VPERMPS (YMM, YMM, YMM)

With unroll_count=500 and no inner loop

Code:

   0:	c4 e2 75 16 c2       	vpermps 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 YMM1, [R14];
VMOVUPD YMM2, [R14]

Show nanoBench command
Results:
- MPERF: 0.44
- APERF: 0.5
- UOPS: 1.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.5
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	c4 e2 75 16 c2       	vpermps 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 YMM1, [R14];
VMOVUPD YMM2, [R14]

Show nanoBench command
Results:
- MPERF: 0.43
- APERF: 0.5
- UOPS: 1.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.5
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	c4 e2 75 16 c2       	vpermps 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 YMM1, [R14];
VMOVUPD YMM2, [R14]

Show nanoBench command
Results:
- MPERF: 0.43
- APERF: 0.5
- UOPS: 1.01
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.5
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

   0:	c4 e2 75 16 c2       	vpermps ymm0,ymm1,ymm2
   5:	c4 e2 75 16 da       	vpermps ymm3,ymm1,ymm2
   a:	c4 e2 75 16 e2       	vpermps ymm4,ymm1,ymm2
   f:	c4 e2 75 16 ea       	vpermps ymm5,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 YMM1, [R14];
VMOVUPD YMM2, [R14]

Show nanoBench command
Results:
- MPERF: 1.61
- APERF: 2.0
- UOPS: 4.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 2.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=2

Code:

   0:	c4 e2 75 16 c2       	vpermps ymm0,ymm1,ymm2
   5:	c4 e2 75 16 da       	vpermps ymm3,ymm1,ymm2
   a:	c4 e2 75 16 e2       	vpermps ymm4,ymm1,ymm2
   f:	c4 e2 75 16 ea       	vpermps ymm5,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 YMM1, [R14];
VMOVUPD YMM2, [R14]

Show nanoBench command
Results:
- MPERF: 1.72
- APERF: 2.0
- UOPS: 4.5
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 2.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=20

Code:

   0:	c4 e2 75 16 c2       	vpermps ymm0,ymm1,ymm2
   5:	c4 e2 75 16 da       	vpermps ymm3,ymm1,ymm2
   a:	c4 e2 75 16 e2       	vpermps ymm4,ymm1,ymm2
   f:	c4 e2 75 16 ea       	vpermps ymm5,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 YMM1, [R14];
VMOVUPD YMM2, [R14]

Show nanoBench command
Results:
- MPERF: 1.74
- APERF: 2.0
- UOPS: 4.05
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 2.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With 8 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 e2 75 16 c2       	vpermps ymm0,ymm1,ymm2
   5:	c4 e2 75 16 da       	vpermps ymm3,ymm1,ymm2
   a:	c4 e2 75 16 e2       	vpermps ymm4,ymm1,ymm2
   f:	c4 e2 75 16 ea       	vpermps ymm5,ymm1,ymm2
  14:	c4 e2 75 16 f2       	vpermps ymm6,ymm1,ymm2
  19:	c4 e2 75 16 fa       	vpermps ymm7,ymm1,ymm2
  1e:	c4 62 75 16 c2       	vpermps ymm8,ymm1,ymm2
  23:	c4 62 75 16 ca       	vpermps ymm9,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 YMM1, [R14];
VMOVUPD YMM2, [R14]

Show nanoBench command
Results:
- MPERF: 3.21
- APERF: 4.0
- UOPS: 8.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c4 e2 75 16 c2       	vpermps ymm0,ymm1,ymm2
   5:	c4 e2 75 16 da       	vpermps ymm3,ymm1,ymm2
   a:	c4 e2 75 16 e2       	vpermps ymm4,ymm1,ymm2
   f:	c4 e2 75 16 ea       	vpermps ymm5,ymm1,ymm2
  14:	c4 e2 75 16 f2       	vpermps ymm6,ymm1,ymm2
  19:	c4 e2 75 16 fa       	vpermps ymm7,ymm1,ymm2
  1e:	c4 62 75 16 c2       	vpermps ymm8,ymm1,ymm2
  23:	c4 62 75 16 ca       	vpermps ymm9,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 YMM1, [R14];
VMOVUPD YMM2, [R14]

