VFMADD231PS (ZMM, ZMM, ZMM)

With unroll_count=500 and no inner loop

Code:

   0:	62 f2 75 48 b8 c2    	vfmadd231ps zmm0,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14]

Show nanoBench command
Results:
- MPERF: 3.42
- APERF: 4.0
- UOPS: 1.0
- FpuPipeAssignment.Total0: 0.5
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.0
- 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:	62 f2 75 48 b8 c2    	vfmadd231ps zmm0,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14]

Show nanoBench command
Results:
- MPERF: 3.45
- APERF: 4.0
- UOPS: 1.1
- FpuPipeAssignment.Total0: 0.5
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.0
- 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:	62 f2 75 48 b8 c2    	vfmadd231ps zmm0,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14]

Show nanoBench command
Results:
- MPERF: 3.45
- APERF: 4.0
- UOPS: 1.01
- FpuPipeAssignment.Total0: 0.5
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.0
- 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:	62 f2 75 48 b8 c2    	vfmadd231ps zmm0,zmm1,zmm2
   6:	62 f2 75 48 b8 da    	vfmadd231ps zmm3,zmm1,zmm2
   c:	62 f2 75 48 b8 e2    	vfmadd231ps zmm4,zmm1,zmm2
  12:	62 f2 75 48 b8 ea    	vfmadd231ps zmm5,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14];
VMOVUPD ZMM3, [R14];
VMOVUPD ZMM4, [R14];
VMOVUPD ZMM5, [R14]

Show nanoBench command
Results:
- MPERF: 3.53
- APERF: 4.0
- UOPS: 4.0
- FpuPipeAssignment.Total0: 2.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 0.0
- 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:	62 f2 75 48 b8 c2    	vfmadd231ps zmm0,zmm1,zmm2
   6:	62 f2 75 48 b8 da    	vfmadd231ps zmm3,zmm1,zmm2
   c:	62 f2 75 48 b8 e2    	vfmadd231ps zmm4,zmm1,zmm2
  12:	62 f2 75 48 b8 ea    	vfmadd231ps zmm5,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14];
VMOVUPD ZMM3, [R14];
VMOVUPD ZMM4, [R14];
VMOVUPD ZMM5, [R14]

Show nanoBench command
Results:
- MPERF: 3.45
- APERF: 4.0
- UOPS: 4.5
- FpuPipeAssignment.Total0: 2.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 0.0
- 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:	62 f2 75 48 b8 c2    	vfmadd231ps zmm0,zmm1,zmm2
   6:	62 f2 75 48 b8 da    	vfmadd231ps zmm3,zmm1,zmm2
   c:	62 f2 75 48 b8 e2    	vfmadd231ps zmm4,zmm1,zmm2
  12:	62 f2 75 48 b8 ea    	vfmadd231ps zmm5,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14];
VMOVUPD ZMM3, [R14];
VMOVUPD ZMM4, [R14];
VMOVUPD ZMM5, [R14]

Show nanoBench command
Results:
- MPERF: 3.45
- APERF: 4.0
- UOPS: 4.05
- FpuPipeAssignment.Total0: 2.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 0.0
- 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:	62 f2 75 48 b8 c2    	vfmadd231ps zmm0,zmm1,zmm2
   6:	62 f2 75 48 b8 da    	vfmadd231ps zmm3,zmm1,zmm2
   c:	62 f2 75 48 b8 e2    	vfmadd231ps zmm4,zmm1,zmm2
  12:	62 f2 75 48 b8 ea    	vfmadd231ps zmm5,zmm1,zmm2
  18:	62 f2 75 48 b8 f2    	vfmadd231ps zmm6,zmm1,zmm2
  1e:	62 f2 75 48 b8 fa    	vfmadd231ps zmm7,zmm1,zmm2
  24:	62 72 75 48 b8 c2    	vfmadd231ps zmm8,zmm1,zmm2
  2a:	62 72 75 48 b8 ca    	vfmadd231ps zmm9,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14];
VMOVUPD ZMM3, [R14];
VMOVUPD ZMM4, [R14];
VMOVUPD ZMM5, [R14];
VMOVUPD ZMM6, [R14];
VMOVUPD ZMM7, [R14];
VMOVUPD ZMM8, [R14];
VMOVUPD ZMM9, [R14]

