VADDPD (YMM, YMM, YMM)

With unroll_count=500 and no inner loop

Code:

   0:	c5 f5 58 c2          	vaddpd 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: 0.87
- APERF: 1.0
- UOPS: 2.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 1.0
- FpuPipeAssignment.Total3: 1.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	c5 f5 58 c2          	vaddpd 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: 0.87
- APERF: 1.0
- UOPS: 2.2
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 1.0
- FpuPipeAssignment.Total3: 1.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	c5 f5 58 c2          	vaddpd 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: 0.87
- APERF: 1.0
- UOPS: 2.02
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 1.0
- FpuPipeAssignment.Total3: 1.0
- DIV_CYCLES: 0.0

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

   0:	c5 f5 58 c2          	vaddpd ymm0,ymm1,ymm2
   4:	c5 f5 58 da          	vaddpd ymm3,ymm1,ymm2
   8:	c5 f5 58 e2          	vaddpd ymm4,ymm1,ymm2
   c:	c5 f5 58 ea          	vaddpd 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: 3.49
- APERF: 4.0
- UOPS: 8.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 4.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=2

Code:

   0:	c5 f5 58 c2          	vaddpd ymm0,ymm1,ymm2
   4:	c5 f5 58 da          	vaddpd ymm3,ymm1,ymm2
   8:	c5 f5 58 e2          	vaddpd ymm4,ymm1,ymm2
   c:	c5 f5 58 ea          	vaddpd 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: 3.49
- APERF: 4.0
- UOPS: 9.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 4.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=20

Code:

   0:	c5 f5 58 c2          	vaddpd ymm0,ymm1,ymm2
   4:	c5 f5 58 da          	vaddpd ymm3,ymm1,ymm2
   8:	c5 f5 58 e2          	vaddpd ymm4,ymm1,ymm2
   c:	c5 f5 58 ea          	vaddpd 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: 3.49
- APERF: 4.0
- UOPS: 8.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 4.0
- DIV_CYCLES: 0.0

With 8 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c5 f5 58 c2          	vaddpd ymm0,ymm1,ymm2
   4:	c5 f5 58 da          	vaddpd ymm3,ymm1,ymm2
   8:	c5 f5 58 e2          	vaddpd ymm4,ymm1,ymm2
   c:	c5 f5 58 ea          	vaddpd ymm5,ymm1,ymm2
  10:	c5 f5 58 f2          	vaddpd ymm6,ymm1,ymm2
  14:	c5 f5 58 fa          	vaddpd ymm7,ymm1,ymm2
  18:	c5 75 58 c2          	vaddpd ymm8,ymm1,ymm2
  1c:	c5 75 58 ca          	vaddpd 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: 6.97
- APERF: 8.0
- UOPS: 16.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 8.0
- FpuPipeAssignment.Total3: 8.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c5 f5 58 c2          	vaddpd ymm0,ymm1,ymm2
   4:	c5 f5 58 da          	vaddpd ymm3,ymm1,ymm2
   8:	c5 f5 58 e2          	vaddpd ymm4,ymm1,ymm2
   c:	c5 f5 58 ea          	vaddpd ymm5,ymm1,ymm2
  10:	c5 f5 58 f2          	vaddpd ymm6,ymm1,ymm2
  14:	c5 f5 58 fa          	vaddpd ymm7,ymm1,ymm2
  18:	c5 75 58 c2          	vaddpd ymm8,ymm1,ymm2
  1c:	c5 75 58 ca          	vaddpd 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: 6.97
- APERF: 8.0
- UOPS: 18.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 8.0
- FpuPipeAssignment.Total3: 8.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c5 f5 58 c2          	vaddpd ymm0,ymm1,ymm2
   4:	c5 f5 58 da          	vaddpd ymm3,ymm1,ymm2
   8:	c5 f5 58 e2          	vaddpd ymm4,ymm1,ymm2
   c:	c5 f5 58 ea          	vaddpd ymm5,ymm1,ymm2
  10:	c5 f5 58 f2          	vaddpd ymm6,ymm1,ymm2
  14:	c5 f5 58 fa          	vaddpd ymm7,ymm1,ymm2
  18:	c5 75 58 c2          	vaddpd ymm8,ymm1,ymm2
  1c:	c5 75 58 ca          	vaddpd 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: 6.97
- APERF: 8.0
- UOPS: 16.2
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 8.0
- FpuPipeAssignment.Total3: 8.0
- DIV_CYCLES: 0.0

