VPERMT2W_Z (YMM, K, YMM, YMM) - Port Usage

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:	62 f2 f5 a9 7d c2    	vpermt2w ymm0{k1}{z},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: 19.0
- Core cycles: 20.11
- Reference cycles: 15.53
- UOPS_PORT_5: 19.98

⇨ 2 μops that can only use port '5'

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:	62 f2 f5 a9 7d c2    	vpermt2w ymm0{k1}{z},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: 37.0
- Core cycles: 18.26
- Reference cycles: 13.89
- UOPS_PORT_1: 18.0
- UOPS_PORT_0: 17.96

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

Code:

   0:	c5 d9 55 dd          	vandnpd xmm3,xmm4,xmm5
   4:	c5 d9 55 f5          	vandnpd xmm6,xmm4,xmm5
   8:	c5 d9 55 fd          	vandnpd xmm7,xmm4,xmm5
   c:	c5 59 55 c5          	vandnpd xmm8,xmm4,xmm5
  10:	c5 59 55 cd          	vandnpd xmm9,xmm4,xmm5
  14:	c5 59 55 d5          	vandnpd xmm10,xmm4,xmm5
  18:	c5 59 55 dd          	vandnpd xmm11,xmm4,xmm5
  1c:	c5 59 55 e5          	vandnpd xmm12,xmm4,xmm5
  20:	c5 d9 55 dd          	vandnpd xmm3,xmm4,xmm5
  24:	c5 d9 55 f5          	vandnpd xmm6,xmm4,xmm5
  28:	c5 d9 55 fd          	vandnpd xmm7,xmm4,xmm5
  2c:	c5 59 55 c5          	vandnpd xmm8,xmm4,xmm5
  30:	c5 59 55 cd          	vandnpd xmm9,xmm4,xmm5
  34:	c5 59 55 d5          	vandnpd xmm10,xmm4,xmm5
  38:	c5 59 55 dd          	vandnpd xmm11,xmm4,xmm5
  3c:	c5 59 55 e5          	vandnpd xmm12,xmm4,xmm5
  40:	c5 d9 55 dd          	vandnpd xmm3,xmm4,xmm5
  44:	c5 d9 55 f5          	vandnpd xmm6,xmm4,xmm5
  48:	c5 d9 55 fd          	vandnpd xmm7,xmm4,xmm5
  4c:	c5 59 55 c5          	vandnpd xmm8,xmm4,xmm5
  50:	c5 59 55 cd          	vandnpd xmm9,xmm4,xmm5
  54:	c5 59 55 d5          	vandnpd xmm10,xmm4,xmm5
  58:	c5 59 55 dd          	vandnpd xmm11,xmm4,xmm5
  5c:	c5 59 55 e5          	vandnpd xmm12,xmm4,xmm5
  60:	c5 d9 55 dd          	vandnpd xmm3,xmm4,xmm5
  64:	c5 d9 55 f5          	vandnpd xmm6,xmm4,xmm5
  68:	c5 d9 55 fd          	vandnpd xmm7,xmm4,xmm5
  6c:	c5 59 55 c5          	vandnpd xmm8,xmm4,xmm5
  70:	c5 59 55 cd          	vandnpd xmm9,xmm4,xmm5
  74:	c5 59 55 d5          	vandnpd xmm10,xmm4,xmm5
  78:	c5 59 55 dd          	vandnpd xmm11,xmm4,xmm5
  7c:	c5 59 55 e5          	vandnpd xmm12,xmm4,xmm5
  80:	c5 d9 55 dd          	vandnpd xmm3,xmm4,xmm5
  84:	c5 d9 55 f5          	vandnpd xmm6,xmm4,xmm5
  88:	c5 d9 55 fd          	vandnpd xmm7,xmm4,xmm5
  8c:	c5 59 55 c5          	vandnpd xmm8,xmm4,xmm5
  90:	c5 59 55 cd          	vandnpd xmm9,xmm4,xmm5
  94:	c5 59 55 d5          	vandnpd xmm10,xmm4,xmm5
  98:	c5 59 55 dd          	vandnpd xmm11,xmm4,xmm5
  9c:	c5 59 55 e5          	vandnpd xmm12,xmm4,xmm5
  a0:	c5 d9 55 dd          	vandnpd xmm3,xmm4,xmm5
  a4:	c5 d9 55 f5          	vandnpd xmm6,xmm4,xmm5
  a8:	c5 d9 55 fd          	vandnpd xmm7,xmm4,xmm5
  ac:	c5 59 55 c5          	vandnpd xmm8,xmm4,xmm5
  b0:	c5 59 55 cd          	vandnpd xmm9,xmm4,xmm5
  b4:	c5 59 55 d5          	vandnpd xmm10,xmm4,xmm5
  b8:	c5 59 55 dd          	vandnpd xmm11,xmm4,xmm5
  bc:	c5 59 55 e5          	vandnpd xmm12,xmm4,xmm5
  c0:	c5 d9 55 dd          	vandnpd xmm3,xmm4,xmm5
  c4:	c5 d9 55 f5          	vandnpd xmm6,xmm4,xmm5
  c8:	c5 d9 55 fd          	vandnpd xmm7,xmm4,xmm5
  cc:	c5 59 55 c5          	vandnpd xmm8,xmm4,xmm5
  d0:	c5 59 55 cd          	vandnpd xmm9,xmm4,xmm5
  d4:	c5 59 55 d5          	vandnpd xmm10,xmm4,xmm5
  d8:	62 f2 f5 a9 7d c2    	vpermt2w 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 YMM0, YMM0, YMM0;
VXORPS YMM1, YMM1, YMM1;
VXORPS YMM2, YMM2, YMM2

Show nanoBench command
Results:
- Instructions retired: 55.0
- Core cycles: 19.56
- Reference cycles: 13.89
- UOPS_PORT_1: 18.94
- UOPS_PORT_5: 19.0
- UOPS_PORT_0: 19.0

⇨ One μop that can only use ports {'0', '1', '5'}