VGATHERQPD (ZMM, K, VSIB_ZMM) - Port Usage

With blocking instructions for port '1':

Code:

   0:	41 0f c4 c0 02       	pinsrw mm0,r8d,0x2
   5:	41 0f c4 c8 02       	pinsrw mm1,r8d,0x2
   a:	41 0f c4 d0 02       	pinsrw mm2,r8d,0x2
   f:	41 0f c4 d8 02       	pinsrw mm3,r8d,0x2
  14:	41 0f c4 e0 02       	pinsrw mm4,r8d,0x2
  19:	41 0f c4 e8 02       	pinsrw mm5,r8d,0x2
  1e:	41 0f c4 f0 02       	pinsrw mm6,r8d,0x2
  23:	41 0f c4 f8 02       	pinsrw mm7,r8d,0x2
  28:	41 0f c4 c0 02       	pinsrw mm0,r8d,0x2
  2d:	41 0f c4 c8 02       	pinsrw mm1,r8d,0x2
  32:	41 0f c4 d0 02       	pinsrw mm2,r8d,0x2
  37:	41 0f c4 d8 02       	pinsrw mm3,r8d,0x2
  3c:	41 0f c4 e0 02       	pinsrw mm4,r8d,0x2
  41:	41 0f c4 e8 02       	pinsrw mm5,r8d,0x2
  46:	41 0f c4 f0 02       	pinsrw mm6,r8d,0x2
  4b:	41 0f c4 f8 02       	pinsrw mm7,r8d,0x2
  50:	41 0f c4 c0 02       	pinsrw mm0,r8d,0x2
  55:	41 0f c4 c8 02       	pinsrw mm1,r8d,0x2
  5a:	41 0f c4 d0 02       	pinsrw mm2,r8d,0x2
  5f:	41 0f c4 d8 02       	pinsrw mm3,r8d,0x2
  64:	41 0f c4 e0 02       	pinsrw mm4,r8d,0x2
  69:	41 0f c4 e8 02       	pinsrw mm5,r8d,0x2
  6e:	41 0f c4 f0 02       	pinsrw mm6,r8d,0x2
  73:	41 0f c4 f8 02       	pinsrw mm7,r8d,0x2
  78:	41 0f c4 c0 02       	pinsrw mm0,r8d,0x2
  7d:	41 0f c4 c8 02       	pinsrw mm1,r8d,0x2
  82:	41 0f c4 d0 02       	pinsrw mm2,r8d,0x2
  87:	41 0f c4 d8 02       	pinsrw mm3,r8d,0x2
  8c:	41 0f c4 e0 02       	pinsrw mm4,r8d,0x2
  91:	41 0f c4 e8 02       	pinsrw mm5,r8d,0x2
  96:	41 0f c4 f0 02       	pinsrw mm6,r8d,0x2
  9b:	41 0f c4 f8 02       	pinsrw mm7,r8d,0x2
  a0:	41 0f c4 c0 02       	pinsrw mm0,r8d,0x2
  a5:	41 0f c4 c8 02       	pinsrw mm1,r8d,0x2
  aa:	41 0f c4 d0 02       	pinsrw mm2,r8d,0x2
  af:	41 0f c4 d8 02       	pinsrw mm3,r8d,0x2
  b4:	41 0f c4 e0 02       	pinsrw mm4,r8d,0x2
  b9:	41 0f c4 e8 02       	pinsrw mm5,r8d,0x2
  be:	41 0f c4 f0 02       	pinsrw mm6,r8d,0x2
  c3:	41 0f c4 f8 02       	pinsrw mm7,r8d,0x2
  c8:	41 0f c4 c0 02       	pinsrw mm0,r8d,0x2
  cd:	41 0f c4 c8 02       	pinsrw mm1,r8d,0x2
  d2:	41 0f c4 d0 02       	pinsrw mm2,r8d,0x2
  d7:	41 0f c4 d8 02       	pinsrw mm3,r8d,0x2
  dc:	41 0f c4 e0 02       	pinsrw mm4,r8d,0x2
  e1:	41 0f c4 e8 02       	pinsrw mm5,r8d,0x2
  e6:	41 0f c4 f0 02       	pinsrw mm6,r8d,0x2
  eb:	41 0f c4 f8 02       	pinsrw mm7,r8d,0x2
  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 MM0, MM0;
PXOR MM1, MM1;
PXOR MM2, MM2;
PXOR MM3, MM3;
PXOR MM4, MM4;
PXOR MM5, MM5;
PXOR MM6, MM6;
PXOR MM7, MM7;
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:
- MPERF: 57.34
- APERF: 66.37
- FpuPipeAssignment.Total0: 4.32
- FpuPipeAssignment.Total1: 23.01
- FpuPipeAssignment.Total2: 18.46
- FpuPipeAssignment.Total3: 16.21
- FpuPipeAssignment.Total4: 5.96
- FpuPipeAssignment.Total5: 4.04

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

Code:

