VGATHERQPD (ZMM, K, VSIB_ZMM) - Port Usage

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

Code:

   0:	c4 e2 e9 98 cb       	vfmadd132pd xmm1,xmm2,xmm3
   5:	c4 e2 e9 98 e3       	vfmadd132pd xmm4,xmm2,xmm3
   a:	c4 e2 e9 98 eb       	vfmadd132pd xmm5,xmm2,xmm3
   f:	c4 e2 e9 98 f3       	vfmadd132pd xmm6,xmm2,xmm3
  14:	c4 e2 e9 98 fb       	vfmadd132pd xmm7,xmm2,xmm3
  19:	c4 62 e9 98 c3       	vfmadd132pd xmm8,xmm2,xmm3
  1e:	c4 62 e9 98 cb       	vfmadd132pd xmm9,xmm2,xmm3
  23:	c4 62 e9 98 d3       	vfmadd132pd xmm10,xmm2,xmm3
  28:	c4 62 e9 98 db       	vfmadd132pd xmm11,xmm2,xmm3
  2d:	c4 62 e9 98 e3       	vfmadd132pd xmm12,xmm2,xmm3
  32:	c4 e2 e9 98 cb       	vfmadd132pd xmm1,xmm2,xmm3
  37:	c4 e2 e9 98 e3       	vfmadd132pd xmm4,xmm2,xmm3
  3c:	c4 e2 e9 98 eb       	vfmadd132pd xmm5,xmm2,xmm3
  41:	c4 e2 e9 98 f3       	vfmadd132pd xmm6,xmm2,xmm3
  46:	c4 e2 e9 98 fb       	vfmadd132pd xmm7,xmm2,xmm3
  4b:	c4 62 e9 98 c3       	vfmadd132pd xmm8,xmm2,xmm3
  50:	c4 62 e9 98 cb       	vfmadd132pd xmm9,xmm2,xmm3
  55:	c4 62 e9 98 d3       	vfmadd132pd xmm10,xmm2,xmm3
  5a:	c4 62 e9 98 db       	vfmadd132pd xmm11,xmm2,xmm3
  5f:	c4 62 e9 98 e3       	vfmadd132pd xmm12,xmm2,xmm3
  64:	c4 e2 e9 98 cb       	vfmadd132pd xmm1,xmm2,xmm3
  69:	c4 e2 e9 98 e3       	vfmadd132pd xmm4,xmm2,xmm3
  6e:	c4 e2 e9 98 eb       	vfmadd132pd xmm5,xmm2,xmm3
  73:	c4 e2 e9 98 f3       	vfmadd132pd xmm6,xmm2,xmm3
  78:	c4 e2 e9 98 fb       	vfmadd132pd xmm7,xmm2,xmm3
  7d:	c4 62 e9 98 c3       	vfmadd132pd xmm8,xmm2,xmm3
  82:	c4 62 e9 98 cb       	vfmadd132pd xmm9,xmm2,xmm3
  87:	c4 62 e9 98 d3       	vfmadd132pd xmm10,xmm2,xmm3
  8c:	c4 62 e9 98 db       	vfmadd132pd xmm11,xmm2,xmm3
  91:	c4 62 e9 98 e3       	vfmadd132pd xmm12,xmm2,xmm3
  96:	c4 e2 e9 98 cb       	vfmadd132pd xmm1,xmm2,xmm3
  9b:	c4 e2 e9 98 e3       	vfmadd132pd xmm4,xmm2,xmm3
  a0:	c4 e2 e9 98 eb       	vfmadd132pd xmm5,xmm2,xmm3
  a5:	c4 e2 e9 98 f3       	vfmadd132pd xmm6,xmm2,xmm3
  aa:	c4 e2 e9 98 fb       	vfmadd132pd xmm7,xmm2,xmm3
  af:	c4 62 e9 98 c3       	vfmadd132pd xmm8,xmm2,xmm3
  b4:	c4 62 e9 98 cb       	vfmadd132pd xmm9,xmm2,xmm3
  b9:	c4 62 e9 98 d3       	vfmadd132pd xmm10,xmm2,xmm3
  be:	c4 62 e9 98 db       	vfmadd132pd xmm11,xmm2,xmm3
  c3:	c4 62 e9 98 e3       	vfmadd132pd xmm12,xmm2,xmm3
  c8:	c4 e2 e9 98 cb       	vfmadd132pd xmm1,xmm2,xmm3
  cd:	c4 e2 e9 98 e3       	vfmadd132pd xmm4,xmm2,xmm3
  d2:	c4 e2 e9 98 eb       	vfmadd132pd xmm5,xmm2,xmm3