With 11 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c5 f5 58 c2          	vaddpd ymm0,ymm1,ymm2
   4:	c5 f5 58 da          	vaddpd ymm3,ymm1,ymm2
   8:	c5 f5 58 e2          	vaddpd ymm4,ymm1,ymm2
   c:	c5 f5 58 ea          	vaddpd ymm5,ymm1,ymm2
  10:	c5 f5 58 f2          	vaddpd ymm6,ymm1,ymm2
  14:	c5 f5 58 fa          	vaddpd ymm7,ymm1,ymm2
  18:	c5 75 58 c2          	vaddpd ymm8,ymm1,ymm2
  1c:	c5 75 58 ca          	vaddpd ymm9,ymm1,ymm2
  20:	c5 75 58 d2          	vaddpd ymm10,ymm1,ymm2
  24:	c5 75 58 da          	vaddpd ymm11,ymm1,ymm2
  28:	c5 75 58 e2          	vaddpd 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: 9.63
- APERF: 11.0
- UOPS: 22.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 11.0
- FpuPipeAssignment.Total3: 11.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c5 f5 58 c2          	vaddpd ymm0,ymm1,ymm2
   4:	c5 f5 58 da          	vaddpd ymm3,ymm1,ymm2
   8:	c5 f5 58 e2          	vaddpd ymm4,ymm1,ymm2
   c:	c5 f5 58 ea          	vaddpd ymm5,ymm1,ymm2
  10:	c5 f5 58 f2          	vaddpd ymm6,ymm1,ymm2
  14:	c5 f5 58 fa          	vaddpd ymm7,ymm1,ymm2
  18:	c5 75 58 c2          	vaddpd ymm8,ymm1,ymm2
  1c:	c5 75 58 ca          	vaddpd ymm9,ymm1,ymm2
  20:	c5 75 58 d2          	vaddpd ymm10,ymm1,ymm2
  24:	c5 75 58 da          	vaddpd ymm11,ymm1,ymm2
  28:	c5 75 58 e2          	vaddpd 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: 9.59
- APERF: 11.0
- UOPS: 24.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 11.0
- FpuPipeAssignment.Total3: 11.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c5 f5 58 c2          	vaddpd ymm0,ymm1,ymm2
   4:	c5 f5 58 da          	vaddpd ymm3,ymm1,ymm2
   8:	c5 f5 58 e2          	vaddpd ymm4,ymm1,ymm2
   c:	c5 f5 58 ea          	vaddpd ymm5,ymm1,ymm2
  10:	c5 f5 58 f2          	vaddpd ymm6,ymm1,ymm2
  14:	c5 f5 58 fa          	vaddpd ymm7,ymm1,ymm2
  18:	c5 75 58 c2          	vaddpd ymm8,ymm1,ymm2
  1c:	c5 75 58 ca          	vaddpd ymm9,ymm1,ymm2
  20:	c5 75 58 d2          	vaddpd ymm10,ymm1,ymm2
  24:	c5 75 58 da          	vaddpd ymm11,ymm1,ymm2
  28:	c5 75 58 e2          	vaddpd 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: 9.59
- APERF: 11.0
- UOPS: 22.2
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 11.0
- FpuPipeAssignment.Total3: 11.0
- 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 fd 58 c0          	vaddpd 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: 2.62
- APERF: 3.0
- UOPS: 2.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 1.0
- FpuPipeAssignment.Total3: 1.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	c5 fd 58 c0          	vaddpd 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: 2.61
- APERF: 3.0
- UOPS: 2.2
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 1.0
- FpuPipeAssignment.Total3: 1.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	c5 fd 58 c0          	vaddpd 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: 2.61
- APERF: 3.0
- UOPS: 2.02
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 1.0
- FpuPipeAssignment.Total3: 1.0
- DIV_CYCLES: 0.0

