VCMPPD (XMM, XMM, XMM, I8)

With unroll_count=500 and no inner loop

Code:

   0:	c5 f1 c2 c2 02       	vcmplepd xmm0,xmm1,xmm2

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: 0.43
- APERF: 0.5
- UOPS: 1.0
- FpuPipeAssignment.Total0: 0.5
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	c5 f1 c2 c2 02       	vcmplepd xmm0,xmm1,xmm2

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: 0.42
- APERF: 0.5
- UOPS: 1.2
- FpuPipeAssignment.Total0: 0.51
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	c5 f1 c2 c2 02       	vcmplepd xmm0,xmm1,xmm2

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: 0.42
- APERF: 0.5
- UOPS: 1.02
- FpuPipeAssignment.Total0: 0.5
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

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

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: 1.68
- APERF: 2.0
- UOPS: 4.0
- FpuPipeAssignment.Total0: 2.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=2

Code:

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

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: 1.69
- APERF: 2.0
- UOPS: 5.0
- FpuPipeAssignment.Total0: 2.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=20

Code:

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

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: 1.69
- APERF: 2.0
- UOPS: 4.1
- FpuPipeAssignment.Total0: 2.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 8 independent instructions

With unroll_count=100 and no inner loop

Code:

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

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: 3.42
- APERF: 4.0
- UOPS: 8.0
- FpuPipeAssignment.Total0: 4.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

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

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: 3.38
- APERF: 4.01
- UOPS: 10.0
- FpuPipeAssignment.Total0: 4.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

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

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: 3.38
- APERF: 4.01
- UOPS: 8.2
- FpuPipeAssignment.Total0: 4.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 11 independent instructions

With unroll_count=100 and no inner loop

Code:

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

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: 4.68
- APERF: 5.5
- UOPS: 11.0
- FpuPipeAssignment.Total0: 5.5
- FpuPipeAssignment.Total1: 5.5
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

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

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: 4.64
- APERF: 5.51
- UOPS: 13.0
- FpuPipeAssignment.Total0: 5.5
- FpuPipeAssignment.Total1: 5.5
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

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

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: 4.64
- APERF: 5.51
- UOPS: 11.2
- FpuPipeAssignment.Total0: 5.5
- FpuPipeAssignment.Total1: 5.5
- FpuPipeAssignment.Total2: 0.0
- 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 c2 c0 02       	vcmplepd 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]

Show nanoBench command
Results:
- MPERF: 0.8
- APERF: 1.0
- UOPS: 1.0
- FpuPipeAssignment.Total0: 0.5
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	c5 f9 c2 c0 02       	vcmplepd 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]

Show nanoBench command
Results:
- MPERF: 0.84
- APERF: 1.0
- UOPS: 1.2
- FpuPipeAssignment.Total0: 0.5
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	c5 f9 c2 c0 02       	vcmplepd 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]

Show nanoBench command
Results:
- MPERF: 0.84
- APERF: 1.0
- UOPS: 1.02
- FpuPipeAssignment.Total0: 0.5
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

   0:	c5 f9 c2 c0 02       	vcmplepd xmm0,xmm0,xmm0
   5:	c5 f1 c2 c9 02       	vcmplepd xmm1,xmm1,xmm1
   a:	c5 e9 c2 d2 02       	vcmplepd xmm2,xmm2,xmm2
   f:	c5 e1 c2 db 02       	vcmplepd xmm3,xmm3,xmm3

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: 1.68
- APERF: 2.0
- UOPS: 4.0
- FpuPipeAssignment.Total0: 2.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=2

Code:

   0:	c5 f9 c2 c0 02       	vcmplepd xmm0,xmm0,xmm0
   5:	c5 f1 c2 c9 02       	vcmplepd xmm1,xmm1,xmm1
   a:	c5 e9 c2 d2 02       	vcmplepd xmm2,xmm2,xmm2
   f:	c5 e1 c2 db 02       	vcmplepd xmm3,xmm3,xmm3

