VDIVPH (ZMM, 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:	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:	0f 7e c1             	movd   ecx,mm0
  71:	0f 7e c2             	movd   edx,mm0
  74:	41 0f 7e c0          	movd   r8d,mm0
  78:	41 0f 7e c1          	movd   r9d,mm0
  7c:	41 0f 7e c2          	movd   r10d,mm0
  80:	41 0f 7e c3          	movd   r11d,mm0
  84:	41 0f 7e c4          	movd   r12d,mm0
  88:	0f 7e c3             	movd   ebx,mm0
  8b:	0f 7e c1             	movd   ecx,mm0
  8e:	0f 7e c2             	movd   edx,mm0
  91:	41 0f 7e c0          	movd   r8d,mm0
  95:	41 0f 7e c1          	movd   r9d,mm0
  99:	41 0f 7e c2          	movd   r10d,mm0
  9d:	41 0f 7e c3          	movd   r11d,mm0
  a1:	41 0f 7e c4          	movd   r12d,mm0
  a5:	0f 7e c3             	movd   ebx,mm0
  a8:	0f 7e c1             	movd   ecx,mm0
  ab:	0f 7e c2             	movd   edx,mm0
  ae:	41 0f 7e c0          	movd   r8d,mm0
  b2:	41 0f 7e c1          	movd   r9d,mm0
  b6:	41 0f 7e c2          	movd   r10d,mm0
  ba:	41 0f 7e c3          	movd   r11d,mm0
  be:	41 0f 7e c4          	movd   r12d,mm0
  c2:	0f 7e c3             	movd   ebx,mm0
  c5:	0f 7e c1             	movd   ecx,mm0
  c8:	0f 7e c2             	movd   edx,mm0
  cb:	41 0f 7e c0          	movd   r8d,mm0
  cf:	41 0f 7e c1          	movd   r9d,mm0
  d3:	41 0f 7e c2          	movd   r10d,mm0
  d7:	41 0f 7e c3          	movd   r11d,mm0
  db:	41 0f 7e c4          	movd   r12d,mm0
  df:	0f 7e c3             	movd   ebx,mm0
  e2:	0f 7e c1             	movd   ecx,mm0
  e5:	0f 7e c2             	movd   edx,mm0
  e8:	62 f5 7c 48 5e d1    	vdivph zmm2,zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
PXOR MM0, MM0;
VZEROALL;
MOV RAX, 0x2769276927692769;
MOV RBX, 0x3CCF3CCF3CCF3CCF;
MOV [R14+0], RBX;
MOV [R14+8], RBX;
MOV [R14+16], RBX;
MOV [R14+24], RBX;
MOV [R14+32], RBX;
MOV [R14+40], RBX;
MOV [R14+48], RBX;
MOV [R14+56], RBX;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPD ZMM0, [R14+64];
VMOVUPD ZMM1, [R14]

Show nanoBench command
Results:
- Instructions retired: 65.0
- Core cycles: 71.36
- Reference cycles: 51.2
- UOPS_PORT_0: 68.0

