VPGATHERDD (YMM, VSIB_YMM, YMM) - Port Usage

With blocking instructions for port '4':

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:	c4 82 75 90 04 36    	vpgatherdd ymm0,DWORD PTR [r14+ymm14*1],ymm1

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 YMM14, YMM14, YMM14

Show nanoBench command
Results:
- Instructions retired: 14.0
- Core cycles: 14.33
- Reference cycles: 15.0
- UOPS_PORT_4: 14.0

⇨ One μop that can only use port '4'

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:	c4 82 75 90 04 36    	vpgatherdd ymm0,DWORD PTR [r14+ymm14*1],ymm1

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 YMM14, YMM14, YMM14

Show nanoBench command
Results:
- Instructions retired: 14.0
- Core cycles: 16.26
- Reference cycles: 17.11
- UOPS_PORT_5: 15.99

⇨ 3 μops that can only use port '5'

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

Code:

   0:	c4 e2 e1 98 d4       	vfmadd132pd xmm2,xmm3,xmm4
   5:	c4 e2 e1 98 ec       	vfmadd132pd xmm5,xmm3,xmm4
   a:	c4 e2 e1 98 f4       	vfmadd132pd xmm6,xmm3,xmm4
   f:	c4 e2 e1 98 fc       	vfmadd132pd xmm7,xmm3,xmm4
  14:	c4 62 e1 98 c4       	vfmadd132pd xmm8,xmm3,xmm4
  19:	c4 62 e1 98 cc       	vfmadd132pd xmm9,xmm3,xmm4
  1e:	c4 62 e1 98 d4       	vfmadd132pd xmm10,xmm3,xmm4
  23:	c4 62 e1 98 dc       	vfmadd132pd xmm11,xmm3,xmm4
  28:	c4 62 e1 98 e4       	vfmadd132pd xmm12,xmm3,xmm4
  2d:	c4 e2 e1 98 d4       	vfmadd132pd xmm2,xmm3,xmm4
  32:	c4 e2 e1 98 ec       	vfmadd132pd xmm5,xmm3,xmm4
  37:	c4 e2 e1 98 f4       	vfmadd132pd xmm6,xmm3,xmm4
  3c:	c4 e2 e1 98 fc       	vfmadd132pd xmm7,xmm3,xmm4
  41:	c4 62 e1 98 c4       	vfmadd132pd xmm8,xmm3,xmm4
  46:	c4 62 e1 98 cc       	vfmadd132pd xmm9,xmm3,xmm4
  4b:	c4 62 e1 98 d4       	vfmadd132pd xmm10,xmm3,xmm4
  50:	c4 62 e1 98 dc       	vfmadd132pd xmm11,xmm3,xmm4
  55:	c4 62 e1 98 e4       	vfmadd132pd xmm12,xmm3,xmm4
  5a:	c4 e2 e1 98 d4       	vfmadd132pd xmm2,xmm3,xmm4
  5f:	c4 e2 e1 98 ec       	vfmadd132pd xmm5,xmm3,xmm4
  64:	c4 e2 e1 98 f4       	vfmadd132pd xmm6,xmm3,xmm4
  69:	c4 e2 e1 98 fc       	vfmadd132pd xmm7,xmm3,xmm4
  6e:	c4 62 e1 98 c4       	vfmadd132pd xmm8,xmm3,xmm4
  73:	c4 62 e1 98 cc       	vfmadd132pd xmm9,xmm3,xmm4
  78:	c4 62 e1 98 d4       	vfmadd132pd xmm10,xmm3,xmm4
  7d:	c4 62 e1 98 dc       	vfmadd132pd xmm11,xmm3,xmm4
  82:	c4 82 75 90 04 36    	vpgatherdd ymm0,DWORD PTR [r14+ymm14*1],ymm1

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 XMM2, [R14];
VMOVUPD XMM3, [R14];
VMOVUPD XMM4, [R14];
VMOVUPD XMM5, [R14];
VMOVUPD XMM6, [R14];
VMOVUPD XMM7, [R14];
VMOVUPD XMM8, [R14];
VMOVUPD XMM9, [R14];
VMOVUPD XMM10, [R14];
VMOVUPD XMM11, [R14];
VMOVUPD XMM12, [R14];
VXORPS YMM0, YMM0, YMM0;
VXORPS YMM1, YMM1, YMM1;
VXORPS YMM14, YMM14, YMM14