   0:	0f ec c1             	paddsb mm0,mm1
   3:	0f ec d1             	paddsb mm2,mm1
   6:	0f ec d9             	paddsb mm3,mm1
   9:	0f ec e1             	paddsb mm4,mm1
   c:	0f ec e9             	paddsb mm5,mm1
   f:	0f ec f1             	paddsb mm6,mm1
  12:	0f ec f9             	paddsb mm7,mm1
  15:	0f ec c1             	paddsb mm0,mm1
  18:	0f ec d1             	paddsb mm2,mm1
  1b:	0f ec d9             	paddsb mm3,mm1
  1e:	0f ec e1             	paddsb mm4,mm1
  21:	0f ec e9             	paddsb mm5,mm1
  24:	0f ec f1             	paddsb mm6,mm1
  27:	0f ec f9             	paddsb mm7,mm1
  2a:	0f ec c1             	paddsb mm0,mm1
  2d:	0f ec d1             	paddsb mm2,mm1
  30:	0f ec d9             	paddsb mm3,mm1
  33:	0f ec e1             	paddsb mm4,mm1
  36:	0f ec e9             	paddsb mm5,mm1
  39:	0f ec f1             	paddsb mm6,mm1
  3c:	0f ec f9             	paddsb mm7,mm1
  3f:	0f ec c1             	paddsb mm0,mm1
  42:	0f ec d1             	paddsb mm2,mm1
  45:	0f ec d9             	paddsb mm3,mm1
  48:	0f ec e1             	paddsb mm4,mm1
  4b:	0f ec e9             	paddsb mm5,mm1
  4e:	0f ec f1             	paddsb mm6,mm1
  51:	0f ec f9             	paddsb mm7,mm1
  54:	0f ec c1             	paddsb mm0,mm1
  57:	0f ec d1             	paddsb mm2,mm1
  5a:	0f ec d9             	paddsb mm3,mm1
  5d:	0f ec e1             	paddsb mm4,mm1
  60:	0f ec e9             	paddsb mm5,mm1
  63:	0f ec f1             	paddsb mm6,mm1
  66:	0f ec f9             	paddsb mm7,mm1
  69:	0f ec c1             	paddsb mm0,mm1
  6c:	0f ec d1             	paddsb mm2,mm1
  6f:	0f ec d9             	paddsb mm3,mm1
  72:	0f ec e1             	paddsb mm4,mm1
  75:	0f ec e9             	paddsb mm5,mm1
  78:	0f ec f1             	paddsb mm6,mm1
  7b:	0f ec f9             	paddsb mm7,mm1
  7e:	0f ec c1             	paddsb mm0,mm1
  81:	0f ec d1             	paddsb mm2,mm1
  84:	0f ec d9             	paddsb mm3,mm1
  87:	0f ec e1             	paddsb mm4,mm1
  8a:	0f ec e9             	paddsb mm5,mm1
  8d:	0f ec f1             	paddsb mm6,mm1
  90:	0f ec f9             	paddsb mm7,mm1
  93:	0f ec c1             	paddsb mm0,mm1
  96:	0f ec d1             	paddsb mm2,mm1
  99:	0f ec d9             	paddsb mm3,mm1
  9c:	0f ec e1             	paddsb mm4,mm1
  9f:	0f ec e9             	paddsb mm5,mm1
  a2:	0f ec f1             	paddsb mm6,mm1
  a5:	0f ec f9             	paddsb mm7,mm1
  a8:	0f ec c1             	paddsb mm0,mm1
  ab:	0f ec d1             	paddsb mm2,mm1
  ae:	0f ec d9             	paddsb mm3,mm1
  b1:	0f ec e1             	paddsb mm4,mm1
  b4:	0f ec e9             	paddsb mm5,mm1
  b7:	0f ec f1             	paddsb mm6,mm1
  ba:	0f ec f9             	paddsb mm7,mm1
  bd:	0f ec c1             	paddsb mm0,mm1
  c0:	0f ec d1             	paddsb mm2,mm1
  c3:	0f ec d9             	paddsb mm3,mm1
  c6:	0f ec e1             	paddsb mm4,mm1
  c9:	0f ec e9             	paddsb mm5,mm1
  cc:	0f ec f1             	paddsb mm6,mm1
  cf:	0f ec f9             	paddsb mm7,mm1
  d2:	0f ec c1             	paddsb mm0,mm1
  d5:	0f ec d1             	paddsb mm2,mm1
  d8:	0f ec d9             	paddsb mm3,mm1
  db:	0f ec e1             	paddsb mm4,mm1
  de:	0f ec e9             	paddsb mm5,mm1
  e1:	0f ec f1             	paddsb mm6,mm1
  e4:	0f ec f9             	paddsb mm7,mm1
  e7:	0f ec c1             	paddsb mm0,mm1
  ea:	0f ec d1             	paddsb mm2,mm1
  ed:	0f ec d9             	paddsb mm3,mm1
  f0:	0f ec e1             	paddsb mm4,mm1
  f3:	0f ec e9             	paddsb mm5,mm1
  f6:	0f ec f1             	paddsb mm6,mm1
  f9:	0f ec f9             	paddsb mm7,mm1
  fc:	0f ec c1             	paddsb mm0,mm1
  ff:	0f ec d1             	paddsb mm2,mm1
 102:	0f ec d9             	paddsb mm3,mm1
 105:	0f ec e1             	paddsb mm4,mm1
 108:	0f ec e9             	paddsb mm5,mm1
 10b:	0f ec f1             	paddsb mm6,mm1
 10e:	0f ec f9             	paddsb mm7,mm1
 111:	0f ec c1             	paddsb mm0,mm1
 114:	0f ec d1             	paddsb mm2,mm1
 117:	0f ec d9             	paddsb mm3,mm1
 11a:	0f ec e1             	paddsb mm4,mm1
 11d:	0f ec e9             	paddsb mm5,mm1
 120:	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;
PXOR MM1, MM1;
PXOR MM2, MM2;
PXOR MM3, MM3;
PXOR MM4, MM4;
PXOR MM5, MM5;
PXOR MM6, MM6;
PXOR MM7, MM7;
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:
- MPERF: 42.46
- APERF: 49.1
- FpuPipeAssignment.Total0: 48.99
- FpuPipeAssignment.Total1: 47.01
- FpuPipeAssignment.Total2: 9.01
- FpuPipeAssignment.Total3: 4.99
- FpuPipeAssignment.Total4: 3.0
- FpuPipeAssignment.Total5: 7.0

