VSHUFPD (XMM, XMM, XMM, I8)

With unroll_count=500 and no inner loop

Code:

   0:	c5 f1 c6 c2 02       	vshufpd xmm0,xmm1,xmm2,0x2

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 XMM1, [R14];
VMOVUPD XMM2, [R14]

Show nanoBench command
Results:
- MPERF: 0.46
- APERF: 0.5
- UOPS: 1.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.5
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	c5 f1 c6 c2 02       	vshufpd xmm0,xmm1,xmm2,0x2

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 XMM1, [R14];
VMOVUPD XMM2, [R14]

Show nanoBench command
Results:
- MPERF: 0.44
- APERF: 0.5
- UOPS: 1.2
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.49
- FpuPipeAssignment.Total2: 0.49
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	c5 f1 c6 c2 02       	vshufpd xmm0,xmm1,xmm2,0x2

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 XMM1, [R14];
VMOVUPD XMM2, [R14]

Show nanoBench command
Results:
- MPERF: 0.44
- APERF: 0.5
- UOPS: 1.02
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.5
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

   0:	c5 f1 c6 c2 02       	vshufpd xmm0,xmm1,xmm2,0x2
   5:	c5 f1 c6 da 02       	vshufpd xmm3,xmm1,xmm2,0x2
   a:	c5 f1 c6 e2 02       	vshufpd xmm4,xmm1,xmm2,0x2
   f:	c5 f1 c6 ea 02       	vshufpd xmm5,xmm1,xmm2,0x2

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 XMM1, [R14];
VMOVUPD XMM2, [R14]

Show nanoBench command
Results:
- MPERF: 1.73
- APERF: 2.0
- UOPS: 4.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 2.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=2

Code:

   0:	c5 f1 c6 c2 02       	vshufpd xmm0,xmm1,xmm2,0x2
   5:	c5 f1 c6 da 02       	vshufpd xmm3,xmm1,xmm2,0x2
   a:	c5 f1 c6 e2 02       	vshufpd xmm4,xmm1,xmm2,0x2
   f:	c5 f1 c6 ea 02       	vshufpd xmm5,xmm1,xmm2,0x2

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 XMM1, [R14];
VMOVUPD XMM2, [R14]

Show nanoBench command
Results:
- MPERF: 1.74
- APERF: 2.0
- UOPS: 5.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 2.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=20

Code:

   0:	c5 f1 c6 c2 02       	vshufpd xmm0,xmm1,xmm2,0x2
   5:	c5 f1 c6 da 02       	vshufpd xmm3,xmm1,xmm2,0x2
   a:	c5 f1 c6 e2 02       	vshufpd xmm4,xmm1,xmm2,0x2
   f:	c5 f1 c6 ea 02       	vshufpd xmm5,xmm1,xmm2,0x2

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 XMM1, [R14];
VMOVUPD XMM2, [R14]

Show nanoBench command
Results:
- MPERF: 1.84
- APERF: 2.11
- UOPS: 4.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 2.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 8 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c5 f1 c6 c2 02       	vshufpd xmm0,xmm1,xmm2,0x2
   5:	c5 f1 c6 da 02       	vshufpd xmm3,xmm1,xmm2,0x2
   a:	c5 f1 c6 e2 02       	vshufpd xmm4,xmm1,xmm2,0x2
   f:	c5 f1 c6 ea 02       	vshufpd xmm5,xmm1,xmm2,0x2
  14:	c5 f1 c6 f2 02       	vshufpd xmm6,xmm1,xmm2,0x2
  19:	c5 f1 c6 fa 02       	vshufpd xmm7,xmm1,xmm2,0x2
  1e:	c5 71 c6 c2 02       	vshufpd xmm8,xmm1,xmm2,0x2
  23:	c5 71 c6 ca 02       	vshufpd xmm9,xmm1,xmm2,0x2

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 XMM1, [R14];
VMOVUPD XMM2, [R14]

