xmm5,xmm2,xmm3
  84:	c5 e9 58 f3          	vaddpd xmm6,xmm2,xmm3
  88:	c5 e9 58 fb          	vaddpd xmm7,xmm2,xmm3
  8c:	c5 69 58 c3          	vaddpd xmm8,xmm2,xmm3
  90:	c5 69 58 cb          	vaddpd xmm9,xmm2,xmm3
  94:	c5 69 58 d3          	vaddpd xmm10,xmm2,xmm3
  98:	c5 69 58 db          	vaddpd xmm11,xmm2,xmm3
  9c:	c5 69 58 e3          	vaddpd xmm12,xmm2,xmm3
  a0:	c5 e9 58 cb          	vaddpd xmm1,xmm2,xmm3
  a4:	c5 e9 58 e3          	vaddpd xmm4,xmm2,xmm3
  a8:	c5 e9 58 eb          	vaddpd xmm5,xmm2,xmm3
  ac:	c5 e9 58 f3          	vaddpd xmm6,xmm2,xmm3
  b0:	c5 e9 58 fb          	vaddpd xmm7,xmm2,xmm3
  b4:	c5 69 58 c3          	vaddpd xmm8,xmm2,xmm3
  b8:	c5 69 58 cb          	vaddpd xmm9,xmm2,xmm3
  bc:	c5 69 58 d3          	vaddpd xmm10,xmm2,xmm3
  c0:	c5 69 58 db          	vaddpd xmm11,xmm2,xmm3
  c4:	c5 69 58 e3          	vaddpd xmm12,xmm2,xmm3
  c8:	c5 e9 58 cb          	vaddpd xmm1,xmm2,xmm3
  cc:	c5 e9 58 e3          	vaddpd xmm4,xmm2,xmm3
  d0:	c5 e9 58 eb          	vaddpd xmm5,xmm2,xmm3
  d4:	c5 e9 58 f3          	vaddpd xmm6,xmm2,xmm3
  d8:	c5 e9 58 fb          	vaddpd xmm7,xmm2,xmm3
  dc:	c5 69 58 c3          	vaddpd xmm8,xmm2,xmm3
  e0:	c5 69 58 cb          	vaddpd xmm9,xmm2,xmm3
  e4:	c5 69 58 d3          	vaddpd xmm10,xmm2,xmm3
  e8:	c5 69 58 db          	vaddpd xmm11,xmm2,xmm3
  ec:	c5 69 58 e3          	vaddpd xmm12,xmm2,xmm3
  f0:	c5 e9 58 cb          	vaddpd xmm1,xmm2,xmm3
  f4:	c5 e9 58 e3          	vaddpd xmm4,xmm2,xmm3
  f8:	c5 e9 58 eb          	vaddpd xmm5,xmm2,xmm3
  fc:	c5 e9 58 f3          	vaddpd xmm6,xmm2,xmm3
 100:	c5 e9 58 fb          	vaddpd xmm7,xmm2,xmm3
 104:	c5 69 58 c3          	vaddpd xmm8,xmm2,xmm3
 108:	c5 69 58 cb          	vaddpd xmm9,xmm2,xmm3
 10c:	c5 69 58 d3          	vaddpd xmm10,xmm2,xmm3
 110:	c5 69 58 db          	vaddpd xmm11,xmm2,xmm3
 114:	c5 69 58 e3          	vaddpd xmm12,xmm2,xmm3
 118:	c5 e9 58 cb          	vaddpd xmm1,xmm2,xmm3
 11c:	c5 e9 58 e3          	vaddpd xmm4,xmm2,xmm3
 120:	c5 e9 58 eb          	vaddpd xmm5,xmm2,xmm3
 124:	c5 e9 58 f3          	vaddpd xmm6,xmm2,xmm3
 128:	c5 e9 58 fb          	vaddpd xmm7,xmm2,xmm3
 12c:	c5 69 58 c3          	vaddpd xmm8,xmm2,xmm3
 130:	c5 69 58 cb          	vaddpd xmm9,xmm2,xmm3
 134:	c5 69 58 d3          	vaddpd xmm10,xmm2,xmm3
 138:	c5 69 58 db          	vaddpd xmm11,xmm2,xmm3
 13c:	c5 69 58 e3          	vaddpd xmm12,xmm2,xmm3
 140:	62 92 fd 49 93 04 36 	vgatherqpd zmm0{k1},QWORD PTR [r14+zmm14*1]