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

   0:	c5 fd 58 c0          	vaddpd ymm0,ymm0,ymm0
   4:	c5 f5 58 c9          	vaddpd ymm1,ymm1,ymm1
   8:	c5 ed 58 d2          	vaddpd ymm2,ymm2,ymm2
   c:	c5 e5 58 db          	vaddpd 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: 3.49
- APERF: 4.0
- UOPS: 8.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 4.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=2

Code:

   0:	c5 fd 58 c0          	vaddpd ymm0,ymm0,ymm0
   4:	c5 f5 58 c9          	vaddpd ymm1,ymm1,ymm1
   8:	c5 ed 58 d2          	vaddpd ymm2,ymm2,ymm2
   c:	c5 e5 58 db          	vaddpd 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: 3.49
- APERF: 4.0
- UOPS: 9.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 4.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=20

Code:

   0:	c5 fd 58 c0          	vaddpd ymm0,ymm0,ymm0
   4:	c5 f5 58 c9          	vaddpd ymm1,ymm1,ymm1
   8:	c5 ed 58 d2          	vaddpd ymm2,ymm2,ymm2
   c:	c5 e5 58 db          	vaddpd 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: 3.49
- APERF: 4.0
- UOPS: 8.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 4.0
- DIV_CYCLES: 0.0

With 8 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c5 fd 58 c0          	vaddpd ymm0,ymm0,ymm0
   4:	c5 f5 58 c9          	vaddpd ymm1,ymm1,ymm1
   8:	c5 ed 58 d2          	vaddpd ymm2,ymm2,ymm2
   c:	c5 e5 58 db          	vaddpd ymm3,ymm3,ymm3
  10:	c5 dd 58 e4          	vaddpd ymm4,ymm4,ymm4
  14:	c5 d5 58 ed          	vaddpd ymm5,ymm5,ymm5
  18:	c5 cd 58 f6          	vaddpd ymm6,ymm6,ymm6
  1c:	c5 c5 58 ff          	vaddpd 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: 6.97
- APERF: 8.0
- UOPS: 16.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 8.0
- FpuPipeAssignment.Total3: 8.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c5 fd 58 c0          	vaddpd ymm0,ymm0,ymm0
   4:	c5 f5 58 c9          	vaddpd ymm1,ymm1,ymm1
   8:	c5 ed 58 d2          	vaddpd ymm2,ymm2,ymm2
   c:	c5 e5 58 db          	vaddpd ymm3,ymm3,ymm3
  10:	c5 dd 58 e4          	vaddpd ymm4,ymm4,ymm4
  14:	c5 d5 58 ed          	vaddpd ymm5,ymm5,ymm5
  18:	c5 cd 58 f6          	vaddpd ymm6,ymm6,ymm6
  1c:	c5 c5 58 ff          	vaddpd 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: 6.97
- APERF: 8.0
- UOPS: 18.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 8.0
- FpuPipeAssignment.Total3: 8.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c5 fd 58 c0          	vaddpd ymm0,ymm0,ymm0
   4:	c5 f5 58 c9          	vaddpd ymm1,ymm1,ymm1
   8:	c5 ed 58 d2          	vaddpd ymm2,ymm2,ymm2
   c:	c5 e5 58 db          	vaddpd ymm3,ymm3,ymm3
  10:	c5 dd 58 e4          	vaddpd ymm4,ymm4,ymm4
  14:	c5 d5 58 ed          	vaddpd ymm5,ymm5,ymm5
  18:	c5 cd 58 f6          	vaddpd ymm6,ymm6,ymm6
  1c:	c5 c5 58 ff          	vaddpd 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: 6.97
- APERF: 8.0
- UOPS: 16.2
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 8.0
- FpuPipeAssignment.Total3: 8.0
- DIV_CYCLES: 0.0

