VMULPS (YMM, YMM, YMM) - Latency

   0:	c5 fc 59 ca          	vmulps ymm1,ymm0,ymm2
   4:	c5 f5 c6 c1 00       	vshufpd ymm0,ymm1,ymm1,0x0
   9:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
   e:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
  13:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
  18:	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: 8.99
• Reference cycles: 5.6
• UOPS_EXECUTED.THREAD: 6.0

   0:	c5 fc 59 ca          	vmulps ymm1,ymm0,ymm2
   4:	c5 f5 c6 c1 00       	vshufpd ymm0,ymm1,ymm1,0x0
   9:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
   e:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
  13:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
  18:	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];
VMULPS YMM0, YMM1, YMM2;
VMULPS YMM2, YMM0, YMM1

• Instructions retired: 6.0
• Core cycles: 8.99
• Reference cycles: 5.48
• UOPS_EXECUTED.THREAD: 6.0

   0:	c5 ec 59 c8          	vmulps ymm1,ymm2,ymm0
   4:	c5 f5 c6 c1 00       	vshufpd ymm0,ymm1,ymm1,0x0
   9:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
   e:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
  13:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
  18:	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: 8.99
• Reference cycles: 5.84
• UOPS_EXECUTED.THREAD: 6.0

   0:	c5 ec 59 c8          	vmulps ymm1,ymm2,ymm0
   4:	c5 f5 c6 c1 00       	vshufpd ymm0,ymm1,ymm1,0x0
   9:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
   e:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
  13:	c5 fd c6 c0 00       	vshufpd ymm0,ymm0,ymm0,0x0
  18:	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];
VMULPS YMM2, YMM0, YMM1;
VMULPS YMM0, YMM1, YMM2

• Instructions retired: 6.0
• Core cycles: 8.99
• Reference cycles: 5.84
• UOPS_EXECUTED.THREAD: 6.0