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:	0f 7e c0             	movd   eax,mm0
  20:	41 0f 7e c0          	movd   r8d,mm0
  24:	41 0f 7e c1          	movd   r9d,mm0
  28:	41 0f 7e c2          	movd   r10d,mm0
  2c:	41 0f 7e c3          	movd   r11d,mm0
  30:	41 0f 7e c4          	movd   r12d,mm0
  34:	0f 7e c3             	movd   ebx,mm0
  37:	0f 7e c1             	movd   ecx,mm0
  3a:	0f 7e c2             	movd   edx,mm0
  3d:	0f 7e c0             	movd   eax,mm0
  40:	41 0f 7e c0          	movd   r8d,mm0
  44:	41 0f 7e c1          	movd   r9d,mm0
  48:	41 0f 7e c2          	movd   r10d,mm0
  4c:	41 0f 7e c3          	movd   r11d,mm0
  50:	41 0f 7e c4          	movd   r12d,mm0
  54:	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: 24.0
- Core cycles: 30.11
- Reference cycles: 18.6
- UOPS_PORT_0: 30.0

⇨ 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:	41 0f 6e f0          	movd   mm6,r8d
  5c:	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: 24.0
- Core cycles: 32.3
- Reference cycles: 20.47
- UOPS_PORT_5B: 32.0
- UOPS_PORT_5B>=2: 0.0

⇨ 9 μops that can only use port '5'

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

Code:

   0:	c4 e2 61 de d4       	vaesdec xmm2,xmm3,xmm4
   5:	c4 e2 61 de ec       	vaesdec xmm5,xmm3,xmm4
   a:	c4 e2 61 de f4       	vaesdec xmm6,xmm3,xmm4
   f:	c4 e2 61 de fc       	vaesdec xmm7,xmm3,xmm4
  14:	c4 62 61 de c4       	vaesdec xmm8,xmm3,xmm4
  19:	c4 62 61 de cc       	vaesdec xmm9,xmm3,xmm4
  1e:	c4 62 61 de d4       	vaesdec xmm10,xmm3,xmm4
  23:	c4 62 61 de dc       	vaesdec xmm11,xmm3,xmm4
  28:	c4 62 61 de e4       	vaesdec xmm12,xmm3,xmm4
  2d:	c4 e2 61 de d4       	vaesdec xmm2,xmm3,xmm4
  32:	c4 e2 61 de ec       	vaesdec xmm5,xmm3,xmm4
  37:	c4 e2 61 de f4       	vaesdec xmm6,xmm3,xmm4
  3c:	c4 e2 61 de fc       	vaesdec xmm7,xmm3,xmm4
  41:	c4 62 61 de c4       	vaesdec xmm8,xmm3,xmm4
  46:	c4 62 61 de cc       	vaesdec xmm9,xmm3,xmm4
  4b:	c4 62 61 de d4       	vaesdec xmm10,xmm3,xmm4
  50:	c4 62 61 de dc       	vaesdec xmm11,xmm3,xmm4
  55:	c4 62 61 de e4       	vaesdec xmm12,xmm3,xmm4
  5a:	c4 e2 61 de d4       	vaesdec xmm2,xmm3,xmm4
  5f:	c4 e2 61 de ec       	vaesdec xmm5,xmm3,xmm4
  64:	c4 e2 61 de f4       	vaesdec xmm6,xmm3,xmm4
  69:	c4 e2 61 de fc       	vaesdec xmm7,xmm3,xmm4
  6e:	c4 62 61 de c4       	vaesdec xmm8,xmm3,xmm4
  73:	c4 62 61 de cc       	vaesdec xmm9,xmm3,xmm4
  78:	c4 62 61 de d4       	vaesdec xmm10,xmm3,xmm4
  7d:	c4 62 61 de dc       	vaesdec xmm11,xmm3,xmm4
  82:	c4 62 61 de e4       	vaesdec xmm12,xmm3,xmm4
  87:	c4 e2 61 de d4       	vaesdec xmm2,xmm3,xmm4
  8c:	c4 e2 61 de ec       	vaesdec xmm5,xmm3,xmm4
  91:	c4 e2 61 de f4       	vaesdec xmm6,xmm3,xmm4
  96:	c4 e2 61 de fc       	vaesdec xmm7,xmm3,xmm4
  9b:	c4 62 61 de c4       	vaesdec xmm8,xmm3,xmm4
  a0:	c4 62 61 de cc       	vaesdec xmm9,xmm3,xmm4
  a5:	c4 62 61 de d4       	vaesdec xmm10,xmm3,xmm4
  aa:	c4 62 61 de dc       	vaesdec xmm11,xmm3,xmm4
  af:	c4 62 61 de e4       	vaesdec xmm12,xmm3,xmm4
  b4:	c4 e2 61 de d4       	vaesdec xmm2,xmm3,xmm4
  b9:	c4 e2 61 de ec       	vaesdec xmm5,xmm3,xmm4
  be:	c4 e2 61 de f4       	vaesdec xmm6,xmm3,xmm4
  c3:	c4 e2 61 de fc       	vaesdec xmm7,xmm3,xmm4
  c8:	c4 62 61 de c4       	vaesdec xmm8,xmm3,xmm4
  cd:	c4 62 61 de cc       	vaesdec xmm9,xmm3,xmm4
  d2:	c4 62 61 de d4       	vaesdec xmm10,xmm3,xmm4
  d7:	c4 62 61 de dc       	vaesdec xmm11,xmm3,xmm4
  dc:	c4 62 61 de e4       	vaesdec xmm12,xmm3,xmm4
  e1:	c4 e2 61 de d4       	vaesdec xmm2,xmm3,xmm4
  e6:	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 XMM3, XMM3, XMM3;
VXORPS XMM4, XMM4, XMM4;
VXORPS ZMM1, ZMM1, ZMM1

