VSCATTERQPD (VSIB_ZMM, K, ZMM) - Port Usage

With blocking instructions for port '0':

• 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:	41 0f 7e c0          	movd   r8d,mm0
    21:	41 0f 7e c1          	movd   r9d,mm0
    25:	41 0f 7e c2          	movd   r10d,mm0
    29:	41 0f 7e c3          	movd   r11d,mm0
    2d:	41 0f 7e c4          	movd   r12d,mm0
    31:	0f 7e c3             	movd   ebx,mm0
    34:	0f 7e c1             	movd   ecx,mm0
    37:	0f 7e c2             	movd   edx,mm0
    3a:	41 0f 7e c0          	movd   r8d,mm0
    3e:	41 0f 7e c1          	movd   r9d,mm0
    42:	41 0f 7e c2          	movd   r10d,mm0
    46:	62 92 fd 49 a3 04 36 	vscatterqpd QWORD PTR [r14+zmm14*1]{k1},zmm0
  

• 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:
  • Instructions retired: 20.0
  • Core cycles: 21.4
  • Reference cycles: 7.25
  • UOPS_PORT_0: 21.0

With blocking instructions for port '49':

• Code:

     0:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
     4:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
     8:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
     c:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
    10:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
    14:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
    18:	4d 89 46 70          	mov    QWORD PTR [r14+0x70],r8
    1c:	4d 89 46 78          	mov    QWORD PTR [r14+0x78],r8
    20:	4d 89 86 80 00 00 00 	mov    QWORD PTR [r14+0x80],r8
    27:	4d 89 86 88 00 00 00 	mov    QWORD PTR [r14+0x88],r8
    2e:	4d 89 86 90 00 00 00 	mov    QWORD PTR [r14+0x90],r8
    35:	4d 89 86 98 00 00 00 	mov    QWORD PTR [r14+0x98],r8
    3c:	4d 89 86 a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r8
    43:	4d 89 86 a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r8
    4a:	4d 89 86 b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r8
    51:	4d 89 86 b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r8
    58:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
    5c:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
    60:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
    64:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
    68:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
    6c:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
    70:	4d 89 46 70          	mov    QWORD PTR [r14+0x70],r8
    74:	4d 89 46 78          	mov    QWORD PTR [r14+0x78],r8
    78:	4d 89 86 80 00 00 00 	mov    QWORD PTR [r14+0x80],r8
    7f:	4d 89 86 88 00 00 00 	mov    QWORD PTR [r14+0x88],r8
    86:	4d 89 86 90 00 00 00 	mov    QWORD PTR [r14+0x90],r8
    8d:	4d 89 86 98 00 00 00 	mov    QWORD PTR [r14+0x98],r8
    94:	4d 89 86 a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r8
    9b:	4d 89 86 a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r8
    a2:	4d 89 86 b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r8
    a9:	4d 89 86 b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r8
    b0:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
    b4:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
    b8:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
    bc:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
    c0:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
    c4:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
    c8:	62 92 fd 49 a3 04 36 	vscatterqpd QWORD PTR [r14+zmm14*1]{k1},zmm0
  

• 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;
  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:
  • Instructions retired: 39.0
  • Core cycles: 24.27
  • Reference cycles: 8.35
  • UOPS_PORT_49: 46.0

With blocking instructions for port '5':

• Code:

     0:	41 0f 6e c0          	movd   mm0,r8d
     4:	41 0f 6e c8          	movd   mm1,r8d
     8:	41 0f 6e d0          	movd   mm2,r8d
     c:	41 0f 6e d8          	movd   mm3,r8d
    10:	41 0f 6e e0          	movd   mm4,r8d
    14:	41 0f 6e e8          	movd   mm5,r8d
    18:	41 0f 6e f0          	movd   mm6,r8d
    1c:	41 0f 6e f8          	movd   mm7,r8d
    20:	41 0f 6e c0          	movd   mm0,r8d
    24:	41 0f 6e c8          	movd   mm1,r8d
    28:	41 0f 6e d0          	movd   mm2,r8d
    2c:	41 0f 6e d8          	movd   mm3,r8d
    30:	41 0f 6e e0          	movd   mm4,r8d
    34:	41 0f 6e e8          	movd   mm5,r8d
    38:	41 0f 6e f0          	movd   mm6,r8d
    3c:	41 0f 6e f8          	movd   mm7,r8d
    40:	41 0f 6e c0          	movd   mm0,r8d
    44:	41 0f 6e c8          	movd   mm1,r8d
    48:	41 0f 6e d0          	movd   mm2,r8d
    4c:	62 92 fd 49 a3 04 36 	vscatterqpd QWORD PTR [r14+zmm14*1]{k1},zmm0
  