Show nanoBench command
Results:
- MPERF: 6.82
- APERF: 8.0
- UOPS: 8.0
- FpuPipeAssignment.Total0: 4.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 0.0
- 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:	62 f2 75 48 b8 c2    	vfmadd231ps zmm0,zmm1,zmm2
   6:	62 f2 75 48 b8 da    	vfmadd231ps zmm3,zmm1,zmm2
   c:	62 f2 75 48 b8 e2    	vfmadd231ps zmm4,zmm1,zmm2
  12:	62 f2 75 48 b8 ea    	vfmadd231ps zmm5,zmm1,zmm2
  18:	62 f2 75 48 b8 f2    	vfmadd231ps zmm6,zmm1,zmm2
  1e:	62 f2 75 48 b8 fa    	vfmadd231ps zmm7,zmm1,zmm2
  24:	62 72 75 48 b8 c2    	vfmadd231ps zmm8,zmm1,zmm2
  2a:	62 72 75 48 b8 ca    	vfmadd231ps zmm9,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14];
VMOVUPD ZMM3, [R14];
VMOVUPD ZMM4, [R14];
VMOVUPD ZMM5, [R14];
VMOVUPD ZMM6, [R14];
VMOVUPD ZMM7, [R14];
VMOVUPD ZMM8, [R14];
VMOVUPD ZMM9, [R14]

Show nanoBench command
Results:
- MPERF: 6.91
- APERF: 8.01
- UOPS: 9.0
- FpuPipeAssignment.Total0: 4.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 0.0
- 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:	62 f2 75 48 b8 c2    	vfmadd231ps zmm0,zmm1,zmm2
   6:	62 f2 75 48 b8 da    	vfmadd231ps zmm3,zmm1,zmm2
   c:	62 f2 75 48 b8 e2    	vfmadd231ps zmm4,zmm1,zmm2
  12:	62 f2 75 48 b8 ea    	vfmadd231ps zmm5,zmm1,zmm2
  18:	62 f2 75 48 b8 f2    	vfmadd231ps zmm6,zmm1,zmm2
  1e:	62 f2 75 48 b8 fa    	vfmadd231ps zmm7,zmm1,zmm2
  24:	62 72 75 48 b8 c2    	vfmadd231ps zmm8,zmm1,zmm2
  2a:	62 72 75 48 b8 ca    	vfmadd231ps zmm9,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14];
VMOVUPD ZMM3, [R14];
VMOVUPD ZMM4, [R14];
VMOVUPD ZMM5, [R14];
VMOVUPD ZMM6, [R14];
VMOVUPD ZMM7, [R14];
VMOVUPD ZMM8, [R14];
VMOVUPD ZMM9, [R14]

Show nanoBench command
Results:
- MPERF: 6.91
- APERF: 8.01
- UOPS: 8.1
- FpuPipeAssignment.Total0: 4.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With 16 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	62 f2 75 48 b8 c2    	vfmadd231ps zmm0,zmm1,zmm2
   6:	62 f2 75 48 b8 da    	vfmadd231ps zmm3,zmm1,zmm2
   c:	62 f2 75 48 b8 e2    	vfmadd231ps zmm4,zmm1,zmm2
  12:	62 f2 75 48 b8 ea    	vfmadd231ps zmm5,zmm1,zmm2
  18:	62 f2 75 48 b8 f2    	vfmadd231ps zmm6,zmm1,zmm2
  1e:	62 f2 75 48 b8 fa    	vfmadd231ps zmm7,zmm1,zmm2
  24:	62 72 75 48 b8 c2    	vfmadd231ps zmm8,zmm1,zmm2
  2a:	62 72 75 48 b8 ca    	vfmadd231ps zmm9,zmm1,zmm2
  30:	62 72 75 48 b8 d2    	vfmadd231ps zmm10,zmm1,zmm2
  36:	62 72 75 48 b8 da    	vfmadd231ps zmm11,zmm1,zmm2
  3c:	62 72 75 48 b8 e2    	vfmadd231ps zmm12,zmm1,zmm2
  42:	62 e2 75 48 b8 c2    	vfmadd231ps zmm16,zmm1,zmm2
  48:	62 e2 75 48 b8 ca    	vfmadd231ps zmm17,zmm1,zmm2
  4e:	62 e2 75 48 b8 d2    	vfmadd231ps zmm18,zmm1,zmm2
  54:	62 e2 75 48 b8 da    	vfmadd231ps zmm19,zmm1,zmm2
  5a:	62 e2 75 48 b8 e2    	vfmadd231ps zmm20,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14];
VMOVUPD ZMM3, [R14];
VMOVUPD ZMM4, [R14];
VMOVUPD ZMM5, [R14];
VMOVUPD ZMM6, [R14];
VMOVUPD ZMM7, [R14];
VMOVUPD ZMM8, [R14];
VMOVUPD ZMM9, [R14];
VMOVUPD ZMM10, [R14];
VMOVUPD ZMM11, [R14];
VMOVUPD ZMM12, [R14];
VMOVUPD ZMM16, [R14];
VMOVUPD ZMM17, [R14];
VMOVUPD ZMM18, [R14];
VMOVUPD ZMM19, [R14];
VMOVUPD ZMM20, [R14]

