VSCATTERQPD (VSIB_ZMM, K, 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:	62 92 fd 49 a3 04 36 	vscatterqpd QWORD PTR [r14+zmm14*1]{k1},zmm0

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
PXOR MM0, MM0;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VXORPS ZMM14, ZMM14, ZMM14

Show nanoBench command
Results:
- Instructions retired: 20.0
- Core cycles: 21.23
- Reference cycles: 16.62
- UOPS_PORT_0: 21.0

⇨ 2 μops that can only use port '0'

With blocking instructions for port '49':

Code:

   0:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
   4:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
   8:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
   c:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
  10:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
  14:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
  18:	4d 89 46 70          	mov    QWORD PTR [r14+0x70],r8
  1c:	4d 89 46 78          	mov    QWORD PTR [r14+0x78],r8
  20:	4d 89 86 80 00 00 00 	mov    QWORD PTR [r14+0x80],r8
  27:	4d 89 86 88 00 00 00 	mov    QWORD PTR [r14+0x88],r8
  2e:	4d 89 86 90 00 00 00 	mov    QWORD PTR [r14+0x90],r8
  35:	4d 89 86 98 00 00 00 	mov    QWORD PTR [r14+0x98],r8
  3c:	4d 89 86 a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r8
  43:	4d 89 86 a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r8
  4a:	4d 89 86 b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r8
  51:	4d 89 86 b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r8
  58:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
  5c:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
  60:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
  64:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
  68:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
  6c:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
  70:	4d 89 46 70          	mov    QWORD PTR [r14+0x70],r8
  74:	4d 89 46 78          	mov    QWORD PTR [r14+0x78],r8
  78:	4d 89 86 80 00 00 00 	mov    QWORD PTR [r14+0x80],r8
  7f:	4d 89 86 88 00 00 00 	mov    QWORD PTR [r14+0x88],r8
  86:	4d 89 86 90 00 00 00 	mov    QWORD PTR [r14+0x90],r8
  8d:	4d 89 86 98 00 00 00 	mov    QWORD PTR [r14+0x98],r8
  94:	4d 89 86 a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r8
  9b:	4d 89 86 a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r8
  a2:	4d 89 86 b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r8
  a9:	4d 89 86 b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r8
  b0:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
  b4:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
  b8:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
  bc:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
  c0:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
  c4:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
  c8:	62 92 fd 49 a3 04 36 	vscatterqpd QWORD PTR [r14+zmm14*1]{k1},zmm0

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;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VXORPS ZMM14, ZMM14, ZMM14

Show nanoBench command
Results:
- Instructions retired: 39.0
- Core cycles: 24.14
- Reference cycles: 19.08
- UOPS_PORT_49: 46.0

⇨ 8 μops that can only use port '49'

With blocking instructions for port '78':

Code:

   0:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
   4:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
   8:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
   c:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
  10:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
  14:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
  18:	4d 89 46 70          	mov    QWORD PTR [r14+0x70],r8
  1c:	4d 89 46 78          	mov    QWORD PTR [r14+0x78],r8
  20:	4d 89 86 80 00 00 00 	mov    QWORD PTR [r14+0x80],r8
  27:	4d 89 86 88 00 00 00 	mov    QWORD PTR [r14+0x88],r8
  2e:	4d 89 86 90 00 00 00 	mov    QWORD PTR [r14+0x90],r8
  35:	4d 89 86 98 00 00 00 	mov    QWORD PTR [r14+0x98],r8
  3c:	4d 89 86 a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r8
  43:	4d 89 86 a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r8
  4a:	4d 89 86 b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r8
  51:	4d 89 86 b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r8
  58:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
  5c:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
  60:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
  64:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
  68:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
  6c:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
  70:	4d 89 46 70          	mov    QWORD PTR [r14+0x70],r8
  74:	4d 89 46 78          	mov    QWORD PTR [r14+0x78],r8
  78:	4d 89 86 80 00 00 00 	mov    QWORD PTR [r14+0x80],r8
  7f:	4d 89 86 88 00 00 00 	mov    QWORD PTR [r14+0x88],r8
  86:	4d 89 86 90 00 00 00 	mov    QWORD PTR [r14+0x90],r8
  8d:	4d 89 86 98 00 00 00 	mov    QWORD PTR [r14+0x98],r8
  94:	4d 89 86 a0 00 00 00 	mov    QWORD PTR [r14+0xa0],r8
  9b:	4d 89 86 a8 00 00 00 	mov    QWORD PTR [r14+0xa8],r8
  a2:	4d 89 86 b0 00 00 00 	mov    QWORD PTR [r14+0xb0],r8
  a9:	4d 89 86 b8 00 00 00 	mov    QWORD PTR [r14+0xb8],r8
  b0:	4d 89 46 40          	mov    QWORD PTR [r14+0x40],r8
  b4:	4d 89 46 48          	mov    QWORD PTR [r14+0x48],r8
  b8:	4d 89 46 50          	mov    QWORD PTR [r14+0x50],r8
  bc:	4d 89 46 58          	mov    QWORD PTR [r14+0x58],r8
  c0:	4d 89 46 60          	mov    QWORD PTR [r14+0x60],r8
  c4:	4d 89 46 68          	mov    QWORD PTR [r14+0x68],r8
  c8:	62 92 fd 49 a3 04 36 	vscatterqpd QWORD PTR [r14+zmm14*1]{k1},zmm0

