VPERMILPS (YMM, YMM, YMM) - Latency

   0:	c4 e2 7d 0c ca       	vpermilps ymm1,ymm0,ymm2
   5:	c5 f5 c6 c1 00       	vshufpd ymm0,ymm1,ymm1,0x0
   a:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
   f:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
  14:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
  19:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0

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 YMM0, [R14];
VXORPS YMM2, YMM2, YMM2

• Instructions retired: 6.0
• Core cycles: 6.0
• Reference cycles: 5.76
• UOPS_EXECUTED.THREAD: 6.0

   0:	c4 e2 7d 0c ca       	vpermilps ymm1,ymm0,ymm2
   5:	c5 f5 c6 c1 00       	vshufpd ymm0,ymm1,ymm1,0x0
   a:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
   f:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
  14:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
  19:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0

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 YMM0, [R14];
VXORPS YMM2, YMM2, YMM2;
VPERMILPS YMM0, YMM1, YMM2;
VPERMILPS YMM2, YMM0, YMM1

• Instructions retired: 6.0
• Core cycles: 6.0
• Reference cycles: 5.87
• UOPS_EXECUTED.THREAD: 6.0

   0:	c4 e2 6d 0c c8       	vpermilps ymm1,ymm2,ymm0
   5:	c5 f5 c6 c1 00       	vshufpd ymm0,ymm1,ymm1,0x0
   a:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
   f:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
  14:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
  19:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0

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 YMM2, [R14];
VXORPS YMM0, YMM0, YMM0

• Instructions retired: 6.0
• Core cycles: 6.0
• Reference cycles: 5.81
• UOPS_EXECUTED.THREAD: 6.0

   0:	c4 e2 6d 0c c8       	vpermilps ymm1,ymm2,ymm0
   5:	c5 f5 c6 c1 00       	vshufpd ymm0,ymm1,ymm1,0x0
   a:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
   f:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
  14:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
  19:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0

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 YMM2, [R14];
VXORPS YMM0, YMM0, YMM0;
VPERMILPS YMM2, YMM0, YMM1;
VPERMILPS YMM0, YMM1, YMM2

• Instructions retired: 6.0
• Core cycles: 6.0
• Reference cycles: 5.81
• UOPS_EXECUTED.THREAD: 6.0