Show nanoBench command
Results:
- MPERF: 13.94
- APERF: 16.0
- UOPS: 16.0
- FpuPipeAssignment.Total0: 8.0
- FpuPipeAssignment.Total1: 8.0
- FpuPipeAssignment.Total2: 0.0
- 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:	62 f2 75 48 b8 c2    	vfmadd231ps zmm0,zmm1,zmm2
   6:	62 f2 75 48 b8 da    	vfmadd231ps zmm3,zmm1,zmm2
   c:	62 f2 75 48 b8 e2    	vfmadd231ps zmm4,zmm1,zmm2
  12:	62 f2 75 48 b8 ea    	vfmadd231ps zmm5,zmm1,zmm2
  18:	62 f2 75 48 b8 f2    	vfmadd231ps zmm6,zmm1,zmm2
  1e:	62 f2 75 48 b8 fa    	vfmadd231ps zmm7,zmm1,zmm2
  24:	62 72 75 48 b8 c2    	vfmadd231ps zmm8,zmm1,zmm2
  2a:	62 72 75 48 b8 ca    	vfmadd231ps zmm9,zmm1,zmm2
  30:	62 72 75 48 b8 d2    	vfmadd231ps zmm10,zmm1,zmm2
  36:	62 72 75 48 b8 da    	vfmadd231ps zmm11,zmm1,zmm2
  3c:	62 72 75 48 b8 e2    	vfmadd231ps zmm12,zmm1,zmm2
  42:	62 e2 75 48 b8 c2    	vfmadd231ps zmm16,zmm1,zmm2
  48:	62 e2 75 48 b8 ca    	vfmadd231ps zmm17,zmm1,zmm2
  4e:	62 e2 75 48 b8 d2    	vfmadd231ps zmm18,zmm1,zmm2
  54:	62 e2 75 48 b8 da    	vfmadd231ps zmm19,zmm1,zmm2
  5a:	62 e2 75 48 b8 e2    	vfmadd231ps zmm20,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14];
VMOVUPD ZMM3, [R14];
VMOVUPD ZMM4, [R14];
VMOVUPD ZMM5, [R14];
VMOVUPD ZMM6, [R14];
VMOVUPD ZMM7, [R14];
VMOVUPD ZMM8, [R14];
VMOVUPD ZMM9, [R14];
VMOVUPD ZMM10, [R14];
VMOVUPD ZMM11, [R14];
VMOVUPD ZMM12, [R14];
VMOVUPD ZMM16, [R14];
VMOVUPD ZMM17, [R14];
VMOVUPD ZMM18, [R14];
VMOVUPD ZMM19, [R14];
VMOVUPD ZMM20, [R14]

