VMOVD (XMM, R32) - Latency

Experiment 1

• Instruction: VMOVD XMM0, R8D
• Chain instruction: VCVTSD2SI R8D, XMM0
• Chain latency: ≥1
• Code:

     0:	c4 c1 79 6e c0       	vmovd  xmm0,r8d
     5:	c5 7b 2d c0          	vcvtsd2si r8d,xmm0
  

• Init:

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

• Show nanoBench command
• Results:
  • MPERF: 7.76
  • APERF: 9.0
  • UOPS: 3.0

Experiment 2

• Instruction: VMOVD XMM0, R8D
• Chain instruction: VCVTSD2SI R8, XMM0
• Chain latency: ≥1
• Code:

     0:	c4 c1 79 6e c0       	vmovd  xmm0,r8d
     5:	c4 61 fb 2d c0       	vcvtsd2si r8,xmm0
  

• Init:

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

• Show nanoBench command
• Results:
  • MPERF: 7.68
  • APERF: 9.0
  • UOPS: 3.0

Experiment 3

• Instruction: VMOVD XMM0, R8D
• Chain instruction: VCVTSS2SI R8D, XMM0
• Chain latency: ≥1
• Code:

     0:	c4 c1 79 6e c0       	vmovd  xmm0,r8d
     5:	c5 7a 2d c0          	vcvtss2si r8d,xmm0
  

• Init:

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

• Show nanoBench command
• Results:
  • MPERF: 7.76
  • APERF: 9.0
  • UOPS: 3.0

Experiment 4

• Instruction: VMOVD XMM0, R8D
• Chain instruction: VCVTSS2SI R8, XMM0
• Chain latency: ≥1
• Code:

     0:	c4 c1 79 6e c0       	vmovd  xmm0,r8d
     5:	c4 61 fa 2d c0       	vcvtss2si r8,xmm0
  

• Init:

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

• Show nanoBench command
• Results:
  • MPERF: 7.76
  • APERF: 9.0
  • UOPS: 3.0

Experiment 5

• Instruction: VMOVD XMM0, R8D
• Chain instruction: VCVTTSD2SI R8D, XMM0
• Chain latency: ≥1
• Code:

     0:	c4 c1 79 6e c0       	vmovd  xmm0,r8d
     5:	c5 7b 2c c0          	vcvttsd2si r8d,xmm0
  

• Init:

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

• Show nanoBench command
• Results:
  • MPERF: 7.91
  • APERF: 9.0
  • UOPS: 3.0

Experiment 6

• Instruction: VMOVD XMM0, R8D
• Chain instruction: VCVTTSD2SI R8, XMM0
• Chain latency: ≥1
• Code:

     0:	c4 c1 79 6e c0       	vmovd  xmm0,r8d
     5:	c4 61 fb 2c c0       	vcvttsd2si r8,xmm0
  

• Init:

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

• Show nanoBench command
• Results:
  • MPERF: 7.68
  • APERF: 9.0
  • UOPS: 3.0

Experiment 7

• Instruction: VMOVD XMM0, R8D
• Chain instruction: VCVTTSS2SI R8D, XMM0
• Chain latency: ≥1
• Code:

     0:	c4 c1 79 6e c0       	vmovd  xmm0,r8d
     5:	c5 7a 2c c0          	vcvttss2si r8d,xmm0
  

• Init:

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

• Show nanoBench command
• Results:
  • MPERF: 7.83
  • APERF: 9.0
  • UOPS: 3.0

Experiment 8

• Instruction: VMOVD XMM0, R8D
• Chain instruction: VCVTTSS2SI R8, XMM0
• Chain latency: ≥1
• Code:

     0:	c4 c1 79 6e c0       	vmovd  xmm0,r8d
     5:	c4 61 fa 2c c0       	vcvttss2si r8,xmm0
  

• Init:

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

• Show nanoBench command
• Results:
  • MPERF: 7.68
  • APERF: 9.0
  • UOPS: 3.0

Experiment 9

• Instruction: VMOVD XMM0, R8D
• Chain instruction: VEXTRACTPS R8D, XMM0, 2
• Chain latency: ≥1
• Code:

     0:	c4 c1 79 6e c0       	vmovd  xmm0,r8d
     5:	c4 c3 79 17 c0 02    	vextractps r8d,xmm0,0x2
  

• Init:

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

• Show nanoBench command
• Results:
  • MPERF: 6.03
  • APERF: 7.0
  • UOPS: 3.0

Experiment 10

• Instruction: VMOVD XMM0, R8D
• Chain instruction: VMOVD R8D, XMM0
• Chain latency: ≥1
• Code:

     0:	c4 c1 79 6e c0       	vmovd  xmm0,r8d
     5:	c4 c1 79 7e c0       	vmovd  r8d,xmm0
  

• Init:

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

• Show nanoBench command
• Results:
  • MPERF: 5.17
  • APERF: 6.0
  • UOPS: 2.0

Experiment 11

• Instruction: VMOVD XMM0, R8D
• Chain instruction: VMOVMSKPD R8D, XMM0
• Chain latency: ≥1
• Code:

     0:	c4 c1 79 6e c0       	vmovd  xmm0,r8d
     5:	c5 79 50 c0          	vmovmskpd r8d,xmm0
  

• Init:

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

• Show nanoBench command
• Results:
  • MPERF: 5.17
  • APERF: 6.0
  • UOPS: 2.0

Experiment 12

• Instruction: VMOVD XMM0, R8D
• Chain instruction: VMOVMSKPS R8D, XMM0
• Chain latency: ≥1
• Code:

     0:	c4 c1 79 6e c0       	vmovd  xmm0,r8d
     5:	c5 78 50 c0          	vmovmskps r8d,xmm0
  

• Init:

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

• Show nanoBench command
• Results:
  • MPERF: 5.17
  • APERF: 6.0
  • UOPS: 2.0

Experiment 13

• Instruction: VMOVD XMM0, R8D
• Chain instruction: VMOVQ R8, XMM0
• Chain latency: ≥1
• Code:

     0:	c4 c1 79 6e c0       	vmovd  xmm0,r8d
     5:	c4 c1 f9 7e c0       	vmovq  r8,xmm0
  

• Init:

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

• Show nanoBench command
• Results:
  • MPERF: 5.17
  • APERF: 6.0
  • UOPS: 2.0

Experiment 14

• Instruction: VMOVD XMM0, R8D
• Chain instruction: VPEXTRB R8D, XMM0, 2
• Chain latency: ≥1
• Code:

     0:	c4 c1 79 6e c0       	vmovd  xmm0,r8d
     5:	c4 c3 79 14 c0 02    	vpextrb r8d,xmm0,0x2
  

• Init:

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

• Show nanoBench command
• Results:
  • MPERF: 6.82
  • APERF: 8.0
  • UOPS: 3.0

Experiment 15

• Instruction: VMOVD XMM0, R8D
• Chain instruction: VPEXTRD R8D, XMM0, 2
• Chain latency: ≥1
• Code:

     0:	c4 c1 79 6e c0       	vmovd  xmm0,r8d
     5:	c4 c3 79 16 c0 02    	vpextrd r8d,xmm0,0x2
  

• Init:

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

• Show nanoBench command
• Results:
  • MPERF: 6.03
  • APERF: 7.0
  • UOPS: 3.0

Experiment 16

• Instruction: VMOVD XMM0, R8D
• Chain instruction: VPEXTRQ R8, XMM0, 2
• Chain latency: ≥1
• Code:

     0:	c4 c1 79 6e c0       	vmovd  xmm0,r8d
     5:	c4 c3 f9 16 c0 02    	vpextrq r8,xmm0,0x2
  

• Init:

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

• Show nanoBench command
• Results:
  • MPERF: 5.95
  • APERF: 7.0
  • UOPS: 3.0

Experiment 17

• Instruction: VMOVD XMM0, R8D
• Chain instruction: VPEXTRW R8D, XMM0, 2
• Chain latency: ≥1
• Code:

     0:	c4 c1 79 6e c0       	vmovd  xmm0,r8d
     5:	c5 79 c5 c0 02       	vpextrw r8d,xmm0,0x2
  

• Init:

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

• Show nanoBench command
• Results:
  • MPERF: 6.03
  • APERF: 7.0
  • UOPS: 3.0

Experiment 18

• Instruction: VMOVD XMM0, R8D
• Chain instruction: VPMOVMSKB R8D, XMM0
• Chain latency: ≥1
• Code:

     0:	c4 c1 79 6e c0       	vmovd  xmm0,r8d
     5:	c5 79 d7 c0          	vpmovmskb r8d,xmm0
  

• Init:

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

• Show nanoBench command
• Results:
  • MPERF: 5.17
  • APERF: 6.0
  • UOPS: 2.0