With blocking instructions for ports {'1', '2'}:

Code:

   0:	0f 6b c1             	packssdw mm0,mm1
   3:	0f 6b d1             	packssdw mm2,mm1
   6:	0f 6b d9             	packssdw mm3,mm1
   9:	0f 6b e1             	packssdw mm4,mm1
   c:	0f 6b e9             	packssdw mm5,mm1
   f:	0f 6b f1             	packssdw mm6,mm1
  12:	0f 6b f9             	packssdw mm7,mm1
  15:	0f 6b c1             	packssdw mm0,mm1
  18:	0f 6b d1             	packssdw mm2,mm1
  1b:	0f 6b d9             	packssdw mm3,mm1
  1e:	0f 6b e1             	packssdw mm4,mm1
  21:	0f 6b e9             	packssdw mm5,mm1
  24:	0f 6b f1             	packssdw mm6,mm1
  27:	0f 6b f9             	packssdw mm7,mm1
  2a:	0f 6b c1             	packssdw mm0,mm1
  2d:	0f 6b d1             	packssdw mm2,mm1
  30:	0f 6b d9             	packssdw mm3,mm1
  33:	0f 6b e1             	packssdw mm4,mm1
  36:	0f 6b e9             	packssdw mm5,mm1
  39:	0f 6b f1             	packssdw mm6,mm1
  3c:	0f 6b f9             	packssdw mm7,mm1
  3f:	0f 6b c1             	packssdw mm0,mm1
  42:	0f 6b d1             	packssdw mm2,mm1
  45:	0f 6b d9             	packssdw mm3,mm1
  48:	0f 6b e1             	packssdw mm4,mm1
  4b:	0f 6b e9             	packssdw mm5,mm1
  4e:	0f 6b f1             	packssdw mm6,mm1
  51:	0f 6b f9             	packssdw mm7,mm1
  54:	0f 6b c1             	packssdw mm0,mm1
  57:	0f 6b d1             	packssdw mm2,mm1
  5a:	0f 6b d9             	packssdw mm3,mm1
  5d:	0f 6b e1             	packssdw mm4,mm1
  60:	0f 6b e9             	packssdw mm5,mm1
  63:	0f 6b f1             	packssdw mm6,mm1
  66:	0f 6b f9             	packssdw mm7,mm1
  69:	0f 6b c1             	packssdw mm0,mm1
  6c:	0f 6b d1             	packssdw mm2,mm1
  6f:	0f 6b d9             	packssdw mm3,mm1
  72:	0f 6b e1             	packssdw mm4,mm1
  75:	0f 6b e9             	packssdw mm5,mm1
  78:	0f 6b f1             	packssdw mm6,mm1
  7b:	0f 6b f9             	packssdw mm7,mm1
  7e:	0f 6b c1             	packssdw mm0,mm1
  81:	0f 6b d1             	packssdw mm2,mm1
  84:	0f 6b d9             	packssdw mm3,mm1
  87:	0f 6b e1             	packssdw mm4,mm1
  8a:	0f 6b e9             	packssdw mm5,mm1
  8d:	0f 6b f1             	packssdw mm6,mm1
  90:	0f 6b f9             	packssdw mm7,mm1
  93:	0f 6b c1             	packssdw mm0,mm1
  96:	0f 6b d1             	packssdw mm2,mm1
  99:	0f 6b d9             	packssdw mm3,mm1
  9c:	0f 6b e1             	packssdw mm4,mm1
  9f:	0f 6b e9             	packssdw mm5,mm1
  a2:	0f 6b f1             	packssdw mm6,mm1
  a5:	0f 6b f9             	packssdw mm7,mm1
  a8:	0f 6b c1             	packssdw mm0,mm1
  ab:	0f 6b d1             	packssdw mm2,mm1
  ae:	0f 6b d9             	packssdw mm3,mm1
  b1:	0f 6b e1             	packssdw mm4,mm1
  b4:	0f 6b e9             	packssdw mm5,mm1
  b7:	0f 6b f1             	packssdw mm6,mm1
  ba:	0f 6b f9             	packssdw mm7,mm1
  bd:	0f 6b c1             	packssdw mm0,mm1
  c0:	0f 6b d1             	packssdw mm2,mm1
  c3:	0f 6b d9             	packssdw mm3,mm1
  c6:	0f 6b e1             	packssdw mm4,mm1
  c9:	0f 6b e9             	packssdw mm5,mm1
  cc:	0f 6b f1             	packssdw mm6,mm1
  cf:	0f 6b f9             	packssdw mm7,mm1
  d2:	0f 6b c1             	packssdw mm0,mm1
  d5:	0f 6b d1             	packssdw mm2,mm1
  d8:	0f 6b d9             	packssdw mm3,mm1
  db:	0f 6b e1             	packssdw mm4,mm1
  de:	0f 6b e9             	packssdw mm5,mm1
  e1:	0f 6b f1             	packssdw mm6,mm1
  e4:	0f 6b f9             	packssdw mm7,mm1
  e7:	0f 6b c1             	packssdw mm0,mm1
  ea:	0f 6b d1             	packssdw mm2,mm1
  ed:	0f 6b d9             	packssdw mm3,mm1
  f0:	0f 6b e1             	packssdw mm4,mm1
  f3:	0f 6b e9             	packssdw mm5,mm1
  f6:	0f 6b f1             	packssdw mm6,mm1
  f9:	0f 6b f9             	packssdw mm7,mm1
  fc:	0f 6b c1             	packssdw mm0,mm1
  ff:	0f 6b d1             	packssdw mm2,mm1
 102:	0f 6b d9             	packssdw mm3,mm1
 105:	0f 6b e1             	packssdw mm4,mm1
 108:	0f 6b e9             	packssdw mm5,mm1
 10b:	0f 6b f1             	packssdw mm6,mm1
 10e:	0f 6b f9             	packssdw mm7,mm1
 111:	0f 6b c1             	packssdw mm0,mm1
 114:	0f 6b d1             	packssdw mm2,mm1
 117:	0f 6b d9             	packssdw mm3,mm1
 11a:	0f 6b e1             	packssdw mm4,mm1
 11d:	0f 6b e9             	packssdw mm5,mm1
 120:	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;
PXOR MM1, MM1;
PXOR MM2, MM2;
PXOR MM3, MM3;
PXOR MM4, MM4;
PXOR MM5, MM5;
PXOR MM6, MM6;
PXOR MM7, MM7;
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:
- MPERF: 46.92
- APERF: 54.2
- FpuPipeAssignment.Total0: 4.75
- FpuPipeAssignment.Total1: 50.5
- FpuPipeAssignment.Total2: 48.5
- FpuPipeAssignment.Total3: 6.25
- FpuPipeAssignment.Total4: 5.77
- FpuPipeAssignment.Total5: 4.23

