VBLENDVPS (YMM, YMM, YMM, YMM) - Port Usage

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

• Code:

     0:	c5 d1 58 e6          	vaddpd xmm4,xmm5,xmm6
     4:	c5 d1 58 fe          	vaddpd xmm7,xmm5,xmm6
     8:	c5 51 58 c6          	vaddpd xmm8,xmm5,xmm6
     c:	c5 51 58 ce          	vaddpd xmm9,xmm5,xmm6
    10:	c5 51 58 d6          	vaddpd xmm10,xmm5,xmm6
    14:	c5 51 58 de          	vaddpd xmm11,xmm5,xmm6
    18:	c5 51 58 e6          	vaddpd xmm12,xmm5,xmm6
    1c:	c5 d1 58 e6          	vaddpd xmm4,xmm5,xmm6
    20:	c5 d1 58 fe          	vaddpd xmm7,xmm5,xmm6
    24:	c5 51 58 c6          	vaddpd xmm8,xmm5,xmm6
    28:	c4 e3 75 4a c2 30    	vblendvps ymm0,ymm1,ymm2,ymm3
  

• 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 XMM5, [R14];
  VMOVUPD XMM6, [R14];
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  VMOVUPD YMM1, [R14];
  VMOVUPD YMM2, [R14];
  VXORPS YMM3, YMM3, YMM3

• Show nanoBench command
• Results:
  • Instructions retired: 11.0
  • Core cycles: 5.12
  • Reference cycles: 2.92
  • UOPS_PORT_1: 5.01
  • UOPS_PORT_0: 5.0

With blocking instructions for ports {'0', '5'}:

• 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:	c4 e3 75 4a c2 30    	vblendvps ymm0,ymm1,ymm2,ymm3
  

• 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 YMM1, [R14];
  VMOVUPD YMM2, [R14];
  VXORPS YMM3, YMM3, YMM3

• Show nanoBench command
• Results:
  • Instructions retired: 11.0
  • Core cycles: 5.1
  • Reference cycles: 2.92
  • UOPS_PORT_0: 5.0
  • UOPS_PORT_5: 5.0

With blocking instructions for ports {'1', '5'}:

• Code:

     0:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
     4:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
     8:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
     c:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
    10:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
    14:	43 8d 1c 6e          	lea    ebx,[r14+r13*2]
    18:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
    1c:	43 8d 14 6e          	lea    edx,[r14+r13*2]
    20:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
    24:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
    28:	c4 e3 75 4a c2 30    	vblendvps ymm0,ymm1,ymm2,ymm3
  

• 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;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  VMOVUPD YMM1, [R14];
  VMOVUPD YMM2, [R14];
  VXORPS YMM3, YMM3, YMM3

• Show nanoBench command
• Results:
  • Instructions retired: 11.0
  • Core cycles: 5.04
  • Reference cycles: 3.04
  • UOPS_PORT_1: 5.01
  • UOPS_PORT_5: 5.01

With blocking instructions for ports {'0', '1', '5'}:

• Code:

     0:	c5 d1 55 e6          	vandnpd xmm4,xmm5,xmm6
     4:	c5 d1 55 fe          	vandnpd xmm7,xmm5,xmm6
     8:	c5 51 55 c6          	vandnpd xmm8,xmm5,xmm6
     c:	c5 51 55 ce          	vandnpd xmm9,xmm5,xmm6
    10:	c5 51 55 d6          	vandnpd xmm10,xmm5,xmm6
    14:	c5 51 55 de          	vandnpd xmm11,xmm5,xmm6
    18:	c5 51 55 e6          	vandnpd xmm12,xmm5,xmm6
    1c:	c5 d1 55 e6          	vandnpd xmm4,xmm5,xmm6
    20:	c5 d1 55 fe          	vandnpd xmm7,xmm5,xmm6
    24:	c5 51 55 c6          	vandnpd xmm8,xmm5,xmm6
    28:	c4 e3 75 4a c2 30    	vblendvps ymm0,ymm1,ymm2,ymm3
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS XMM5, XMM5, XMM5;
  VXORPS XMM6, XMM6, XMM6;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  VMOVUPD YMM1, [R14];
  VMOVUPD YMM2, [R14];
  VXORPS YMM3, YMM3, YMM3

• Show nanoBench command
• Results:
  • Instructions retired: 11.0
  • Core cycles: 4.11
  • Reference cycles: 2.19
  • UOPS_PORT_1: 4.01
  • UOPS_PORT_0: 4.0
  • UOPS_PORT_5: 3.99