• 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;
  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:
  • Instructions retired: 20.0
  • Core cycles: 19.21
  • Reference cycles: 6.56
  • UOPS_PORT_5: 18.98

With blocking instructions for port '78':

• Code:

     0:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
     4:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
     8:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
     c:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
    10:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
    14:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
    18:	4d 89 46 70          	mov    QWORD PTR [r14+0x70],r8
    1c:	4d 89 46 78          	mov    QWORD PTR [r14+0x78],r8
    20:	4d 89 86 80 00 00 00 	mov    QWORD PTR [r14+0x80],r8
    27:	4d 89 86 88 00 00 00 	mov    QWORD PTR [r14+0x88],r8
    2e:	4d 89 86 90 00 00 00 	mov    QWORD PTR [r14+0x90],r8
    35:	4d 89 86 98 00 00 00 	mov    QWORD PTR [r14+0x98],r8
    3c:	4d 89 86 a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r8
    43:	4d 89 86 a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r8
    4a:	4d 89 86 b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r8
    51:	4d 89 86 b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r8
    58:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
    5c:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
    60:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
    64:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
    68:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
    6c:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
    70:	4d 89 46 70          	mov    QWORD PTR [r14+0x70],r8
    74:	4d 89 46 78          	mov    QWORD PTR [r14+0x78],r8
    78:	4d 89 86 80 00 00 00 	mov    QWORD PTR [r14+0x80],r8
    7f:	4d 89 86 88 00 00 00 	mov    QWORD PTR [r14+0x88],r8
    86:	4d 89 86 90 00 00 00 	mov    QWORD PTR [r14+0x90],r8
    8d:	4d 89 86 98 00 00 00 	mov    QWORD PTR [r14+0x98],r8
    94:	4d 89 86 a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r8
    9b:	4d 89 86 a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r8
    a2:	4d 89 86 b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r8
    a9:	4d 89 86 b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r8
    b0:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
    b4:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
    b8:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
    bc:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
    c0:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
    c4:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
    c8:	62 92 fd 49 a3 04 36 	vscatterqpd QWORD PTR [r14+zmm14*1]{k1},zmm0
  

• 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;
  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:
  • Instructions retired: 39.0
  • Core cycles: 24.31
  • Reference cycles: 8.15
  • UOPS_PORT_78: 46.0

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:	0f 6f e1             	movq   mm4,mm1
    21:	0f 6f e9             	movq   mm5,mm1
    24:	0f 6f f1             	movq   mm6,mm1
    27:	0f 6f f9             	movq   mm7,mm1
    2a:	0f 6f c1             	movq   mm0,mm1
    2d:	0f 6f d1             	movq   mm2,mm1
    30:	0f 6f d9             	movq   mm3,mm1
    33:	0f 6f e1             	movq   mm4,mm1
    36:	0f 6f e9             	movq   mm5,mm1
    39:	0f 6f f1             	movq   mm6,mm1
    3c:	0f 6f f9             	movq   mm7,mm1
    3f:	0f 6f c1             	movq   mm0,mm1
    42:	0f 6f d1             	movq   mm2,mm1
    45:	0f 6f d9             	movq   mm3,mm1
    48:	0f 6f e1             	movq   mm4,mm1
    4b:	0f 6f e9             	movq   mm5,mm1
    4e:	0f 6f f1             	movq   mm6,mm1
    51:	0f 6f f9             	movq   mm7,mm1
    54:	0f 6f c1             	movq   mm0,mm1
    57:	0f 6f d1             	movq   mm2,mm1
    5a:	0f 6f d9             	movq   mm3,mm1
    5d:	0f 6f e1             	movq   mm4,mm1
    60:	0f 6f e9             	movq   mm5,mm1
    63:	0f 6f f1             	movq   mm6,mm1
    66:	0f 6f f9             	movq   mm7,mm1
    69:	0f 6f c1             	movq   mm0,mm1
    6c:	0f 6f d1             	movq   mm2,mm1
    6f:	0f 6f d9             	movq   mm3,mm1
    72:	62 92 fd 49 a3 04 36 	vscatterqpd QWORD PTR [r14+zmm14*1]{k1},zmm0
  

