VPMULLQ (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:	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:	41 0f 7e c3          	movd   r11d,mm0
  4a:	41 0f 7e c4          	movd   r12d,mm0
  4e:	0f 7e c3             	movd   ebx,mm0
  51:	0f 7e c1             	movd   ecx,mm0
  54:	0f 7e c2             	movd   edx,mm0
  57:	41 0f 7e c0          	movd   r8d,mm0
  5b:	41 0f 7e c1          	movd   r9d,mm0
  5f:	41 0f 7e c2          	movd   r10d,mm0
  63:	41 0f 7e c3          	movd   r11d,mm0
  67:	41 0f 7e c4          	movd   r12d,mm0
  6b:	0f 7e c3             	movd   ebx,mm0
  6e:	62 f2 f5 29 40 c2    	vpmullq ymm0{k1},ymm1,ymm2

Init:

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

Show nanoBench command
Results:
- Instructions retired: 31.0
- Core cycles: 30.27
- Reference cycles: 27.28
- UOPS_PORT_0: 30.0

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:	47 8d 94 6e 80 00 00 	lea    r10d,[r14+r13*2+0x80]
  57:	00 
  58:	47 8d 9c 6e 80 00 00 	lea    r11d,[r14+r13*2+0x80]
  5f:	00 
  60:	47 8d a4 6e 80 00 00 	lea    r12d,[r14+r13*2+0x80]
  67:	00 
  68:	43 8d 9c 6e 80 00 00 	lea    ebx,[r14+r13*2+0x80]
  6f:	00 
  70:	43 8d 8c 6e 80 00 00 	lea    ecx,[r14+r13*2+0x80]
  77:	00 
  78:	43 8d 94 6e 80 00 00 	lea    edx,[r14+r13*2+0x80]
  7f:	00 
  80:	47 8d 84 6e 80 00 00 	lea    r8d,[r14+r13*2+0x80]
  87:	00 
  88:	47 8d 8c 6e 80 00 00 	lea    r9d,[r14+r13*2+0x80]
  8f:	00 
  90:	47 8d 94 6e 80 00 00 	lea    r10d,[r14+r13*2+0x80]
  97:	00 
  98:	47 8d 9c 6e 80 00 00 	lea    r11d,[r14+r13*2+0x80]
  9f:	00 
  a0:	47 8d a4 6e 80 00 00 	lea    r12d,[r14+r13*2+0x80]
  a7:	00 
  a8:	43 8d 9c 6e 80 00 00 	lea    ebx,[r14+r13*2+0x80]
  af:	00 
  b0:	43 8d 8c 6e 80 00 00 	lea    ecx,[r14+r13*2+0x80]
  b7:	00 
  b8:	43 8d 94 6e 80 00 00 	lea    edx,[r14+r13*2+0x80]
  bf:	00 
  c0:	47 8d 84 6e 80 00 00 	lea    r8d,[r14+r13*2+0x80]
  c7:	00 
  c8:	47 8d 8c 6e 80 00 00 	lea    r9d,[r14+r13*2+0x80]
  cf:	00 
  d0:	47 8d 94 6e 80 00 00 	lea    r10d,[r14+r13*2+0x80]
  d7:	00 
  d8:	47 8d 9c 6e 80 00 00 	lea    r11d,[r14+r13*2+0x80]
  df:	00 
  e0:	47 8d a4 6e 80 00 00 	lea    r12d,[r14+r13*2+0x80]
  e7:	00 
  e8:	43 8d 9c 6e 80 00 00 	lea    ebx,[r14+r13*2+0x80]
  ef:	00 
  f0:	62 f2 f5 29 40 c2    	vpmullq ymm0{k1},ymm1,ymm2

Init:

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

Show nanoBench command
Results:
- Instructions retired: 31.0
- Core cycles: 30.24
- Reference cycles: 26.55
- UOPS_PORT_1: 30.0

