VSHUFPS (YMM, YMM, M256, I8) - Port Usage

With lfence (to avoid incorrect counts due to replays)

Code:

   0:	c4 c1 74 c6 06 02    	vshufps ymm0,ymm1,YMMWORD PTR [r14],0x2
   6:	90                   	nop
   7:	90                   	nop
   8:	90                   	nop
   9:	90                   	nop
   a:	90                   	nop
   b:	90                   	nop
   c:	90                   	nop
   d:	90                   	nop
   e:	90                   	nop
   f:	90                   	nop
  10:	0f ae e8             	lfence

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;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM1, [R14]

Show nanoBench command
Results:
- Instructions retired: 12.0
- Core cycles: 21.0
- Reference cycles: 14.48
- UOPS_DISPATCHED.INT_EU_ALL: 1.0
- UOPS_DISPATCHED.ALU: 1.0
- UOPS_DISPATCHED.LD: 1.0
- UOPS_DISPATCHED.SLOW: 0.0
- UOPS_DISPATCHED.STD: 0.0
- UOPS_DISPATCHED.SHIFT: 0.0
- UOPS_DISPATCHED.JMP: 0.0
- UOPS_DISPATCHED.STA: 0.0

No uops

With an indexed addressing mode

With lfence (to avoid incorrect counts due to replays)

Code:

   0:	c4 81 74 c6 04 2e 02 	vshufps ymm0,ymm1,YMMWORD PTR [r14+r13*1],0x2
   7:	90                   	nop
   8:	90                   	nop
   9:	90                   	nop
   a:	90                   	nop
   b:	90                   	nop
   c:	90                   	nop
   d:	90                   	nop
   e:	90                   	nop
   f:	90                   	nop
  10:	90                   	nop
  11:	0f ae e8             	lfence

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;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM1, [R14];
XOR R13, R13

Show nanoBench command
Results:
- Instructions retired: 12.0
- Core cycles: 21.0
- Reference cycles: 15.49
- UOPS_DISPATCHED.INT_EU_ALL: 1.0
- UOPS_DISPATCHED.ALU: 1.0
- UOPS_DISPATCHED.LD: 1.0
- UOPS_DISPATCHED.SLOW: 0.0
- UOPS_DISPATCHED.STD: 0.0
- UOPS_DISPATCHED.SHIFT: 0.0
- UOPS_DISPATCHED.JMP: 0.0
- UOPS_DISPATCHED.STA: 0.0

No uops