• Init:

  MOV R15, 10000;
  L: VADDPS ZMM0, ZMM1, ZMM1;
  VADDPS ZMM0, ZMM1, ZMM1;
  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;
  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:
  • Instructions retired: 39.0
  • Core cycles: 21.0
  • Reference cycles: 7.15
  • UOPS_PORT_0: 19.96
  • UOPS_PORT_5: 19.92

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:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
    2c:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
    30:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
    34:	43 8d 1c 6e          	lea    ebx,[r14+r13*2]
    38:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
    3c:	43 8d 14 6e          	lea    edx,[r14+r13*2]
    40:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
    44:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
    48:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
    4c:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
    50:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
    54:	43 8d 1c 6e          	lea    ebx,[r14+r13*2]
    58:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
    5c:	43 8d 14 6e          	lea    edx,[r14+r13*2]
    60:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
    64:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
    68:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
    6c:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
    70:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
    74:	43 8d 1c 6e          	lea    ebx,[r14+r13*2]
    78:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
    7c:	43 8d 14 6e          	lea    edx,[r14+r13*2]
    80:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
    84:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
    88:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
    8c:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
    90:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
    94:	43 8d 1c 6e          	lea    ebx,[r14+r13*2]
    98:	62 92 fd 49 a3 04 36 	vscatterqpd QWORD PTR [r14+zmm14*1]{k1},zmm0
  

• 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;
  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:
  • Instructions retired: 39.0
  • Core cycles: 19.46
  • Reference cycles: 6.16
  • UOPS_PORT_1: 18.96
  • UOPS_PORT_5: 19.04

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

• Code:

