VDIVPS (ZMM, ZMM, ZMM)

With unroll_count=500 and no inner loop

Code:

   0:	62 f1 7c 48 5e d1    	vdivps zmm2,zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x3f8000003f800000;
MOV RBX, 0x3f8000003f800000;
MOV [R14+0], RBX;
MOV [R14+8], RBX;
MOV [R14+16], RBX;
MOV [R14+24], RBX;
MOV [R14+32], RBX;
MOV [R14+40], RBX;
MOV [R14+48], RBX;
MOV [R14+56], RBX;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPS ZMM0, [R14+64];
VMOVUPS ZMM1, [R14]

Show nanoBench command
Results:
- MPERF: 5.17
- APERF: 6.0
- 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 unroll_count=500 and no inner loop

Code:

   0:	62 f1 7c 48 5e d1    	vdivps zmm2,zmm0,zmm1
   6:	0f ae e8             	lfence

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x3f8000003f800000;
MOV RBX, 0x3f8000003f800000;
MOV [R14+0], RBX;
MOV [R14+8], RBX;
MOV [R14+16], RBX;
MOV [R14+24], RBX;
MOV [R14+32], RBX;
MOV [R14+40], RBX;
MOV [R14+48], RBX;
MOV [R14+56], RBX;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPS ZMM0, [R14+64];
VMOVUPS ZMM1, [R14]

Show nanoBench command
Results:
- MPERF: 24.16
- APERF: 28.0
- UOPS: 2.0
- FpuPipeAssignment.Total0: 1.0
- FpuPipeAssignment.Total1: 0.0
- 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=10

Code:

   0:	62 f1 7c 48 5e d1    	vdivps zmm2,zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x3f8000003f800000;
MOV RBX, 0x3f8000003f800000;
MOV [R14+0], RBX;
MOV [R14+8], RBX;
MOV [R14+16], RBX;
MOV [R14+24], RBX;
MOV [R14+32], RBX;
MOV [R14+40], RBX;
MOV [R14+48], RBX;
MOV [R14+56], RBX;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPS ZMM0, [R14+64];
VMOVUPS ZMM1, [R14]

Show nanoBench command
Results:
- MPERF: 5.17
- APERF: 6.0
- 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 f1 7c 48 5e d1    	vdivps zmm2,zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x3f8000003f800000;
MOV RBX, 0x3f8000003f800000;
MOV [R14+0], RBX;
MOV [R14+8], RBX;
MOV [R14+16], RBX;
MOV [R14+24], RBX;
MOV [R14+32], RBX;
MOV [R14+40], RBX;
MOV [R14+48], RBX;
MOV [R14+56], RBX;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPS ZMM0, [R14+64];
VMOVUPS ZMM1, [R14]

Show nanoBench command
Results:
- MPERF: 5.17
- APERF: 6.0
- 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 f1 7c 48 5e d1    	vdivps zmm2,zmm0,zmm1
   6:	62 f1 7c 48 5e d9    	vdivps zmm3,zmm0,zmm1
   c:	62 f1 7c 48 5e e1    	vdivps zmm4,zmm0,zmm1
  12:	62 f1 7c 48 5e e9    	vdivps zmm5,zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x3f8000003f800000;
MOV RBX, 0x3f8000003f800000;
MOV [R14+0], RBX;
MOV [R14+8], RBX;
MOV [R14+16], RBX;
MOV [R14+24], RBX;
MOV [R14+32], RBX;
MOV [R14+40], RBX;
MOV [R14+48], RBX;
MOV [R14+56], RBX;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPS ZMM0, [R14+64];
VMOVUPS ZMM1, [R14]

