VSCALEFPD (ZMM, ZMM, ZMM) - Port Usage

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:	62 f2 f5 48 2c c2    	vscalefpd zmm0,zmm1,zmm2
  

• 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 ZMM1, [R14];
  VMOVUPD ZMM2, [R14]

• Show nanoBench command
• Results:
  • MPERF: 4.47
  • APERF: 5.2
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 5.01
  • FpuPipeAssignment.Total2: 5.05
  • FpuPipeAssignment.Total3: 1.94
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0

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:	62 f2 f5 48 2c c2    	vscalefpd zmm0,zmm1,zmm2
  

• 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 ZMM1, [R14];
  VMOVUPD ZMM2, [R14]

• Show nanoBench command
• Results:
  • MPERF: 6.11
  • APERF: 7.07
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 6.0
  • FpuPipeAssignment.Total3: 6.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0