     0:	c5 e9 55 cb          	vandnpd xmm1,xmm2,xmm3
     4:	c5 e9 55 e3          	vandnpd xmm4,xmm2,xmm3
     8:	c5 e9 55 eb          	vandnpd xmm5,xmm2,xmm3
     c:	c5 e9 55 f3          	vandnpd xmm6,xmm2,xmm3
    10:	c5 e9 55 fb          	vandnpd xmm7,xmm2,xmm3
    14:	c5 69 55 c3          	vandnpd xmm8,xmm2,xmm3
    18:	c5 69 55 cb          	vandnpd xmm9,xmm2,xmm3
    1c:	c5 69 55 d3          	vandnpd xmm10,xmm2,xmm3
    20:	c5 69 55 db          	vandnpd xmm11,xmm2,xmm3
    24:	c5 69 55 e3          	vandnpd xmm12,xmm2,xmm3
    28:	c5 e9 55 cb          	vandnpd xmm1,xmm2,xmm3
    2c:	c5 e9 55 e3          	vandnpd xmm4,xmm2,xmm3
    30:	c5 e9 55 eb          	vandnpd xmm5,xmm2,xmm3
    34:	c5 e9 55 f3          	vandnpd xmm6,xmm2,xmm3
    38:	c5 e9 55 fb          	vandnpd xmm7,xmm2,xmm3
    3c:	c5 69 55 c3          	vandnpd xmm8,xmm2,xmm3
    40:	c5 69 55 cb          	vandnpd xmm9,xmm2,xmm3
    44:	c5 69 55 d3          	vandnpd xmm10,xmm2,xmm3
    48:	c5 69 55 db          	vandnpd xmm11,xmm2,xmm3
    4c:	c5 69 55 e3          	vandnpd xmm12,xmm2,xmm3
    50:	c5 e9 55 cb          	vandnpd xmm1,xmm2,xmm3
    54:	c5 e9 55 e3          	vandnpd xmm4,xmm2,xmm3
    58:	c5 e9 55 eb          	vandnpd xmm5,xmm2,xmm3
    5c:	c5 e9 55 f3          	vandnpd xmm6,xmm2,xmm3
    60:	c5 e9 55 fb          	vandnpd xmm7,xmm2,xmm3
    64:	c5 69 55 c3          	vandnpd xmm8,xmm2,xmm3
    68:	c5 69 55 cb          	vandnpd xmm9,xmm2,xmm3
    6c:	c5 69 55 d3          	vandnpd xmm10,xmm2,xmm3
    70:	c5 69 55 db          	vandnpd xmm11,xmm2,xmm3
    74:	c5 69 55 e3          	vandnpd xmm12,xmm2,xmm3
    78:	c5 e9 55 cb          	vandnpd xmm1,xmm2,xmm3
    7c:	c5 e9 55 e3          	vandnpd xmm4,xmm2,xmm3
    80:	c5 e9 55 eb          	vandnpd xmm5,xmm2,xmm3
    84:	c5 e9 55 f3          	vandnpd xmm6,xmm2,xmm3
    88:	c5 e9 55 fb          	vandnpd xmm7,xmm2,xmm3
    8c:	c5 69 55 c3          	vandnpd xmm8,xmm2,xmm3
    90:	c5 69 55 cb          	vandnpd xmm9,xmm2,xmm3
    94:	c5 69 55 d3          	vandnpd xmm10,xmm2,xmm3
    98:	c5 69 55 db          	vandnpd xmm11,xmm2,xmm3
    9c:	c5 69 55 e3          	vandnpd xmm12,xmm2,xmm3
    a0:	c5 e9 55 cb          	vandnpd xmm1,xmm2,xmm3
    a4:	c5 e9 55 e3          	vandnpd xmm4,xmm2,xmm3
    a8:	c5 e9 55 eb          	vandnpd xmm5,xmm2,xmm3
    ac:	c5 e9 55 f3          	vandnpd xmm6,xmm2,xmm3
    b0:	c5 e9 55 fb          	vandnpd xmm7,xmm2,xmm3
    b4:	c5 69 55 c3          	vandnpd xmm8,xmm2,xmm3
    b8:	c5 69 55 cb          	vandnpd xmm9,xmm2,xmm3
    bc:	c5 69 55 d3          	vandnpd xmm10,xmm2,xmm3
    c0:	c5 69 55 db          	vandnpd xmm11,xmm2,xmm3
    c4:	c5 69 55 e3          	vandnpd xmm12,xmm2,xmm3
    c8:	c5 e9 55 cb          	vandnpd xmm1,xmm2,xmm3
    cc:	c5 e9 55 e3          	vandnpd xmm4,xmm2,xmm3
    d0:	c5 e9 55 eb          	vandnpd xmm5,xmm2,xmm3
    d4:	c5 e9 55 f3          	vandnpd xmm6,xmm2,xmm3
    d8:	c5 e9 55 fb          	vandnpd xmm7,xmm2,xmm3
    dc:	c5 69 55 c3          	vandnpd xmm8,xmm2,xmm3
    e0:	c5 69 55 cb          	vandnpd xmm9,xmm2,xmm3
    e4:	62 92 fd 49 a3 04 36 	vscatterqpd QWORD PTR [r14+zmm14*1]{k1},zmm0
  

• Init:

  MOV R15, 10000;
  L: VADDPS ZMM0, ZMM1, ZMM1;
  VADDPS ZMM0, ZMM1, ZMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS XMM2, XMM2, XMM2;
  VXORPS XMM3, XMM3, XMM3;
  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:
  • Instructions retired: 58.0
  • Core cycles: 30.15
  • Reference cycles: 10.03
  • UOPS_PORT_0: 29.06
  • UOPS_PORT_1: 2.18
  • UOPS_PORT_5: 28.82