Show nanoBench command
Results:
- MPERF: 13.82
- APERF: 16.01
- UOPS: 17.0
- FpuPipeAssignment.Total0: 8.0
- FpuPipeAssignment.Total1: 8.0
- FpuPipeAssignment.Total2: 0.0
- 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:	62 f2 75 48 b8 c2    	vfmadd231ps zmm0,zmm1,zmm2
   6:	62 f2 75 48 b8 da    	vfmadd231ps zmm3,zmm1,zmm2
   c:	62 f2 75 48 b8 e2    	vfmadd231ps zmm4,zmm1,zmm2
  12:	62 f2 75 48 b8 ea    	vfmadd231ps zmm5,zmm1,zmm2
  18:	62 f2 75 48 b8 f2    	vfmadd231ps zmm6,zmm1,zmm2
  1e:	62 f2 75 48 b8 fa    	vfmadd231ps zmm7,zmm1,zmm2
  24:	62 72 75 48 b8 c2    	vfmadd231ps zmm8,zmm1,zmm2
  2a:	62 72 75 48 b8 ca    	vfmadd231ps zmm9,zmm1,zmm2
  30:	62 72 75 48 b8 d2    	vfmadd231ps zmm10,zmm1,zmm2
  36:	62 72 75 48 b8 da    	vfmadd231ps zmm11,zmm1,zmm2
  3c:	62 72 75 48 b8 e2    	vfmadd231ps zmm12,zmm1,zmm2
  42:	62 e2 75 48 b8 c2    	vfmadd231ps zmm16,zmm1,zmm2
  48:	62 e2 75 48 b8 ca    	vfmadd231ps zmm17,zmm1,zmm2
  4e:	62 e2 75 48 b8 d2    	vfmadd231ps zmm18,zmm1,zmm2
  54:	62 e2 75 48 b8 da    	vfmadd231ps zmm19,zmm1,zmm2
  5a:	62 e2 75 48 b8 e2    	vfmadd231ps zmm20,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14];
VMOVUPD ZMM3, [R14];
VMOVUPD ZMM4, [R14];
VMOVUPD ZMM5, [R14];
VMOVUPD ZMM6, [R14];
VMOVUPD ZMM7, [R14];
VMOVUPD ZMM8, [R14];
VMOVUPD ZMM9, [R14];
VMOVUPD ZMM10, [R14];
VMOVUPD ZMM11, [R14];
VMOVUPD ZMM12, [R14];
VMOVUPD ZMM16, [R14];
VMOVUPD ZMM17, [R14];
VMOVUPD ZMM18, [R14];
VMOVUPD ZMM19, [R14];
VMOVUPD ZMM20, [R14]

Show nanoBench command
Results:
- MPERF: 13.81
- APERF: 16.01
- UOPS: 16.1
- FpuPipeAssignment.Total0: 8.0
- FpuPipeAssignment.Total1: 8.0
- FpuPipeAssignment.Total2: 0.0
- 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:	62 f2 7d 48 b8 c0    	vfmadd231ps zmm0,zmm0,zmm0

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14]

Show nanoBench command
Results:
- MPERF: 3.4
- APERF: 4.0
- UOPS: 1.0
- FpuPipeAssignment.Total0: 0.5
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.0
- 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:	62 f2 7d 48 b8 c0    	vfmadd231ps zmm0,zmm0,zmm0

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14]

Show nanoBench command
Results:
- MPERF: 3.45
- APERF: 4.0
- UOPS: 1.1
- FpuPipeAssignment.Total0: 0.5
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.0
- 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:	62 f2 7d 48 b8 c0    	vfmadd231ps zmm0,zmm0,zmm0

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14]

Show nanoBench command
Results:
- MPERF: 3.45
- APERF: 4.0
- UOPS: 1.01
- FpuPipeAssignment.Total0: 0.5
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.0
- 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:	62 f2 7d 48 b8 c0    	vfmadd231ps zmm0,zmm0,zmm0
   6:	62 f2 75 48 b8 c9    	vfmadd231ps zmm1,zmm1,zmm1
   c:	62 f2 6d 48 b8 d2    	vfmadd231ps zmm2,zmm2,zmm2
  12:	62 f2 65 48 b8 db    	vfmadd231ps zmm3,zmm3,zmm3

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14];
VMOVUPD ZMM3, [R14]

Show nanoBench command
Results:
- MPERF: 3.29
- APERF: 4.0
- UOPS: 4.0
- FpuPipeAssignment.Total0: 2.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 0.0
- 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:	62 f2 7d 48 b8 c0    	vfmadd231ps zmm0,zmm0,zmm0
   6:	62 f2 75 48 b8 c9    	vfmadd231ps zmm1,zmm1,zmm1
   c:	62 f2 6d 48 b8 d2    	vfmadd231ps zmm2,zmm2,zmm2
  12:	62 f2 65 48 b8 db    	vfmadd231ps zmm3,zmm3,zmm3