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

With blocking instructions for ports {'2', '3'}:

Code:

   0:	0f 72 f0 02          	pslld  mm0,0x2
   4:	0f 72 f1 02          	pslld  mm1,0x2
   8:	0f 72 f2 02          	pslld  mm2,0x2
   c:	0f 72 f3 02          	pslld  mm3,0x2
  10:	0f 72 f4 02          	pslld  mm4,0x2
  14:	0f 72 f5 02          	pslld  mm5,0x2
  18:	0f 72 f6 02          	pslld  mm6,0x2
  1c:	0f 72 f7 02          	pslld  mm7,0x2
  20:	0f 72 f0 02          	pslld  mm0,0x2
  24:	0f 72 f1 02          	pslld  mm1,0x2
  28:	0f 72 f2 02          	pslld  mm2,0x2
  2c:	0f 72 f3 02          	pslld  mm3,0x2
  30:	0f 72 f4 02          	pslld  mm4,0x2
  34:	0f 72 f5 02          	pslld  mm5,0x2
  38:	0f 72 f6 02          	pslld  mm6,0x2
  3c:	0f 72 f7 02          	pslld  mm7,0x2
  40:	0f 72 f0 02          	pslld  mm0,0x2
  44:	0f 72 f1 02          	pslld  mm1,0x2
  48:	0f 72 f2 02          	pslld  mm2,0x2
  4c:	0f 72 f3 02          	pslld  mm3,0x2
  50:	0f 72 f4 02          	pslld  mm4,0x2
  54:	0f 72 f5 02          	pslld  mm5,0x2
  58:	0f 72 f6 02          	pslld  mm6,0x2
  5c:	0f 72 f7 02          	pslld  mm7,0x2
  60:	0f 72 f0 02          	pslld  mm0,0x2
  64:	0f 72 f1 02          	pslld  mm1,0x2
  68:	0f 72 f2 02          	pslld  mm2,0x2
  6c:	0f 72 f3 02          	pslld  mm3,0x2
  70:	0f 72 f4 02          	pslld  mm4,0x2
  74:	0f 72 f5 02          	pslld  mm5,0x2
  78:	0f 72 f6 02          	pslld  mm6,0x2
  7c:	0f 72 f7 02          	pslld  mm7,0x2
  80:	0f 72 f0 02          	pslld  mm0,0x2
  84:	0f 72 f1 02          	pslld  mm1,0x2
  88:	0f 72 f2 02          	pslld  mm2,0x2
  8c:	0f 72 f3 02          	pslld  mm3,0x2
  90:	0f 72 f4 02          	pslld  mm4,0x2
  94:	0f 72 f5 02          	pslld  mm5,0x2
  98:	0f 72 f6 02          	pslld  mm6,0x2
  9c:	0f 72 f7 02          	pslld  mm7,0x2
  a0:	0f 72 f0 02          	pslld  mm0,0x2
  a4:	0f 72 f1 02          	pslld  mm1,0x2
  a8:	0f 72 f2 02          	pslld  mm2,0x2
  ac:	0f 72 f3 02          	pslld  mm3,0x2
  b0:	0f 72 f4 02          	pslld  mm4,0x2
  b4:	0f 72 f5 02          	pslld  mm5,0x2
  b8:	0f 72 f6 02          	pslld  mm6,0x2
  bc:	0f 72 f7 02          	pslld  mm7,0x2
  c0:	0f 72 f0 02          	pslld  mm0,0x2
  c4:	0f 72 f1 02          	pslld  mm1,0x2
  c8:	0f 72 f2 02          	pslld  mm2,0x2
  cc:	0f 72 f3 02          	pslld  mm3,0x2
  d0:	0f 72 f4 02          	pslld  mm4,0x2
  d4:	0f 72 f5 02          	pslld  mm5,0x2
  d8:	0f 72 f6 02          	pslld  mm6,0x2
  dc:	0f 72 f7 02          	pslld  mm7,0x2
  e0:	0f 72 f0 02          	pslld  mm0,0x2
  e4:	0f 72 f1 02          	pslld  mm1,0x2
  e8:	0f 72 f2 02          	pslld  mm2,0x2
  ec:	0f 72 f3 02          	pslld  mm3,0x2
  f0:	0f 72 f4 02          	pslld  mm4,0x2
  f4:	0f 72 f5 02          	pslld  mm5,0x2
  f8:	0f 72 f6 02          	pslld  mm6,0x2
  fc:	0f 72 f7 02          	pslld  mm7,0x2
 100:	0f 72 f0 02          	pslld  mm0,0x2
 104:	0f 72 f1 02          	pslld  mm1,0x2
 108:	0f 72 f2 02          	pslld  mm2,0x2
 10c:	0f 72 f3 02          	pslld  mm3,0x2
 110:	0f 72 f4 02          	pslld  mm4,0x2
 114:	0f 72 f5 02          	pslld  mm5,0x2
 118:	0f 72 f6 02          	pslld  mm6,0x2
 11c:	0f 72 f7 02          	pslld  mm7,0x2
 120:	0f 72 f0 02          	pslld  mm0,0x2
 124:	0f 72 f1 02          	pslld  mm1,0x2
 128:	0f 72 f2 02          	pslld  mm2,0x2
 12c:	0f 72 f3 02          	pslld  mm3,0x2
 130:	0f 72 f4 02          	pslld  mm4,0x2
 134:	0f 72 f5 02          	pslld  mm5,0x2
 138:	0f 72 f6 02          	pslld  mm6,0x2
 13c:	0f 72 f7 02          	pslld  mm7,0x2
 140:	0f 72 f0 02          	pslld  mm0,0x2
 144:	0f 72 f1 02          	pslld  mm1,0x2
 148:	0f 72 f2 02          	pslld  mm2,0x2
 14c:	0f 72 f3 02          	pslld  mm3,0x2
 150:	0f 72 f4 02          	pslld  mm4,0x2
 154:	0f 72 f5 02          	pslld  mm5,0x2
 158:	0f 72 f6 02          	pslld  mm6,0x2
 15c:	0f 72 f7 02          	pslld  mm7,0x2
 160:	0f 72 f0 02          	pslld  mm0,0x2
 164:	0f 72 f1 02          	pslld  mm1,0x2
 168:	0f 72 f2 02          	pslld  mm2,0x2
 16c:	0f 72 f3 02          	pslld  mm3,0x2
 170:	0f 72 f4 02          	pslld  mm4,0x2
 174:	0f 72 f5 02          	pslld  mm5,0x2
 178:	0f 72 f6 02          	pslld  mm6,0x2
 17c:	0f 72 f7 02          	pslld  mm7,0x2
 180:	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;
PXOR MM1, MM1;
PXOR MM2, MM2;
PXOR MM3, MM3;
PXOR MM4, MM4;
PXOR MM5, MM5;
PXOR MM6, MM6;
PXOR MM7, MM7;
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:
- MPERF: 43.24
- APERF: 50.09
- FpuPipeAssignment.Total0: 2.99
- FpuPipeAssignment.Total1: 10.01
- FpuPipeAssignment.Total2: 49.0
- FpuPipeAssignment.Total3: 48.0
- FpuPipeAssignment.Total4: 7.0
- FpuPipeAssignment.Total5: 3.0

