VCOMPRESSPD (YMM, K, 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:	62 f2 fd 29 8a c8    	vcompresspd ymm0{k1},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];
  VMOVUPD YMM1, [R14]

• Show nanoBench command
• Results:
  • MPERF: 6.46
  • APERF: 9.22
  • FpuPipeAssignment.Total0: 7.51
  • FpuPipeAssignment.Total1: 8.98
  • FpuPipeAssignment.Total2: 1.52
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0

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:	62 f2 fd 29 8a c8    	vcompresspd ymm0{k1},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];
  VMOVUPD YMM1, [R14]

• Show nanoBench command
• Results:
  • MPERF: 6.46
  • APERF: 9.25
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 9.0
  • FpuPipeAssignment.Total2: 9.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0