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14];
VMOVUPD ZMM3, [R14]

Show nanoBench command
Results:
- MPERF: 3.45
- APERF: 4.0
- UOPS: 4.5
- FpuPipeAssignment.Total0: 2.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 0.0
- 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:	62 f2 7d 48 b8 c0    	vfmadd231ps zmm0,zmm0,zmm0
   6:	62 f2 75 48 b8 c9    	vfmadd231ps zmm1,zmm1,zmm1
   c:	62 f2 6d 48 b8 d2    	vfmadd231ps zmm2,zmm2,zmm2
  12:	62 f2 65 48 b8 db    	vfmadd231ps zmm3,zmm3,zmm3

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14];
VMOVUPD ZMM3, [R14]

Show nanoBench command
Results:
- MPERF: 3.45
- APERF: 4.0
- UOPS: 4.05
- FpuPipeAssignment.Total0: 2.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 0.0
- 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:	62 f2 7d 48 b8 c0    	vfmadd231ps zmm0,zmm0,zmm0
   6:	62 f2 75 48 b8 c9    	vfmadd231ps zmm1,zmm1,zmm1
   c:	62 f2 6d 48 b8 d2    	vfmadd231ps zmm2,zmm2,zmm2
  12:	62 f2 65 48 b8 db    	vfmadd231ps zmm3,zmm3,zmm3
  18:	62 f2 5d 48 b8 e4    	vfmadd231ps zmm4,zmm4,zmm4
  1e:	62 f2 55 48 b8 ed    	vfmadd231ps zmm5,zmm5,zmm5
  24:	62 f2 4d 48 b8 f6    	vfmadd231ps zmm6,zmm6,zmm6
  2a:	62 f2 45 48 b8 ff    	vfmadd231ps zmm7,zmm7,zmm7

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14];
VMOVUPD ZMM3, [R14];
VMOVUPD ZMM4, [R14];
VMOVUPD ZMM5, [R14];
VMOVUPD ZMM6, [R14];
VMOVUPD ZMM7, [R14]

Show nanoBench command
Results:
- MPERF: 6.58
- APERF: 8.0
- UOPS: 8.0
- FpuPipeAssignment.Total0: 4.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 0.0
- 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:	62 f2 7d 48 b8 c0    	vfmadd231ps zmm0,zmm0,zmm0
   6:	62 f2 75 48 b8 c9    	vfmadd231ps zmm1,zmm1,zmm1
   c:	62 f2 6d 48 b8 d2    	vfmadd231ps zmm2,zmm2,zmm2
  12:	62 f2 65 48 b8 db    	vfmadd231ps zmm3,zmm3,zmm3
  18:	62 f2 5d 48 b8 e4    	vfmadd231ps zmm4,zmm4,zmm4
  1e:	62 f2 55 48 b8 ed    	vfmadd231ps zmm5,zmm5,zmm5
  24:	62 f2 4d 48 b8 f6    	vfmadd231ps zmm6,zmm6,zmm6
  2a:	62 f2 45 48 b8 ff    	vfmadd231ps zmm7,zmm7,zmm7

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14];
VMOVUPD ZMM3, [R14];
VMOVUPD ZMM4, [R14];
VMOVUPD ZMM5, [R14];
VMOVUPD ZMM6, [R14];
VMOVUPD ZMM7, [R14]

Show nanoBench command
Results:
- MPERF: 6.91
- APERF: 8.01
- UOPS: 9.0
- FpuPipeAssignment.Total0: 4.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 0.0
- 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:	62 f2 7d 48 b8 c0    	vfmadd231ps zmm0,zmm0,zmm0
   6:	62 f2 75 48 b8 c9    	vfmadd231ps zmm1,zmm1,zmm1
   c:	62 f2 6d 48 b8 d2    	vfmadd231ps zmm2,zmm2,zmm2
  12:	62 f2 65 48 b8 db    	vfmadd231ps zmm3,zmm3,zmm3
  18:	62 f2 5d 48 b8 e4    	vfmadd231ps zmm4,zmm4,zmm4
  1e:	62 f2 55 48 b8 ed    	vfmadd231ps zmm5,zmm5,zmm5
  24:	62 f2 4d 48 b8 f6    	vfmadd231ps zmm6,zmm6,zmm6
  2a:	62 f2 45 48 b8 ff    	vfmadd231ps zmm7,zmm7,zmm7