  d7:	c4 e2 e9 98 f3       	vfmadd132pd xmm6,xmm2,xmm3
  dc:	c4 e2 e9 98 fb       	vfmadd132pd xmm7,xmm2,xmm3
  e1:	c4 62 e9 98 c3       	vfmadd132pd xmm8,xmm2,xmm3
  e6:	c4 62 e9 98 cb       	vfmadd132pd xmm9,xmm2,xmm3
  eb:	c4 62 e9 98 d3       	vfmadd132pd xmm10,xmm2,xmm3
  f0:	c4 62 e9 98 db       	vfmadd132pd xmm11,xmm2,xmm3
  f5:	c4 62 e9 98 e3       	vfmadd132pd xmm12,xmm2,xmm3
  fa:	c4 e2 e9 98 cb       	vfmadd132pd xmm1,xmm2,xmm3
  ff:	c4 e2 e9 98 e3       	vfmadd132pd xmm4,xmm2,xmm3
 104:	c4 e2 e9 98 eb       	vfmadd132pd xmm5,xmm2,xmm3
 109:	c4 e2 e9 98 f3       	vfmadd132pd xmm6,xmm2,xmm3
 10e:	c4 e2 e9 98 fb       	vfmadd132pd xmm7,xmm2,xmm3
 113:	c4 62 e9 98 c3       	vfmadd132pd xmm8,xmm2,xmm3
 118:	c4 62 e9 98 cb       	vfmadd132pd xmm9,xmm2,xmm3
 11d:	c4 62 e9 98 d3       	vfmadd132pd xmm10,xmm2,xmm3
 122:	c4 62 e9 98 db       	vfmadd132pd xmm11,xmm2,xmm3
 127:	c4 62 e9 98 e3       	vfmadd132pd xmm12,xmm2,xmm3
 12c:	c4 e2 e9 98 cb       	vfmadd132pd xmm1,xmm2,xmm3
 131:	c4 e2 e9 98 e3       	vfmadd132pd xmm4,xmm2,xmm3
 136:	c4 e2 e9 98 eb       	vfmadd132pd xmm5,xmm2,xmm3
 13b:	c4 e2 e9 98 f3       	vfmadd132pd xmm6,xmm2,xmm3
 140:	c4 e2 e9 98 fb       	vfmadd132pd xmm7,xmm2,xmm3
 145:	c4 62 e9 98 c3       	vfmadd132pd xmm8,xmm2,xmm3
 14a:	c4 62 e9 98 cb       	vfmadd132pd xmm9,xmm2,xmm3
 14f:	c4 62 e9 98 d3       	vfmadd132pd xmm10,xmm2,xmm3
 154:	c4 62 e9 98 db       	vfmadd132pd xmm11,xmm2,xmm3
 159:	c4 62 e9 98 e3       	vfmadd132pd xmm12,xmm2,xmm3
 15e:	c4 e2 e9 98 cb       	vfmadd132pd xmm1,xmm2,xmm3
 163:	c4 e2 e9 98 e3       	vfmadd132pd xmm4,xmm2,xmm3
 168:	c4 e2 e9 98 eb       	vfmadd132pd xmm5,xmm2,xmm3
 16d:	c4 e2 e9 98 f3       	vfmadd132pd xmm6,xmm2,xmm3
 172:	c4 e2 e9 98 fb       	vfmadd132pd xmm7,xmm2,xmm3
 177:	c4 62 e9 98 c3       	vfmadd132pd xmm8,xmm2,xmm3
 17c:	c4 62 e9 98 cb       	vfmadd132pd xmm9,xmm2,xmm3
 181:	c4 62 e9 98 d3       	vfmadd132pd xmm10,xmm2,xmm3
 186:	c4 62 e9 98 db       	vfmadd132pd xmm11,xmm2,xmm3
 18b:	c4 62 e9 98 e3       	vfmadd132pd 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;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
VMOVUPD XMM1, [R14];
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;
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: 28.12
- APERF: 40.66
- FpuPipeAssignment.Total0: 40.0
- FpuPipeAssignment.Total1: 40.0
- FpuPipeAssignment.Total2: 8.0
- FpuPipeAssignment.Total3: 8.0
- FpuPipeAssignment.Total4: 4.5
- FpuPipeAssignment.Total5: 4.5