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
VMOVUPD XMM2, [R14];
VMOVUPD XMM3, [R14];
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VXORPS ZMM14, ZMM14, ZMM14

Show nanoBench command
Results:
- Instructions retired: 81.0
- Core cycles: 81.18
- Reference cycles: 43.33
- UOPS_PORT_1: 4.42
- UOPS_PORT_0: 77.5

⇨ One μop 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:	0f 6f e9             	movq   mm5,mm1
  b7:	0f 6f f1             	movq   mm6,mm1
  ba:	0f 6f f9             	movq   mm7,mm1
  bd:	0f 6f c1             	movq   mm0,mm1
  c0:	0f 6f d1             	movq   mm2,mm1
  c3:	0f 6f d9             	movq   mm3,mm1
  c6:	0f 6f e1             	movq   mm4,mm1
  c9:	0f 6f e9             	movq   mm5,mm1
  cc:	0f 6f f1             	movq   mm6,mm1
  cf:	0f 6f f9             	movq   mm7,mm1
  d2:	0f 6f c1             	movq   mm0,mm1
  d5:	0f 6f d1             	movq   mm2,mm1
  d8:	0f 6f d9             	movq   mm3,mm1
  db:	0f 6f e1             	movq   mm4,mm1
  de:	0f 6f e9             	movq   mm5,mm1
  e1:	0f 6f f1             	movq   mm6,mm1
  e4:	0f 6f f9             	movq   mm7,mm1
  e7:	0f 6f c1             	movq   mm0,mm1
  ea:	0f 6f d1             	movq   mm2,mm1
  ed:	0f 6f d9             	movq   mm3,mm1
  f0:	62 92 fd 49 93 04 36 	vgatherqpd zmm0{k1},QWORD PTR [r14+zmm14*1]

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
PXOR MM1, MM1;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VXORPS ZMM14, ZMM14, ZMM14

Show nanoBench command
Results:
- Instructions retired: 81.0
- Core cycles: 46.72
- Reference cycles: 21.67
- UOPS_PORT_5: 42.92
- UOPS_PORT_0: 42.83