⇨ One μop that can only use ports {'2', '3'}

With blocking instructions for ports {'4', '5'}:

Code:

   0:	c4 c1 79 7e c8       	vmovd  r8d,xmm1
   5:	c4 c1 79 7e c9       	vmovd  r9d,xmm1
   a:	c4 c1 79 7e ca       	vmovd  r10d,xmm1
   f:	c4 c1 79 7e cb       	vmovd  r11d,xmm1
  14:	c4 c1 79 7e cc       	vmovd  r12d,xmm1
  19:	c5 f9 7e cb          	vmovd  ebx,xmm1
  1d:	c5 f9 7e c9          	vmovd  ecx,xmm1
  21:	c5 f9 7e ca          	vmovd  edx,xmm1
  25:	c4 c1 79 7e c8       	vmovd  r8d,xmm1
  2a:	c4 c1 79 7e c9       	vmovd  r9d,xmm1
  2f:	c4 c1 79 7e ca       	vmovd  r10d,xmm1
  34:	c4 c1 79 7e cb       	vmovd  r11d,xmm1
  39:	c4 c1 79 7e cc       	vmovd  r12d,xmm1
  3e:	c5 f9 7e cb          	vmovd  ebx,xmm1
  42:	c5 f9 7e c9          	vmovd  ecx,xmm1
  46:	c5 f9 7e ca          	vmovd  edx,xmm1
  4a:	c4 c1 79 7e c8       	vmovd  r8d,xmm1
  4f:	c4 c1 79 7e c9       	vmovd  r9d,xmm1
  54:	c4 c1 79 7e ca       	vmovd  r10d,xmm1
  59:	c4 c1 79 7e cb       	vmovd  r11d,xmm1
  5e:	c4 c1 79 7e cc       	vmovd  r12d,xmm1
  63:	c5 f9 7e cb          	vmovd  ebx,xmm1
  67:	c5 f9 7e c9          	vmovd  ecx,xmm1
  6b:	c5 f9 7e ca          	vmovd  edx,xmm1
  6f:	c4 c1 79 7e c8       	vmovd  r8d,xmm1
  74:	c4 c1 79 7e c9       	vmovd  r9d,xmm1
  79:	c4 c1 79 7e ca       	vmovd  r10d,xmm1
  7e:	c4 c1 79 7e cb       	vmovd  r11d,xmm1
  83:	c4 c1 79 7e cc       	vmovd  r12d,xmm1
  88:	c5 f9 7e cb          	vmovd  ebx,xmm1
  8c:	c5 f9 7e c9          	vmovd  ecx,xmm1
  90:	c5 f9 7e ca          	vmovd  edx,xmm1
  94:	c4 c1 79 7e c8       	vmovd  r8d,xmm1
  99:	c4 c1 79 7e c9       	vmovd  r9d,xmm1
  9e:	c4 c1 79 7e ca       	vmovd  r10d,xmm1
  a3:	c4 c1 79 7e cb       	vmovd  r11d,xmm1
  a8:	c4 c1 79 7e cc       	vmovd  r12d,xmm1
  ad:	c5 f9 7e cb          	vmovd  ebx,xmm1
  b1:	c5 f9 7e c9          	vmovd  ecx,xmm1
  b5:	c5 f9 7e ca          	vmovd  edx,xmm1
  b9:	c4 c1 79 7e c8       	vmovd  r8d,xmm1
  be:	c4 c1 79 7e c9       	vmovd  r9d,xmm1
  c3:	c4 c1 79 7e ca       	vmovd  r10d,xmm1
  c8:	c4 c1 79 7e cb       	vmovd  r11d,xmm1
  cd:	c4 c1 79 7e cc       	vmovd  r12d,xmm1
  d2:	c5 f9 7e cb          	vmovd  ebx,xmm1
  d6:	c5 f9 7e c9          	vmovd  ecx,xmm1
  da:	c5 f9 7e ca          	vmovd  edx,xmm1
  de:	c4 c1 79 7e c8       	vmovd  r8d,xmm1
  e3:	c4 c1 79 7e c9       	vmovd  r9d,xmm1
  e8:	c4 c1 79 7e ca       	vmovd  r10d,xmm1
  ed:	c4 c1 79 7e cb       	vmovd  r11d,xmm1
  f2:	c4 c1 79 7e cc       	vmovd  r12d,xmm1
  f7:	c5 f9 7e cb          	vmovd  ebx,xmm1
  fb:	c5 f9 7e c9          	vmovd  ecx,xmm1
  ff:	c5 f9 7e ca          	vmovd  edx,xmm1
 103:	c4 c1 79 7e c8       	vmovd  r8d,xmm1
 108:	c4 c1 79 7e c9       	vmovd  r9d,xmm1
 10d:	c4 c1 79 7e ca       	vmovd  r10d,xmm1
 112:	c4 c1 79 7e cb       	vmovd  r11d,xmm1
 117:	c4 c1 79 7e cc       	vmovd  r12d,xmm1
 11c:	c5 f9 7e cb          	vmovd  ebx,xmm1
 120:	c5 f9 7e c9          	vmovd  ecx,xmm1
 124:	c5 f9 7e ca          	vmovd  edx,xmm1
 128:	c4 c1 79 7e c8       	vmovd  r8d,xmm1
 12d:	c4 c1 79 7e c9       	vmovd  r9d,xmm1
 132:	c4 c1 79 7e ca       	vmovd  r10d,xmm1
 137:	c4 c1 79 7e cb       	vmovd  r11d,xmm1
 13c:	c4 c1 79 7e cc       	vmovd  r12d,xmm1
 141:	c5 f9 7e cb          	vmovd  ebx,xmm1
 145:	c5 f9 7e c9          	vmovd  ecx,xmm1
 149:	c5 f9 7e ca          	vmovd  edx,xmm1
 14d:	c4 c1 79 7e c8       	vmovd  r8d,xmm1
 152:	c4 c1 79 7e c9       	vmovd  r9d,xmm1
 157:	c4 c1 79 7e ca       	vmovd  r10d,xmm1
 15c:	c4 c1 79 7e cb       	vmovd  r11d,xmm1
 161:	c4 c1 79 7e cc       	vmovd  r12d,xmm1
 166:	c5 f9 7e cb          	vmovd  ebx,xmm1
 16a:	c5 f9 7e c9          	vmovd  ecx,xmm1
 16e:	c5 f9 7e ca          	vmovd  edx,xmm1
 172:	c4 c1 79 7e c8       	vmovd  r8d,xmm1
 177:	c4 c1 79 7e c9       	vmovd  r9d,xmm1
 17c:	c4 c1 79 7e ca       	vmovd  r10d,xmm1
 181:	c4 c1 79 7e cb       	vmovd  r11d,xmm1
 186:	c4 c1 79 7e cc       	vmovd  r12d,xmm1
 18b:	c5 f9 7e cb          	vmovd  ebx,xmm1
 18f:	c5 f9 7e c9          	vmovd  ecx,xmm1
 193:	c5 f9 7e ca          	vmovd  edx,xmm1
 197:	c4 c1 79 7e c8       	vmovd  r8d,xmm1
 19c:	c4 c1 79 7e c9       	vmovd  r9d,xmm1
 1a1:	c4 c1 79 7e ca       	vmovd  r10d,xmm1
 1a6:	c4 c1 79 7e cb       	vmovd  r11d,xmm1
 1ab:	c4 c1 79 7e cc       	vmovd  r12d,xmm1
 1b0:	c5 f9 7e cb          	vmovd  ebx,xmm1
 1b4:	c5 f9 7e c9          	vmovd  ecx,xmm1
 1b8:	c5 f9 7e ca          	vmovd  edx,xmm1
 1bc:	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 XMM1, XMM1, XMM1;
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:
- MPERF: 90.24
- APERF: 104.68
- FpuPipeAssignment.Total0: 2.08
- FpuPipeAssignment.Total1: 4.93
- FpuPipeAssignment.Total2: 0.98
- FpuPipeAssignment.Total3: 6.01
- FpuPipeAssignment.Total4: 54.02
- FpuPipeAssignment.Total5: 51.98