Show nanoBench command
Results:
- Instructions retired: 47.0
- Core cycles: 52.13
- Reference cycles: 34.29
- UOPS_PORT_1: 1.14
- UOPS_PORT_0: 51.86

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:	0f 6f d9             	movq   mm3,mm1
  87:	0f 6f e1             	movq   mm4,mm1
  8a:	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: 47.0
- Core cycles: 34.6
- Reference cycles: 22.86
- UOPS_PORT_0: 34.0
- UOPS_PORT_5B: 34.0
- UOPS_PORT_5B>=2: 0.0

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

With blocking instructions for ports {'0', '6'}:

Code:

   0:	66 41 c1 c0 00       	rol    r8w,0x0
   5:	66 41 c1 c1 00       	rol    r9w,0x0
   a:	66 41 c1 c2 00       	rol    r10w,0x0
   f:	66 41 c1 c3 00       	rol    r11w,0x0
  14:	66 41 c1 c4 00       	rol    r12w,0x0
  19:	66 c1 c3 00          	rol    bx,0x0
  1d:	66 c1 c1 00          	rol    cx,0x0
  21:	66 c1 c2 00          	rol    dx,0x0
  25:	66 c1 c0 00          	rol    ax,0x0
  29:	66 41 c1 c0 00       	rol    r8w,0x0
  2e:	66 41 c1 c1 00       	rol    r9w,0x0
  33:	66 41 c1 c2 00       	rol    r10w,0x0
  38:	66 41 c1 c3 00       	rol    r11w,0x0
  3d:	66 41 c1 c4 00       	rol    r12w,0x0
  42:	66 c1 c3 00          	rol    bx,0x0
  46:	66 c1 c1 00          	rol    cx,0x0
  4a:	66 c1 c2 00          	rol    dx,0x0
  4e:	66 c1 c0 00          	rol    ax,0x0
  52:	66 41 c1 c0 00       	rol    r8w,0x0
  57:	66 41 c1 c1 00       	rol    r9w,0x0
  5c:	66 41 c1 c2 00       	rol    r10w,0x0
  61:	66 41 c1 c3 00       	rol    r11w,0x0
  66:	66 41 c1 c4 00       	rol    r12w,0x0
  6b:	66 c1 c3 00          	rol    bx,0x0
  6f:	66 c1 c1 00          	rol    cx,0x0
  73:	66 c1 c2 00          	rol    dx,0x0
  77:	66 c1 c0 00          	rol    ax,0x0
  7b:	66 41 c1 c0 00       	rol    r8w,0x0
  80:	66 41 c1 c1 00       	rol    r9w,0x0
  85:	66 41 c1 c2 00       	rol    r10w,0x0
  8a:	66 41 c1 c3 00       	rol    r11w,0x0
  8f:	66 41 c1 c4 00       	rol    r12w,0x0
  94:	66 c1 c3 00          	rol    bx,0x0
  98:	66 c1 c1 00          	rol    cx,0x0
  9c:	66 c1 c2 00          	rol    dx,0x0
  a0:	66 c1 c0 00          	rol    ax,0x0
  a4:	66 41 c1 c0 00       	rol    r8w,0x0
  a9:	66 41 c1 c1 00       	rol    r9w,0x0
  ae:	66 41 c1 c2 00       	rol    r10w,0x0
  b3:	66 41 c1 c3 00       	rol    r11w,0x0
  b8:	66 41 c1 c4 00       	rol    r12w,0x0
  bd:	66 c1 c3 00          	rol    bx,0x0
  c1:	66 c1 c1 00          	rol    cx,0x0
  c5:	66 c1 c2 00          	rol    dx,0x0
  c9:	66 c1 c0 00          	rol    ax,0x0
  cd:	66 41 c1 c0 00       	rol    r8w,0x0
  d2:	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: 47.0
- Core cycles: 27.64
- Reference cycles: 19.05
- UOPS_PORT_6: 26.75
- UOPS_PORT_0: 27.21

⇨ One μop that can only use ports {'0', '6'}