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14];
VMOVUPD ZMM3, [R14];
VMOVUPD ZMM4, [R14];
VMOVUPD ZMM5, [R14];
VMOVUPD ZMM6, [R14];
VMOVUPD ZMM7, [R14]

Show nanoBench command
Results:
- MPERF: 6.91
- APERF: 8.01
- UOPS: 8.1
- FpuPipeAssignment.Total0: 4.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With 16 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	62 f2 7d 48 b8 c0    	vfmadd231ps zmm0,zmm0,zmm0
   6:	62 f2 75 48 b8 c9    	vfmadd231ps zmm1,zmm1,zmm1
   c:	62 f2 6d 48 b8 d2    	vfmadd231ps zmm2,zmm2,zmm2
  12:	62 f2 65 48 b8 db    	vfmadd231ps zmm3,zmm3,zmm3
  18:	62 f2 5d 48 b8 e4    	vfmadd231ps zmm4,zmm4,zmm4
  1e:	62 f2 55 48 b8 ed    	vfmadd231ps zmm5,zmm5,zmm5
  24:	62 f2 4d 48 b8 f6    	vfmadd231ps zmm6,zmm6,zmm6
  2a:	62 f2 45 48 b8 ff    	vfmadd231ps zmm7,zmm7,zmm7
  30:	62 52 3d 48 b8 c0    	vfmadd231ps zmm8,zmm8,zmm8
  36:	62 52 35 48 b8 c9    	vfmadd231ps zmm9,zmm9,zmm9
  3c:	62 52 2d 48 b8 d2    	vfmadd231ps zmm10,zmm10,zmm10
  42:	62 52 25 48 b8 db    	vfmadd231ps zmm11,zmm11,zmm11
  48:	62 52 1d 48 b8 e4    	vfmadd231ps zmm12,zmm12,zmm12
  4e:	62 a2 7d 40 b8 c0    	vfmadd231ps zmm16,zmm16,zmm16
  54:	62 a2 75 40 b8 c9    	vfmadd231ps zmm17,zmm17,zmm17
  5a:	62 a2 6d 40 b8 d2    	vfmadd231ps zmm18,zmm18,zmm18

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14];
VMOVUPD ZMM3, [R14];
VMOVUPD ZMM4, [R14];
VMOVUPD ZMM5, [R14];
VMOVUPD ZMM6, [R14];
VMOVUPD ZMM7, [R14];
VMOVUPD ZMM8, [R14];
VMOVUPD ZMM9, [R14];
VMOVUPD ZMM10, [R14];
VMOVUPD ZMM11, [R14];
VMOVUPD ZMM12, [R14];
VMOVUPD ZMM16, [R14];
VMOVUPD ZMM17, [R14];
VMOVUPD ZMM18, [R14]

Show nanoBench command
Results:
- MPERF: 13.87
- APERF: 15.97
- UOPS: 16.0
- FpuPipeAssignment.Total0: 8.0
- FpuPipeAssignment.Total1: 8.0
- FpuPipeAssignment.Total2: 0.0
- 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:	62 f2 7d 48 b8 c0    	vfmadd231ps zmm0,zmm0,zmm0
   6:	62 f2 75 48 b8 c9    	vfmadd231ps zmm1,zmm1,zmm1
   c:	62 f2 6d 48 b8 d2    	vfmadd231ps zmm2,zmm2,zmm2
  12:	62 f2 65 48 b8 db    	vfmadd231ps zmm3,zmm3,zmm3
  18:	62 f2 5d 48 b8 e4    	vfmadd231ps zmm4,zmm4,zmm4
  1e:	62 f2 55 48 b8 ed    	vfmadd231ps zmm5,zmm5,zmm5
  24:	62 f2 4d 48 b8 f6    	vfmadd231ps zmm6,zmm6,zmm6
  2a:	62 f2 45 48 b8 ff    	vfmadd231ps zmm7,zmm7,zmm7
  30:	62 52 3d 48 b8 c0    	vfmadd231ps zmm8,zmm8,zmm8
  36:	62 52 35 48 b8 c9    	vfmadd231ps zmm9,zmm9,zmm9
  3c:	62 52 2d 48 b8 d2    	vfmadd231ps zmm10,zmm10,zmm10
  42:	62 52 25 48 b8 db    	vfmadd231ps zmm11,zmm11,zmm11
  48:	62 52 1d 48 b8 e4    	vfmadd231ps zmm12,zmm12,zmm12
  4e:	62 a2 7d 40 b8 c0    	vfmadd231ps zmm16,zmm16,zmm16
  54:	62 a2 75 40 b8 c9    	vfmadd231ps zmm17,zmm17,zmm17
  5a:	62 a2 6d 40 b8 d2    	vfmadd231ps zmm18,zmm18,zmm18

