SHLX (R64, M64, R64) - Latency

   0:	c4 42 b1 f7 06       	shlx   r8,QWORD PTR [r14],r9
   5:	4d 63 c0             	movsxd r8,r8d
   8:	4d 31 c6             	xor    r14,r8
   b:	4d 31 c6             	xor    r14,r8
   e:	4d 31 c6             	xor    r14,r8
  11:	4d 31 c6             	xor    r14,r8

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

• Instructions retired: 6.0
• Core cycles: 11.0
• Reference cycles: 10.93
• UOPS_EXECUTED.CORE: 7.0

   0:	c4 02 b1 f7 04 2e    	shlx   r8,QWORD PTR [r14+r13*1],r9
   6:	4d 63 c0             	movsxd r8,r8d
   9:	4d 31 c5             	xor    r13,r8
   c:	4d 31 c5             	xor    r13,r8
   f:	4d 31 c5             	xor    r13,r8
  12:	4d 31 c5             	xor    r13,r8

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: 11.0
• Reference cycles: 10.99
• UOPS_EXECUTED.CORE: 7.0

   0:	c4 42 b1 f7 06       	shlx   r8,QWORD PTR [r14],r9
   5:	4d 63 e0             	movsxd r12,r8d
   8:	4d 63 e4             	movsxd r12,r12d
   b:	4d 63 e4             	movsxd r12,r12d
   e:	4d 63 e4             	movsxd r12,r12d
  11:	4d 89 26             	mov    QWORD PTR [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: 10.0
• Reference cycles: 9.92
• UOPS_EXECUTED.CORE: 8.0

   0:	c4 42 b9 f7 0e       	shlx   r9,QWORD PTR [r14],r8
   5:	4d 63 c1             	movsxd r8,r9d
   8:	4d 63 c0             	movsxd r8,r8d
   b:	4d 63 c0             	movsxd r8,r8d
   e:	4d 63 c0             	movsxd r8,r8d
  11:	4d 63 c0             	movsxd r8,r8d

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

• Instructions retired: 6.0
• Core cycles: 6.0
• Reference cycles: 5.97
• UOPS_EXECUTED.CORE: 7.0