Show nanoBench command
Results:
- MPERF: 3.51
- APERF: 4.0
- UOPS: 8.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c5 f1 c6 c2 02       	vshufpd xmm0,xmm1,xmm2,0x2
   5:	c5 f1 c6 da 02       	vshufpd xmm3,xmm1,xmm2,0x2
   a:	c5 f1 c6 e2 02       	vshufpd xmm4,xmm1,xmm2,0x2
   f:	c5 f1 c6 ea 02       	vshufpd xmm5,xmm1,xmm2,0x2
  14:	c5 f1 c6 f2 02       	vshufpd xmm6,xmm1,xmm2,0x2
  19:	c5 f1 c6 fa 02       	vshufpd xmm7,xmm1,xmm2,0x2
  1e:	c5 71 c6 c2 02       	vshufpd xmm8,xmm1,xmm2,0x2
  23:	c5 71 c6 ca 02       	vshufpd xmm9,xmm1,xmm2,0x2

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 XMM1, [R14];
VMOVUPD XMM2, [R14]

Show nanoBench command
Results:
- MPERF: 3.48
- APERF: 4.0
- UOPS: 10.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 4.01
- FpuPipeAssignment.Total2: 4.01
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c5 f1 c6 c2 02       	vshufpd xmm0,xmm1,xmm2,0x2
   5:	c5 f1 c6 da 02       	vshufpd xmm3,xmm1,xmm2,0x2
   a:	c5 f1 c6 e2 02       	vshufpd xmm4,xmm1,xmm2,0x2
   f:	c5 f1 c6 ea 02       	vshufpd xmm5,xmm1,xmm2,0x2
  14:	c5 f1 c6 f2 02       	vshufpd xmm6,xmm1,xmm2,0x2
  19:	c5 f1 c6 fa 02       	vshufpd xmm7,xmm1,xmm2,0x2
  1e:	c5 71 c6 c2 02       	vshufpd xmm8,xmm1,xmm2,0x2
  23:	c5 71 c6 ca 02       	vshufpd xmm9,xmm1,xmm2,0x2

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 XMM1, [R14];
VMOVUPD XMM2, [R14]

Show nanoBench command
Results:
- MPERF: 3.67
- APERF: 4.21
- UOPS: 8.2
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 11 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c5 f1 c6 c2 02       	vshufpd xmm0,xmm1,xmm2,0x2
   5:	c5 f1 c6 da 02       	vshufpd xmm3,xmm1,xmm2,0x2
   a:	c5 f1 c6 e2 02       	vshufpd xmm4,xmm1,xmm2,0x2
   f:	c5 f1 c6 ea 02       	vshufpd xmm5,xmm1,xmm2,0x2
  14:	c5 f1 c6 f2 02       	vshufpd xmm6,xmm1,xmm2,0x2
  19:	c5 f1 c6 fa 02       	vshufpd xmm7,xmm1,xmm2,0x2
  1e:	c5 71 c6 c2 02       	vshufpd xmm8,xmm1,xmm2,0x2
  23:	c5 71 c6 ca 02       	vshufpd xmm9,xmm1,xmm2,0x2
  28:	c5 71 c6 d2 02       	vshufpd xmm10,xmm1,xmm2,0x2
  2d:	c5 71 c6 da 02       	vshufpd xmm11,xmm1,xmm2,0x2
  32:	c5 71 c6 e2 02       	vshufpd xmm12,xmm1,xmm2,0x2

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 XMM1, [R14];
VMOVUPD XMM2, [R14]