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

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 c1 c0 00          	rol    ax,0x0
  29:	66 41 c1 c0 00       	rol    r8w,0x0
  2e:	66 41 c1 c1 00       	rol    r9w,0x0
  33:	66 41 c1 c2 00       	rol    r10w,0x0
  38:	66 41 c1 c3 00       	rol    r11w,0x0
  3d:	66 41 c1 c4 00       	rol    r12w,0x0
  42:	66 c1 c3 00          	rol    bx,0x0
  46:	66 c1 c1 00          	rol    cx,0x0
  4a:	66 c1 c2 00          	rol    dx,0x0
  4e:	66 c1 c0 00          	rol    ax,0x0
  52:	66 41 c1 c0 00       	rol    r8w,0x0
  57:	66 41 c1 c1 00       	rol    r9w,0x0
  5c:	66 41 c1 c2 00       	rol    r10w,0x0
  61:	66 41 c1 c3 00       	rol    r11w,0x0
  66:	66 41 c1 c4 00       	rol    r12w,0x0
  6b:	66 c1 c3 00          	rol    bx,0x0
  6f:	66 c1 c1 00          	rol    cx,0x0
  73:	66 c1 c2 00          	rol    dx,0x0
  77:	66 c1 c0 00          	rol    ax,0x0
  7b:	66 41 c1 c0 00       	rol    r8w,0x0
  80:	66 41 c1 c1 00       	rol    r9w,0x0
  85:	66 41 c1 c2 00       	rol    r10w,0x0
  8a:	66 41 c1 c3 00       	rol    r11w,0x0
  8f:	66 41 c1 c4 00       	rol    r12w,0x0
  94:	66 c1 c3 00          	rol    bx,0x0
  98:	66 c1 c1 00          	rol    cx,0x0
  9c:	66 c1 c2 00          	rol    dx,0x0
  a0:	66 c1 c0 00          	rol    ax,0x0
  a4:	66 41 c1 c0 00       	rol    r8w,0x0
  a9:	66 41 c1 c1 00       	rol    r9w,0x0
  ae:	66 41 c1 c2 00       	rol    r10w,0x0
  b3:	66 41 c1 c3 00       	rol    r11w,0x0
  b8:	66 41 c1 c4 00       	rol    r12w,0x0
  bd:	66 c1 c3 00          	rol    bx,0x0
  c1:	66 c1 c1 00          	rol    cx,0x0
  c5:	66 c1 c2 00          	rol    dx,0x0
  c9:	66 c1 c0 00          	rol    ax,0x0
  cd:	66 41 c1 c0 00       	rol    r8w,0x0
  d2:	66 41 c1 c1 00       	rol    r9w,0x0
  d7:	66 41 c1 c2 00       	rol    r10w,0x0
  dc:	66 41 c1 c3 00       	rol    r11w,0x0
  e1:	66 41 c1 c4 00       	rol    r12w,0x0
  e6:	66 c1 c3 00          	rol    bx,0x0
  ea:	66 c1 c1 00          	rol    cx,0x0
  ee:	66 c1 c2 00          	rol    dx,0x0
  f2:	66 c1 c0 00          	rol    ax,0x0
  f6:	66 41 c1 c0 00       	rol    r8w,0x0
  fb:	66 41 c1 c1 00       	rol    r9w,0x0
 100:	66 41 c1 c2 00       	rol    r10w,0x0
 105:	66 41 c1 c3 00       	rol    r11w,0x0
 10a:	66 41 c1 c4 00       	rol    r12w,0x0
 10f:	66 c1 c3 00          	rol    bx,0x0
 113:	66 c1 c1 00          	rol    cx,0x0
 117:	66 c1 c2 00          	rol    dx,0x0
 11b:	66 c1 c0 00          	rol    ax,0x0
 11f:	66 41 c1 c0 00       	rol    r8w,0x0
 124:	66 41 c1 c1 00       	rol    r9w,0x0
 129:	66 41 c1 c2 00       	rol    r10w,0x0
 12e:	66 41 c1 c3 00       	rol    r11w,0x0
 133:	66 41 c1 c4 00       	rol    r12w,0x0
 138:	66 c1 c3 00          	rol    bx,0x0
 13c:	66 c1 c1 00          	rol    cx,0x0
 140:	66 c1 c2 00          	rol    dx,0x0
 144:	66 c1 c0 00          	rol    ax,0x0
 148:	66 41 c1 c0 00       	rol    r8w,0x0
 14d:	66 41 c1 c1 00       	rol    r9w,0x0
 152:	66 41 c1 c2 00       	rol    r10w,0x0
 157:	66 41 c1 c3 00       	rol    r11w,0x0
 15c:	66 41 c1 c4 00       	rol    r12w,0x0
 161:	66 c1 c3 00          	rol    bx,0x0
 165:	66 c1 c1 00          	rol    cx,0x0
 169:	66 c1 c2 00          	rol    dx,0x0
 16d:	62 92 fd 49 93 04 36 	vgatherqpd zmm0{k1},QWORD PTR [r14+zmm14*1]

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VXORPS ZMM14, ZMM14, ZMM14

Show nanoBench command
Results:
- Instructions retired: 81.0
- Core cycles: 44.57
- Reference cycles: 20.22
- UOPS_PORT_6: 41.17
- UOPS_PORT_0: 40.83

⇨ One μop that can only use ports {'0', '6'}

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

Code:

   0:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
   4:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
   8:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
   c:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
  10:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
  14:	43 8d 1c 6e          	lea    ebx,[r14+r13*2]
  18:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
  1c:	43 8d 14 6e          	lea    edx,[r14+r13*2]
  20:	43 8d 04 6e          	lea    eax,[r14+r13*2]
  24:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
  28:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
  2c:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
  30:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
  34:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
  38:	43 8d 1c 6e          	lea    ebx,[r14+r13*2]
  3c:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
  40:	43 8d 14 6e          	lea    edx,[r14+r13*2]
  44:	43 8d 04 6e          	lea    eax,[r14+r13*2]
  48:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
  4c:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
  50:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
  54:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
  58:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
  5c:	43 8d 1c 6e          	lea    ebx,[r14+r13*2]
  60:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
  64:	43 8d 14 6e          	lea    edx,[r14+r13*2]
  68:	43 8d 04 6e          	lea    eax,[r14+r13*2]
  6c:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
  70:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
  74:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
  78:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
  7c:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
  80:	43 8d 1c 6e          	lea    ebx,[r14+r13*2]
  84:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
  88:	43 8d 14 6e          	lea    edx,[r14+r13*2]
  8c:	43 8d 04 6e          	lea    eax,[r14+r13*2]
  90:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
  94:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
  98:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
  9c:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
  a0:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
  a4:	43 8d 1c 6e          	lea    ebx,[r14+r13*2]
  a8:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
  ac:	43 8d 14 6e          	lea    edx,[r14+r13*2]
  b0:	43 8d 04 6e          	lea    eax,[r14+r13*2]
  b4:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
  b8:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
  bc:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
  c0:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
  c4:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
  c8:	43 8d 1c 6e          	lea    ebx,[r14+r13*2]
  cc:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
  d0:	43 8d 14 6e          	lea    edx,[r14+r13*2]
  d4:	43 8d 04 6e          	lea    eax,[r14+r13*2]
  d8:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
  dc:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
  e0:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
  e4:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
  e8:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
  ec:	43 8d 1c 6e          	lea    ebx,[r14+r13*2]
  f0:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
  f4:	43 8d 14 6e          	lea    edx,[r14+r13*2]
  f8:	43 8d 04 6e          	lea    eax,[r14+r13*2]
  fc:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
 100:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
 104:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
 108:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
 10c:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
 110:	43 8d 1c 6e          	lea    ebx,[r14+r13*2]
 114:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
 118:	43 8d 14 6e          	lea    edx,[r14+r13*2]
 11c:	43 8d 04 6e          	lea    eax,[r14+r13*2]
 120:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
 124:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
 128:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
 12c:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
 130:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
 134:	43 8d 1c 6e          	lea    ebx,[r14+r13*2]
 138:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
 13c:	43 8d 14 6e          	lea    edx,[r14+r13*2]
 140:	62 92 fd 49 93 04 36 	vgatherqpd zmm0{k1},QWORD PTR [r14+zmm14*1]

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VXORPS ZMM14, ZMM14, ZMM14

Show nanoBench command
Results:
- Instructions retired: 81.0
- Core cycles: 42.72
- Reference cycles: 18.78
- UOPS_PORT_5: 40.5
- UOPS_PORT_1: 40.5

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

Code:

   0:	c5 e9 55 cb          	vandnpd xmm1,xmm2,xmm3
   4:	c5 e9 55 e3          	vandnpd xmm4,xmm2,xmm3
   8:	c5 e9 55 eb          	vandnpd xmm5,xmm2,xmm3
   c:	c5 e9 55 f3          	vandnpd xmm6,xmm2,xmm3
  10:	c5 e9 55 fb          	vandnpd xmm7,xmm2,xmm3
  14:	c5 69 55 c3          	vandnpd xmm8,xmm2,xmm3
  18:	c5 69 55 cb          	vandnpd xmm9,xmm2,xmm3
  1c:	c5 69 55 d3          	vandnpd xmm10,xmm2,xmm3
  20:	c5 69 55 db          	vandnpd xmm11,xmm2,xmm3
  24:	c5 69 55 e3          	vandnpd xmm12,xmm2,xmm3
  28:	c5 e9 55 cb          	vandnpd xmm1,xmm2,xmm3
  2c:	c5 e9 55 e3          	vandnpd xmm4,xmm2,xmm3
  30:	c5 e9 55 eb          	vandnpd xmm5,xmm2,xmm3
  34:	c5 e9 55 f3          	vandnpd xmm6,xmm2,xmm3
  38:	c5 e9 55 fb          	vandnpd xmm7,xmm2,xmm3
  3c:	c5 69 55 c3          	vandnpd xmm8,xmm2,xmm3
  40:	c5 69 55 cb          	vandnpd xmm9,xmm2,xmm3
  44:	c5 69 55 d3          	vandnpd xmm10,xmm2,xmm3
  48:	c5 69 55 db          	vandnpd xmm11,xmm2,xmm3
  4c:	c5 69 55 e3          	vandnpd xmm12,xmm2,xmm3
  50:	c5 e9 55 cb          	vandnpd xmm1,xmm2,xmm3
  54:	c5 e9 55 e3          	vandnpd xmm4,xmm2,xmm3
  58:	c5 e9 55 eb          	vandnpd xmm5,xmm2,xmm3
  5c:	c5 e9 55 f3          	vandnpd xmm6,xmm2,xmm3
  60:	c5 e9 55 fb          	vandnpd xmm7,xmm2,xmm3
  64:	c5 69 55 c3          	vandnpd xmm8,xmm2,xmm3
  68:	c5 69 55 cb          	vandnpd xmm9,xmm2,xmm3
  6c:	c5 69 55 d3          	vandnpd xmm10,xmm2,xmm3
  70:	c5 69 55 db          	vandnpd xmm11,xmm2,xmm3
  74:	c5 69 55 e3          	vandnpd xmm12,xmm2,xmm3
  78:	c5 e9 55 cb          	vandnpd xmm1,xmm2,xmm3
  7c:	c5 e9 55 e3          	vandnpd xmm4,xmm2,xmm3
  80:	c5 e9 55 eb          	vandnpd xmm5,xmm2,xmm3
  84:	c5 e9 55 f3          	vandnpd xmm6,xmm2,xmm3
  88:	c5 e9 55 fb          	vandnpd xmm7,xmm2,xmm3
  8c:	c5 69 55 c3          	vandnpd xmm8,xmm2,xmm3
  90:	c5 69 55 cb          	vandnpd xmm9,xmm2,xmm3
  94:	c5 69 55 d3          	vandnpd xmm10,xmm2,xmm3
  98:	c5 69 55 db          	vandnpd xmm11,xmm2,xmm3
  9c:	c5 69 55 e3          	vandnpd xmm12,xmm2,xmm3
  a0:	c5 e9 55 cb          	vandnpd xmm1,xmm2,xmm3
  a4:	c5 e9 55 e3          	vandnpd xmm4,xmm2,xmm3
  a8:	c5 e9 55 eb          	vandnpd xmm5,xmm2,xmm3
  ac:	c5 e9 55 f3          	vandnpd xmm6,xmm2,xmm3
  b0:	c5 e9 55 fb          	vandnpd xmm7,xmm2,xmm3
  b4:	c5 69 55 c3          	vandnpd xmm8,xmm2,xmm3
  b8:	c5 69 55 cb          	vandnpd xmm9,xmm2,xmm3
  bc:	c5 69 55 d3          	vandnpd xmm10,xmm2,xmm3
  c0:	c5 69 55 db          	vandnpd xmm11,xmm2,xmm3
  c4:	c5 69 55 e3          	vandnpd xmm12,xmm2,xmm3
  c8:	c5 e9 55 cb          	vandnpd xmm1,xmm2,xmm3