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14];
VMOVUPD ZMM3, [R14];
VMOVUPD ZMM4, [R14];
VMOVUPD ZMM5, [R14];
VMOVUPD ZMM6, [R14];
VMOVUPD ZMM7, [R14];
VMOVUPD ZMM8, [R14];
VMOVUPD ZMM9, [R14];
VMOVUPD ZMM10, [R14];
VMOVUPD ZMM11, [R14];
VMOVUPD ZMM12, [R14];
VMOVUPD ZMM16, [R14];
VMOVUPD ZMM17, [R14];
VMOVUPD ZMM18, [R14]

Show nanoBench command
Results:
- MPERF: 13.82
- APERF: 16.01
- UOPS: 17.0
- FpuPipeAssignment.Total0: 8.0
- FpuPipeAssignment.Total1: 8.0
- FpuPipeAssignment.Total2: 0.0
- 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:	62 f2 7d 48 b8 c0    	vfmadd231ps zmm0,zmm0,zmm0
   6:	62 f2 75 48 b8 c9    	vfmadd231ps zmm1,zmm1,zmm1
   c:	62 f2 6d 48 b8 d2    	vfmadd231ps zmm2,zmm2,zmm2
  12:	62 f2 65 48 b8 db    	vfmadd231ps zmm3,zmm3,zmm3
  18:	62 f2 5d 48 b8 e4    	vfmadd231ps zmm4,zmm4,zmm4
  1e:	62 f2 55 48 b8 ed    	vfmadd231ps zmm5,zmm5,zmm5
  24:	62 f2 4d 48 b8 f6    	vfmadd231ps zmm6,zmm6,zmm6
  2a:	62 f2 45 48 b8 ff    	vfmadd231ps zmm7,zmm7,zmm7
  30:	62 52 3d 48 b8 c0    	vfmadd231ps zmm8,zmm8,zmm8
  36:	62 52 35 48 b8 c9    	vfmadd231ps zmm9,zmm9,zmm9
  3c:	62 52 2d 48 b8 d2    	vfmadd231ps zmm10,zmm10,zmm10
  42:	62 52 25 48 b8 db    	vfmadd231ps zmm11,zmm11,zmm11
  48:	62 52 1d 48 b8 e4    	vfmadd231ps zmm12,zmm12,zmm12
  4e:	62 a2 7d 40 b8 c0    	vfmadd231ps zmm16,zmm16,zmm16
  54:	62 a2 75 40 b8 c9    	vfmadd231ps zmm17,zmm17,zmm17
  5a:	62 a2 6d 40 b8 d2    	vfmadd231ps zmm18,zmm18,zmm18

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14];
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14];
VMOVUPD ZMM3, [R14];
VMOVUPD ZMM4, [R14];
VMOVUPD ZMM5, [R14];
VMOVUPD ZMM6, [R14];
VMOVUPD ZMM7, [R14];
VMOVUPD ZMM8, [R14];
VMOVUPD ZMM9, [R14];
VMOVUPD ZMM10, [R14];
VMOVUPD ZMM11, [R14];
VMOVUPD ZMM12, [R14];
VMOVUPD ZMM16, [R14];
VMOVUPD ZMM17, [R14];
VMOVUPD ZMM18, [R14]

Show nanoBench command
Results:
- MPERF: 13.82
- APERF: 16.01
- UOPS: 16.1
- FpuPipeAssignment.Total0: 8.0
- FpuPipeAssignment.Total1: 8.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

VFMADD231PS (ZMM, ZMM, ZMM) - 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 16 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 16 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