Show nanoBench command
Results:
- MPERF: 4.76
- APERF: 5.5
- UOPS: 11.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 5.5
- FpuPipeAssignment.Total2: 5.5
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c5 f1 c6 c2 02       	vshufpd xmm0,xmm1,xmm2,0x2
   5:	c5 f1 c6 da 02       	vshufpd xmm3,xmm1,xmm2,0x2
   a:	c5 f1 c6 e2 02       	vshufpd xmm4,xmm1,xmm2,0x2
   f:	c5 f1 c6 ea 02       	vshufpd xmm5,xmm1,xmm2,0x2
  14:	c5 f1 c6 f2 02       	vshufpd xmm6,xmm1,xmm2,0x2
  19:	c5 f1 c6 fa 02       	vshufpd xmm7,xmm1,xmm2,0x2
  1e:	c5 71 c6 c2 02       	vshufpd xmm8,xmm1,xmm2,0x2
  23:	c5 71 c6 ca 02       	vshufpd xmm9,xmm1,xmm2,0x2
  28:	c5 71 c6 d2 02       	vshufpd xmm10,xmm1,xmm2,0x2
  2d:	c5 71 c6 da 02       	vshufpd xmm11,xmm1,xmm2,0x2
  32:	c5 71 c6 e2 02       	vshufpd xmm12,xmm1,xmm2,0x2

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 XMM1, [R14];
VMOVUPD XMM2, [R14]

Show nanoBench command
Results:
- MPERF: 4.79
- APERF: 5.5
- UOPS: 13.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 5.5
- FpuPipeAssignment.Total2: 5.5
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c5 f1 c6 c2 02       	vshufpd xmm0,xmm1,xmm2,0x2
   5:	c5 f1 c6 da 02       	vshufpd xmm3,xmm1,xmm2,0x2
   a:	c5 f1 c6 e2 02       	vshufpd xmm4,xmm1,xmm2,0x2
   f:	c5 f1 c6 ea 02       	vshufpd xmm5,xmm1,xmm2,0x2
  14:	c5 f1 c6 f2 02       	vshufpd xmm6,xmm1,xmm2,0x2
  19:	c5 f1 c6 fa 02       	vshufpd xmm7,xmm1,xmm2,0x2
  1e:	c5 71 c6 c2 02       	vshufpd xmm8,xmm1,xmm2,0x2
  23:	c5 71 c6 ca 02       	vshufpd xmm9,xmm1,xmm2,0x2
  28:	c5 71 c6 d2 02       	vshufpd xmm10,xmm1,xmm2,0x2
  2d:	c5 71 c6 da 02       	vshufpd xmm11,xmm1,xmm2,0x2
  32:	c5 71 c6 e2 02       	vshufpd xmm12,xmm1,xmm2,0x2

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 XMM1, [R14];
VMOVUPD XMM2, [R14]

Show nanoBench command
Results:
- MPERF: 4.8
- APERF: 5.51
- UOPS: 11.2
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 5.2
- FpuPipeAssignment.Total2: 5.2
- FpuPipeAssignment.Total3: 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:	c5 f9 c6 c0 02       	vshufpd xmm0,xmm0,xmm0,0x2

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]

Show nanoBench command
Results:
- MPERF: 0.86
- APERF: 1.0
- UOPS: 1.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.5
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	c5 f9 c6 c0 02       	vshufpd xmm0,xmm0,xmm0,0x2

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]

Show nanoBench command
Results:
- MPERF: 0.87
- APERF: 1.0
- UOPS: 1.2
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.5
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	c5 f9 c6 c0 02       	vshufpd xmm0,xmm0,xmm0,0x2

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]

Show nanoBench command
Results:
- MPERF: 0.87
- APERF: 1.0
- UOPS: 1.02
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.5
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

   0:	c5 f9 c6 c0 02       	vshufpd xmm0,xmm0,xmm0,0x2
   5:	c5 f1 c6 c9 02       	vshufpd xmm1,xmm1,xmm1,0x2
   a:	c5 e9 c6 d2 02       	vshufpd xmm2,xmm2,xmm2,0x2
   f:	c5 e1 c6 db 02       	vshufpd xmm3,xmm3,xmm3,0x2

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 XMM1, [R14];
VMOVUPD XMM2, [R14];
VMOVUPD XMM3, [R14]

