VGATHERQPD (YMM, VSIB_YMM, YMM) - 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:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],ymm1

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
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;
VMOVUPD YMM0, [R14];
VXORPS YMM1, YMM1, YMM1;
VXORPS YMM14, YMM14, YMM14

Show nanoBench command
Results:
- MPERF: 22.2
- APERF: 27.17
- FpuPipeAssignment.Total0: 4.0
- FpuPipeAssignment.Total1: 24.99
- FpuPipeAssignment.Total2: 1.01
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 1.0
- FpuPipeAssignment.Total5: 4.0

⇨ 2 μops that can only use port '1'

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:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],ymm1

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
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;
VMOVUPD YMM0, [R14];
VXORPS YMM1, YMM1, YMM1;
VXORPS YMM14, YMM14, YMM14

Show nanoBench command
Results:
- MPERF: 20.66
- APERF: 25.09
- FpuPipeAssignment.Total0: 25.04
- FpuPipeAssignment.Total1: 24.98
- FpuPipeAssignment.Total2: 2.98
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 2.46
- FpuPipeAssignment.Total5: 2.54

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

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

Code:

   0:	0f f5 c1             	pmaddwd mm0,mm1
   3:	0f f5 d1             	pmaddwd mm2,mm1
   6:	0f f5 d9             	pmaddwd mm3,mm1
   9:	0f f5 e1             	pmaddwd mm4,mm1
   c:	0f f5 e9             	pmaddwd mm5,mm1
   f:	0f f5 f1             	pmaddwd mm6,mm1
  12:	0f f5 f9             	pmaddwd mm7,mm1
  15:	0f f5 c1             	pmaddwd mm0,mm1
  18:	0f f5 d1             	pmaddwd mm2,mm1
  1b:	0f f5 d9             	pmaddwd mm3,mm1
  1e:	0f f5 e1             	pmaddwd mm4,mm1
  21:	0f f5 e9             	pmaddwd mm5,mm1
  24:	0f f5 f1             	pmaddwd mm6,mm1
  27:	0f f5 f9             	pmaddwd mm7,mm1
  2a:	0f f5 c1             	pmaddwd mm0,mm1
  2d:	0f f5 d1             	pmaddwd mm2,mm1
  30:	0f f5 d9             	pmaddwd mm3,mm1
  33:	0f f5 e1             	pmaddwd mm4,mm1
  36:	0f f5 e9             	pmaddwd mm5,mm1
  39:	0f f5 f1             	pmaddwd mm6,mm1
  3c:	0f f5 f9             	pmaddwd mm7,mm1
  3f:	0f f5 c1             	pmaddwd mm0,mm1
  42:	0f f5 d1             	pmaddwd mm2,mm1
  45:	0f f5 d9             	pmaddwd mm3,mm1
  48:	0f f5 e1             	pmaddwd mm4,mm1
  4b:	0f f5 e9             	pmaddwd mm5,mm1
  4e:	0f f5 f1             	pmaddwd mm6,mm1
  51:	0f f5 f9             	pmaddwd mm7,mm1
  54:	0f f5 c1             	pmaddwd mm0,mm1
  57:	0f f5 d1             	pmaddwd mm2,mm1
  5a:	0f f5 d9             	pmaddwd mm3,mm1
  5d:	0f f5 e1             	pmaddwd mm4,mm1
  60:	0f f5 e9             	pmaddwd mm5,mm1
  63:	0f f5 f1             	pmaddwd mm6,mm1
  66:	0f f5 f9             	pmaddwd mm7,mm1
  69:	0f f5 c1             	pmaddwd mm0,mm1
  6c:	0f f5 d1             	pmaddwd mm2,mm1
  6f:	0f f5 d9             	pmaddwd mm3,mm1
  72:	0f f5 e1             	pmaddwd mm4,mm1
  75:	0f f5 e9             	pmaddwd mm5,mm1
  78:	0f f5 f1             	pmaddwd mm6,mm1
  7b:	0f f5 f9             	pmaddwd mm7,mm1
  7e:	0f f5 c1             	pmaddwd mm0,mm1
  81:	0f f5 d1             	pmaddwd mm2,mm1
  84:	0f f5 d9             	pmaddwd mm3,mm1
  87:	0f f5 e1             	pmaddwd mm4,mm1
  8a:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],ymm1

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
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;
VMOVUPD YMM0, [R14];
VXORPS YMM1, YMM1, YMM1;
VXORPS YMM14, YMM14, YMM14

Show nanoBench command
Results:
- MPERF: 19.61
- APERF: 24.11
- FpuPipeAssignment.Total0: 23.52
- FpuPipeAssignment.Total1: 5.01
- FpuPipeAssignment.Total2: 1.95
- FpuPipeAssignment.Total3: 22.52
- FpuPipeAssignment.Total4: 2.47
- FpuPipeAssignment.Total5: 2.53

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:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],ymm1

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
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;
VMOVUPD YMM0, [R14];
VXORPS YMM1, YMM1, YMM1;
VXORPS YMM14, YMM14, YMM14

Show nanoBench command
Results:
- MPERF: 20.35
- APERF: 24.76
- FpuPipeAssignment.Total0: 4.0
- FpuPipeAssignment.Total1: 24.67
- FpuPipeAssignment.Total2: 24.33
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 2.66
- FpuPipeAssignment.Total5: 2.34