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;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VXORPS ZMM14, ZMM14, ZMM14

Show nanoBench command
Results:
- Instructions retired: 39.0
- Core cycles: 24.12
- Reference cycles: 18.46
- UOPS_PORT_78: 46.0

⇨ 8 μops that can only use port '78'

With blocking instructions for ports {'0', '5', '6'}:

Code:

   0:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
   4:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
   8:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
   c:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
  10:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
  14:	43 8d 1c 6e          	lea    ebx,[r14+r13*2]
  18:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
  1c:	43 8d 14 6e          	lea    edx,[r14+r13*2]
  20:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
  24:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
  28:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
  2c:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
  30:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
  34:	43 8d 1c 6e          	lea    ebx,[r14+r13*2]
  38:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
  3c:	43 8d 14 6e          	lea    edx,[r14+r13*2]
  40:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
  44:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
  48:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
  4c:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
  50:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
  54:	43 8d 1c 6e          	lea    ebx,[r14+r13*2]
  58:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
  5c:	43 8d 14 6e          	lea    edx,[r14+r13*2]
  60:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
  64:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
  68:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
  6c:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
  70:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
  74:	43 8d 1c 6e          	lea    ebx,[r14+r13*2]
  78:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
  7c:	43 8d 14 6e          	lea    edx,[r14+r13*2]
  80:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
  84:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
  88:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
  8c:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
  90:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
  94:	43 8d 1c 6e          	lea    ebx,[r14+r13*2]
  98:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
  9c:	43 8d 14 6e          	lea    edx,[r14+r13*2]
  a0:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
  a4:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
  a8:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
  ac:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
  b0:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
  b4:	43 8d 1c 6e          	lea    ebx,[r14+r13*2]
  b8:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
  bc:	43 8d 14 6e          	lea    edx,[r14+r13*2]
  c0:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
  c4:	47 8d 0c 6e          	lea    r9d,[r14+r13*2]
  c8:	47 8d 14 6e          	lea    r10d,[r14+r13*2]
  cc:	47 8d 1c 6e          	lea    r11d,[r14+r13*2]
  d0:	47 8d 24 6e          	lea    r12d,[r14+r13*2]
  d4:	43 8d 1c 6e          	lea    ebx,[r14+r13*2]
  d8:	43 8d 0c 6e          	lea    ecx,[r14+r13*2]
  dc:	43 8d 14 6e          	lea    edx,[r14+r13*2]
  e0:	47 8d 04 6e          	lea    r8d,[r14+r13*2]
  e4:	62 92 fd 49 a3 04 36 	vscatterqpd QWORD PTR [r14+zmm14*1]{k1},zmm0

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;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VXORPS ZMM14, ZMM14, ZMM14

Show nanoBench command
Results:
- Instructions retired: 58.0
- Core cycles: 20.62
- Reference cycles: 14.12
- UOPS_PORT_6: 19.61
- UOPS_PORT_0: 19.74
- UOPS_PORT_5B: 20.22
- UOPS_PORT_5B>=2: 0.59

With blocking instructions for ports {'0', '1', '5', '6', 'B'}:

Code:

   0:	45 8d 06             	lea    r8d,[r14]
   3:	45 8d 0e             	lea    r9d,[r14]
   6:	45 8d 16             	lea    r10d,[r14]
   9:	45 8d 1e             	lea    r11d,[r14]
   c:	45 8d 26             	lea    r12d,[r14]
   f:	41 8d 1e             	lea    ebx,[r14]
  12:	41 8d 0e             	lea    ecx,[r14]
  15:	41 8d 16             	lea    edx,[r14]
  18:	45 8d 06             	lea    r8d,[r14]
  1b:	45 8d 0e             	lea    r9d,[r14]
  1e:	45 8d 16             	lea    r10d,[r14]
  21:	45 8d 1e             	lea    r11d,[r14]
  24:	45 8d 26             	lea    r12d,[r14]
  27:	41 8d 1e             	lea    ebx,[r14]
  2a:	41 8d 0e             	lea    ecx,[r14]
  2d:	41 8d 16             	lea    edx,[r14]
  30:	45 8d 06             	lea    r8d,[r14]
  33:	45 8d 0e             	lea    r9d,[r14]
  36:	45 8d 16             	lea    r10d,[r14]
  39:	45 8d 1e             	lea    r11d,[r14]
  3c:	45 8d 26             	lea    r12d,[r14]
  3f:	41 8d 1e             	lea    ebx,[r14]
  42:	41 8d 0e             	lea    ecx,[r14]
  45:	41 8d 16             	lea    edx,[r14]
  48:	45 8d 06             	lea    r8d,[r14]
  4b:	45 8d 0e             	lea    r9d,[r14]
  4e:	45 8d 16             	lea    r10d,[r14]
  51:	45 8d 1e             	lea    r11d,[r14]
  54:	45 8d 26             	lea    r12d,[r14]
  57:	41 8d 1e             	lea    ebx,[r14]
  5a:	41 8d 0e             	lea    ecx,[r14]
  5d:	41 8d 16             	lea    edx,[r14]
  60:	45 8d 06             	lea    r8d,[r14]
  63:	45 8d 0e             	lea    r9d,[r14]
  66:	45 8d 16             	lea    r10d,[r14]
  69:	45 8d 1e             	lea    r11d,[r14]
  6c:	45 8d 26             	lea    r12d,[r14]
  6f:	41 8d 1e             	lea    ebx,[r14]
  72:	41 8d 0e             	lea    ecx,[r14]
  75:	41 8d 16             	lea    edx,[r14]
  78:	45 8d 06             	lea    r8d,[r14]
  7b:	45 8d 0e             	lea    r9d,[r14]
  7e:	45 8d 16             	lea    r10d,[r14]
  81:	45 8d 1e             	lea    r11d,[r14]
  84:	45 8d 26             	lea    r12d,[r14]
  87:	41 8d 1e             	lea    ebx,[r14]
  8a:	41 8d 0e             	lea    ecx,[r14]
  8d:	41 8d 16             	lea    edx,[r14]
  90:	45 8d 06             	lea    r8d,[r14]
  93:	45 8d 0e             	lea    r9d,[r14]
  96:	45 8d 16             	lea    r10d,[r14]
  99:	45 8d 1e             	lea    r11d,[r14]
  9c:	45 8d 26             	lea    r12d,[r14]
  9f:	41 8d 1e             	lea    ebx,[r14]
  a2:	41 8d 0e             	lea    ecx,[r14]
  a5:	41 8d 16             	lea    edx,[r14]
  a8:	45 8d 06             	lea    r8d,[r14]
  ab:	45 8d 0e             	lea    r9d,[r14]
  ae:	45 8d 16             	lea    r10d,[r14]
  b1:	45 8d 1e             	lea    r11d,[r14]
  b4:	45 8d 26             	lea    r12d,[r14]
  b7:	41 8d 1e             	lea    ebx,[r14]
  ba:	41 8d 0e             	lea    ecx,[r14]
  bd:	41 8d 16             	lea    edx,[r14]
  c0:	45 8d 06             	lea    r8d,[r14]
  c3:	45 8d 0e             	lea    r9d,[r14]
  c6:	45 8d 16             	lea    r10d,[r14]
  c9:	45 8d 1e             	lea    r11d,[r14]
  cc:	45 8d 26             	lea    r12d,[r14]
  cf:	41 8d 1e             	lea    ebx,[r14]
  d2:	41 8d 0e             	lea    ecx,[r14]
  d5:	41 8d 16             	lea    edx,[r14]
  d8:	45 8d 06             	lea    r8d,[r14]
  db:	45 8d 0e             	lea    r9d,[r14]
  de:	45 8d 16             	lea    r10d,[r14]
  e1:	45 8d 1e             	lea    r11d,[r14]
  e4:	45 8d 26             	lea    r12d,[r14]
  e7:	41 8d 1e             	lea    ebx,[r14]
  ea:	41 8d 0e             	lea    ecx,[r14]
  ed:	41 8d 16             	lea    edx,[r14]
  f0:	45 8d 06             	lea    r8d,[r14]
  f3:	45 8d 0e             	lea    r9d,[r14]
  f6:	45 8d 16             	lea    r10d,[r14]
  f9:	45 8d 1e             	lea    r11d,[r14]
  fc:	45 8d 26             	lea    r12d,[r14]
  ff:	41 8d 1e             	lea    ebx,[r14]
 102:	41 8d 0e             	lea    ecx,[r14]
 105:	41 8d 16             	lea    edx,[r14]
 108:	45 8d 06             	lea    r8d,[r14]
 10b:	45 8d 0e             	lea    r9d,[r14]
 10e:	45 8d 16             	lea    r10d,[r14]
 111:	45 8d 1e             	lea    r11d,[r14]
 114:	45 8d 26             	lea    r12d,[r14]
 117:	41 8d 1e             	lea    ebx,[r14]
 11a:	41 8d 0e             	lea    ecx,[r14]
 11d:	62 92 fd 49 a3 04 36 	vscatterqpd QWORD PTR [r14+zmm14*1]{k1},zmm0

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;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VXORPS ZMM14, ZMM14, ZMM14

Show nanoBench command
Results:
- Instructions retired: 96.0
- Core cycles: 25.43
- Reference cycles: 19.2
- UOPS_PORT_6: 19.53
- UOPS_PORT_0: 20.0
- UOPS_PORT_1: 19.2
- UOPS_PORT_5B: 39.25

⇨ One μop that can only use ports {'0', '1', '5', '6', 'B'}