  cc:	c5 e9 55 e3          	vandnpd xmm4,xmm2,xmm3
  d0:	c5 e9 55 eb          	vandnpd xmm5,xmm2,xmm3
  d4:	c5 e9 55 f3          	vandnpd xmm6,xmm2,xmm3
  d8:	c5 e9 55 fb          	vandnpd xmm7,xmm2,xmm3
  dc:	c5 69 55 c3          	vandnpd xmm8,xmm2,xmm3
  e0:	c5 69 55 cb          	vandnpd xmm9,xmm2,xmm3
  e4:	c5 69 55 d3          	vandnpd xmm10,xmm2,xmm3
  e8:	c5 69 55 db          	vandnpd xmm11,xmm2,xmm3
  ec:	c5 69 55 e3          	vandnpd xmm12,xmm2,xmm3
  f0:	c5 e9 55 cb          	vandnpd xmm1,xmm2,xmm3
  f4:	c5 e9 55 e3          	vandnpd xmm4,xmm2,xmm3
  f8:	c5 e9 55 eb          	vandnpd xmm5,xmm2,xmm3
  fc:	c5 e9 55 f3          	vandnpd xmm6,xmm2,xmm3
 100:	c5 e9 55 fb          	vandnpd xmm7,xmm2,xmm3
 104:	c5 69 55 c3          	vandnpd xmm8,xmm2,xmm3
 108:	c5 69 55 cb          	vandnpd xmm9,xmm2,xmm3
 10c:	c5 69 55 d3          	vandnpd xmm10,xmm2,xmm3
 110:	c5 69 55 db          	vandnpd xmm11,xmm2,xmm3
 114:	c5 69 55 e3          	vandnpd xmm12,xmm2,xmm3
 118:	c5 e9 55 cb          	vandnpd xmm1,xmm2,xmm3
 11c:	c5 e9 55 e3          	vandnpd xmm4,xmm2,xmm3
 120:	c5 e9 55 eb          	vandnpd xmm5,xmm2,xmm3
 124:	c5 e9 55 f3          	vandnpd xmm6,xmm2,xmm3
 128:	c5 e9 55 fb          	vandnpd xmm7,xmm2,xmm3
 12c:	c5 69 55 c3          	vandnpd xmm8,xmm2,xmm3
 130:	c5 69 55 cb          	vandnpd xmm9,xmm2,xmm3
 134:	c5 69 55 d3          	vandnpd xmm10,xmm2,xmm3
 138:	c5 69 55 db          	vandnpd xmm11,xmm2,xmm3
 13c:	c5 69 55 e3          	vandnpd xmm12,xmm2,xmm3
 140:	c5 e9 55 cb          	vandnpd xmm1,xmm2,xmm3
 144:	c5 e9 55 e3          	vandnpd xmm4,xmm2,xmm3
 148:	c5 e9 55 eb          	vandnpd xmm5,xmm2,xmm3
 14c:	c5 e9 55 f3          	vandnpd xmm6,xmm2,xmm3
 150:	c5 e9 55 fb          	vandnpd xmm7,xmm2,xmm3
 154:	c5 69 55 c3          	vandnpd xmm8,xmm2,xmm3
 158:	c5 69 55 cb          	vandnpd xmm9,xmm2,xmm3
 15c:	c5 69 55 d3          	vandnpd xmm10,xmm2,xmm3
 160:	c5 69 55 db          	vandnpd xmm11,xmm2,xmm3
 164:	c5 69 55 e3          	vandnpd xmm12,xmm2,xmm3
 168:	c5 e9 55 cb          	vandnpd xmm1,xmm2,xmm3
 16c:	c5 e9 55 e3          	vandnpd xmm4,xmm2,xmm3
 170:	c5 e9 55 eb          	vandnpd xmm5,xmm2,xmm3
 174:	c5 e9 55 f3          	vandnpd xmm6,xmm2,xmm3
 178:	c5 e9 55 fb          	vandnpd xmm7,xmm2,xmm3
 17c:	c5 69 55 c3          	vandnpd xmm8,xmm2,xmm3
 180:	c5 69 55 cb          	vandnpd xmm9,xmm2,xmm3
 184:	c5 69 55 d3          	vandnpd xmm10,xmm2,xmm3
 188:	c5 69 55 db          	vandnpd xmm11,xmm2,xmm3
 18c:	c5 69 55 e3          	vandnpd xmm12,xmm2,xmm3
 190:	62 92 fd 49 93 04 36 	vgatherqpd zmm0{k1},QWORD PTR [r14+zmm14*1]

