VMOVDQA (YMM, M256) - Latency

   0:	c4 c1 7d 6f 06       	vmovdqa ymm0,YMMWORD PTR [r14]
   5:	c4 c1 f9 7e c4       	vmovq  r12,xmm0
   a:	4d 31 e6             	xor    r14,r12
   d:	4d 31 e6             	xor    r14,r12
  10:	4d 31 e6             	xor    r14,r12
  13:	4d 31 e6             	xor    r14,r12

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

• Instructions retired: 6.0
• Core cycles: 12.0
• Reference cycles: 12.05
• UOPS_EXECUTED.CORE: 6.0

   0:	c4 81 7d 6f 04 2e    	vmovdqa ymm0,YMMWORD PTR [r14+r13*1]
   6:	c4 c1 f9 7e c4       	vmovq  r12,xmm0
   b:	4d 31 e5             	xor    r13,r12
   e:	4d 31 e5             	xor    r13,r12
  11:	4d 31 e5             	xor    r13,r12
  14:	4d 31 e5             	xor    r13,r12

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

• Instructions retired: 6.0
• Core cycles: 12.0
• Reference cycles: 12.0
• UOPS_EXECUTED.CORE: 6.0

   0:	c4 c1 7d 6f 06       	vmovdqa ymm0,YMMWORD PTR [r14]
   5:	c5 7d c6 e8 00       	vshufpd ymm13,ymm0,ymm0,0x0
   a:	c4 41 15 c6 ed 00    	vshufpd ymm13,ymm13,ymm13,0x0
  10:	c4 41 15 c6 ed 00    	vshufpd ymm13,ymm13,ymm13,0x0
  16:	c4 41 15 c6 ed 00    	vshufpd ymm13,ymm13,ymm13,0x0
  1c:	c4 41 15 c6 ed 00    	vshufpd ymm13,ymm13,ymm13,0x0
  22:	c4 41 7d 11 2e       	vmovupd YMMWORD PTR [r14],ymm13

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

• Instructions retired: 7.0
• Core cycles: 12.0
• Reference cycles: 12.05
• UOPS_EXECUTED.CORE: 8.0