⇨ 4 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:	41 0f 6e f8          	movd   mm7,r8d
  60:	41 0f 6e c0          	movd   mm0,r8d
  64:	41 0f 6e c8          	movd   mm1,r8d
  68:	41 0f 6e d0          	movd   mm2,r8d
  6c:	41 0f 6e d8          	movd   mm3,r8d
  70:	41 0f 6e e0          	movd   mm4,r8d
  74:	41 0f 6e e8          	movd   mm5,r8d
  78:	41 0f 6e f0          	movd   mm6,r8d
  7c:	41 0f 6e f8          	movd   mm7,r8d
  80:	41 0f 6e c0          	movd   mm0,r8d
  84:	41 0f 6e c8          	movd   mm1,r8d
  88:	41 0f 6e d0          	movd   mm2,r8d
  8c:	41 0f 6e d8          	movd   mm3,r8d
  90:	41 0f 6e e0          	movd   mm4,r8d
  94:	41 0f 6e e8          	movd   mm5,r8d
  98:	41 0f 6e f0          	movd   mm6,r8d
  9c:	41 0f 6e f8          	movd   mm7,r8d
  a0:	41 0f 6e c0          	movd   mm0,r8d
  a4:	41 0f 6e c8          	movd   mm1,r8d
  a8:	41 0f 6e d0          	movd   mm2,r8d
  ac:	41 0f 6e d8          	movd   mm3,r8d
  b0:	41 0f 6e e0          	movd   mm4,r8d
  b4:	41 0f 6e e8          	movd   mm5,r8d
  b8:	41 0f 6e f0          	movd   mm6,r8d
  bc:	41 0f 6e f8          	movd   mm7,r8d
  c0:	41 0f 6e c0          	movd   mm0,r8d
  c4:	41 0f 6e c8          	movd   mm1,r8d
  c8:	41 0f 6e d0          	movd   mm2,r8d
  cc:	41 0f 6e d8          	movd   mm3,r8d
  d0:	41 0f 6e e0          	movd   mm4,r8d
  d4:	41 0f 6e e8          	movd   mm5,r8d
  d8:	41 0f 6e f0          	movd   mm6,r8d
  dc:	41 0f 6e f8          	movd   mm7,r8d
  e0:	41 0f 6e c0          	movd   mm0,r8d
  e4:	41 0f 6e c8          	movd   mm1,r8d
  e8:	41 0f 6e d0          	movd   mm2,r8d
  ec:	41 0f 6e d8          	movd   mm3,r8d
  f0:	41 0f 6e e0          	movd   mm4,r8d
  f4:	41 0f 6e e8          	movd   mm5,r8d
  f8:	41 0f 6e f0          	movd   mm6,r8d
  fc:	41 0f 6e f8          	movd   mm7,r8d
 100:	62 f5 7c 48 5e d1    	vdivph zmm2,zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x2769276927692769;
MOV RBX, 0x3CCF3CCF3CCF3CCF;
MOV [R14+0], RBX;
MOV [R14+8], RBX;
MOV [R14+16], RBX;
MOV [R14+24], RBX;
MOV [R14+32], RBX;
MOV [R14+40], RBX;
MOV [R14+48], RBX;
MOV [R14+56], RBX;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPD ZMM0, [R14+64];
VMOVUPD ZMM1, [R14]

Show nanoBench command
Results:
- Instructions retired: 65.0
- Core cycles: 65.17
- Reference cycles: 49.07
- UOPS_PORT_5B: 65.0
- UOPS_PORT_5B>=2: 0.0