Show nanoBench command
Results:
- MPERF: 3.45
- APERF: 4.01
- UOPS: 9.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c4 e2 75 16 c2       	vpermps ymm0,ymm1,ymm2
   5:	c4 e2 75 16 da       	vpermps ymm3,ymm1,ymm2
   a:	c4 e2 75 16 e2       	vpermps ymm4,ymm1,ymm2
   f:	c4 e2 75 16 ea       	vpermps ymm5,ymm1,ymm2
  14:	c4 e2 75 16 f2       	vpermps ymm6,ymm1,ymm2
  19:	c4 e2 75 16 fa       	vpermps ymm7,ymm1,ymm2
  1e:	c4 62 75 16 c2       	vpermps ymm8,ymm1,ymm2
  23:	c4 62 75 16 ca       	vpermps ymm9,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 YMM1, [R14];
VMOVUPD YMM2, [R14]

Show nanoBench command
Results:
- MPERF: 3.45
- APERF: 4.01
- UOPS: 8.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With 11 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 e2 75 16 c2       	vpermps ymm0,ymm1,ymm2
   5:	c4 e2 75 16 da       	vpermps ymm3,ymm1,ymm2
   a:	c4 e2 75 16 e2       	vpermps ymm4,ymm1,ymm2
   f:	c4 e2 75 16 ea       	vpermps ymm5,ymm1,ymm2
  14:	c4 e2 75 16 f2       	vpermps ymm6,ymm1,ymm2
  19:	c4 e2 75 16 fa       	vpermps ymm7,ymm1,ymm2
  1e:	c4 62 75 16 c2       	vpermps ymm8,ymm1,ymm2
  23:	c4 62 75 16 ca       	vpermps ymm9,ymm1,ymm2
  28:	c4 62 75 16 d2       	vpermps ymm10,ymm1,ymm2
  2d:	c4 62 75 16 da       	vpermps ymm11,ymm1,ymm2
  32:	c4 62 75 16 e2       	vpermps ymm12,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 YMM1, [R14];
VMOVUPD YMM2, [R14]

Show nanoBench command
Results:
- MPERF: 4.78
- APERF: 5.5
- UOPS: 11.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 5.5
- FpuPipeAssignment.Total2: 5.5
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c4 e2 75 16 c2       	vpermps ymm0,ymm1,ymm2
   5:	c4 e2 75 16 da       	vpermps ymm3,ymm1,ymm2
   a:	c4 e2 75 16 e2       	vpermps ymm4,ymm1,ymm2
   f:	c4 e2 75 16 ea       	vpermps ymm5,ymm1,ymm2
  14:	c4 e2 75 16 f2       	vpermps ymm6,ymm1,ymm2
  19:	c4 e2 75 16 fa       	vpermps ymm7,ymm1,ymm2
  1e:	c4 62 75 16 c2       	vpermps ymm8,ymm1,ymm2
  23:	c4 62 75 16 ca       	vpermps ymm9,ymm1,ymm2
  28:	c4 62 75 16 d2       	vpermps ymm10,ymm1,ymm2
  2d:	c4 62 75 16 da       	vpermps ymm11,ymm1,ymm2
  32:	c4 62 75 16 e2       	vpermps ymm12,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 YMM1, [R14];
VMOVUPD YMM2, [R14]

Show nanoBench command
Results:
- MPERF: 4.75
- APERF: 5.51
- UOPS: 12.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 5.5
- FpuPipeAssignment.Total2: 5.5
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c4 e2 75 16 c2       	vpermps ymm0,ymm1,ymm2
   5:	c4 e2 75 16 da       	vpermps ymm3,ymm1,ymm2
   a:	c4 e2 75 16 e2       	vpermps ymm4,ymm1,ymm2
   f:	c4 e2 75 16 ea       	vpermps ymm5,ymm1,ymm2
  14:	c4 e2 75 16 f2       	vpermps ymm6,ymm1,ymm2
  19:	c4 e2 75 16 fa       	vpermps ymm7,ymm1,ymm2
  1e:	c4 62 75 16 c2       	vpermps ymm8,ymm1,ymm2
  23:	c4 62 75 16 ca       	vpermps ymm9,ymm1,ymm2
  28:	c4 62 75 16 d2       	vpermps ymm10,ymm1,ymm2
  2d:	c4 62 75 16 da       	vpermps ymm11,ymm1,ymm2
  32:	c4 62 75 16 e2       	vpermps ymm12,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 YMM1, [R14];
VMOVUPD YMM2, [R14]