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS XMM2, XMM2, XMM2;
VXORPS XMM3, XMM3, XMM3;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VXORPS ZMM14, ZMM14, ZMM14

Show nanoBench command
Results:
- Instructions retired: 101.0
- Core cycles: 55.8
- Reference cycles: 24.27
- UOPS_PORT_5: 51.3
- UOPS_PORT_1: 4.3
- UOPS_PORT_0: 51.2

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

With blocking instructions for ports {'0', '1', '5', '6'}:

Code:

   0:	45 8d 46 08          	lea    r8d,[r14+0x8]
   4:	45 8d 4e 08          	lea    r9d,[r14+0x8]
   8:	45 8d 56 08          	lea    r10d,[r14+0x8]
   c:	45 8d 5e 08          	lea    r11d,[r14+0x8]
  10:	45 8d 66 08          	lea    r12d,[r14+0x8]
  14:	41 8d 5e 08          	lea    ebx,[r14+0x8]
  18:	41 8d 4e 08          	lea    ecx,[r14+0x8]
  1c:	41 8d 56 08          	lea    edx,[r14+0x8]
  20:	41 8d 46 08          	lea    eax,[r14+0x8]
  24:	45 8d 46 08          	lea    r8d,[r14+0x8]
  28:	45 8d 4e 08          	lea    r9d,[r14+0x8]
  2c:	45 8d 56 08          	lea    r10d,[r14+0x8]
  30:	45 8d 5e 08          	lea    r11d,[r14+0x8]
  34:	45 8d 66 08          	lea    r12d,[r14+0x8]
  38:	41 8d 5e 08          	lea    ebx,[r14+0x8]
  3c:	41 8d 4e 08          	lea    ecx,[r14+0x8]
  40:	41 8d 56 08          	lea    edx,[r14+0x8]
  44:	41 8d 46 08          	lea    eax,[r14+0x8]
  48:	45 8d 46 08          	lea    r8d,[r14+0x8]
  4c:	45 8d 4e 08          	lea    r9d,[r14+0x8]
  50:	45 8d 56 08          	lea    r10d,[r14+0x8]
  54:	45 8d 5e 08          	lea    r11d,[r14+0x8]
  58:	45 8d 66 08          	lea    r12d,[r14+0x8]
  5c:	41 8d 5e 08          	lea    ebx,[r14+0x8]
  60:	41 8d 4e 08          	lea    ecx,[r14+0x8]
  64:	41 8d 56 08          	lea    edx,[r14+0x8]
  68:	41 8d 46 08          	lea    eax,[r14+0x8]
  6c:	45 8d 46 08          	lea    r8d,[r14+0x8]
  70:	45 8d 4e 08          	lea    r9d,[r14+0x8]
  74:	45 8d 56 08          	lea    r10d,[r14+0x8]
  78:	45 8d 5e 08          	lea    r11d,[r14+0x8]
  7c:	45 8d 66 08          	lea    r12d,[r14+0x8]
  80:	41 8d 5e 08          	lea    ebx,[r14+0x8]
  84:	41 8d 4e 08          	lea    ecx,[r14+0x8]
  88:	41 8d 56 08          	lea    edx,[r14+0x8]
  8c:	41 8d 46 08          	lea    eax,[r14+0x8]
  90:	45 8d 46 08          	lea    r8d,[r14+0x8]
  94:	45 8d 4e 08          	lea    r9d,[r14+0x8]
  98:	45 8d 56 08          	lea    r10d,[r14+0x8]
  9c:	45 8d 5e 08          	lea    r11d,[r14+0x8]
  a0:	45 8d 66 08          	lea    r12d,[r14+0x8]
  a4:	41 8d 5e 08          	lea    ebx,[r14+0x8]
  a8:	41 8d 4e 08          	lea    ecx,[r14+0x8]
  ac:	41 8d 56 08          	lea    edx,[r14+0x8]
  b0:	41 8d 46 08          	lea    eax,[r14+0x8]
  b4:	45 8d 46 08          	lea    r8d,[r14+0x8]
  b8:	45 8d 4e 08          	lea    r9d,[r14+0x8]
  bc:	45 8d 56 08          	lea    r10d,[r14+0x8]
  c0:	45 8d 5e 08          	lea    r11d,[r14+0x8]
