VPMULLQ (YMM, YMM, YMM) - 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:	62 f2 f5 28 40 c2    	vpmullq ymm0,ymm1,ymm2
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  PXOR MM0, MM0;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  VXORPS YMM2, YMM2, YMM2

• Show nanoBench command
• Results:
  • Instructions retired: 11.0
  • Core cycles: 10.07
  • Reference cycles: 7.05
  • UOPS_PORT_0: 9.99

With blocking instructions for port '1':

• Code:

     0:	47 8d 84 6e 80 00 00 	lea    r8d,[r14+r13*2+0x80]
     7:	00 
     8:	47 8d 8c 6e 80 00 00 	lea    r9d,[r14+r13*2+0x80]
     f:	00 
    10:	47 8d 94 6e 80 00 00 	lea    r10d,[r14+r13*2+0x80]
    17:	00 
    18:	47 8d 9c 6e 80 00 00 	lea    r11d,[r14+r13*2+0x80]
    1f:	00 
    20:	47 8d a4 6e 80 00 00 	lea    r12d,[r14+r13*2+0x80]
    27:	00 
    28:	43 8d 9c 6e 80 00 00 	lea    ebx,[r14+r13*2+0x80]
    2f:	00 
    30:	43 8d 8c 6e 80 00 00 	lea    ecx,[r14+r13*2+0x80]
    37:	00 
    38:	43 8d 94 6e 80 00 00 	lea    edx,[r14+r13*2+0x80]
    3f:	00 
    40:	47 8d 84 6e 80 00 00 	lea    r8d,[r14+r13*2+0x80]
    47:	00 
    48:	47 8d 8c 6e 80 00 00 	lea    r9d,[r14+r13*2+0x80]
    4f:	00 
    50:	62 f2 f5 28 40 c2    	vpmullq ymm0,ymm1,ymm2
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  VXORPS YMM2, YMM2, YMM2

• Show nanoBench command
• Results:
  • Instructions retired: 11.0
  • Core cycles: 10.06
  • Reference cycles: 6.75
  • UOPS_PORT_1: 10.0

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

• Code:

     0:	c5 d9 58 dd          	vaddpd xmm3,xmm4,xmm5
     4:	c5 d9 58 f5          	vaddpd xmm6,xmm4,xmm5
     8:	c5 d9 58 fd          	vaddpd xmm7,xmm4,xmm5
     c:	c5 59 58 c5          	vaddpd xmm8,xmm4,xmm5
    10:	c5 59 58 cd          	vaddpd xmm9,xmm4,xmm5
    14:	c5 59 58 d5          	vaddpd xmm10,xmm4,xmm5
    18:	c5 59 58 dd          	vaddpd xmm11,xmm4,xmm5
    1c:	c5 59 58 e5          	vaddpd xmm12,xmm4,xmm5
    20:	c5 d9 58 dd          	vaddpd xmm3,xmm4,xmm5
    24:	c5 d9 58 f5          	vaddpd xmm6,xmm4,xmm5
    28:	62 f2 f5 28 40 c2    	vpmullq ymm0,ymm1,ymm2
  

• 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 XMM4, [R14];
  VMOVUPD XMM5, [R14];
  VXORPS YMM1, YMM1, YMM1;
  VXORPS YMM2, YMM2, YMM2

• Show nanoBench command
• Results:
  • Instructions retired: 11.0
  • Core cycles: 6.69
  • Reference cycles: 4.91
  • UOPS_PORT_1: 6.5
  • UOPS_PORT_0: 6.51