Show nanoBench command
Results:
- MPERF: 4.75
- APERF: 5.51
- UOPS: 11.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 5.5
- FpuPipeAssignment.Total2: 5.5
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With the same register for for different operands

With 1 independent instruction

With unroll_count=500 and no inner loop

Code:

   0:	c4 e2 7d 16 c0       	vpermps 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]

Show nanoBench command
Results:
- MPERF: 3.38
- APERF: 4.0
- UOPS: 1.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.5
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	c4 e2 7d 16 c0       	vpermps 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]

Show nanoBench command
Results:
- MPERF: 3.45
- APERF: 4.0
- UOPS: 1.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.5
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	c4 e2 7d 16 c0       	vpermps 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]

Show nanoBench command
Results:
- MPERF: 3.45
- APERF: 4.0
- UOPS: 1.01
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.5
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

   0:	c4 e2 7d 16 c0       	vpermps ymm0,ymm0,ymm0
   5:	c4 e2 75 16 c9       	vpermps ymm1,ymm1,ymm1
   a:	c4 e2 6d 16 d2       	vpermps ymm2,ymm2,ymm2
   f:	c4 e2 65 16 db       	vpermps ymm3,ymm3,ymm3

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14]

Show nanoBench command
Results:
- MPERF: 3.41
- APERF: 4.0
- UOPS: 4.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 2.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=2

Code:

   0:	c4 e2 7d 16 c0       	vpermps ymm0,ymm0,ymm0
   5:	c4 e2 75 16 c9       	vpermps ymm1,ymm1,ymm1
   a:	c4 e2 6d 16 d2       	vpermps ymm2,ymm2,ymm2
   f:	c4 e2 65 16 db       	vpermps ymm3,ymm3,ymm3

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14]

Show nanoBench command
Results:
- MPERF: 3.45
- APERF: 4.0
- UOPS: 4.5
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 2.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=20

Code:

   0:	c4 e2 7d 16 c0       	vpermps ymm0,ymm0,ymm0
   5:	c4 e2 75 16 c9       	vpermps ymm1,ymm1,ymm1
   a:	c4 e2 6d 16 d2       	vpermps ymm2,ymm2,ymm2
   f:	c4 e2 65 16 db       	vpermps ymm3,ymm3,ymm3

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14]

Show nanoBench command
Results:
- MPERF: 3.45
- APERF: 4.0
- UOPS: 4.05
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 2.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With 8 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 e2 7d 16 c0       	vpermps ymm0,ymm0,ymm0
   5:	c4 e2 75 16 c9       	vpermps ymm1,ymm1,ymm1
   a:	c4 e2 6d 16 d2       	vpermps ymm2,ymm2,ymm2
   f:	c4 e2 65 16 db       	vpermps ymm3,ymm3,ymm3
  14:	c4 e2 5d 16 e4       	vpermps ymm4,ymm4,ymm4
  19:	c4 e2 55 16 ed       	vpermps ymm5,ymm5,ymm5
  1e:	c4 e2 4d 16 f6       	vpermps ymm6,ymm6,ymm6
  23:	c4 e2 45 16 ff       	vpermps ymm7,ymm7,ymm7

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14];
VMOVUPD YMM4, [R14];
VMOVUPD YMM5, [R14];
VMOVUPD YMM6, [R14];
VMOVUPD YMM7, [R14]

Show nanoBench command
Results:
- MPERF: 3.21
- APERF: 4.0
- UOPS: 8.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c4 e2 7d 16 c0       	vpermps ymm0,ymm0,ymm0
   5:	c4 e2 75 16 c9       	vpermps ymm1,ymm1,ymm1
   a:	c4 e2 6d 16 d2       	vpermps ymm2,ymm2,ymm2
   f:	c4 e2 65 16 db       	vpermps ymm3,ymm3,ymm3
  14:	c4 e2 5d 16 e4       	vpermps ymm4,ymm4,ymm4
  19:	c4 e2 55 16 ed       	vpermps ymm5,ymm5,ymm5
  1e:	c4 e2 4d 16 f6       	vpermps ymm6,ymm6,ymm6
  23:	c4 e2 45 16 ff       	vpermps ymm7,ymm7,ymm7