⇨ 10 μops that can only use ports {'4', '5'}

With blocking instructions for ports {'1', '2', '3'}:

Code:

   0:	0f 70 c1 02          	pshufw mm0,mm1,0x2
   4:	0f 70 d1 02          	pshufw mm2,mm1,0x2
   8:	0f 70 d9 02          	pshufw mm3,mm1,0x2
   c:	0f 70 e1 02          	pshufw mm4,mm1,0x2
  10:	0f 70 e9 02          	pshufw mm5,mm1,0x2
  14:	0f 70 f1 02          	pshufw mm6,mm1,0x2
  18:	0f 70 f9 02          	pshufw mm7,mm1,0x2
  1c:	0f 70 c1 02          	pshufw mm0,mm1,0x2
  20:	0f 70 d1 02          	pshufw mm2,mm1,0x2
  24:	0f 70 d9 02          	pshufw mm3,mm1,0x2
  28:	0f 70 e1 02          	pshufw mm4,mm1,0x2
  2c:	0f 70 e9 02          	pshufw mm5,mm1,0x2
  30:	0f 70 f1 02          	pshufw mm6,mm1,0x2
  34:	0f 70 f9 02          	pshufw mm7,mm1,0x2
  38:	0f 70 c1 02          	pshufw mm0,mm1,0x2
  3c:	0f 70 d1 02          	pshufw mm2,mm1,0x2
  40:	0f 70 d9 02          	pshufw mm3,mm1,0x2
  44:	0f 70 e1 02          	pshufw mm4,mm1,0x2
  48:	0f 70 e9 02          	pshufw mm5,mm1,0x2
  4c:	0f 70 f1 02          	pshufw mm6,mm1,0x2
  50:	0f 70 f9 02          	pshufw mm7,mm1,0x2
  54:	0f 70 c1 02          	pshufw mm0,mm1,0x2
  58:	0f 70 d1 02          	pshufw mm2,mm1,0x2
  5c:	0f 70 d9 02          	pshufw mm3,mm1,0x2
  60:	0f 70 e1 02          	pshufw mm4,mm1,0x2
  64:	0f 70 e9 02          	pshufw mm5,mm1,0x2
  68:	0f 70 f1 02          	pshufw mm6,mm1,0x2
  6c:	0f 70 f9 02          	pshufw mm7,mm1,0x2
  70:	0f 70 c1 02          	pshufw mm0,mm1,0x2
  74:	0f 70 d1 02          	pshufw mm2,mm1,0x2
  78:	0f 70 d9 02          	pshufw mm3,mm1,0x2
  7c:	0f 70 e1 02          	pshufw mm4,mm1,0x2
  80:	0f 70 e9 02          	pshufw mm5,mm1,0x2
  84:	0f 70 f1 02          	pshufw mm6,mm1,0x2
  88:	0f 70 f9 02          	pshufw mm7,mm1,0x2
  8c:	0f 70 c1 02          	pshufw mm0,mm1,0x2
  90:	0f 70 d1 02          	pshufw mm2,mm1,0x2
  94:	0f 70 d9 02          	pshufw mm3,mm1,0x2
  98:	0f 70 e1 02          	pshufw mm4,mm1,0x2
  9c:	0f 70 e9 02          	pshufw mm5,mm1,0x2
  a0:	0f 70 f1 02          	pshufw mm6,mm1,0x2
  a4:	0f 70 f9 02          	pshufw mm7,mm1,0x2
  a8:	0f 70 c1 02          	pshufw mm0,mm1,0x2
  ac:	0f 70 d1 02          	pshufw mm2,mm1,0x2
  b0:	0f 70 d9 02          	pshufw mm3,mm1,0x2
  b4:	0f 70 e1 02          	pshufw mm4,mm1,0x2
  b8:	0f 70 e9 02          	pshufw mm5,mm1,0x2
  bc:	0f 70 f1 02          	pshufw mm6,mm1,0x2
  c0:	0f 70 f9 02          	pshufw mm7,mm1,0x2
  c4:	0f 70 c1 02          	pshufw mm0,mm1,0x2
  c8:	0f 70 d1 02          	pshufw mm2,mm1,0x2
  cc:	0f 70 d9 02          	pshufw mm3,mm1,0x2