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: 1.69
- APERF: 2.01
- UOPS: 5.0
- FpuPipeAssignment.Total0: 1.99
- FpuPipeAssignment.Total1: 1.99
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=20

Code:

   0:	c5 f9 c2 c0 02       	vcmplepd xmm0,xmm0,xmm0
   5:	c5 f1 c2 c9 02       	vcmplepd xmm1,xmm1,xmm1
   a:	c5 e9 c2 d2 02       	vcmplepd xmm2,xmm2,xmm2
   f:	c5 e1 c2 db 02       	vcmplepd xmm3,xmm3,xmm3

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: 1.68
- APERF: 2.0
- UOPS: 4.1
- FpuPipeAssignment.Total0: 2.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 8 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c5 f9 c2 c0 02       	vcmplepd xmm0,xmm0,xmm0
   5:	c5 f1 c2 c9 02       	vcmplepd xmm1,xmm1,xmm1
   a:	c5 e9 c2 d2 02       	vcmplepd xmm2,xmm2,xmm2
   f:	c5 e1 c2 db 02       	vcmplepd xmm3,xmm3,xmm3
  14:	c5 d9 c2 e4 02       	vcmplepd xmm4,xmm4,xmm4
  19:	c5 d1 c2 ed 02       	vcmplepd xmm5,xmm5,xmm5
  1e:	c5 c9 c2 f6 02       	vcmplepd xmm6,xmm6,xmm6
  23:	c5 c1 c2 ff 02       	vcmplepd xmm7,xmm7,xmm7

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: 3.3
- APERF: 4.0
- UOPS: 8.0
- FpuPipeAssignment.Total0: 4.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c5 f9 c2 c0 02       	vcmplepd xmm0,xmm0,xmm0
   5:	c5 f1 c2 c9 02       	vcmplepd xmm1,xmm1,xmm1
   a:	c5 e9 c2 d2 02       	vcmplepd xmm2,xmm2,xmm2
   f:	c5 e1 c2 db 02       	vcmplepd xmm3,xmm3,xmm3
  14:	c5 d9 c2 e4 02       	vcmplepd xmm4,xmm4,xmm4
  19:	c5 d1 c2 ed 02       	vcmplepd xmm5,xmm5,xmm5
  1e:	c5 c9 c2 f6 02       	vcmplepd xmm6,xmm6,xmm6
  23:	c5 c1 c2 ff 02       	vcmplepd xmm7,xmm7,xmm7

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: 3.38
- APERF: 4.01
- UOPS: 10.0
- FpuPipeAssignment.Total0: 4.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c5 f9 c2 c0 02       	vcmplepd xmm0,xmm0,xmm0
   5:	c5 f1 c2 c9 02       	vcmplepd xmm1,xmm1,xmm1
   a:	c5 e9 c2 d2 02       	vcmplepd xmm2,xmm2,xmm2
   f:	c5 e1 c2 db 02       	vcmplepd xmm3,xmm3,xmm3
  14:	c5 d9 c2 e4 02       	vcmplepd xmm4,xmm4,xmm4
  19:	c5 d1 c2 ed 02       	vcmplepd xmm5,xmm5,xmm5
  1e:	c5 c9 c2 f6 02       	vcmplepd xmm6,xmm6,xmm6
  23:	c5 c1 c2 ff 02       	vcmplepd xmm7,xmm7,xmm7

