VPMULLQ_Z (YMM, K, 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 a9 40 c2    	vpmullq ymm0{k1}{z},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: 10.03
  • Reference cycles: 7.52
  • UOPS_PORT_0: 10.0

With blocking instructions for port '1':

• Code:

     0:	44 8d 05 80 00 00 00 	lea    r8d,[rip+0x80]        # 0x87
     7:	44 8d 0d 80 00 00 00 	lea    r9d,[rip+0x80]        # 0x8e
     e:	44 8d 15 80 00 00 00 	lea    r10d,[rip+0x80]        # 0x95
    15:	44 8d 1d 80 00 00 00 	lea    r11d,[rip+0x80]        # 0x9c
    1c:	44 8d 25 80 00 00 00 	lea    r12d,[rip+0x80]        # 0xa3
    23:	8d 1d 80 00 00 00    	lea    ebx,[rip+0x80]        # 0xa9
    29:	8d 0d 80 00 00 00    	lea    ecx,[rip+0x80]        # 0xaf
    2f:	8d 15 80 00 00 00    	lea    edx,[rip+0x80]        # 0xb5
    35:	44 8d 05 80 00 00 00 	lea    r8d,[rip+0x80]        # 0xbc
    3c:	44 8d 0d 80 00 00 00 	lea    r9d,[rip+0x80]        # 0xc3
    43:	62 f2 f5 a9 40 c2    	vpmullq ymm0{k1}{z},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: 10.0
  • Reference cycles: 7.52
  • UOPS_PORT_1: 10.01

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

• Code:

     0:	c4 e2 59 de dd       	vaesdec xmm3,xmm4,xmm5
     5:	c4 e2 59 de f5       	vaesdec xmm6,xmm4,xmm5
     a:	c4 e2 59 de fd       	vaesdec xmm7,xmm4,xmm5
     f:	c4 62 59 de c5       	vaesdec xmm8,xmm4,xmm5
    14:	c4 62 59 de cd       	vaesdec xmm9,xmm4,xmm5
    19:	c4 62 59 de d5       	vaesdec xmm10,xmm4,xmm5
    1e:	c4 62 59 de dd       	vaesdec xmm11,xmm4,xmm5
    23:	c4 62 59 de e5       	vaesdec xmm12,xmm4,xmm5
    28:	c4 e2 59 de dd       	vaesdec xmm3,xmm4,xmm5
    2d:	c4 e2 59 de f5       	vaesdec xmm6,xmm4,xmm5
    32:	62 f2 f5 a9 40 c2    	vpmullq ymm0{k1}{z},ymm1,ymm2
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS XMM4, XMM4, XMM4;
  VXORPS XMM5, XMM5, XMM5;
  VXORPS YMM1, YMM1, YMM1;
  VXORPS YMM2, YMM2, YMM2

• Show nanoBench command
• Results:
  • Instructions retired: 11.0
  • Core cycles: 6.63
  • Reference cycles: 4.8
  • UOPS_PORT_0: 6.5
  • UOPS_PORT_1: 6.5