  d0:	0f 70 e1 02          	pshufw mm4,mm1,0x2
  d4:	0f 70 e9 02          	pshufw mm5,mm1,0x2
  d8:	0f 70 f1 02          	pshufw mm6,mm1,0x2
  dc:	0f 70 f9 02          	pshufw mm7,mm1,0x2
  e0:	0f 70 c1 02          	pshufw mm0,mm1,0x2
  e4:	0f 70 d1 02          	pshufw mm2,mm1,0x2
  e8:	0f 70 d9 02          	pshufw mm3,mm1,0x2
  ec:	0f 70 e1 02          	pshufw mm4,mm1,0x2
  f0:	0f 70 e9 02          	pshufw mm5,mm1,0x2
  f4:	0f 70 f1 02          	pshufw mm6,mm1,0x2
  f8:	0f 70 f9 02          	pshufw mm7,mm1,0x2
  fc:	0f 70 c1 02          	pshufw mm0,mm1,0x2
 100:	0f 70 d1 02          	pshufw mm2,mm1,0x2
 104:	0f 70 d9 02          	pshufw mm3,mm1,0x2
 108:	0f 70 e1 02          	pshufw mm4,mm1,0x2
 10c:	0f 70 e9 02          	pshufw mm5,mm1,0x2
 110:	0f 70 f1 02          	pshufw mm6,mm1,0x2
 114:	0f 70 f9 02          	pshufw mm7,mm1,0x2
 118:	0f 70 c1 02          	pshufw mm0,mm1,0x2
 11c:	0f 70 d1 02          	pshufw mm2,mm1,0x2
 120:	0f 70 d9 02          	pshufw mm3,mm1,0x2
 124:	0f 70 e1 02          	pshufw mm4,mm1,0x2
 128:	0f 70 e9 02          	pshufw mm5,mm1,0x2
 12c:	0f 70 f1 02          	pshufw mm6,mm1,0x2
 130:	0f 70 f9 02          	pshufw mm7,mm1,0x2
 134:	0f 70 c1 02          	pshufw mm0,mm1,0x2
 138:	0f 70 d1 02          	pshufw mm2,mm1,0x2
 13c:	0f 70 d9 02          	pshufw mm3,mm1,0x2
 140:	0f 70 e1 02          	pshufw mm4,mm1,0x2
 144:	0f 70 e9 02          	pshufw mm5,mm1,0x2
 148:	0f 70 f1 02          	pshufw mm6,mm1,0x2
 14c:	0f 70 f9 02          	pshufw mm7,mm1,0x2
 150:	0f 70 c1 02          	pshufw mm0,mm1,0x2
 154:	0f 70 d1 02          	pshufw mm2,mm1,0x2
 158:	0f 70 d9 02          	pshufw mm3,mm1,0x2
 15c:	0f 70 e1 02          	pshufw mm4,mm1,0x2
 160:	0f 70 e9 02          	pshufw mm5,mm1,0x2
 164:	0f 70 f1 02          	pshufw mm6,mm1,0x2
 168:	0f 70 f9 02          	pshufw mm7,mm1,0x2
 16c:	0f 70 c1 02          	pshufw mm0,mm1,0x2
 170:	0f 70 d1 02          	pshufw mm2,mm1,0x2
 174:	0f 70 d9 02          	pshufw mm3,mm1,0x2
 178:	0f 70 e1 02          	pshufw mm4,mm1,0x2
 17c:	0f 70 e9 02          	pshufw mm5,mm1,0x2
 180:	0f 70 f1 02          	pshufw mm6,mm1,0x2
 184:	0f 70 f9 02          	pshufw mm7,mm1,0x2
 188:	0f 70 c1 02          	pshufw mm0,mm1,0x2
 18c:	0f 70 d1 02          	pshufw mm2,mm1,0x2
 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;
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:
- MPERF: 33.37
- APERF: 38.58
- FpuPipeAssignment.Total0: 4.29
- FpuPipeAssignment.Total1: 37.12
- FpuPipeAssignment.Total2: 35.41
- FpuPipeAssignment.Total3: 37.18
- FpuPipeAssignment.Total4: 5.1
- FpuPipeAssignment.Total5: 4.91

