VPCONFLICTQ (ZMM, ZMM) - 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:	62 f2 fd 48 c4 c1    	vpconflictq zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
PXOR MM0, MM0;
VZEROALL;
VXORPS ZMM1, ZMM1, ZMM1

Show nanoBench command
Results:
- Instructions retired: 23.0
- Core cycles: 29.27
- Reference cycles: 20.01
- UOPS_PORT_0: 29.0

⇨ 7 μops that can only use port '0'

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:	41 0f 6e d0          	movd   mm2,r8d
  4c:	41 0f 6e d8          	movd   mm3,r8d
  50:	41 0f 6e e0          	movd   mm4,r8d
  54:	41 0f 6e e8          	movd   mm5,r8d
  58:	62 f2 fd 48 c4 c1    	vpconflictq zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM1, ZMM1, ZMM1

Show nanoBench command
Results:
- Instructions retired: 23.0
- Core cycles: 31.42
- Reference cycles: 21.63
- UOPS_PORT_5: 30.98

⇨ 9 μops that can only use port '5'

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

Code:

   0:	c5 e1 58 d4          	vaddpd xmm2,xmm3,xmm4
   4:	c5 e1 58 ec          	vaddpd xmm5,xmm3,xmm4
   8:	c5 e1 58 f4          	vaddpd xmm6,xmm3,xmm4
   c:	c5 e1 58 fc          	vaddpd xmm7,xmm3,xmm4
  10:	c5 61 58 c4          	vaddpd xmm8,xmm3,xmm4
  14:	c5 61 58 cc          	vaddpd xmm9,xmm3,xmm4
  18:	c5 61 58 d4          	vaddpd xmm10,xmm3,xmm4
  1c:	c5 61 58 dc          	vaddpd xmm11,xmm3,xmm4
  20:	c5 61 58 e4          	vaddpd xmm12,xmm3,xmm4
  24:	c5 e1 58 d4          	vaddpd xmm2,xmm3,xmm4
  28:	c5 e1 58 ec          	vaddpd xmm5,xmm3,xmm4
  2c:	c5 e1 58 f4          	vaddpd xmm6,xmm3,xmm4
  30:	c5 e1 58 fc          	vaddpd xmm7,xmm3,xmm4
  34:	c5 61 58 c4          	vaddpd xmm8,xmm3,xmm4
  38:	c5 61 58 cc          	vaddpd xmm9,xmm3,xmm4
  3c:	c5 61 58 d4          	vaddpd xmm10,xmm3,xmm4
  40:	c5 61 58 dc          	vaddpd xmm11,xmm3,xmm4
  44:	c5 61 58 e4          	vaddpd xmm12,xmm3,xmm4
  48:	c5 e1 58 d4          	vaddpd xmm2,xmm3,xmm4
  4c:	c5 e1 58 ec          	vaddpd xmm5,xmm3,xmm4
  50:	c5 e1 58 f4          	vaddpd xmm6,xmm3,xmm4
  54:	c5 e1 58 fc          	vaddpd xmm7,xmm3,xmm4
  58:	c5 61 58 c4          	vaddpd xmm8,xmm3,xmm4
  5c:	c5 61 58 cc          	vaddpd xmm9,xmm3,xmm4
  60:	c5 61 58 d4          	vaddpd xmm10,xmm3,xmm4
  64:	c5 61 58 dc          	vaddpd xmm11,xmm3,xmm4
  68:	c5 61 58 e4          	vaddpd xmm12,xmm3,xmm4
  6c:	c5 e1 58 d4          	vaddpd xmm2,xmm3,xmm4
  70:	c5 e1 58 ec          	vaddpd xmm5,xmm3,xmm4
  74:	c5 e1 58 f4          	vaddpd xmm6,xmm3,xmm4
  78:	c5 e1 58 fc          	vaddpd xmm7,xmm3,xmm4
  7c:	c5 61 58 c4          	vaddpd xmm8,xmm3,xmm4
  80:	c5 61 58 cc          	vaddpd xmm9,xmm3,xmm4
  84:	c5 61 58 d4          	vaddpd xmm10,xmm3,xmm4
  88:	c5 61 58 dc          	vaddpd xmm11,xmm3,xmm4
  8c:	c5 61 58 e4          	vaddpd xmm12,xmm3,xmm4
  90:	c5 e1 58 d4          	vaddpd xmm2,xmm3,xmm4
  94:	c5 e1 58 ec          	vaddpd xmm5,xmm3,xmm4
  98:	c5 e1 58 f4          	vaddpd xmm6,xmm3,xmm4
  9c:	c5 e1 58 fc          	vaddpd xmm7,xmm3,xmm4
  a0:	c5 61 58 c4          	vaddpd xmm8,xmm3,xmm4
  a4:	c5 61 58 cc          	vaddpd xmm9,xmm3,xmm4
  a8:	c5 61 58 d4          	vaddpd xmm10,xmm3,xmm4
  ac:	c5 61 58 dc          	vaddpd xmm11,xmm3,xmm4
  b0:	62 f2 fd 48 c4 c1    	vpconflictq zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
VMOVUPD XMM3, [R14];
VMOVUPD XMM4, [R14];
VXORPS ZMM1, ZMM1, ZMM1

