VMOVDQA (M256, YMM) - Port Usage

With blocking instructions for port '4':

• 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:	c4 c1 7d 7f 06       	vmovdqa YMMWORD PTR [r14],ymm0
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM0, YMM0, YMM0

• Show nanoBench command
• Results:
  • Instructions retired: 11.0
  • Core cycles: 12.09
  • Reference cycles: 13.39
  • UOPS_PORT_4: 11.0

With blocking instructions for ports {'2', '3'}:

• Code:

     0:	45 8b 46 40          	mov    r8d,DWORD PTR [r14+0x40]
     4:	45 8b 4e 44          	mov    r9d,DWORD PTR [r14+0x44]
     8:	45 8b 56 48          	mov    r10d,DWORD PTR [r14+0x48]
     c:	45 8b 5e 4c          	mov    r11d,DWORD PTR [r14+0x4c]
    10:	45 8b 66 50          	mov    r12d,DWORD PTR [r14+0x50]
    14:	41 8b 5e 54          	mov    ebx,DWORD PTR [r14+0x54]
    18:	41 8b 4e 58          	mov    ecx,DWORD PTR [r14+0x58]
    1c:	41 8b 56 5c          	mov    edx,DWORD PTR [r14+0x5c]
    20:	45 8b 46 40          	mov    r8d,DWORD PTR [r14+0x40]
    24:	45 8b 4e 44          	mov    r9d,DWORD PTR [r14+0x44]
    28:	c4 c1 7d 7f 06       	vmovdqa YMMWORD PTR [r14],ymm0
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM0, YMM0, YMM0

• Show nanoBench command
• Results:
  • Instructions retired: 11.0
  • Core cycles: 5.64
  • Reference cycles: 6.24
  • UOPS_PORT_3: 5.51
  • UOPS_PORT_2: 5.51

With an indexed addressing mode

With blocking instructions for port '4':

• 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:	c4 81 7d 7f 04 2e    	vmovdqa YMMWORD PTR [r14+r13*1],ymm0
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM0, YMM0, YMM0;
  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 11.0
  • Core cycles: 12.1
  • Reference cycles: 13.28
  • UOPS_PORT_4: 11.0

With blocking instructions for ports {'2', '3'}:

• Code:

     0:	45 8b 46 40          	mov    r8d,DWORD PTR [r14+0x40]
     4:	45 8b 4e 44          	mov    r9d,DWORD PTR [r14+0x44]
     8:	45 8b 56 48          	mov    r10d,DWORD PTR [r14+0x48]
     c:	45 8b 5e 4c          	mov    r11d,DWORD PTR [r14+0x4c]
    10:	45 8b 66 50          	mov    r12d,DWORD PTR [r14+0x50]
    14:	41 8b 5e 54          	mov    ebx,DWORD PTR [r14+0x54]
    18:	41 8b 4e 58          	mov    ecx,DWORD PTR [r14+0x58]
    1c:	41 8b 56 5c          	mov    edx,DWORD PTR [r14+0x5c]
    20:	45 8b 46 40          	mov    r8d,DWORD PTR [r14+0x40]
    24:	45 8b 4e 44          	mov    r9d,DWORD PTR [r14+0x44]
    28:	c4 81 7d 7f 04 2e    	vmovdqa YMMWORD PTR [r14+r13*1],ymm0
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM0, YMM0, YMM0;
  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 11.0
  • Core cycles: 5.65
  • Reference cycles: 6.24
  • UOPS_PORT_3: 5.51
  • UOPS_PORT_2: 5.51