PCLMULQDQ (XMM, XMM, I8) - Port Usage

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

Code:

   0:	66 0f 38 de d3       	aesdec xmm2,xmm3
   5:	66 0f 38 de e3       	aesdec xmm4,xmm3
   a:	66 0f 38 de eb       	aesdec xmm5,xmm3
   f:	66 0f 38 de f3       	aesdec xmm6,xmm3
  14:	66 0f 38 de fb       	aesdec xmm7,xmm3
  19:	66 44 0f 38 de c3    	aesdec xmm8,xmm3
  1f:	66 44 0f 38 de cb    	aesdec xmm9,xmm3
  25:	66 44 0f 38 de d3    	aesdec xmm10,xmm3
  2b:	66 44 0f 38 de db    	aesdec xmm11,xmm3
  31:	66 44 0f 38 de e3    	aesdec xmm12,xmm3
  37:	66 0f 38 de d3       	aesdec xmm2,xmm3
  3c:	66 0f 38 de e3       	aesdec xmm4,xmm3
  41:	66 0f 38 de eb       	aesdec xmm5,xmm3
  46:	66 0f 38 de f3       	aesdec xmm6,xmm3
  4b:	66 0f 38 de fb       	aesdec xmm7,xmm3
  50:	66 44 0f 38 de c3    	aesdec xmm8,xmm3
  56:	66 0f 3a 44 c1 02    	pclmullqhqdq xmm0,xmm1

Init:

VZEROALL;
PXOR XMM2, XMM2;
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 XMM0, XMM0;
PXOR XMM1, XMM1

Show nanoBench command
Results:
- MPERF: 7.52
- APERF: 8.58
- FpuPipeAssignment.Total0: 8.51
- FpuPipeAssignment.Total1: 8.49
- FpuPipeAssignment.Total2: 1.0
- FpuPipeAssignment.Total3: 1.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0

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

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

Code:

   0:	66 0f 79 d3          	extrq  xmm2,xmm3
   4:	66 0f 79 e3          	extrq  xmm4,xmm3
   8:	66 0f 79 eb          	extrq  xmm5,xmm3
   c:	66 0f 79 f3          	extrq  xmm6,xmm3
  10:	66 0f 79 fb          	extrq  xmm7,xmm3
  14:	66 44 0f 79 c3       	extrq  xmm8,xmm3
  19:	66 44 0f 79 cb       	extrq  xmm9,xmm3
  1e:	66 44 0f 79 d3       	extrq  xmm10,xmm3
  23:	66 44 0f 79 db       	extrq  xmm11,xmm3
  28:	66 44 0f 79 e3       	extrq  xmm12,xmm3
  2d:	66 0f 79 d3          	extrq  xmm2,xmm3
  31:	66 0f 79 e3          	extrq  xmm4,xmm3
  35:	66 0f 79 eb          	extrq  xmm5,xmm3
  39:	66 0f 79 f3          	extrq  xmm6,xmm3
  3d:	66 0f 79 fb          	extrq  xmm7,xmm3
  41:	66 44 0f 79 c3       	extrq  xmm8,xmm3
  46:	66 0f 3a 44 c1 02    	pclmullqhqdq xmm0,xmm1

Init:

VZEROALL;
PXOR XMM3, XMM3;
PXOR XMM0, XMM0;
PXOR XMM1, XMM1

Show nanoBench command
Results:
- MPERF: 7.05
- APERF: 8.1
- FpuPipeAssignment.Total0: 0.99
- FpuPipeAssignment.Total1: 8.02
- FpuPipeAssignment.Total2: 8.04
- FpuPipeAssignment.Total3: 1.96
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0

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

Code:

   0:	66 0f 58 d3          	addpd  xmm2,xmm3
   4:	66 0f 58 e3          	addpd  xmm4,xmm3
   8:	66 0f 58 eb          	addpd  xmm5,xmm3
   c:	66 0f 58 f3          	addpd  xmm6,xmm3
  10:	66 0f 58 fb          	addpd  xmm7,xmm3
  14:	66 44 0f 58 c3       	addpd  xmm8,xmm3
  19:	66 44 0f 58 cb       	addpd  xmm9,xmm3
  1e:	66 44 0f 58 d3       	addpd  xmm10,xmm3
  23:	66 44 0f 58 db       	addpd  xmm11,xmm3
  28:	66 44 0f 58 e3       	addpd  xmm12,xmm3
  2d:	66 0f 58 d3          	addpd  xmm2,xmm3
  31:	66 0f 58 e3          	addpd  xmm4,xmm3
  35:	66 0f 58 eb          	addpd  xmm5,xmm3
  39:	66 0f 58 f3          	addpd  xmm6,xmm3
  3d:	66 0f 58 fb          	addpd  xmm7,xmm3
  41:	66 44 0f 58 c3       	addpd  xmm8,xmm3
  46:	66 0f 3a 44 c1 02    	pclmullqhqdq xmm0,xmm1

Init:

VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM2, [R14];
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 XMM0, XMM0;
PXOR XMM1, XMM1

Show nanoBench command
Results:
- MPERF: 7.91
- APERF: 9.06
- FpuPipeAssignment.Total0: 0.49
- FpuPipeAssignment.Total1: 1.46
- FpuPipeAssignment.Total2: 8.96
- FpuPipeAssignment.Total3: 8.09
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0

⇨ One μop that can only use ports {'2', '3'}

With blocking instructions for ports {'1', '2', '3'}:

Code:

   0:	f2 0f 12 d3          	movddup xmm2,xmm3
   4:	f2 0f 12 e3          	movddup xmm4,xmm3
   8:	f2 0f 12 eb          	movddup xmm5,xmm3
   c:	f2 0f 12 f3          	movddup xmm6,xmm3
  10:	f2 0f 12 fb          	movddup xmm7,xmm3
  14:	f2 44 0f 12 c3       	movddup xmm8,xmm3
  19:	f2 44 0f 12 cb       	movddup xmm9,xmm3
  1e:	f2 44 0f 12 d3       	movddup xmm10,xmm3
  23:	f2 44 0f 12 db       	movddup xmm11,xmm3
  28:	f2 44 0f 12 e3       	movddup xmm12,xmm3
  2d:	f2 0f 12 d3          	movddup xmm2,xmm3
  31:	f2 0f 12 e3          	movddup xmm4,xmm3
  35:	f2 0f 12 eb          	movddup xmm5,xmm3
  39:	f2 0f 12 f3          	movddup xmm6,xmm3
  3d:	f2 0f 12 fb          	movddup xmm7,xmm3
  41:	f2 44 0f 12 c3       	movddup xmm8,xmm3
  46:	f2 44 0f 12 cb       	movddup xmm9,xmm3
  4b:	f2 44 0f 12 d3       	movddup xmm10,xmm3
  50:	f2 44 0f 12 db       	movddup xmm11,xmm3
  55:	f2 44 0f 12 e3       	movddup xmm12,xmm3
  5a:	f2 0f 12 d3          	movddup xmm2,xmm3
  5e:	f2 0f 12 e3          	movddup xmm4,xmm3
  62:	f2 0f 12 eb          	movddup xmm5,xmm3
  66:	f2 0f 12 f3          	movddup xmm6,xmm3
  6a:	66 0f 3a 44 c1 02    	pclmullqhqdq xmm0,xmm1

Init:

VZEROALL;
PXOR XMM3, XMM3;
PXOR XMM0, XMM0;
PXOR XMM1, XMM1

Show nanoBench command
Results:
- MPERF: 7.91
- APERF: 9.08
- FpuPipeAssignment.Total0: 0.89
- FpuPipeAssignment.Total1: 9.0
- FpuPipeAssignment.Total2: 8.19
- FpuPipeAssignment.Total3: 8.93
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0

⇨ One μop that can only use ports {'1', '2', '3'}