Show nanoBench command
Results:
- Instructions retired: 27.0
- Core cycles: 17.39
- Reference cycles: 18.25
- UOPS_PORT_1: 13.03
- UOPS_PORT_0: 12.97

With blocking instructions for ports {'2', '3'}:

Code:

   0:	45 8b 46 40          	mov    r8d,DWORD PTR [r14+0x40]
   4:	45 8b 4e 44          	mov    r9d,DWORD PTR [r14+0x44]
   8:	45 8b 56 48          	mov    r10d,DWORD PTR [r14+0x48]
   c:	45 8b 5e 4c          	mov    r11d,DWORD PTR [r14+0x4c]
  10:	45 8b 66 50          	mov    r12d,DWORD PTR [r14+0x50]
  14:	41 8b 5e 54          	mov    ebx,DWORD PTR [r14+0x54]
  18:	41 8b 4e 58          	mov    ecx,DWORD PTR [r14+0x58]
  1c:	41 8b 56 5c          	mov    edx,DWORD PTR [r14+0x5c]
  20:	45 8b 46 40          	mov    r8d,DWORD PTR [r14+0x40]
  24:	45 8b 4e 44          	mov    r9d,DWORD PTR [r14+0x44]
  28:	45 8b 56 48          	mov    r10d,DWORD PTR [r14+0x48]
  2c:	45 8b 5e 4c          	mov    r11d,DWORD PTR [r14+0x4c]
  30:	45 8b 66 50          	mov    r12d,DWORD PTR [r14+0x50]
  34:	41 8b 5e 54          	mov    ebx,DWORD PTR [r14+0x54]
  38:	41 8b 4e 58          	mov    ecx,DWORD PTR [r14+0x58]
  3c:	41 8b 56 5c          	mov    edx,DWORD PTR [r14+0x5c]
  40:	45 8b 46 40          	mov    r8d,DWORD PTR [r14+0x40]
  44:	45 8b 4e 44          	mov    r9d,DWORD PTR [r14+0x44]
  48:	45 8b 56 48          	mov    r10d,DWORD PTR [r14+0x48]
  4c:	45 8b 5e 4c          	mov    r11d,DWORD PTR [r14+0x4c]
  50:	45 8b 66 50          	mov    r12d,DWORD PTR [r14+0x50]
  54:	41 8b 5e 54          	mov    ebx,DWORD PTR [r14+0x54]
  58:	41 8b 4e 58          	mov    ecx,DWORD PTR [r14+0x58]
  5c:	41 8b 56 5c          	mov    edx,DWORD PTR [r14+0x5c]
  60:	45 8b 46 40          	mov    r8d,DWORD PTR [r14+0x40]
  64:	45 8b 4e 44          	mov    r9d,DWORD PTR [r14+0x44]
  68:	c4 82 75 90 04 36    	vpgatherdd ymm0,DWORD PTR [r14+ymm14*1],ymm1

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 YMM14, YMM14, YMM14

Show nanoBench command
Results:
- Instructions retired: 27.0
- Core cycles: 18.43
- Reference cycles: 19.47
- UOPS_PORT_2: 17.0
- UOPS_PORT_3: 17.0

⇨ 8 μops that can only use ports {'2', '3'}

With blocking instructions for ports {'0', '1', '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:	c4 82 75 90 04 36    	vpgatherdd ymm0,DWORD PTR [r14+ymm14*1],ymm1

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
PXOR MM1, MM1;
VZEROALL;
VXORPS YMM0, YMM0, YMM0;
VXORPS YMM1, YMM1, YMM1;
VXORPS YMM14, YMM14, YMM14

Show nanoBench command
Results:
- Instructions retired: 40.0
- Core cycles: 16.81
- Reference cycles: 17.6
- UOPS_PORT_1: 14.32
- UOPS_PORT_0: 14.4
- UOPS_PORT_5: 14.24

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