VCMPPD (XMM, XMM, XMM, I8)

Experiment 1

Instruction: VCMPPD XMM1, XMM0, XMM2, 2
Chain instructions: VANDPD XMM0, XMM1, XMM1;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0
Chain latency: 5

Code:

   0:	c5 f9 c2 ca 02       	vcmplepd xmm1,xmm0,xmm2
   5:	c5 f1 54 c1          	vandpd xmm0,xmm1,xmm1
   9:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
   d:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  11:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  15:	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;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
VMOVUPD XMM0, [R14];
VMOVUPD XMM2, [R14]

Show nanoBench command
Results:
- MPERF: 5.1
- APERF: 6.0
- UOPS: 6.0

Experiment 2

Instruction: VCMPPD XMM1, XMM0, XMM2, 2
Chain instructions: VPAND XMM0, XMM1, XMM1;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0
Chain latency: 5

Code:

   0:	c5 f9 c2 ca 02       	vcmplepd xmm1,xmm0,xmm2
   5:	c5 f1 db c1          	vpand  xmm0,xmm1,xmm1
   9:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
   d:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  11:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  15:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0

Init:

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;
VMOVUPD XMM0, [R14];
VMOVUPD XMM2, [R14]

Show nanoBench command
Results:
- MPERF: 6.72
- APERF: 8.0
- UOPS: 6.0

Experiment 3 (source registers initialized by an instruction of the same kind)

Instruction: VCMPPD XMM1, XMM0, XMM2, 2
Chain instructions: VANDPD XMM0, XMM1, XMM1;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0
Chain latency: 5

Code:

   0:	c5 f9 c2 ca 02       	vcmplepd xmm1,xmm0,xmm2
   5:	c5 f1 54 c1          	vandpd xmm0,xmm1,xmm1
   9:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
   d:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  11:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  15:	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;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
VMOVUPD XMM0, [R14];
VMOVUPD XMM2, [R14];
VCMPPD XMM0, XMM1, XMM2, 2;
VCMPPD XMM2, XMM0, XMM1, 2

Show nanoBench command
Results:
- MPERF: 5.04
- APERF: 6.0
- UOPS: 6.0

Experiment 4 (source registers initialized by an instruction of the same kind)

Instruction: VCMPPD XMM1, XMM0, XMM2, 2
Chain instructions: VPAND XMM0, XMM1, XMM1;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0
Chain latency: 5

Code:

   0:	c5 f9 c2 ca 02       	vcmplepd xmm1,xmm0,xmm2
   5:	c5 f1 db c1          	vpand  xmm0,xmm1,xmm1
   9:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
   d:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  11:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  15:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0

Init:

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;
VMOVUPD XMM0, [R14];
VMOVUPD XMM2, [R14];
VCMPPD XMM0, XMM1, XMM2, 2;
VCMPPD XMM2, XMM0, XMM1, 2

Show nanoBench command
Results:
- MPERF: 6.78
- APERF: 8.0
- UOPS: 6.0

Experiment 1

Instruction: VCMPPD XMM1, XMM2, XMM0, 2
Chain instructions: VANDPD XMM0, XMM1, XMM1;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0
Chain latency: 5

Code:

   0:	c5 e9 c2 c8 02       	vcmplepd xmm1,xmm2,xmm0
   5:	c5 f1 54 c1          	vandpd xmm0,xmm1,xmm1
   9:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
   d:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  11:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  15:	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;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
VMOVUPD XMM2, [R14];
VMOVUPD XMM0, [R14]

Show nanoBench command
Results:
- MPERF: 4.98
- APERF: 6.0
- UOPS: 6.0

Experiment 2

Instruction: VCMPPD XMM1, XMM2, XMM0, 2
Chain instructions: VPAND XMM0, XMM1, XMM1;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0
Chain latency: 5

Code:

   0:	c5 e9 c2 c8 02       	vcmplepd xmm1,xmm2,xmm0
   5:	c5 f1 db c1          	vpand  xmm0,xmm1,xmm1
   9:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
   d:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  11:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  15:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0

Init:

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;
VMOVUPD XMM2, [R14];
VMOVUPD XMM0, [R14]

Show nanoBench command
Results:
- MPERF: 6.72
- APERF: 8.0
- UOPS: 6.0

Experiment 3 (source registers initialized by an instruction of the same kind)

Instruction: VCMPPD XMM1, XMM2, XMM0, 2
Chain instructions: VANDPD XMM0, XMM1, XMM1;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0
Chain latency: 5

Code:

   0:	c5 e9 c2 c8 02       	vcmplepd xmm1,xmm2,xmm0
   5:	c5 f1 54 c1          	vandpd xmm0,xmm1,xmm1
   9:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
   d:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  11:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  15:	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;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
VMOVUPD XMM2, [R14];
VMOVUPD XMM0, [R14];
VCMPPD XMM2, XMM0, XMM1, 2;
VCMPPD XMM0, XMM1, XMM2, 2

Show nanoBench command
Results:
- MPERF: 4.98
- APERF: 6.0
- UOPS: 6.0

Experiment 4 (source registers initialized by an instruction of the same kind)

Instruction: VCMPPD XMM1, XMM2, XMM0, 2
Chain instructions: VPAND XMM0, XMM1, XMM1;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0
Chain latency: 5

Code:

   0:	c5 e9 c2 c8 02       	vcmplepd xmm1,xmm2,xmm0
   5:	c5 f1 db c1          	vpand  xmm0,xmm1,xmm1
   9:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
   d:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  11:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  15:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0

Init:

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;
VMOVUPD XMM2, [R14];
VMOVUPD XMM0, [R14];
VCMPPD XMM2, XMM0, XMM1, 2;
VCMPPD XMM0, XMM1, XMM2, 2

Show nanoBench command
Results:
- MPERF: 6.72
- APERF: 8.0
- UOPS: 6.0

VCMPPD (XMM, XMM, XMM, I8) - Latency

Operands

Latency operand 2 → 1: 1

Latency operand 3 → 1: 1

Latency operand 2 → 1: 1

Experiment 1

Experiment 2

Experiment 3 (source registers initialized by an instruction of the same kind)

Experiment 4 (source registers initialized by an instruction of the same kind)

Latency operand 3 → 1: 1

Experiment 1

Experiment 2

Experiment 3 (source registers initialized by an instruction of the same kind)

Experiment 4 (source registers initialized by an instruction of the same kind)