Show nanoBench command
Results:
- MPERF: 1.76
- APERF: 2.0
- UOPS: 4.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 2.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=2

Code:

   0:	c5 f9 c6 c0 02       	vshufpd xmm0,xmm0,xmm0,0x2
   5:	c5 f1 c6 c9 02       	vshufpd xmm1,xmm1,xmm1,0x2
   a:	c5 e9 c6 d2 02       	vshufpd xmm2,xmm2,xmm2,0x2
   f:	c5 e1 c6 db 02       	vshufpd xmm3,xmm3,xmm3,0x2

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 XMM1, [R14];
VMOVUPD XMM2, [R14];
VMOVUPD XMM3, [R14]

Show nanoBench command
Results:
- MPERF: 1.74
- APERF: 2.0
- UOPS: 5.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 2.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=20

Code:

   0:	c5 f9 c6 c0 02       	vshufpd xmm0,xmm0,xmm0,0x2
   5:	c5 f1 c6 c9 02       	vshufpd xmm1,xmm1,xmm1,0x2
   a:	c5 e9 c6 d2 02       	vshufpd xmm2,xmm2,xmm2,0x2
   f:	c5 e1 c6 db 02       	vshufpd xmm3,xmm3,xmm3,0x2

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 XMM1, [R14];
VMOVUPD XMM2, [R14];
VMOVUPD XMM3, [R14]

Show nanoBench command
Results:
- MPERF: 1.84
- APERF: 2.11
- UOPS: 4.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 2.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 8 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c5 f9 c6 c0 02       	vshufpd xmm0,xmm0,xmm0,0x2
   5:	c5 f1 c6 c9 02       	vshufpd xmm1,xmm1,xmm1,0x2
   a:	c5 e9 c6 d2 02       	vshufpd xmm2,xmm2,xmm2,0x2
   f:	c5 e1 c6 db 02       	vshufpd xmm3,xmm3,xmm3,0x2
  14:	c5 d9 c6 e4 02       	vshufpd xmm4,xmm4,xmm4,0x2
  19:	c5 d1 c6 ed 02       	vshufpd xmm5,xmm5,xmm5,0x2
  1e:	c5 c9 c6 f6 02       	vshufpd xmm6,xmm6,xmm6,0x2
  23:	c5 c1 c6 ff 02       	vshufpd xmm7,xmm7,xmm7,0x2

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 XMM1, [R14];
VMOVUPD XMM2, [R14];
VMOVUPD XMM3, [R14];
VMOVUPD XMM4, [R14];
VMOVUPD XMM5, [R14];
VMOVUPD XMM6, [R14];
VMOVUPD XMM7, [R14]

Show nanoBench command
Results:
- MPERF: 3.57
- APERF: 4.0
- UOPS: 8.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c5 f9 c6 c0 02       	vshufpd xmm0,xmm0,xmm0,0x2
   5:	c5 f1 c6 c9 02       	vshufpd xmm1,xmm1,xmm1,0x2
   a:	c5 e9 c6 d2 02       	vshufpd xmm2,xmm2,xmm2,0x2
   f:	c5 e1 c6 db 02       	vshufpd xmm3,xmm3,xmm3,0x2
  14:	c5 d9 c6 e4 02       	vshufpd xmm4,xmm4,xmm4,0x2
  19:	c5 d1 c6 ed 02       	vshufpd xmm5,xmm5,xmm5,0x2
  1e:	c5 c9 c6 f6 02       	vshufpd xmm6,xmm6,xmm6,0x2
  23:	c5 c1 c6 ff 02       	vshufpd xmm7,xmm7,xmm7,0x2

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 XMM1, [R14];
VMOVUPD XMM2, [R14];
VMOVUPD XMM3, [R14];
VMOVUPD XMM4, [R14];
VMOVUPD XMM5, [R14];
VMOVUPD XMM6, [R14];
VMOVUPD XMM7, [R14]

