VMOVDQA (M256, YMM) - Latency

Experiment 1

• Instruction: VMOVDQA ymmword ptr [R14], YMM0
• Chain instructions: MOV R12, [R14];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR R14, R12; XOR R14, R12
• Chain latency: ≥7
• Code:

     0:	c4 c1 7d 7f 06       	vmovdqa YMMWORD PTR [r14],ymm0
     5:	4d 8b 26             	mov    r12,QWORD PTR [r14]
     8:	4d 63 e4             	movsxd r12,r12d
     b:	4d 63 e4             	movsxd r12,r12d
     e:	4d 63 e4             	movsxd r12,r12d
    11:	4d 63 e4             	movsxd r12,r12d
    14:	4d 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
  

• Init:

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

• Show nanoBench command
• Results:
  • MPERF: 14.0
  • APERF: 17.03
  • UOPS: 8.0

Experiment 2 (with additional nop)

• Instruction: VMOVDQA ymmword ptr [R14], YMM0
• Chain instructions: MOV R12, [R14];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR R14, R12; XOR R14, R12;nop
• Chain latency: ≥7
• Code:

     0:	c4 c1 7d 7f 06       	vmovdqa YMMWORD PTR [r14],ymm0
     5:	4d 8b 26             	mov    r12,QWORD PTR [r14]
     8:	4d 63 e4             	movsxd r12,r12d
     b:	4d 63 e4             	movsxd r12,r12d
     e:	4d 63 e4             	movsxd r12,r12d
    11:	4d 63 e4             	movsxd r12,r12d
    14:	4d 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
    1a:	90                   	nop
  

• Init:

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

• Show nanoBench command
• Results:
  • MPERF: 14.06
  • APERF: 17.2
  • UOPS: 9.0

Experiment 1

• Instruction: VMOVDQA ymmword ptr [R14+R13], YMM0
• Chain instructions: MOV R12, [R14+R13];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR R13, R12; XOR R13, R12
• Chain latency: ≥7
• Code:

     0:	c4 81 7d 7f 04 2e    	vmovdqa YMMWORD PTR [r14+r13*1],ymm0
     6:	4f 8b 24 2e          	mov    r12,QWORD PTR [r14+r13*1]
     a:	4d 63 e4             	movsxd r12,r12d
     d:	4d 63 e4             	movsxd r12,r12d
    10:	4d 63 e4             	movsxd r12,r12d
    13:	4d 63 e4             	movsxd r12,r12d
    16:	4d 31 e5             	xor    r13,r12
    19:	4d 31 e5             	xor    r13,r12
  

• Init:

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

• Show nanoBench command
• Results:
  • MPERF: 13.81
  • APERF: 17.03
  • UOPS: 8.0

Experiment 2 (with additional nop)

• Instruction: VMOVDQA ymmword ptr [R14+R13], YMM0
• Chain instructions: MOV R12, [R14+R13];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR R13, R12; XOR R13, R12;nop
• Chain latency: ≥7
• Code:

     0:	c4 81 7d 7f 04 2e    	vmovdqa YMMWORD PTR [r14+r13*1],ymm0
     6:	4f 8b 24 2e          	mov    r12,QWORD PTR [r14+r13*1]
     a:	4d 63 e4             	movsxd r12,r12d
     d:	4d 63 e4             	movsxd r12,r12d
    10:	4d 63 e4             	movsxd r12,r12d
    13:	4d 63 e4             	movsxd r12,r12d
    16:	4d 31 e5             	xor    r13,r12
    19:	4d 31 e5             	xor    r13,r12
    1c:	90                   	nop
  

• Init:

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

• Show nanoBench command
• Results:
  • MPERF: 14.06
  • APERF: 17.2
  • UOPS: 9.0

Experiment 1

• Instruction: VMOVDQA ymmword ptr [R14], YMM0
• Chain instructions: VMOVUPD XMM13, [R14];VANDPD XMM0, XMM13, XMM13;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0
• Chain latency: ≥6
• Code:

     0:	c4 c1 7d 7f 06       	vmovdqa YMMWORD PTR [r14],ymm0
     5:	c4 41 79 10 2e       	vmovupd xmm13,XMMWORD PTR [r14]
     a:	c4 c1 11 54 c5       	vandpd xmm0,xmm13,xmm13
     f:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
    13:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
    17:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
    1b:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  

• Init:

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

• Show nanoBench command
• Results:
  • MPERF: 12.15
  • APERF: 15.0
  • UOPS: 7.0