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14];
VMOVUPD YMM4, [R14];
VMOVUPD YMM5, [R14];
VMOVUPD YMM6, [R14];
VMOVUPD YMM7, [R14]

Show nanoBench command
Results:
- MPERF: 3.44
- APERF: 4.01
- UOPS: 9.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c4 e2 7d 16 c0       	vpermps ymm0,ymm0,ymm0
   5:	c4 e2 75 16 c9       	vpermps ymm1,ymm1,ymm1
   a:	c4 e2 6d 16 d2       	vpermps ymm2,ymm2,ymm2
   f:	c4 e2 65 16 db       	vpermps ymm3,ymm3,ymm3
  14:	c4 e2 5d 16 e4       	vpermps ymm4,ymm4,ymm4
  19:	c4 e2 55 16 ed       	vpermps ymm5,ymm5,ymm5
  1e:	c4 e2 4d 16 f6       	vpermps ymm6,ymm6,ymm6
  23:	c4 e2 45 16 ff       	vpermps ymm7,ymm7,ymm7

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14];
VMOVUPD YMM4, [R14];
VMOVUPD YMM5, [R14];
VMOVUPD YMM6, [R14];
VMOVUPD YMM7, [R14]

Show nanoBench command
Results:
- MPERF: 3.45
- APERF: 4.01
- UOPS: 8.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With 13 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 e2 7d 16 c0       	vpermps ymm0,ymm0,ymm0
   5:	c4 e2 75 16 c9       	vpermps ymm1,ymm1,ymm1
   a:	c4 e2 6d 16 d2       	vpermps ymm2,ymm2,ymm2
   f:	c4 e2 65 16 db       	vpermps ymm3,ymm3,ymm3
  14:	c4 e2 5d 16 e4       	vpermps ymm4,ymm4,ymm4
  19:	c4 e2 55 16 ed       	vpermps ymm5,ymm5,ymm5
  1e:	c4 e2 4d 16 f6       	vpermps ymm6,ymm6,ymm6
  23:	c4 e2 45 16 ff       	vpermps ymm7,ymm7,ymm7
  28:	c4 42 3d 16 c0       	vpermps ymm8,ymm8,ymm8
  2d:	c4 42 35 16 c9       	vpermps ymm9,ymm9,ymm9
  32:	c4 42 2d 16 d2       	vpermps ymm10,ymm10,ymm10
  37:	c4 42 25 16 db       	vpermps ymm11,ymm11,ymm11
  3c:	c4 42 1d 16 e4       	vpermps ymm12,ymm12,ymm12

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14];
VMOVUPD YMM4, [R14];
VMOVUPD YMM5, [R14];
VMOVUPD YMM6, [R14];
VMOVUPD YMM7, [R14];
VMOVUPD YMM8, [R14];
VMOVUPD YMM9, [R14];
VMOVUPD YMM10, [R14];
VMOVUPD YMM11, [R14];
VMOVUPD YMM12, [R14]

Show nanoBench command
Results:
- MPERF: 5.64
- APERF: 6.5
- UOPS: 13.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 6.5
- FpuPipeAssignment.Total2: 6.5
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c4 e2 7d 16 c0       	vpermps ymm0,ymm0,ymm0
   5:	c4 e2 75 16 c9       	vpermps ymm1,ymm1,ymm1
   a:	c4 e2 6d 16 d2       	vpermps ymm2,ymm2,ymm2
   f:	c4 e2 65 16 db       	vpermps ymm3,ymm3,ymm3
  14:	c4 e2 5d 16 e4       	vpermps ymm4,ymm4,ymm4
  19:	c4 e2 55 16 ed       	vpermps ymm5,ymm5,ymm5
  1e:	c4 e2 4d 16 f6       	vpermps ymm6,ymm6,ymm6
  23:	c4 e2 45 16 ff       	vpermps ymm7,ymm7,ymm7
  28:	c4 42 3d 16 c0       	vpermps ymm8,ymm8,ymm8
  2d:	c4 42 35 16 c9       	vpermps ymm9,ymm9,ymm9
  32:	c4 42 2d 16 d2       	vpermps ymm10,ymm10,ymm10
  37:	c4 42 25 16 db       	vpermps ymm11,ymm11,ymm11
  3c:	c4 42 1d 16 e4       	vpermps ymm12,ymm12,ymm12