Show nanoBench command
Results:
- MPERF: 3.48
- APERF: 4.0
- UOPS: 10.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 4.01
- FpuPipeAssignment.Total2: 4.01
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c5 f9 c6 c0 02       	vshufpd xmm0,xmm0,xmm0,0x2
   5:	c5 f1 c6 c9 02       	vshufpd xmm1,xmm1,xmm1,0x2
   a:	c5 e9 c6 d2 02       	vshufpd xmm2,xmm2,xmm2,0x2
   f:	c5 e1 c6 db 02       	vshufpd xmm3,xmm3,xmm3,0x2
  14:	c5 d9 c6 e4 02       	vshufpd xmm4,xmm4,xmm4,0x2
  19:	c5 d1 c6 ed 02       	vshufpd xmm5,xmm5,xmm5,0x2
  1e:	c5 c9 c6 f6 02       	vshufpd xmm6,xmm6,xmm6,0x2
  23:	c5 c1 c6 ff 02       	vshufpd xmm7,xmm7,xmm7,0x2

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 XMM1, [R14];
VMOVUPD XMM2, [R14];
VMOVUPD XMM3, [R14];
VMOVUPD XMM4, [R14];
VMOVUPD XMM5, [R14];
VMOVUPD XMM6, [R14];
VMOVUPD XMM7, [R14]

Show nanoBench command
Results:
- MPERF: 3.67
- APERF: 4.21
- UOPS: 8.2
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 13 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c5 f9 c6 c0 02       	vshufpd xmm0,xmm0,xmm0,0x2
   5:	c5 f1 c6 c9 02       	vshufpd xmm1,xmm1,xmm1,0x2
   a:	c5 e9 c6 d2 02       	vshufpd xmm2,xmm2,xmm2,0x2
   f:	c5 e1 c6 db 02       	vshufpd xmm3,xmm3,xmm3,0x2
  14:	c5 d9 c6 e4 02       	vshufpd xmm4,xmm4,xmm4,0x2
  19:	c5 d1 c6 ed 02       	vshufpd xmm5,xmm5,xmm5,0x2
  1e:	c5 c9 c6 f6 02       	vshufpd xmm6,xmm6,xmm6,0x2
  23:	c5 c1 c6 ff 02       	vshufpd xmm7,xmm7,xmm7,0x2
  28:	c4 41 39 c6 c0 02    	vshufpd xmm8,xmm8,xmm8,0x2
  2e:	c4 41 31 c6 c9 02    	vshufpd xmm9,xmm9,xmm9,0x2
  34:	c4 41 29 c6 d2 02    	vshufpd xmm10,xmm10,xmm10,0x2
  3a:	c4 41 21 c6 db 02    	vshufpd xmm11,xmm11,xmm11,0x2
  40:	c4 41 19 c6 e4 02    	vshufpd xmm12,xmm12,xmm12,0x2

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 XMM1, [R14];
VMOVUPD XMM2, [R14];
VMOVUPD XMM3, [R14];
VMOVUPD XMM4, [R14];
VMOVUPD XMM5, [R14];
VMOVUPD XMM6, [R14];
VMOVUPD XMM7, [R14];
VMOVUPD XMM8, [R14];
VMOVUPD XMM9, [R14];
VMOVUPD XMM10, [R14];
VMOVUPD XMM11, [R14];
VMOVUPD XMM12, [R14]