⇨ One μop that can only use port '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 41 c1 c0 00       	rol    r8w,0x0
  2a:	66 41 c1 c1 00       	rol    r9w,0x0
  2f:	66 41 c1 c2 00       	rol    r10w,0x0
  34:	66 41 c1 c3 00       	rol    r11w,0x0
  39:	66 41 c1 c4 00       	rol    r12w,0x0
  3e:	66 c1 c3 00          	rol    bx,0x0
  42:	66 c1 c1 00          	rol    cx,0x0
  46:	66 c1 c2 00          	rol    dx,0x0
  4a:	66 41 c1 c0 00       	rol    r8w,0x0
  4f:	66 41 c1 c1 00       	rol    r9w,0x0
  54:	66 41 c1 c2 00       	rol    r10w,0x0
  59:	66 41 c1 c3 00       	rol    r11w,0x0
  5e:	66 41 c1 c4 00       	rol    r12w,0x0
  63:	66 c1 c3 00          	rol    bx,0x0
  67:	66 c1 c1 00          	rol    cx,0x0
  6b:	66 c1 c2 00          	rol    dx,0x0
  6f:	66 41 c1 c0 00       	rol    r8w,0x0
  74:	66 41 c1 c1 00       	rol    r9w,0x0
  79:	66 41 c1 c2 00       	rol    r10w,0x0
  7e:	66 41 c1 c3 00       	rol    r11w,0x0
  83:	66 41 c1 c4 00       	rol    r12w,0x0
  88:	66 c1 c3 00          	rol    bx,0x0
  8c:	66 c1 c1 00          	rol    cx,0x0
  90:	66 c1 c2 00          	rol    dx,0x0
  94:	66 41 c1 c0 00       	rol    r8w,0x0
  99:	66 41 c1 c1 00       	rol    r9w,0x0
  9e:	66 41 c1 c2 00       	rol    r10w,0x0
  a3:	66 41 c1 c3 00       	rol    r11w,0x0
  a8:	66 41 c1 c4 00       	rol    r12w,0x0
  ad:	66 c1 c3 00          	rol    bx,0x0
  b1:	66 c1 c1 00          	rol    cx,0x0
  b5:	66 c1 c2 00          	rol    dx,0x0
  b9:	66 41 c1 c0 00       	rol    r8w,0x0
  be:	66 41 c1 c1 00       	rol    r9w,0x0
  c3:	66 41 c1 c2 00       	rol    r10w,0x0
  c8:	66 41 c1 c3 00       	rol    r11w,0x0
  cd:	66 41 c1 c4 00       	rol    r12w,0x0
  d2:	66 c1 c3 00          	rol    bx,0x0
  d6:	66 c1 c1 00          	rol    cx,0x0
  da:	66 c1 c2 00          	rol    dx,0x0
  de:	66 41 c1 c0 00       	rol    r8w,0x0
  e3:	66 41 c1 c1 00       	rol    r9w,0x0
  e8:	66 41 c1 c2 00       	rol    r10w,0x0
  ed:	66 41 c1 c3 00       	rol    r11w,0x0
  f2:	66 41 c1 c4 00       	rol    r12w,0x0
  f7:	66 c1 c3 00          	rol    bx,0x0
  fb:	66 c1 c1 00          	rol    cx,0x0
  ff:	66 c1 c2 00          	rol    dx,0x0
 103:	66 41 c1 c0 00       	rol    r8w,0x0
 108:	66 41 c1 c1 00       	rol    r9w,0x0
 10d:	66 41 c1 c2 00       	rol    r10w,0x0
 112:	66 41 c1 c3 00       	rol    r11w,0x0
 117:	66 41 c1 c4 00       	rol    r12w,0x0
 11c:	66 c1 c3 00          	rol    bx,0x0
 120:	66 c1 c1 00          	rol    cx,0x0
 124:	66 c1 c2 00          	rol    dx,0x0
 128:	66 41 c1 c0 00       	rol    r8w,0x0
 12d:	66 41 c1 c1 00       	rol    r9w,0x0
 132:	66 41 c1 c2 00       	rol    r10w,0x0
 137:	66 41 c1 c3 00       	rol    r11w,0x0
 13c:	66 41 c1 c4 00       	rol    r12w,0x0
 141:	66 c1 c3 00          	rol    bx,0x0
 145:	66 c1 c1 00          	rol    cx,0x0
 149:	66 c1 c2 00          	rol    dx,0x0
 14d:	66 41 c1 c0 00       	rol    r8w,0x0
 152:	66 41 c1 c1 00       	rol    r9w,0x0
 157:	66 41 c1 c2 00       	rol    r10w,0x0
 15c:	66 41 c1 c3 00       	rol    r11w,0x0
 161:	66 41 c1 c4 00       	rol    r12w,0x0
 166:	66 c1 c3 00          	rol    bx,0x0
 16a:	66 c1 c1 00          	rol    cx,0x0
 16e:	66 c1 c2 00          	rol    dx,0x0
 172:	66 41 c1 c0 00       	rol    r8w,0x0
 177:	66 41 c1 c1 00       	rol    r9w,0x0
 17c:	66 41 c1 c2 00       	rol    r10w,0x0
 181:	66 41 c1 c3 00       	rol    r11w,0x0
 186:	66 41 c1 c4 00       	rol    r12w,0x0
 18b:	66 c1 c3 00          	rol    bx,0x0
 18f:	66 c1 c1 00          	rol    cx,0x0
 193:	66 c1 c2 00          	rol    dx,0x0
 197:	66 41 c1 c0 00       	rol    r8w,0x0
 19c:	66 41 c1 c1 00       	rol    r9w,0x0
 1a1:	66 41 c1 c2 00       	rol    r10w,0x0
 1a6:	66 41 c1 c3 00       	rol    r11w,0x0
 1ab:	66 41 c1 c4 00       	rol    r12w,0x0
 1b0:	66 c1 c3 00          	rol    bx,0x0
 1b4:	66 c1 c1 00          	rol    cx,0x0
 1b8:	66 c1 c2 00          	rol    dx,0x0
 1bc:	66 41 c1 c0 00       	rol    r8w,0x0
 1c1:	66 41 c1 c1 00       	rol    r9w,0x0
 1c6:	66 41 c1 c2 00       	rol    r10w,0x0
 1cb:	66 41 c1 c3 00       	rol    r11w,0x0
 1d0:	62 f5 7c 48 5e d1    	vdivph zmm2,zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x2769276927692769;
MOV RBX, 0x3CCF3CCF3CCF3CCF;
MOV [R14+0], RBX;
MOV [R14+8], RBX;
MOV [R14+16], RBX;
MOV [R14+24], RBX;
MOV [R14+32], RBX;
MOV [R14+40], RBX;
MOV [R14+48], RBX;
MOV [R14+56], RBX;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPD ZMM0, [R14+64];
VMOVUPD ZMM1, [R14]

Show nanoBench command
Results:
- Instructions retired: 101.0
- Core cycles: 57.2
- Reference cycles: 43.2
- UOPS_PORT_6: 52.47
- UOPS_PORT_0: 52.52

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