⇨ 5 μops that can only use ports {'1', '2', '3'}

With blocking instructions for ports {'0', '1', '2', '3'}:

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:	0f 6f e1             	movq   mm4,mm1
  f3:	0f 6f e9             	movq   mm5,mm1
  f6:	0f 6f f1             	movq   mm6,mm1
  f9:	0f 6f f9             	movq   mm7,mm1
  fc:	0f 6f c1             	movq   mm0,mm1
  ff:	0f 6f d1             	movq   mm2,mm1
 102:	0f 6f d9             	movq   mm3,mm1
 105:	0f 6f e1             	movq   mm4,mm1
 108:	0f 6f e9             	movq   mm5,mm1
 10b:	0f 6f f1             	movq   mm6,mm1
 10e:	0f 6f f9             	movq   mm7,mm1
 111:	0f 6f c1             	movq   mm0,mm1
 114:	0f 6f d1             	movq   mm2,mm1
 117:	0f 6f d9             	movq   mm3,mm1
 11a:	0f 6f e1             	movq   mm4,mm1
 11d:	0f 6f e9             	movq   mm5,mm1
 120:	0f 6f f1             	movq   mm6,mm1
 123:	0f 6f f9             	movq   mm7,mm1
 126:	0f 6f c1             	movq   mm0,mm1
 129:	0f 6f d1             	movq   mm2,mm1
 12c:	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:
- MPERF: 28.67
- APERF: 33.22
- FpuPipeAssignment.Total0: 26.5
- FpuPipeAssignment.Total1: 29.5
- FpuPipeAssignment.Total2: 28.5
- FpuPipeAssignment.Total3: 29.5
- FpuPipeAssignment.Total4: 9.0
- FpuPipeAssignment.Total5: 1.0

⇨ 5 μops that can only use ports {'0', '1', '2', '3'}