PCMPESTRM (XMM, XMM, I8) - Port Usage

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

Code:

   0:	66 0f f1 dc          	psllw  xmm3,xmm4
   4:	66 0f f1 ec          	psllw  xmm5,xmm4
   8:	66 0f f1 f4          	psllw  xmm6,xmm4
   c:	66 0f f1 fc          	psllw  xmm7,xmm4
  10:	66 44 0f f1 c4       	psllw  xmm8,xmm4
  15:	66 44 0f f1 cc       	psllw  xmm9,xmm4
  1a:	66 44 0f f1 d4       	psllw  xmm10,xmm4
  1f:	66 44 0f f1 dc       	psllw  xmm11,xmm4
  24:	66 44 0f f1 e4       	psllw  xmm12,xmm4
  29:	66 0f f1 dc          	psllw  xmm3,xmm4
  2d:	66 0f f1 ec          	psllw  xmm5,xmm4
  31:	66 0f f1 f4          	psllw  xmm6,xmm4
  35:	66 0f f1 fc          	psllw  xmm7,xmm4
  39:	66 44 0f f1 c4       	psllw  xmm8,xmm4
  3e:	66 0f 3a 60 ca 02    	pcmpestrm xmm1,xmm2,0x2

Init:

VZEROALL;
PXOR XMM3, XMM3;
PXOR XMM4, XMM4;
PXOR XMM5, XMM5;
PXOR XMM6, XMM6;
PXOR XMM7, XMM7;
PXOR XMM8, XMM8;
PXOR XMM9, XMM9;
PXOR XMM10, XMM10;
PXOR XMM11, XMM11;
PXOR XMM12, XMM12;
PXOR XMM1, XMM1;
PXOR XMM2, XMM2

Show nanoBench command
Results:
- MPERF: 4.94
- APERF: 7.22
- FpuPipeAssignment.Total0: 7.01
- FpuPipeAssignment.Total1: 7.07
- FpuPipeAssignment.Total2: 2.0
- FpuPipeAssignment.Total3: 1.93
- FpuPipeAssignment.Total4: 0.5
- FpuPipeAssignment.Total5: 0.5

With blocking instructions for ports {'0', '3'}:

Code:

   0:	66 0f 38 0a dc       	psignd xmm3,xmm4
   5:	66 0f 38 0a ec       	psignd xmm5,xmm4
   a:	66 0f 38 0a f4       	psignd xmm6,xmm4
   f:	66 0f 38 0a fc       	psignd xmm7,xmm4
  14:	66 44 0f 38 0a c4    	psignd xmm8,xmm4
  1a:	66 44 0f 38 0a cc    	psignd xmm9,xmm4
  20:	66 44 0f 38 0a d4    	psignd xmm10,xmm4
  26:	66 44 0f 38 0a dc    	psignd xmm11,xmm4
  2c:	66 44 0f 38 0a e4    	psignd xmm12,xmm4
  32:	66 0f 38 0a dc       	psignd xmm3,xmm4
  37:	66 0f 38 0a ec       	psignd xmm5,xmm4
  3c:	66 0f 38 0a f4       	psignd xmm6,xmm4
  41:	66 0f 38 0a fc       	psignd xmm7,xmm4
  46:	66 44 0f 38 0a c4    	psignd xmm8,xmm4
  4c:	66 0f 3a 60 ca 02    	pcmpestrm xmm1,xmm2,0x2

Init:

VZEROALL;
PXOR XMM3, XMM3;
PXOR XMM4, XMM4;
PXOR XMM5, XMM5;
PXOR XMM6, XMM6;
PXOR XMM7, XMM7;
PXOR XMM8, XMM8;
PXOR XMM9, XMM9;
PXOR XMM10, XMM10;
PXOR XMM11, XMM11;
PXOR XMM12, XMM12;
PXOR XMM1, XMM1;
PXOR XMM2, XMM2

Show nanoBench command
Results:
- MPERF: 5.7
- APERF: 8.19
- FpuPipeAssignment.Total0: 8.0
- FpuPipeAssignment.Total1: 1.0
- FpuPipeAssignment.Total2: 1.0
- FpuPipeAssignment.Total3: 8.0
- FpuPipeAssignment.Total4: 0.5
- FpuPipeAssignment.Total5: 0.5

⇨ 2 μops that can only use ports {'0', '3'}

With blocking instructions for ports {'1', '2'}:

Code:

   0:	66 0f 79 dc          	extrq  xmm3,xmm4
   4:	66 0f 79 ec          	extrq  xmm5,xmm4
   8:	66 0f 79 f4          	extrq  xmm6,xmm4
   c:	66 0f 79 fc          	extrq  xmm7,xmm4
  10:	66 44 0f 79 c4       	extrq  xmm8,xmm4
  15:	66 44 0f 79 cc       	extrq  xmm9,xmm4
  1a:	66 44 0f 79 d4       	extrq  xmm10,xmm4
  1f:	66 44 0f 79 dc       	extrq  xmm11,xmm4
  24:	66 44 0f 79 e4       	extrq  xmm12,xmm4
  29:	66 0f 79 dc          	extrq  xmm3,xmm4
  2d:	66 0f 79 ec          	extrq  xmm5,xmm4
  31:	66 0f 79 f4          	extrq  xmm6,xmm4
  35:	66 0f 79 fc          	extrq  xmm7,xmm4
  39:	66 44 0f 79 c4       	extrq  xmm8,xmm4
  3e:	66 0f 3a 60 ca 02    	pcmpestrm xmm1,xmm2,0x2

Init:

VZEROALL;
PXOR XMM4, XMM4;
PXOR XMM1, XMM1;
PXOR XMM2, XMM2

Show nanoBench command
Results:
- MPERF: 5.7
- APERF: 8.31
- FpuPipeAssignment.Total0: 1.01
- FpuPipeAssignment.Total1: 8.0
- FpuPipeAssignment.Total2: 8.0
- FpuPipeAssignment.Total3: 1.0
- FpuPipeAssignment.Total4: 0.5
- FpuPipeAssignment.Total5: 0.5

⇨ 2 μops that can only use ports {'1', '2'}

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

Code:

   0:	66 0f c2 dc 02       	cmplepd xmm3,xmm4
   5:	66 0f c2 ec 02       	cmplepd xmm5,xmm4
   a:	66 0f c2 f4 02       	cmplepd xmm6,xmm4
   f:	66 0f c2 fc 02       	cmplepd xmm7,xmm4
  14:	66 44 0f c2 c4 02    	cmplepd xmm8,xmm4
  1a:	66 44 0f c2 cc 02    	cmplepd xmm9,xmm4
  20:	66 44 0f c2 d4 02    	cmplepd xmm10,xmm4
  26:	66 44 0f c2 dc 02    	cmplepd xmm11,xmm4
  2c:	66 44 0f c2 e4 02    	cmplepd xmm12,xmm4
  32:	66 0f c2 dc 02       	cmplepd xmm3,xmm4
  37:	66 0f c2 ec 02       	cmplepd xmm5,xmm4
  3c:	66 0f c2 f4 02       	cmplepd xmm6,xmm4
  41:	66 0f c2 fc 02       	cmplepd xmm7,xmm4
  46:	66 44 0f c2 c4 02    	cmplepd xmm8,xmm4
  4c:	66 0f 3a 60 ca 02    	pcmpestrm xmm1,xmm2,0x2

Init:

VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM3, [R14];
MOVUPD XMM4, [R14];
MOVUPD XMM5, [R14];
MOVUPD XMM6, [R14];
MOVUPD XMM7, [R14];
MOVUPD XMM8, [R14];
MOVUPD XMM9, [R14];
MOVUPD XMM10, [R14];
MOVUPD XMM11, [R14];
MOVUPD XMM12, [R14];
PXOR XMM1, XMM1;
PXOR XMM2, XMM2

Show nanoBench command
Results:
- MPERF: 4.94
- APERF: 7.16
- FpuPipeAssignment.Total0: 1.99
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 7.07
- FpuPipeAssignment.Total3: 6.96
- FpuPipeAssignment.Total4: 0.5
- FpuPipeAssignment.Total5: 0.5

With blocking instructions for ports {'4', '5'}:

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:	41 0f 7e c0          	movd   r8d,mm0
  1e:	41 0f 7e c1          	movd   r9d,mm0
  22:	41 0f 7e c2          	movd   r10d,mm0
  26:	41 0f 7e c3          	movd   r11d,mm0
  2a:	41 0f 7e c4          	movd   r12d,mm0
  2e:	0f 7e c3             	movd   ebx,mm0
  31:	0f 7e c1             	movd   ecx,mm0
  34:	66 0f 3a 60 ca 02    	pcmpestrm xmm1,xmm2,0x2

Init:

PXOR MM0, MM0;
VZEROALL;
PXOR XMM1, XMM1;
PXOR XMM2, XMM2

Show nanoBench command
Results:
- MPERF: 5.7
- APERF: 8.16
- FpuPipeAssignment.Total0: 0.99
- FpuPipeAssignment.Total1: 1.0
- FpuPipeAssignment.Total2: 1.0
- FpuPipeAssignment.Total3: 1.01
- FpuPipeAssignment.Total4: 7.51
- FpuPipeAssignment.Total5: 7.49

⇨ One μop that can only use ports {'4', '5'}