VCVTPD2PS (XMM, YMM) - Port Usage

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

Code:

   0:	0f ec c1             	paddsb mm0,mm1
   3:	0f ec d1             	paddsb mm2,mm1
   6:	0f ec d9             	paddsb mm3,mm1
   9:	0f ec e1             	paddsb mm4,mm1
   c:	0f ec e9             	paddsb mm5,mm1
   f:	0f ec f1             	paddsb mm6,mm1
  12:	0f ec f9             	paddsb mm7,mm1
  15:	0f ec c1             	paddsb mm0,mm1
  18:	0f ec d1             	paddsb mm2,mm1
  1b:	0f ec d9             	paddsb mm3,mm1
  1e:	c5 fd 5a c1          	vcvtpd2ps xmm0,ymm1

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
PXOR MM0, MM0;
PXOR MM1, MM1;
PXOR MM2, MM2;
PXOR MM3, MM3;
PXOR MM4, MM4;
PXOR MM5, MM5;
PXOR MM6, MM6;
PXOR MM7, MM7;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM1, [R14]

Show nanoBench command
Results:
- MPERF: 4.44
- APERF: 5.56
- FpuPipeAssignment.Total0: 5.48
- FpuPipeAssignment.Total1: 5.52
- FpuPipeAssignment.Total2: 0.57
- FpuPipeAssignment.Total3: 0.43
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0

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

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

Code:

   0:	0f f5 c1             	pmaddwd mm0,mm1
   3:	0f f5 d1             	pmaddwd mm2,mm1
   6:	0f f5 d9             	pmaddwd mm3,mm1
   9:	0f f5 e1             	pmaddwd mm4,mm1
   c:	0f f5 e9             	pmaddwd mm5,mm1
   f:	0f f5 f1             	pmaddwd mm6,mm1
  12:	0f f5 f9             	pmaddwd mm7,mm1
  15:	0f f5 c1             	pmaddwd mm0,mm1
  18:	0f f5 d1             	pmaddwd mm2,mm1
  1b:	0f f5 d9             	pmaddwd mm3,mm1
  1e:	c5 fd 5a c1          	vcvtpd2ps xmm0,ymm1

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
PXOR MM0, MM0;
PXOR MM1, MM1;
PXOR MM2, MM2;
PXOR MM3, MM3;
PXOR MM4, MM4;
PXOR MM5, MM5;
PXOR MM6, MM6;
PXOR MM7, MM7;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM1, [R14]

Show nanoBench command
Results:
- MPERF: 4.81
- APERF: 6.05
- FpuPipeAssignment.Total0: 4.85
- FpuPipeAssignment.Total1: 1.0
- FpuPipeAssignment.Total2: 1.0
- FpuPipeAssignment.Total3: 5.15
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0

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

Code:

   0:	0f 6b c1             	packssdw mm0,mm1
   3:	0f 6b d1             	packssdw mm2,mm1
   6:	0f 6b d9             	packssdw mm3,mm1
   9:	0f 6b e1             	packssdw mm4,mm1
   c:	0f 6b e9             	packssdw mm5,mm1
   f:	0f 6b f1             	packssdw mm6,mm1
  12:	0f 6b f9             	packssdw mm7,mm1
  15:	0f 6b c1             	packssdw mm0,mm1
  18:	0f 6b d1             	packssdw mm2,mm1
  1b:	0f 6b d9             	packssdw mm3,mm1
  1e:	c5 fd 5a c1          	vcvtpd2ps xmm0,ymm1

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
PXOR MM0, MM0;
PXOR MM1, MM1;
PXOR MM2, MM2;
PXOR MM3, MM3;
PXOR MM4, MM4;
PXOR MM5, MM5;
PXOR MM6, MM6;
PXOR MM7, MM7;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM1, [R14]

Show nanoBench command
Results:
- MPERF: 4.07
- APERF: 5.11
- FpuPipeAssignment.Total0: 0.95
- FpuPipeAssignment.Total1: 5.04
- FpuPipeAssignment.Total2: 5.06
- FpuPipeAssignment.Total3: 0.95
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0

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

Code:

   0:	c5 e1 58 d4          	vaddpd xmm2,xmm3,xmm4
   4:	c5 e1 58 ec          	vaddpd xmm5,xmm3,xmm4
   8:	c5 e1 58 f4          	vaddpd xmm6,xmm3,xmm4
   c:	c5 e1 58 fc          	vaddpd xmm7,xmm3,xmm4
  10:	c5 61 58 c4          	vaddpd xmm8,xmm3,xmm4
  14:	c5 61 58 cc          	vaddpd xmm9,xmm3,xmm4
  18:	c5 61 58 d4          	vaddpd xmm10,xmm3,xmm4
  1c:	c5 61 58 dc          	vaddpd xmm11,xmm3,xmm4
  20:	c5 61 58 e4          	vaddpd xmm12,xmm3,xmm4
  24:	c5 e1 58 d4          	vaddpd xmm2,xmm3,xmm4
  28:	c5 fd 5a c1          	vcvtpd2ps xmm0,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 XMM3, [R14];
VMOVUPD XMM4, [R14];
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM1, [R14]

Show nanoBench command
Results:
- MPERF: 4.44
- APERF: 5.58
- FpuPipeAssignment.Total0: 0.45
- FpuPipeAssignment.Total1: 0.55
- FpuPipeAssignment.Total2: 5.49
- FpuPipeAssignment.Total3: 5.51
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0

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