Show nanoBench command
Results:
- MPERF: 20.72
- APERF: 24.0
- 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 f1 7c 48 5e d1    	vdivps zmm2,zmm0,zmm1
   6:	62 f1 7c 48 5e d9    	vdivps zmm3,zmm0,zmm1
   c:	62 f1 7c 48 5e e1    	vdivps zmm4,zmm0,zmm1
  12:	62 f1 7c 48 5e e9    	vdivps zmm5,zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x3f8000003f800000;
MOV RBX, 0x3f8000003f800000;
MOV [R14+0], RBX;
MOV [R14+8], RBX;
MOV [R14+16], RBX;
MOV [R14+24], RBX;
MOV [R14+32], RBX;
MOV [R14+40], RBX;
MOV [R14+48], RBX;
MOV [R14+56], RBX;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPS ZMM0, [R14+64];
VMOVUPS ZMM1, [R14]

Show nanoBench command
Results:
- MPERF: 20.7
- APERF: 24.01
- 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 f1 7c 48 5e d1    	vdivps zmm2,zmm0,zmm1
   6:	62 f1 7c 48 5e d9    	vdivps zmm3,zmm0,zmm1
   c:	62 f1 7c 48 5e e1    	vdivps zmm4,zmm0,zmm1
  12:	62 f1 7c 48 5e e9    	vdivps zmm5,zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x3f8000003f800000;
MOV RBX, 0x3f8000003f800000;
MOV [R14+0], RBX;
MOV [R14+8], RBX;
MOV [R14+16], RBX;
MOV [R14+24], RBX;
MOV [R14+32], RBX;
MOV [R14+40], RBX;
MOV [R14+48], RBX;
MOV [R14+56], RBX;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPS ZMM0, [R14+64];
VMOVUPS ZMM1, [R14]

Show nanoBench command
Results:
- MPERF: 20.7
- APERF: 24.01
- 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 f1 7c 48 5e d1    	vdivps zmm2,zmm0,zmm1
   6:	62 f1 7c 48 5e d9    	vdivps zmm3,zmm0,zmm1
   c:	62 f1 7c 48 5e e1    	vdivps zmm4,zmm0,zmm1
  12:	62 f1 7c 48 5e e9    	vdivps zmm5,zmm0,zmm1
  18:	62 f1 7c 48 5e f1    	vdivps zmm6,zmm0,zmm1
  1e:	62 f1 7c 48 5e f9    	vdivps zmm7,zmm0,zmm1
  24:	62 71 7c 48 5e c1    	vdivps zmm8,zmm0,zmm1
  2a:	62 71 7c 48 5e c9    	vdivps zmm9,zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x3f8000003f800000;
MOV RBX, 0x3f8000003f800000;
MOV [R14+0], RBX;
MOV [R14+8], RBX;
MOV [R14+16], RBX;
MOV [R14+24], RBX;
MOV [R14+32], RBX;
MOV [R14+40], RBX;
MOV [R14+48], RBX;
MOV [R14+56], RBX;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPS ZMM0, [R14+64];
VMOVUPS ZMM1, [R14]

Show nanoBench command
Results:
- MPERF: 41.44
- APERF: 48.0
- 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 f1 7c 48 5e d1    	vdivps zmm2,zmm0,zmm1
   6:	62 f1 7c 48 5e d9    	vdivps zmm3,zmm0,zmm1
   c:	62 f1 7c 48 5e e1    	vdivps zmm4,zmm0,zmm1
  12:	62 f1 7c 48 5e e9    	vdivps zmm5,zmm0,zmm1
  18:	62 f1 7c 48 5e f1    	vdivps zmm6,zmm0,zmm1
  1e:	62 f1 7c 48 5e f9    	vdivps zmm7,zmm0,zmm1
  24:	62 71 7c 48 5e c1    	vdivps zmm8,zmm0,zmm1
  2a:	62 71 7c 48 5e c9    	vdivps zmm9,zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x3f8000003f800000;
MOV RBX, 0x3f8000003f800000;
MOV [R14+0], RBX;
MOV [R14+8], RBX;
MOV [R14+16], RBX;
MOV [R14+24], RBX;
MOV [R14+32], RBX;
MOV [R14+40], RBX;
MOV [R14+48], RBX;
MOV [R14+56], RBX;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPS ZMM0, [R14+64];
VMOVUPS ZMM1, [R14]

