VUCOMISS (XMM, M32) - Port Usage

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

Code:

   0:	c5 e9 58 cb          	vaddpd xmm1,xmm2,xmm3
   4:	c5 e9 58 e3          	vaddpd xmm4,xmm2,xmm3
   8:	c5 e9 58 eb          	vaddpd xmm5,xmm2,xmm3
   c:	c5 e9 58 f3          	vaddpd xmm6,xmm2,xmm3
  10:	c5 e9 58 fb          	vaddpd xmm7,xmm2,xmm3
  14:	c5 69 58 c3          	vaddpd xmm8,xmm2,xmm3
  18:	c5 69 58 cb          	vaddpd xmm9,xmm2,xmm3
  1c:	c5 69 58 d3          	vaddpd xmm10,xmm2,xmm3
  20:	c5 69 58 db          	vaddpd xmm11,xmm2,xmm3
  24:	c5 69 58 e3          	vaddpd xmm12,xmm2,xmm3
  28:	c4 c1 78 2e 06       	vucomiss xmm0,DWORD PTR [r14]

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 XMM0, [R14]

Show nanoBench command
Results:
- MPERF: 4.5
- APERF: 5.58
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 5.52
- FpuPipeAssignment.Total3: 5.48
- FpuPipeAssignment.Total4: 0.42
- FpuPipeAssignment.Total5: 0.58

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

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

Code:

   0:	c4 c1 79 7e c8       	vmovd  r8d,xmm1
   5:	c4 c1 79 7e c9       	vmovd  r9d,xmm1
   a:	c4 c1 79 7e ca       	vmovd  r10d,xmm1
   f:	c4 c1 79 7e cb       	vmovd  r11d,xmm1
  14:	c4 c1 79 7e cc       	vmovd  r12d,xmm1
  19:	c5 f9 7e cb          	vmovd  ebx,xmm1
  1d:	c5 f9 7e c9          	vmovd  ecx,xmm1
  21:	c5 f9 7e ca          	vmovd  edx,xmm1
  25:	c4 c1 79 7e c8       	vmovd  r8d,xmm1
  2a:	c4 c1 79 7e c9       	vmovd  r9d,xmm1
  2f:	c4 c1 78 2e 06       	vucomiss xmm0,DWORD PTR [r14]

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS XMM1, XMM1, XMM1;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
VMOVUPD XMM0, [R14]

Show nanoBench command
Results:
- MPERF: 8.26
- APERF: 10.09
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.51
- FpuPipeAssignment.Total3: 0.49
- FpuPipeAssignment.Total4: 5.52
- FpuPipeAssignment.Total5: 5.48

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

With an indexed addressing mode

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

Code:

   0:	c5 e9 58 cb          	vaddpd xmm1,xmm2,xmm3
   4:	c5 e9 58 e3          	vaddpd xmm4,xmm2,xmm3
   8:	c5 e9 58 eb          	vaddpd xmm5,xmm2,xmm3
   c:	c5 e9 58 f3          	vaddpd xmm6,xmm2,xmm3
  10:	c5 e9 58 fb          	vaddpd xmm7,xmm2,xmm3
  14:	c5 69 58 c3          	vaddpd xmm8,xmm2,xmm3
  18:	c5 69 58 cb          	vaddpd xmm9,xmm2,xmm3
  1c:	c5 69 58 d3          	vaddpd xmm10,xmm2,xmm3
  20:	c5 69 58 db          	vaddpd xmm11,xmm2,xmm3
  24:	c5 69 58 e3          	vaddpd xmm12,xmm2,xmm3
  28:	c4 81 78 2e 04 2e    	vucomiss xmm0,DWORD PTR [r14+r13*1]

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 XMM0, [R14];
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 4.56
- APERF: 5.58
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 5.52
- FpuPipeAssignment.Total3: 5.48
- FpuPipeAssignment.Total4: 0.42
- FpuPipeAssignment.Total5: 0.58

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

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

Code:

   0:	c4 c1 79 7e c8       	vmovd  r8d,xmm1
   5:	c4 c1 79 7e c9       	vmovd  r9d,xmm1
   a:	c4 c1 79 7e ca       	vmovd  r10d,xmm1
   f:	c4 c1 79 7e cb       	vmovd  r11d,xmm1
  14:	c4 c1 79 7e cc       	vmovd  r12d,xmm1
  19:	c5 f9 7e cb          	vmovd  ebx,xmm1
  1d:	c5 f9 7e c9          	vmovd  ecx,xmm1
  21:	c5 f9 7e ca          	vmovd  edx,xmm1
  25:	c4 c1 79 7e c8       	vmovd  r8d,xmm1
  2a:	c4 c1 79 7e c9       	vmovd  r9d,xmm1
  2f:	c4 81 78 2e 04 2e    	vucomiss xmm0,DWORD PTR [r14+r13*1]

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS XMM1, XMM1, XMM1;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
VMOVUPD XMM0, [R14];
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 8.14
- APERF: 10.09
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.54
- FpuPipeAssignment.Total3: 0.46
- FpuPipeAssignment.Total4: 5.47
- FpuPipeAssignment.Total5: 5.53

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