⇨ One μop that can only use ports {'1', '2'}

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

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:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],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];
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VXORPS YMM1, YMM1, YMM1;
VXORPS YMM14, YMM14, YMM14

Show nanoBench command
Results:
- MPERF: 18.87
- APERF: 23.12
- FpuPipeAssignment.Total0: 2.45
- FpuPipeAssignment.Total1: 4.55
- FpuPipeAssignment.Total2: 22.98
- FpuPipeAssignment.Total3: 23.02
- FpuPipeAssignment.Total4: 2.49
- FpuPipeAssignment.Total5: 2.51

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

Code:

   0:	c4 c1 79 7e d0       	vmovd  r8d,xmm2
   5:	c4 c1 79 7e d1       	vmovd  r9d,xmm2
   a:	c4 c1 79 7e d2       	vmovd  r10d,xmm2
   f:	c4 c1 79 7e d3       	vmovd  r11d,xmm2
  14:	c4 c1 79 7e d4       	vmovd  r12d,xmm2
  19:	c5 f9 7e d3          	vmovd  ebx,xmm2
  1d:	c5 f9 7e d1          	vmovd  ecx,xmm2
  21:	c5 f9 7e d2          	vmovd  edx,xmm2
  25:	c4 c1 79 7e d0       	vmovd  r8d,xmm2
  2a:	c4 c1 79 7e d1       	vmovd  r9d,xmm2
  2f:	c4 c1 79 7e d2       	vmovd  r10d,xmm2
  34:	c4 c1 79 7e d3       	vmovd  r11d,xmm2
  39:	c4 c1 79 7e d4       	vmovd  r12d,xmm2
  3e:	c5 f9 7e d3          	vmovd  ebx,xmm2
  42:	c5 f9 7e d1          	vmovd  ecx,xmm2
  46:	c5 f9 7e d2          	vmovd  edx,xmm2
  4a:	c4 c1 79 7e d0       	vmovd  r8d,xmm2
  4f:	c4 c1 79 7e d1       	vmovd  r9d,xmm2
  54:	c4 c1 79 7e d2       	vmovd  r10d,xmm2
  59:	c4 c1 79 7e d3       	vmovd  r11d,xmm2
  5e:	c4 c1 79 7e d4       	vmovd  r12d,xmm2
  63:	c5 f9 7e d3          	vmovd  ebx,xmm2
  67:	c5 f9 7e d1          	vmovd  ecx,xmm2
  6b:	c5 f9 7e d2          	vmovd  edx,xmm2
  6f:	c4 c1 79 7e d0       	vmovd  r8d,xmm2
  74:	c4 c1 79 7e d1       	vmovd  r9d,xmm2
  79:	c4 c1 79 7e d2       	vmovd  r10d,xmm2
  7e:	c4 c1 79 7e d3       	vmovd  r11d,xmm2
  83:	c4 c1 79 7e d4       	vmovd  r12d,xmm2
  88:	c5 f9 7e d3          	vmovd  ebx,xmm2
  8c:	c5 f9 7e d1          	vmovd  ecx,xmm2
  90:	c5 f9 7e d2          	vmovd  edx,xmm2
  94:	c4 c1 79 7e d0       	vmovd  r8d,xmm2
  99:	c4 c1 79 7e d1       	vmovd  r9d,xmm2
  9e:	c4 c1 79 7e d2       	vmovd  r10d,xmm2
  a3:	c4 c1 79 7e d3       	vmovd  r11d,xmm2
  a8:	c4 c1 79 7e d4       	vmovd  r12d,xmm2
  ad:	c5 f9 7e d3          	vmovd  ebx,xmm2
  b1:	c5 f9 7e d1          	vmovd  ecx,xmm2
  b5:	c5 f9 7e d2          	vmovd  edx,xmm2
  b9:	c4 c1 79 7e d0       	vmovd  r8d,xmm2
  be:	c4 c1 79 7e d1       	vmovd  r9d,xmm2
  c3:	c4 c1 79 7e d2       	vmovd  r10d,xmm2
  c8:	c4 c1 79 7e d3       	vmovd  r11d,xmm2
  cd:	c4 c1 79 7e d4       	vmovd  r12d,xmm2
  d2:	c5 f9 7e d3          	vmovd  ebx,xmm2
  d6:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],ymm1

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS XMM2, XMM2, XMM2;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VXORPS YMM1, YMM1, YMM1;
VXORPS YMM14, YMM14, YMM14

Show nanoBench command
Results:
- MPERF: 42.55
- APERF: 51.89
- FpuPipeAssignment.Total0: 1.47
- FpuPipeAssignment.Total1: 2.54
- FpuPipeAssignment.Total2: 2.99
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 25.85
- FpuPipeAssignment.Total5: 25.15

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

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:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],ymm1

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
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;
VMOVUPD YMM0, [R14];
VXORPS YMM1, YMM1, YMM1;
VXORPS YMM14, YMM14, YMM14

Show nanoBench command
Results:
- MPERF: 22.26
- APERF: 27.18
- FpuPipeAssignment.Total0: 26.02
- FpuPipeAssignment.Total1: 25.0
- FpuPipeAssignment.Total2: 24.98
- FpuPipeAssignment.Total3: 23.0
- FpuPipeAssignment.Total4: 1.0
- FpuPipeAssignment.Total5: 4.0

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