VPERMQ (YMM, M256, I8) - Port Usage

With blocking instructions for port '1':

Code:

   0:	41 0f c4 c0 02       	pinsrw mm0,r8d,0x2
   5:	41 0f c4 c8 02       	pinsrw mm1,r8d,0x2
   a:	41 0f c4 d0 02       	pinsrw mm2,r8d,0x2
   f:	41 0f c4 d8 02       	pinsrw mm3,r8d,0x2
  14:	41 0f c4 e0 02       	pinsrw mm4,r8d,0x2
  19:	41 0f c4 e8 02       	pinsrw mm5,r8d,0x2
  1e:	41 0f c4 f0 02       	pinsrw mm6,r8d,0x2
  23:	41 0f c4 f8 02       	pinsrw mm7,r8d,0x2
  28:	41 0f c4 c0 02       	pinsrw mm0,r8d,0x2
  2d:	41 0f c4 c8 02       	pinsrw mm1,r8d,0x2
  32:	c4 c3 fd 00 06 02    	vpermq ymm0,YMMWORD PTR [r14],0x2

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

Show nanoBench command
Results:
- MPERF: 9.0
- APERF: 11.12
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 10.99
- FpuPipeAssignment.Total2: 1.01
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0

⇨ One μop that can only use port '1'

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:	c4 c3 fd 00 06 02    	vpermq ymm0,YMMWORD PTR [r14],0x2

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

Show nanoBench command
Results:
- MPERF: 4.87
- APERF: 6.0
- FpuPipeAssignment.Total0: 0.93
- FpuPipeAssignment.Total1: 5.95
- FpuPipeAssignment.Total2: 5.12
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0

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 c3 fd 00 06 02    	vpermq ymm0,YMMWORD PTR [r14],0x2

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]

Show nanoBench command
Results:
- MPERF: 4.07
- APERF: 5.09
- FpuPipeAssignment.Total0: 0.46
- FpuPipeAssignment.Total1: 1.5
- FpuPipeAssignment.Total2: 5.03
- FpuPipeAssignment.Total3: 5.02
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0

With blocking instructions for ports {'0', '1', '2', '3'}:

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:	c4 c3 fd 00 06 02    	vpermq ymm0,YMMWORD PTR [r14],0x2

Init:

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

Show nanoBench command
Results:
- MPERF: 4.38
- APERF: 5.27
- FpuPipeAssignment.Total0: 4.0
- FpuPipeAssignment.Total1: 5.0
- FpuPipeAssignment.Total2: 5.0
- FpuPipeAssignment.Total3: 4.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0

⇨ One μop that can only use ports {'0', '1', '2', '3'}

With an indexed addressing mode

With blocking instructions for port '1':

Code:

   0:	41 0f c4 c0 02       	pinsrw mm0,r8d,0x2
   5:	41 0f c4 c8 02       	pinsrw mm1,r8d,0x2
   a:	41 0f c4 d0 02       	pinsrw mm2,r8d,0x2
   f:	41 0f c4 d8 02       	pinsrw mm3,r8d,0x2
  14:	41 0f c4 e0 02       	pinsrw mm4,r8d,0x2
  19:	41 0f c4 e8 02       	pinsrw mm5,r8d,0x2
  1e:	41 0f c4 f0 02       	pinsrw mm6,r8d,0x2
  23:	41 0f c4 f8 02       	pinsrw mm7,r8d,0x2
  28:	41 0f c4 c0 02       	pinsrw mm0,r8d,0x2
  2d:	41 0f c4 c8 02       	pinsrw mm1,r8d,0x2
  32:	c4 83 fd 00 04 2e 02 	vpermq ymm0,YMMWORD PTR [r14+r13*1],0x2

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;
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 9.0
- APERF: 11.12
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 10.99
- FpuPipeAssignment.Total2: 1.01
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0

⇨ One μop that can only use port '1'

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:	c4 83 fd 00 04 2e 02 	vpermq ymm0,YMMWORD PTR [r14+r13*1],0x2

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;
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 4.93
- APERF: 6.0
- FpuPipeAssignment.Total0: 0.93
- FpuPipeAssignment.Total1: 5.95
- FpuPipeAssignment.Total2: 5.12
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0

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 83 fd 00 04 2e 02 	vpermq ymm0,YMMWORD PTR [r14+r13*1],0x2

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];
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 4.07
- APERF: 5.09
- FpuPipeAssignment.Total0: 0.46
- FpuPipeAssignment.Total1: 1.5
- FpuPipeAssignment.Total2: 5.03
- FpuPipeAssignment.Total3: 5.02
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0

With blocking instructions for ports {'0', '1', '2', '3'}:

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:	c4 83 fd 00 04 2e 02 	vpermq ymm0,YMMWORD PTR [r14+r13*1],0x2

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
PXOR MM1, MM1;
VZEROALL;
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 4.38
- APERF: 5.27
- FpuPipeAssignment.Total0: 4.0
- FpuPipeAssignment.Total1: 5.0
- FpuPipeAssignment.Total2: 5.0
- FpuPipeAssignment.Total3: 4.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0

⇨ One μop that can only use ports {'0', '1', '2', '3'}