Show nanoBench command
Results:
- Instructions retired: 45.0
- Core cycles: 50.41
- Reference cycles: 30.97
- UOPS_PORT_1: 1.05
- UOPS_PORT_0: 50.05

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

Code:

   0:	0f 6f c1             	movq   mm0,mm1
   3:	0f 6f d1             	movq   mm2,mm1
   6:	0f 6f d9             	movq   mm3,mm1
   9:	0f 6f e1             	movq   mm4,mm1
   c:	0f 6f e9             	movq   mm5,mm1
   f:	0f 6f f1             	movq   mm6,mm1
  12:	0f 6f f9             	movq   mm7,mm1
  15:	0f 6f c1             	movq   mm0,mm1
  18:	0f 6f d1             	movq   mm2,mm1
  1b:	0f 6f d9             	movq   mm3,mm1
  1e:	0f 6f e1             	movq   mm4,mm1
  21:	0f 6f e9             	movq   mm5,mm1
  24:	0f 6f f1             	movq   mm6,mm1
  27:	0f 6f f9             	movq   mm7,mm1
  2a:	0f 6f c1             	movq   mm0,mm1
  2d:	0f 6f d1             	movq   mm2,mm1
  30:	0f 6f d9             	movq   mm3,mm1
  33:	0f 6f e1             	movq   mm4,mm1
  36:	0f 6f e9             	movq   mm5,mm1
  39:	0f 6f f1             	movq   mm6,mm1
  3c:	0f 6f f9             	movq   mm7,mm1
  3f:	0f 6f c1             	movq   mm0,mm1
  42:	0f 6f d1             	movq   mm2,mm1
  45:	0f 6f d9             	movq   mm3,mm1
  48:	0f 6f e1             	movq   mm4,mm1
  4b:	0f 6f e9             	movq   mm5,mm1
  4e:	0f 6f f1             	movq   mm6,mm1
  51:	0f 6f f9             	movq   mm7,mm1
  54:	0f 6f c1             	movq   mm0,mm1
  57:	0f 6f d1             	movq   mm2,mm1
  5a:	0f 6f d9             	movq   mm3,mm1
  5d:	0f 6f e1             	movq   mm4,mm1
  60:	0f 6f e9             	movq   mm5,mm1
  63:	0f 6f f1             	movq   mm6,mm1
  66:	0f 6f f9             	movq   mm7,mm1
  69:	0f 6f c1             	movq   mm0,mm1
  6c:	0f 6f d1             	movq   mm2,mm1
  6f:	0f 6f d9             	movq   mm3,mm1
  72:	0f 6f e1             	movq   mm4,mm1
  75:	0f 6f e9             	movq   mm5,mm1
  78:	0f 6f f1             	movq   mm6,mm1
  7b:	0f 6f f9             	movq   mm7,mm1
  7e:	0f 6f c1             	movq   mm0,mm1
  81:	0f 6f d1             	movq   mm2,mm1
  84:	62 f2 fd 48 c4 c1    	vpconflictq zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
PXOR MM1, MM1;
VZEROALL;
VXORPS ZMM1, ZMM1, ZMM1

Show nanoBench command
Results:
- Instructions retired: 45.0
- Core cycles: 33.82
- Reference cycles: 19.91
- UOPS_PORT_0: 32.95
- UOPS_PORT_5: 33.05

⇨ 6 μops that can only use ports {'0', '5'}