VSHUFPS (YMM, YMM, YMM, I8) - Latency

   0:	c5 fc c6 ca 02       	vshufps ymm1,ymm0,ymm2,0x2
   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];
VMOVUPD YMM2, [R14]

• Instructions retired: 6.0
• Core cycles: 7.1
• Reference cycles: 7.68
• UOPS_RETIRED.ALL: 12.0

   0:	c5 fc c6 ca 02       	vshufps ymm1,ymm0,ymm2,0x2
   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];
VMOVUPD YMM2, [R14];
VSHUFPS YMM0, YMM1, YMM2, 2;
VSHUFPS YMM2, YMM0, YMM1, 2

• Instructions retired: 6.0
• Core cycles: 7.1
• Reference cycles: 7.52
• UOPS_RETIRED.ALL: 12.0

   0:	c5 ec c6 c8 02       	vshufps ymm1,ymm2,ymm0,0x2
   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];
VMOVUPD YMM0, [R14]

• Instructions retired: 6.0
• Core cycles: 7.22
• Reference cycles: 7.04
• UOPS_RETIRED.ALL: 12.0

   0:	c5 ec c6 c8 02       	vshufps ymm1,ymm2,ymm0,0x2
   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];
VMOVUPD YMM0, [R14];
VSHUFPS YMM2, YMM0, YMM1, 2;
VSHUFPS YMM0, YMM1, YMM2, 2

• Instructions retired: 6.0
• Core cycles: 7.25
• Reference cycles: 7.84
• UOPS_RETIRED.ALL: 12.0