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14];
VMOVUPD YMM4, [R14];
VMOVUPD YMM5, [R14];
VMOVUPD YMM6, [R14];
VMOVUPD YMM7, [R14];
VMOVUPD YMM8, [R14];
VMOVUPD YMM9, [R14];
VMOVUPD YMM10, [R14];
VMOVUPD YMM11, [R14];
VMOVUPD YMM12, [R14]

Show nanoBench command
Results:
- MPERF: 5.59
- APERF: 6.51
- UOPS: 14.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 6.5
- FpuPipeAssignment.Total2: 6.5
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c4 e2 7d 16 c0       	vpermps ymm0,ymm0,ymm0
   5:	c4 e2 75 16 c9       	vpermps ymm1,ymm1,ymm1
   a:	c4 e2 6d 16 d2       	vpermps ymm2,ymm2,ymm2
   f:	c4 e2 65 16 db       	vpermps ymm3,ymm3,ymm3
  14:	c4 e2 5d 16 e4       	vpermps ymm4,ymm4,ymm4
  19:	c4 e2 55 16 ed       	vpermps ymm5,ymm5,ymm5
  1e:	c4 e2 4d 16 f6       	vpermps ymm6,ymm6,ymm6
  23:	c4 e2 45 16 ff       	vpermps ymm7,ymm7,ymm7
  28:	c4 42 3d 16 c0       	vpermps ymm8,ymm8,ymm8
  2d:	c4 42 35 16 c9       	vpermps ymm9,ymm9,ymm9
  32:	c4 42 2d 16 d2       	vpermps ymm10,ymm10,ymm10
  37:	c4 42 25 16 db       	vpermps ymm11,ymm11,ymm11
  3c:	c4 42 1d 16 e4       	vpermps ymm12,ymm12,ymm12

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14];
VMOVUPD YMM4, [R14];
VMOVUPD YMM5, [R14];
VMOVUPD YMM6, [R14];
VMOVUPD YMM7, [R14];
VMOVUPD YMM8, [R14];
VMOVUPD YMM9, [R14];
VMOVUPD YMM10, [R14];
VMOVUPD YMM11, [R14];
VMOVUPD YMM12, [R14]

Show nanoBench command
Results:
- MPERF: 5.62
- APERF: 6.51
- UOPS: 13.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 6.5
- FpuPipeAssignment.Total2: 6.5
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

VPERMPS (YMM, YMM, YMM) - Throughput and Uops

With different registers for different operands

With 1 independent instruction

With unroll_count=500 and no inner loop

With loop_count=1000 and unroll_count=10

With loop_count=100 and unroll_count=100

With 4 independent instructions

With unroll_count=200 and no inner loop

With loop_count=1000 and unroll_count=2

With loop_count=100 and unroll_count=20

With 8 independent instructions

With unroll_count=100 and no inner loop

With loop_count=1000 and unroll_count=1

With loop_count=100 and unroll_count=10

With 11 independent instructions

With unroll_count=100 and no inner loop

With loop_count=1000 and unroll_count=1

With loop_count=100 and unroll_count=10

With the same register for for different operands

With 1 independent instruction

With unroll_count=500 and no inner loop

With loop_count=1000 and unroll_count=10

With loop_count=100 and unroll_count=100

With 4 independent instructions

With unroll_count=200 and no inner loop

With loop_count=1000 and unroll_count=2

With loop_count=100 and unroll_count=20

With 8 independent instructions

With unroll_count=100 and no inner loop

With loop_count=1000 and unroll_count=1

With loop_count=100 and unroll_count=10

With 13 independent instructions

With unroll_count=100 and no inner loop

With loop_count=1000 and unroll_count=1

With loop_count=100 and unroll_count=10