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:	c5 d9 58 fd          	vaddpd xmm7,xmm4,xmm5
  2c:	c5 59 58 c5          	vaddpd xmm8,xmm4,xmm5
  30:	c5 59 58 cd          	vaddpd xmm9,xmm4,xmm5
  34:	c5 59 58 d5          	vaddpd xmm10,xmm4,xmm5
  38:	c5 59 58 dd          	vaddpd xmm11,xmm4,xmm5
  3c:	c5 59 58 e5          	vaddpd xmm12,xmm4,xmm5
  40:	c5 d9 58 dd          	vaddpd xmm3,xmm4,xmm5
  44:	c5 d9 58 f5          	vaddpd xmm6,xmm4,xmm5
  48:	c5 d9 58 fd          	vaddpd xmm7,xmm4,xmm5
  4c:	c5 59 58 c5          	vaddpd xmm8,xmm4,xmm5
  50:	c5 59 58 cd          	vaddpd xmm9,xmm4,xmm5
  54:	c5 59 58 d5          	vaddpd xmm10,xmm4,xmm5
  58:	c5 59 58 dd          	vaddpd xmm11,xmm4,xmm5
  5c:	c5 59 58 e5          	vaddpd xmm12,xmm4,xmm5
  60:	c5 d9 58 dd          	vaddpd xmm3,xmm4,xmm5
  64:	c5 d9 58 f5          	vaddpd xmm6,xmm4,xmm5
  68:	c5 d9 58 fd          	vaddpd xmm7,xmm4,xmm5
  6c:	c5 59 58 c5          	vaddpd xmm8,xmm4,xmm5
  70:	c5 59 58 cd          	vaddpd xmm9,xmm4,xmm5
  74:	c5 59 58 d5          	vaddpd xmm10,xmm4,xmm5
  78:	c5 59 58 dd          	vaddpd xmm11,xmm4,xmm5
  7c:	c5 59 58 e5          	vaddpd xmm12,xmm4,xmm5
  80:	c5 d9 58 dd          	vaddpd xmm3,xmm4,xmm5
  84:	c5 d9 58 f5          	vaddpd xmm6,xmm4,xmm5
  88:	c5 d9 58 fd          	vaddpd xmm7,xmm4,xmm5
  8c:	c5 59 58 c5          	vaddpd xmm8,xmm4,xmm5
  90:	c5 59 58 cd          	vaddpd xmm9,xmm4,xmm5
  94:	c5 59 58 d5          	vaddpd xmm10,xmm4,xmm5
  98:	c5 59 58 dd          	vaddpd xmm11,xmm4,xmm5
  9c:	c5 59 58 e5          	vaddpd xmm12,xmm4,xmm5
  a0:	c5 d9 58 dd          	vaddpd xmm3,xmm4,xmm5
  a4:	c5 d9 58 f5          	vaddpd xmm6,xmm4,xmm5
  a8:	c5 d9 58 fd          	vaddpd xmm7,xmm4,xmm5
  ac:	c5 59 58 c5          	vaddpd xmm8,xmm4,xmm5
  b0:	c5 59 58 cd          	vaddpd xmm9,xmm4,xmm5
  b4:	c5 59 58 d5          	vaddpd xmm10,xmm4,xmm5
  b8:	c5 59 58 dd          	vaddpd xmm11,xmm4,xmm5
  bc:	c5 59 58 e5          	vaddpd xmm12,xmm4,xmm5
  c0:	c5 d9 58 dd          	vaddpd xmm3,xmm4,xmm5
  c4:	c5 d9 58 f5          	vaddpd xmm6,xmm4,xmm5
  c8:	c5 d9 58 fd          	vaddpd xmm7,xmm4,xmm5
  cc:	c5 59 58 c5          	vaddpd xmm8,xmm4,xmm5
  d0:	c5 59 58 cd          	vaddpd xmm9,xmm4,xmm5
  d4:	c5 59 58 d5          	vaddpd xmm10,xmm4,xmm5
  d8:	c5 59 58 dd          	vaddpd xmm11,xmm4,xmm5
  dc:	c5 59 58 e5          	vaddpd xmm12,xmm4,xmm5
  e0:	c5 d9 58 dd          	vaddpd xmm3,xmm4,xmm5
  e4:	c5 d9 58 f5          	vaddpd xmm6,xmm4,xmm5
  e8:	c5 d9 58 fd          	vaddpd xmm7,xmm4,xmm5
  ec:	c5 59 58 c5          	vaddpd xmm8,xmm4,xmm5
  f0:	62 f2 f5 29 40 c2    	vpmullq ymm0{k1},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 YMM0, YMM0, YMM0;
VXORPS YMM1, YMM1, YMM1;
VXORPS YMM2, YMM2, YMM2

Show nanoBench command
Results:
- Instructions retired: 61.0
- Core cycles: 32.69
- Reference cycles: 28.9
- UOPS_PORT_1: 31.52
- UOPS_PORT_0: 31.51

⇨ 3 μops that can only use ports {'0', '1'}