VGATHERQPD (YMM, VSIB_YMM, YMM) - Port Usage

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

Code:

   0:	c4 e2 e1 98 d4       	vfmadd132pd xmm2,xmm3,xmm4
   5:	c4 e2 e1 98 ec       	vfmadd132pd xmm5,xmm3,xmm4
   a:	c4 e2 e1 98 f4       	vfmadd132pd xmm6,xmm3,xmm4
   f:	c4 e2 e1 98 fc       	vfmadd132pd xmm7,xmm3,xmm4
  14:	c4 62 e1 98 c4       	vfmadd132pd xmm8,xmm3,xmm4
  19:	c4 62 e1 98 cc       	vfmadd132pd xmm9,xmm3,xmm4
  1e:	c4 62 e1 98 d4       	vfmadd132pd xmm10,xmm3,xmm4
  23:	c4 62 e1 98 dc       	vfmadd132pd xmm11,xmm3,xmm4
  28:	c4 62 e1 98 e4       	vfmadd132pd xmm12,xmm3,xmm4
  2d:	c4 e2 e1 98 d4       	vfmadd132pd xmm2,xmm3,xmm4
  32:	c4 e2 e1 98 ec       	vfmadd132pd xmm5,xmm3,xmm4
  37:	c4 e2 e1 98 f4       	vfmadd132pd xmm6,xmm3,xmm4
  3c:	c4 e2 e1 98 fc       	vfmadd132pd xmm7,xmm3,xmm4
  41:	c4 62 e1 98 c4       	vfmadd132pd xmm8,xmm3,xmm4
  46:	c4 62 e1 98 cc       	vfmadd132pd xmm9,xmm3,xmm4
  4b:	c4 62 e1 98 d4       	vfmadd132pd xmm10,xmm3,xmm4
  50:	c4 62 e1 98 dc       	vfmadd132pd xmm11,xmm3,xmm4
  55:	c4 62 e1 98 e4       	vfmadd132pd xmm12,xmm3,xmm4
  5a:	c4 e2 e1 98 d4       	vfmadd132pd xmm2,xmm3,xmm4
  5f:	c4 e2 e1 98 ec       	vfmadd132pd xmm5,xmm3,xmm4
  64:	c4 e2 e1 98 f4       	vfmadd132pd xmm6,xmm3,xmm4
  69:	c4 e2 e1 98 fc       	vfmadd132pd xmm7,xmm3,xmm4
  6e:	c4 62 e1 98 c4       	vfmadd132pd xmm8,xmm3,xmm4
  73:	c4 62 e1 98 cc       	vfmadd132pd xmm9,xmm3,xmm4
  78:	c4 62 e1 98 d4       	vfmadd132pd xmm10,xmm3,xmm4
  7d:	c4 62 e1 98 dc       	vfmadd132pd xmm11,xmm3,xmm4
  82:	c4 62 e1 98 e4       	vfmadd132pd xmm12,xmm3,xmm4
  87:	c4 e2 e1 98 d4       	vfmadd132pd xmm2,xmm3,xmm4
  8c:	c4 e2 e1 98 ec       	vfmadd132pd xmm5,xmm3,xmm4
  91:	c4 e2 e1 98 f4       	vfmadd132pd xmm6,xmm3,xmm4
  96:	c4 e2 e1 98 fc       	vfmadd132pd xmm7,xmm3,xmm4
  9b:	c4 62 e1 98 c4       	vfmadd132pd xmm8,xmm3,xmm4
  a0:	c4 62 e1 98 cc       	vfmadd132pd xmm9,xmm3,xmm4
  a5:	c4 62 e1 98 d4       	vfmadd132pd xmm10,xmm3,xmm4
  aa:	c4 62 e1 98 dc       	vfmadd132pd xmm11,xmm3,xmm4
  af:	c4 62 e1 98 e4       	vfmadd132pd xmm12,xmm3,xmm4
  b4:	c4 e2 e1 98 d4       	vfmadd132pd xmm2,xmm3,xmm4
  b9:	c4 e2 e1 98 ec       	vfmadd132pd xmm5,xmm3,xmm4
  be:	c4 e2 e1 98 f4       	vfmadd132pd xmm6,xmm3,xmm4
  c3:	c4 e2 e1 98 fc       	vfmadd132pd xmm7,xmm3,xmm4
  c8:	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 XMM2, [R14];
VMOVUPD XMM3, [R14];
VMOVUPD XMM4, [R14];
VMOVUPD XMM5, [R14];
VMOVUPD XMM6, [R14];
VMOVUPD XMM7, [R14];
VMOVUPD XMM8, [R14];
VMOVUPD XMM9, [R14];
VMOVUPD XMM10, [R14];
VMOVUPD XMM11, [R14];
VMOVUPD XMM12, [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: 14.44
- APERF: 21.11
- FpuPipeAssignment.Total0: 19.94
- FpuPipeAssignment.Total1: 20.06
- FpuPipeAssignment.Total2: 2.03
- FpuPipeAssignment.Total3: 3.97
- FpuPipeAssignment.Total4: 2.49
- FpuPipeAssignment.Total5: 2.51