Show nanoBench command
Results:
- MPERF: 5.61
- APERF: 6.5
- UOPS: 13.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 6.5
- FpuPipeAssignment.Total2: 6.5
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c5 f9 c6 c0 02       	vshufpd xmm0,xmm0,xmm0,0x2
   5:	c5 f1 c6 c9 02       	vshufpd xmm1,xmm1,xmm1,0x2
   a:	c5 e9 c6 d2 02       	vshufpd xmm2,xmm2,xmm2,0x2
   f:	c5 e1 c6 db 02       	vshufpd xmm3,xmm3,xmm3,0x2
  14:	c5 d9 c6 e4 02       	vshufpd xmm4,xmm4,xmm4,0x2
  19:	c5 d1 c6 ed 02       	vshufpd xmm5,xmm5,xmm5,0x2
  1e:	c5 c9 c6 f6 02       	vshufpd xmm6,xmm6,xmm6,0x2
  23:	c5 c1 c6 ff 02       	vshufpd xmm7,xmm7,xmm7,0x2
  28:	c4 41 39 c6 c0 02    	vshufpd xmm8,xmm8,xmm8,0x2
  2e:	c4 41 31 c6 c9 02    	vshufpd xmm9,xmm9,xmm9,0x2
  34:	c4 41 29 c6 d2 02    	vshufpd xmm10,xmm10,xmm10,0x2
  3a:	c4 41 21 c6 db 02    	vshufpd xmm11,xmm11,xmm11,0x2
  40:	c4 41 19 c6 e4 02    	vshufpd xmm12,xmm12,xmm12,0x2

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 XMM1, [R14];
VMOVUPD XMM2, [R14];
VMOVUPD XMM3, [R14];
VMOVUPD XMM4, [R14];
VMOVUPD XMM5, [R14];
VMOVUPD XMM6, [R14];
VMOVUPD XMM7, [R14];
VMOVUPD XMM8, [R14];
VMOVUPD XMM9, [R14];
VMOVUPD XMM10, [R14];
VMOVUPD XMM11, [R14];
VMOVUPD XMM12, [R14]

Show nanoBench command
Results:
- MPERF: 5.67
- APERF: 6.5
- UOPS: 15.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 6.56
- FpuPipeAssignment.Total2: 6.5
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c5 f9 c6 c0 02       	vshufpd xmm0,xmm0,xmm0,0x2
   5:	c5 f1 c6 c9 02       	vshufpd xmm1,xmm1,xmm1,0x2
   a:	c5 e9 c6 d2 02       	vshufpd xmm2,xmm2,xmm2,0x2
   f:	c5 e1 c6 db 02       	vshufpd xmm3,xmm3,xmm3,0x2
  14:	c5 d9 c6 e4 02       	vshufpd xmm4,xmm4,xmm4,0x2
  19:	c5 d1 c6 ed 02       	vshufpd xmm5,xmm5,xmm5,0x2
  1e:	c5 c9 c6 f6 02       	vshufpd xmm6,xmm6,xmm6,0x2
  23:	c5 c1 c6 ff 02       	vshufpd xmm7,xmm7,xmm7,0x2
  28:	c4 41 39 c6 c0 02    	vshufpd xmm8,xmm8,xmm8,0x2
  2e:	c4 41 31 c6 c9 02    	vshufpd xmm9,xmm9,xmm9,0x2
  34:	c4 41 29 c6 d2 02    	vshufpd xmm10,xmm10,xmm10,0x2
  3a:	c4 41 21 c6 db 02    	vshufpd xmm11,xmm11,xmm11,0x2
  40:	c4 41 19 c6 e4 02    	vshufpd xmm12,xmm12,xmm12,0x2

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 XMM1, [R14];
VMOVUPD XMM2, [R14];
VMOVUPD XMM3, [R14];
VMOVUPD XMM4, [R14];
VMOVUPD XMM5, [R14];
VMOVUPD XMM6, [R14];
VMOVUPD XMM7, [R14];
VMOVUPD XMM8, [R14];
VMOVUPD XMM9, [R14];
VMOVUPD XMM10, [R14];
VMOVUPD XMM11, [R14];
VMOVUPD XMM12, [R14]

Show nanoBench command
Results:
- MPERF: 5.68
- APERF: 6.51
- UOPS: 13.2
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 6.5
- FpuPipeAssignment.Total2: 6.5
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

VSHUFPD (XMM, XMM, XMM, I8) - 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