VPERMILPS (YMM, YMM, YMM)

Experiment 1

Instruction: VPERMILPS YMM1, YMM0, YMM2
Chain instruction: VPERMILPS YMM0, YMM1, YMM2

Code:

   0:	c4 e2 7d 0c ca       	vpermilps ymm1,ymm0,ymm2
   5:	c4 e2 75 0c c2       	vpermilps ymm0,ymm1,ymm2

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;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VXORPS YMM2, YMM2, YMM2

Show nanoBench command
Results:
- MPERF: 7.03
- APERF: 8.0
- UOPS: 4.0

Experiment 2

Instruction: VPERMILPS YMM1, YMM0, YMM2
Chain instructions: VANDPD YMM0, YMM1, YMM1;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0
Chain latency: 7

Code:

   0:	c4 e2 7d 0c ca       	vpermilps ymm1,ymm0,ymm2
   5:	c5 f5 54 c1          	vandpd ymm0,ymm1,ymm1
   9:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
   d:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  11:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  15:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  19:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  1d:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0

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;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VXORPS YMM2, YMM2, YMM2

Show nanoBench command
Results:
- MPERF: 10.99
- APERF: 12.7
- UOPS: 16.0

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

Instruction: VPERMILPS YMM1, YMM0, YMM2
Chain instruction: VPERMILPS YMM0, YMM1, YMM2

Code:

   0:	c4 e2 7d 0c ca       	vpermilps ymm1,ymm0,ymm2
   5:	c4 e2 75 0c c2       	vpermilps ymm0,ymm1,ymm2

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;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VXORPS YMM2, YMM2, YMM2;
VPERMILPS YMM0, YMM1, YMM2;
VPERMILPS YMM2, YMM0, YMM1

Show nanoBench command
Results:
- MPERF: 7.03
- APERF: 8.0
- UOPS: 4.0

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

Instruction: VPERMILPS YMM1, YMM0, YMM2
Chain instructions: VANDPD YMM0, YMM1, YMM1;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0
Chain latency: 7

Code:

   0:	c4 e2 7d 0c ca       	vpermilps ymm1,ymm0,ymm2
   5:	c5 f5 54 c1          	vandpd ymm0,ymm1,ymm1
   9:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
   d:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  11:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  15:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  19:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  1d:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0

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;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VXORPS YMM2, YMM2, YMM2;
VPERMILPS YMM0, YMM1, YMM2;
VPERMILPS YMM2, YMM0, YMM1

Show nanoBench command
Results:
- MPERF: 11.16
- APERF: 12.74
- UOPS: 16.0

Experiment 1

Instruction: VPERMILPS YMM1, YMM2, YMM0
Chain instruction: VPERMILPS YMM0, YMM2, YMM1

Code:

   0:	c4 e2 6d 0c c8       	vpermilps ymm1,ymm2,ymm0
   5:	c4 e2 6d 0c c1       	vpermilps ymm0,ymm2,ymm1

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;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM2, [R14];
VXORPS YMM0, YMM0, YMM0

Show nanoBench command
Results:
- MPERF: 7.08
- APERF: 8.0
- UOPS: 4.0

Experiment 2

Instruction: VPERMILPS YMM1, YMM2, YMM0
Chain instructions: VANDPD YMM0, YMM1, YMM1;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0
Chain latency: 7

Code:

   0:	c4 e2 6d 0c c8       	vpermilps ymm1,ymm2,ymm0
   5:	c5 f5 54 c1          	vandpd ymm0,ymm1,ymm1
   9:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
   d:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  11:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  15:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  19:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  1d:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0

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;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM2, [R14];
VXORPS YMM0, YMM0, YMM0

Show nanoBench command
Results:
- MPERF: 11.22
- APERF: 12.86
- UOPS: 16.0

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

Instruction: VPERMILPS YMM1, YMM2, YMM0
Chain instruction: VPERMILPS YMM0, YMM2, YMM1

Code:

   0:	c4 e2 6d 0c c8       	vpermilps ymm1,ymm2,ymm0
   5:	c4 e2 6d 0c c1       	vpermilps ymm0,ymm2,ymm1

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;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM2, [R14];
VXORPS YMM0, YMM0, YMM0;
VPERMILPS YMM2, YMM0, YMM1;
VPERMILPS YMM0, YMM1, YMM2

Show nanoBench command
Results:
- MPERF: 7.03
- APERF: 8.0
- UOPS: 4.0

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

Instruction: VPERMILPS YMM1, YMM2, YMM0
Chain instructions: VANDPD YMM0, YMM1, YMM1;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0
Chain latency: 7

Code:

   0:	c4 e2 6d 0c c8       	vpermilps ymm1,ymm2,ymm0
   5:	c5 f5 54 c1          	vandpd ymm0,ymm1,ymm1
   9:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
   d:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  11:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  15:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  19:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  1d:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0

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;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM2, [R14];
VXORPS YMM0, YMM0, YMM0;
VPERMILPS YMM2, YMM0, YMM1;
VPERMILPS YMM0, YMM1, YMM2

Show nanoBench command
Results:
- MPERF: 11.11
- APERF: 12.66
- UOPS: 16.0

VPERMILPS (YMM, YMM, YMM) - Latency

Operands

Latency operand 2 → 1: 4

Latency operand 3 → 1: 4

Latency operand 2 → 1: 4

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: 4

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)