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:	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:	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: 28.06
- APERF: 40.64
- FpuPipeAssignment.Total0: 40.5
- FpuPipeAssignment.Total1: 7.0
- FpuPipeAssignment.Total2: 8.0
- FpuPipeAssignment.Total3: 40.51
- FpuPipeAssignment.Total4: 4.5
- FpuPipeAssignment.Total5: 4.5

⇨ One μop that can only use ports {'0', '3'}

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:	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: 29.13
- APERF: 42.37
- FpuPipeAssignment.Total0: 6.38
- FpuPipeAssignment.Total1: 41.56
- FpuPipeAssignment.Total2: 41.44
- FpuPipeAssignment.Total3: 6.62
- FpuPipeAssignment.Total4: 4.5
- FpuPipeAssignment.Total5: 4.5

⇨ 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:	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: 27.74
- APERF: 40.12
- FpuPipeAssignment.Total0: 8.0
- FpuPipeAssignment.Total1: 8.0
- FpuPipeAssignment.Total2: 40.0
- FpuPipeAssignment.Total3: 40.0
- FpuPipeAssignment.Total4: 4.5
- FpuPipeAssignment.Total5: 4.5

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:	41 0f 7e c4          	movd   r12d,mm0
  94:	0f 7e c3             	movd   ebx,mm0
  97:	0f 7e c1             	movd   ecx,mm0
  9a:	0f 7e c2             	movd   edx,mm0
  9d:	0f 7e c0             	movd   eax,mm0
  a0:	41 0f 7e c0          	movd   r8d,mm0
  a4:	41 0f 7e c1          	movd   r9d,mm0
  a8:	41 0f 7e c2          	movd   r10d,mm0
  ac:	41 0f 7e c3          	movd   r11d,mm0
  b0:	41 0f 7e c4          	movd   r12d,mm0
  b4:	0f 7e c3             	movd   ebx,mm0
  b7:	0f 7e c1             	movd   ecx,mm0
  ba:	0f 7e c2             	movd   edx,mm0
  bd:	0f 7e c0             	movd   eax,mm0
  c0:	41 0f 7e c0          	movd   r8d,mm0
  c4:	41 0f 7e c1          	movd   r9d,mm0
  c8:	41 0f 7e c2          	movd   r10d,mm0
  cc:	41 0f 7e c3          	movd   r11d,mm0
  d0:	41 0f 7e c4          	movd   r12d,mm0
  d4:	0f 7e c3             	movd   ebx,mm0
  d7:	0f 7e c1             	movd   ecx,mm0
  da:	0f 7e c2             	movd   edx,mm0
  dd:	0f 7e c0             	movd   eax,mm0
  e0:	41 0f 7e c0          	movd   r8d,mm0
  e4:	41 0f 7e c1          	movd   r9d,mm0
  e8:	41 0f 7e c2          	movd   r10d,mm0
  ec:	41 0f 7e c3          	movd   r11d,mm0
  f0:	41 0f 7e c4          	movd   r12d,mm0
  f4:	0f 7e c3             	movd   ebx,mm0
  f7:	0f 7e c1             	movd   ecx,mm0
  fa:	0f 7e c2             	movd   edx,mm0
  fd:	0f 7e c0             	movd   eax,mm0
 100:	41 0f 7e c0          	movd   r8d,mm0
 104:	41 0f 7e c1          	movd   r9d,mm0
 108:	41 0f 7e c2          	movd   r10d,mm0
 10c:	41 0f 7e c3          	movd   r11d,mm0
 110:	41 0f 7e c4          	movd   r12d,mm0
 114:	0f 7e c3             	movd   ebx,mm0
 117:	0f 7e c1             	movd   ecx,mm0
 11a:	0f 7e c2             	movd   edx,mm0
 11d:	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:
- MPERF: 32.55
- APERF: 47.22
- FpuPipeAssignment.Total0: 2.81
- FpuPipeAssignment.Total1: 4.25
- FpuPipeAssignment.Total2: 5.13
- FpuPipeAssignment.Total3: 3.81
- FpuPipeAssignment.Total4: 44.5
- FpuPipeAssignment.Total5: 44.5

⇨ 9 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:	0f 65 e1             	pcmpgtw mm4,mm1
  f3:	0f 65 e9             	pcmpgtw mm5,mm1
  f6:	0f 65 f1             	pcmpgtw mm6,mm1
  f9:	0f 65 f9             	pcmpgtw mm7,mm1
  fc:	0f 65 c1             	pcmpgtw mm0,mm1
  ff:	0f 65 d1             	pcmpgtw mm2,mm1
 102:	0f 65 d9             	pcmpgtw mm3,mm1
 105:	0f 65 e1             	pcmpgtw mm4,mm1
 108:	0f 65 e9             	pcmpgtw mm5,mm1
 10b:	0f 65 f1             	pcmpgtw mm6,mm1
 10e:	0f 65 f9             	pcmpgtw mm7,mm1
 111:	0f 65 c1             	pcmpgtw mm0,mm1
 114:	0f 65 d1             	pcmpgtw mm2,mm1
 117:	0f 65 d9             	pcmpgtw mm3,mm1
 11a:	0f 65 e1             	pcmpgtw mm4,mm1
 11d:	0f 65 e9             	pcmpgtw mm5,mm1
 120:	0f 65 f1             	pcmpgtw mm6,mm1
 123:	0f 65 f9             	pcmpgtw mm7,mm1
 126:	0f 65 c1             	pcmpgtw mm0,mm1
 129:	0f 65 d1             	pcmpgtw 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 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: 26.22
- APERF: 38.12
- FpuPipeAssignment.Total0: 28.82
- FpuPipeAssignment.Total1: 28.95
- FpuPipeAssignment.Total2: 29.08
- FpuPipeAssignment.Total3: 29.17
- FpuPipeAssignment.Total4: 4.5
- FpuPipeAssignment.Total5: 4.5

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