With 13 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c5 fd 58 c0          	vaddpd ymm0,ymm0,ymm0
   4:	c5 f5 58 c9          	vaddpd ymm1,ymm1,ymm1
   8:	c5 ed 58 d2          	vaddpd ymm2,ymm2,ymm2
   c:	c5 e5 58 db          	vaddpd ymm3,ymm3,ymm3
  10:	c5 dd 58 e4          	vaddpd ymm4,ymm4,ymm4
  14:	c5 d5 58 ed          	vaddpd ymm5,ymm5,ymm5
  18:	c5 cd 58 f6          	vaddpd ymm6,ymm6,ymm6
  1c:	c5 c5 58 ff          	vaddpd ymm7,ymm7,ymm7
  20:	c4 41 3d 58 c0       	vaddpd ymm8,ymm8,ymm8
  25:	c4 41 35 58 c9       	vaddpd ymm9,ymm9,ymm9
  2a:	c4 41 2d 58 d2       	vaddpd ymm10,ymm10,ymm10
  2f:	c4 41 25 58 db       	vaddpd ymm11,ymm11,ymm11
  34:	c4 41 1d 58 e4       	vaddpd 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: 11.45
- APERF: 13.0
- UOPS: 26.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 13.0
- FpuPipeAssignment.Total3: 13.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c5 fd 58 c0          	vaddpd ymm0,ymm0,ymm0
   4:	c5 f5 58 c9          	vaddpd ymm1,ymm1,ymm1
   8:	c5 ed 58 d2          	vaddpd ymm2,ymm2,ymm2
   c:	c5 e5 58 db          	vaddpd ymm3,ymm3,ymm3
  10:	c5 dd 58 e4          	vaddpd ymm4,ymm4,ymm4
  14:	c5 d5 58 ed          	vaddpd ymm5,ymm5,ymm5
  18:	c5 cd 58 f6          	vaddpd ymm6,ymm6,ymm6
  1c:	c5 c5 58 ff          	vaddpd ymm7,ymm7,ymm7
  20:	c4 41 3d 58 c0       	vaddpd ymm8,ymm8,ymm8
  25:	c4 41 35 58 c9       	vaddpd ymm9,ymm9,ymm9
  2a:	c4 41 2d 58 d2       	vaddpd ymm10,ymm10,ymm10
  2f:	c4 41 25 58 db       	vaddpd ymm11,ymm11,ymm11
  34:	c4 41 1d 58 e4       	vaddpd 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: 11.33
- APERF: 13.0
- UOPS: 28.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 13.0
- FpuPipeAssignment.Total3: 13.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c5 fd 58 c0          	vaddpd ymm0,ymm0,ymm0
   4:	c5 f5 58 c9          	vaddpd ymm1,ymm1,ymm1
   8:	c5 ed 58 d2          	vaddpd ymm2,ymm2,ymm2
   c:	c5 e5 58 db          	vaddpd ymm3,ymm3,ymm3
  10:	c5 dd 58 e4          	vaddpd ymm4,ymm4,ymm4
  14:	c5 d5 58 ed          	vaddpd ymm5,ymm5,ymm5
  18:	c5 cd 58 f6          	vaddpd ymm6,ymm6,ymm6
  1c:	c5 c5 58 ff          	vaddpd ymm7,ymm7,ymm7
  20:	c4 41 3d 58 c0       	vaddpd ymm8,ymm8,ymm8
  25:	c4 41 35 58 c9       	vaddpd ymm9,ymm9,ymm9
  2a:	c4 41 2d 58 d2       	vaddpd ymm10,ymm10,ymm10
  2f:	c4 41 25 58 db       	vaddpd ymm11,ymm11,ymm11
  34:	c4 41 1d 58 e4       	vaddpd 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: 11.34
- APERF: 13.01
- UOPS: 26.2
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 13.0
- FpuPipeAssignment.Total3: 13.0
- DIV_CYCLES: 0.0

VADDPD (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