  c4:	45 8d 66 08          	lea    r12d,[r14+0x8]
  c8:	41 8d 5e 08          	lea    ebx,[r14+0x8]
  cc:	41 8d 4e 08          	lea    ecx,[r14+0x8]
  d0:	41 8d 56 08          	lea    edx,[r14+0x8]
  d4:	41 8d 46 08          	lea    eax,[r14+0x8]
  d8:	45 8d 46 08          	lea    r8d,[r14+0x8]
  dc:	45 8d 4e 08          	lea    r9d,[r14+0x8]
  e0:	45 8d 56 08          	lea    r10d,[r14+0x8]
  e4:	45 8d 5e 08          	lea    r11d,[r14+0x8]
  e8:	45 8d 66 08          	lea    r12d,[r14+0x8]
  ec:	41 8d 5e 08          	lea    ebx,[r14+0x8]
  f0:	41 8d 4e 08          	lea    ecx,[r14+0x8]
  f4:	41 8d 56 08          	lea    edx,[r14+0x8]
  f8:	41 8d 46 08          	lea    eax,[r14+0x8]
  fc:	45 8d 46 08          	lea    r8d,[r14+0x8]
 100:	45 8d 4e 08          	lea    r9d,[r14+0x8]
 104:	45 8d 56 08          	lea    r10d,[r14+0x8]
 108:	45 8d 5e 08          	lea    r11d,[r14+0x8]
 10c:	45 8d 66 08          	lea    r12d,[r14+0x8]
 110:	41 8d 5e 08          	lea    ebx,[r14+0x8]
 114:	41 8d 4e 08          	lea    ecx,[r14+0x8]
 118:	41 8d 56 08          	lea    edx,[r14+0x8]
 11c:	41 8d 46 08          	lea    eax,[r14+0x8]
 120:	45 8d 46 08          	lea    r8d,[r14+0x8]
 124:	45 8d 4e 08          	lea    r9d,[r14+0x8]
 128:	45 8d 56 08          	lea    r10d,[r14+0x8]
 12c:	45 8d 5e 08          	lea    r11d,[r14+0x8]
 130:	45 8d 66 08          	lea    r12d,[r14+0x8]
 134:	41 8d 5e 08          	lea    ebx,[r14+0x8]
 138:	41 8d 4e 08          	lea    ecx,[r14+0x8]
 13c:	41 8d 56 08          	lea    edx,[r14+0x8]
 140:	41 8d 46 08          	lea    eax,[r14+0x8]
 144:	45 8d 46 08          	lea    r8d,[r14+0x8]
 148:	45 8d 4e 08          	lea    r9d,[r14+0x8]
 14c:	45 8d 56 08          	lea    r10d,[r14+0x8]
 150:	45 8d 5e 08          	lea    r11d,[r14+0x8]
 154:	45 8d 66 08          	lea    r12d,[r14+0x8]
 158:	41 8d 5e 08          	lea    ebx,[r14+0x8]
 15c:	41 8d 4e 08          	lea    ecx,[r14+0x8]
 160:	41 8d 56 08          	lea    edx,[r14+0x8]
 164:	41 8d 46 08          	lea    eax,[r14+0x8]
 168:	45 8d 46 08          	lea    r8d,[r14+0x8]
 16c:	45 8d 4e 08          	lea    r9d,[r14+0x8]
 170:	45 8d 56 08          	lea    r10d,[r14+0x8]
 174:	45 8d 5e 08          	lea    r11d,[r14+0x8]
 178:	45 8d 66 08          	lea    r12d,[r14+0x8]
 17c:	41 8d 5e 08          	lea    ebx,[r14+0x8]
 180:	41 8d 4e 08          	lea    ecx,[r14+0x8]
 184:	41 8d 56 08          	lea    edx,[r14+0x8]
 188:	41 8d 46 08          	lea    eax,[r14+0x8]
 18c:	45 8d 46 08          	lea    r8d,[r14+0x8]
 190:	62 92 fd 49 93 04 36 	vgatherqpd zmm0{k1},QWORD PTR [r14+zmm14*1]

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VXORPS ZMM14, ZMM14, ZMM14

Show nanoBench command
Results:
- Instructions retired: 101.0
- Core cycles: 39.82
- Reference cycles: 19.07
- UOPS_PORT_6: 27.5
- UOPS_PORT_5: 28.3
- UOPS_PORT_1: 26.6
- UOPS_PORT_0: 28.5

⇨ 3 μops that can only use ports {'0', '1', '5', '6'}