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: 3.38
- APERF: 4.01
- UOPS: 8.2
- FpuPipeAssignment.Total0: 4.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 13 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c5 f9 c2 c0 02       	vcmplepd xmm0,xmm0,xmm0
   5:	c5 f1 c2 c9 02       	vcmplepd xmm1,xmm1,xmm1
   a:	c5 e9 c2 d2 02       	vcmplepd xmm2,xmm2,xmm2
   f:	c5 e1 c2 db 02       	vcmplepd xmm3,xmm3,xmm3
  14:	c5 d9 c2 e4 02       	vcmplepd xmm4,xmm4,xmm4
  19:	c5 d1 c2 ed 02       	vcmplepd xmm5,xmm5,xmm5
  1e:	c5 c9 c2 f6 02       	vcmplepd xmm6,xmm6,xmm6
  23:	c5 c1 c2 ff 02       	vcmplepd xmm7,xmm7,xmm7
  28:	c4 41 39 c2 c0 02    	vcmplepd xmm8,xmm8,xmm8
  2e:	c4 41 31 c2 c9 02    	vcmplepd xmm9,xmm9,xmm9
  34:	c4 41 29 c2 d2 02    	vcmplepd xmm10,xmm10,xmm10
  3a:	c4 41 21 c2 db 02    	vcmplepd xmm11,xmm11,xmm11
  40:	c4 41 19 c2 e4 02    	vcmplepd xmm12,xmm12,xmm12

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: 5.52
- APERF: 6.5
- UOPS: 13.0
- FpuPipeAssignment.Total0: 6.5
- FpuPipeAssignment.Total1: 6.5
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c5 f9 c2 c0 02       	vcmplepd xmm0,xmm0,xmm0
   5:	c5 f1 c2 c9 02       	vcmplepd xmm1,xmm1,xmm1
   a:	c5 e9 c2 d2 02       	vcmplepd xmm2,xmm2,xmm2
   f:	c5 e1 c2 db 02       	vcmplepd xmm3,xmm3,xmm3
  14:	c5 d9 c2 e4 02       	vcmplepd xmm4,xmm4,xmm4
  19:	c5 d1 c2 ed 02       	vcmplepd xmm5,xmm5,xmm5
  1e:	c5 c9 c2 f6 02       	vcmplepd xmm6,xmm6,xmm6
  23:	c5 c1 c2 ff 02       	vcmplepd xmm7,xmm7,xmm7
  28:	c4 41 39 c2 c0 02    	vcmplepd xmm8,xmm8,xmm8
  2e:	c4 41 31 c2 c9 02    	vcmplepd xmm9,xmm9,xmm9
  34:	c4 41 29 c2 d2 02    	vcmplepd xmm10,xmm10,xmm10
  3a:	c4 41 21 c2 db 02    	vcmplepd xmm11,xmm11,xmm11
  40:	c4 41 19 c2 e4 02    	vcmplepd xmm12,xmm12,xmm12

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: 5.48
- APERF: 6.51
- UOPS: 15.0
- FpuPipeAssignment.Total0: 6.56
- FpuPipeAssignment.Total1: 6.5
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c5 f9 c2 c0 02       	vcmplepd xmm0,xmm0,xmm0
   5:	c5 f1 c2 c9 02       	vcmplepd xmm1,xmm1,xmm1
   a:	c5 e9 c2 d2 02       	vcmplepd xmm2,xmm2,xmm2
   f:	c5 e1 c2 db 02       	vcmplepd xmm3,xmm3,xmm3
  14:	c5 d9 c2 e4 02       	vcmplepd xmm4,xmm4,xmm4
  19:	c5 d1 c2 ed 02       	vcmplepd xmm5,xmm5,xmm5
  1e:	c5 c9 c2 f6 02       	vcmplepd xmm6,xmm6,xmm6
  23:	c5 c1 c2 ff 02       	vcmplepd xmm7,xmm7,xmm7
  28:	c4 41 39 c2 c0 02    	vcmplepd xmm8,xmm8,xmm8
  2e:	c4 41 31 c2 c9 02    	vcmplepd xmm9,xmm9,xmm9
  34:	c4 41 29 c2 d2 02    	vcmplepd xmm10,xmm10,xmm10
  3a:	c4 41 21 c2 db 02    	vcmplepd xmm11,xmm11,xmm11
  40:	c4 41 19 c2 e4 02    	vcmplepd xmm12,xmm12,xmm12

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: 5.48
- APERF: 6.51
- UOPS: 13.2
- FpuPipeAssignment.Total0: 6.5
- FpuPipeAssignment.Total1: 6.5
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

VCMPPD (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