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

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:	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: 13.93
- APERF: 20.12
- FpuPipeAssignment.Total0: 19.99
- FpuPipeAssignment.Total1: 2.51
- FpuPipeAssignment.Total2: 3.49
- FpuPipeAssignment.Total3: 20.01
- FpuPipeAssignment.Total4: 2.51
- FpuPipeAssignment.Total5: 2.49

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:	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: 14.44
- APERF: 20.77
- FpuPipeAssignment.Total0: 2.22
- FpuPipeAssignment.Total1: 20.5
- FpuPipeAssignment.Total2: 20.5
- FpuPipeAssignment.Total3: 2.78
- FpuPipeAssignment.Total4: 2.5
- FpuPipeAssignment.Total5: 2.51

⇨ One μop 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:	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: 13.93
- APERF: 20.12
- FpuPipeAssignment.Total0: 2.01
- FpuPipeAssignment.Total1: 3.99
- FpuPipeAssignment.Total2: 20.0
- FpuPipeAssignment.Total3: 20.0
- FpuPipeAssignment.Total4: 2.5
- FpuPipeAssignment.Total5: 2.5

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

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:	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;
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: 15.96
- APERF: 23.21
- FpuPipeAssignment.Total0: 1.0
- FpuPipeAssignment.Total1: 1.81
- FpuPipeAssignment.Total2: 2.0
- FpuPipeAssignment.Total3: 1.19
- FpuPipeAssignment.Total4: 22.5
- FpuPipeAssignment.Total5: 22.5

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

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

Code:

   0:	0f 65 c1             	pcmpgtw mm0,mm1
   3:	0f 65 d1             	pcmpgtw mm2,mm1
   6:	0f 65 d9             	pcmpgtw mm3,mm1
   9:	0f 65 e1             	pcmpgtw mm4,mm1
   c:	0f 65 e9             	pcmpgtw mm5,mm1
   f:	0f 65 f1             	pcmpgtw mm6,mm1
  12:	0f 65 f9             	pcmpgtw mm7,mm1
  15:	0f 65 c1             	pcmpgtw mm0,mm1
  18:	0f 65 d1             	pcmpgtw mm2,mm1
  1b:	0f 65 d9             	pcmpgtw mm3,mm1
  1e:	0f 65 e1             	pcmpgtw mm4,mm1
  21:	0f 65 e9             	pcmpgtw mm5,mm1
  24:	0f 65 f1             	pcmpgtw mm6,mm1
  27:	0f 65 f9             	pcmpgtw mm7,mm1
  2a:	0f 65 c1             	pcmpgtw mm0,mm1
  2d:	0f 65 d1             	pcmpgtw mm2,mm1
  30:	0f 65 d9             	pcmpgtw mm3,mm1
  33:	0f 65 e1             	pcmpgtw mm4,mm1
  36:	0f 65 e9             	pcmpgtw mm5,mm1
  39:	0f 65 f1             	pcmpgtw mm6,mm1
  3c:	0f 65 f9             	pcmpgtw mm7,mm1
  3f:	0f 65 c1             	pcmpgtw mm0,mm1
  42:	0f 65 d1             	pcmpgtw mm2,mm1
  45:	0f 65 d9             	pcmpgtw mm3,mm1
  48:	0f 65 e1             	pcmpgtw mm4,mm1
  4b:	0f 65 e9             	pcmpgtw mm5,mm1
  4e:	0f 65 f1             	pcmpgtw mm6,mm1
  51:	0f 65 f9             	pcmpgtw mm7,mm1
  54:	0f 65 c1             	pcmpgtw mm0,mm1
  57:	0f 65 d1             	pcmpgtw mm2,mm1
  5a:	0f 65 d9             	pcmpgtw mm3,mm1
  5d:	0f 65 e1             	pcmpgtw mm4,mm1
  60:	0f 65 e9             	pcmpgtw mm5,mm1
  63:	0f 65 f1             	pcmpgtw mm6,mm1
  66:	0f 65 f9             	pcmpgtw mm7,mm1
  69:	0f 65 c1             	pcmpgtw mm0,mm1
  6c:	0f 65 d1             	pcmpgtw mm2,mm1
  6f:	0f 65 d9             	pcmpgtw mm3,mm1
  72:	0f 65 e1             	pcmpgtw mm4,mm1
  75:	0f 65 e9             	pcmpgtw mm5,mm1
  78:	0f 65 f1             	pcmpgtw mm6,mm1
  7b:	0f 65 f9             	pcmpgtw mm7,mm1
  7e:	0f 65 c1             	pcmpgtw mm0,mm1
  81:	0f 65 d1             	pcmpgtw mm2,mm1
  84:	0f 65 d9             	pcmpgtw mm3,mm1
  87:	0f 65 e1             	pcmpgtw mm4,mm1
  8a:	0f 65 e9             	pcmpgtw mm5,mm1
  8d:	0f 65 f1             	pcmpgtw mm6,mm1
  90:	0f 65 f9             	pcmpgtw mm7,mm1
  93:	0f 65 c1             	pcmpgtw mm0,mm1
  96:	0f 65 d1             	pcmpgtw mm2,mm1
  99:	0f 65 d9             	pcmpgtw mm3,mm1
  9c:	0f 65 e1             	pcmpgtw mm4,mm1
  9f:	0f 65 e9             	pcmpgtw mm5,mm1
  a2:	0f 65 f1             	pcmpgtw mm6,mm1
  a5:	0f 65 f9             	pcmpgtw mm7,mm1
  a8:	0f 65 c1             	pcmpgtw mm0,mm1
  ab:	0f 65 d1             	pcmpgtw mm2,mm1
  ae:	0f 65 d9             	pcmpgtw mm3,mm1
  b1:	0f 65 e1             	pcmpgtw mm4,mm1
  b4:	0f 65 e9             	pcmpgtw mm5,mm1
  b7:	0f 65 f1             	pcmpgtw mm6,mm1
  ba:	0f 65 f9             	pcmpgtw mm7,mm1
  bd:	0f 65 c1             	pcmpgtw mm0,mm1
  c0:	0f 65 d1             	pcmpgtw mm2,mm1
  c3:	0f 65 d9             	pcmpgtw mm3,mm1
  c6:	0f 65 e1             	pcmpgtw mm4,mm1
  c9:	0f 65 e9             	pcmpgtw mm5,mm1
  cc:	0f 65 f1             	pcmpgtw mm6,mm1
  cf:	0f 65 f9             	pcmpgtw mm7,mm1
  d2:	0f 65 c1             	pcmpgtw mm0,mm1
  d5:	0f 65 d1             	pcmpgtw mm2,mm1
  d8:	0f 65 d9             	pcmpgtw mm3,mm1
  db:	0f 65 e1             	pcmpgtw mm4,mm1
  de:	0f 65 e9             	pcmpgtw mm5,mm1
  e1:	0f 65 f1             	pcmpgtw mm6,mm1
  e4:	0f 65 f9             	pcmpgtw mm7,mm1
  e7:	0f 65 c1             	pcmpgtw mm0,mm1
  ea:	0f 65 d1             	pcmpgtw mm2,mm1
  ed:	0f 65 d9             	pcmpgtw mm3,mm1
  f0:	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: 20.77
- APERF: 30.08
- FpuPipeAssignment.Total0: 21.1
- FpuPipeAssignment.Total1: 21.72
- FpuPipeAssignment.Total2: 21.7
- FpuPipeAssignment.Total3: 21.51
- FpuPipeAssignment.Total4: 2.5
- FpuPipeAssignment.Total5: 2.5

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