Show nanoBench command
Results:
- MPERF: 41.41
- APERF: 48.01
- 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 f1 7c 48 5e d1    	vdivps zmm2,zmm0,zmm1
   6:	62 f1 7c 48 5e d9    	vdivps zmm3,zmm0,zmm1
   c:	62 f1 7c 48 5e e1    	vdivps zmm4,zmm0,zmm1
  12:	62 f1 7c 48 5e e9    	vdivps zmm5,zmm0,zmm1
  18:	62 f1 7c 48 5e f1    	vdivps zmm6,zmm0,zmm1
  1e:	62 f1 7c 48 5e f9    	vdivps zmm7,zmm0,zmm1
  24:	62 71 7c 48 5e c1    	vdivps zmm8,zmm0,zmm1
  2a:	62 71 7c 48 5e c9    	vdivps zmm9,zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x3f8000003f800000;
MOV RBX, 0x3f8000003f800000;
MOV [R14+0], RBX;
MOV [R14+8], RBX;
MOV [R14+16], RBX;
MOV [R14+24], RBX;
MOV [R14+32], RBX;
MOV [R14+40], RBX;
MOV [R14+48], RBX;
MOV [R14+56], RBX;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPS ZMM0, [R14+64];
VMOVUPS ZMM1, [R14]

Show nanoBench command
Results:
- MPERF: 41.41
- APERF: 48.01
- 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

Slow division

With 1 independent instruction

With unroll_count=500 and no inner loop

Code:

   0:	62 f1 7c 48 5e d1    	vdivps zmm2,zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x54ed392654ed3926;
MOV RBX, 0x3f99f4c03f99f4c0;
MOV [R14+0], RBX;
MOV [R14+8], RBX;
MOV [R14+16], RBX;
MOV [R14+24], RBX;
MOV [R14+32], RBX;
MOV [R14+40], RBX;
MOV [R14+48], RBX;
MOV [R14+56], RBX;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPS ZMM0, [R14+64];
VMOVUPS ZMM1, [R14]

Show nanoBench command
Results:
- MPERF: 5.2
- APERF: 6.0
- 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 unroll_count=500 and no inner loop

Code:

   0:	62 f1 7c 48 5e d1    	vdivps zmm2,zmm0,zmm1
   6:	0f ae e8             	lfence

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x54ed392654ed3926;
MOV RBX, 0x3f99f4c03f99f4c0;
MOV [R14+0], RBX;
MOV [R14+8], RBX;
MOV [R14+16], RBX;
MOV [R14+24], RBX;
MOV [R14+32], RBX;
MOV [R14+40], RBX;
MOV [R14+48], RBX;
MOV [R14+56], RBX;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPS ZMM0, [R14+64];
VMOVUPS ZMM1, [R14]

Show nanoBench command
Results:
- MPERF: 24.14
- APERF: 28.0
- UOPS: 2.0
- FpuPipeAssignment.Total0: 1.0
- FpuPipeAssignment.Total1: 0.0
- 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=10

Code:

   0:	62 f1 7c 48 5e d1    	vdivps zmm2,zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x54ed392654ed3926;
MOV RBX, 0x3f99f4c03f99f4c0;
MOV [R14+0], RBX;
MOV [R14+8], RBX;
MOV [R14+16], RBX;
MOV [R14+24], RBX;
MOV [R14+32], RBX;
MOV [R14+40], RBX;
MOV [R14+48], RBX;
MOV [R14+56], RBX;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPS ZMM0, [R14+64];
VMOVUPS ZMM1, [R14]

Show nanoBench command
Results:
- MPERF: 5.17
- APERF: 6.0
- 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 f1 7c 48 5e d1    	vdivps zmm2,zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x54ed392654ed3926;
MOV RBX, 0x3f99f4c03f99f4c0;
MOV [R14+0], RBX;
MOV [R14+8], RBX;
MOV [R14+16], RBX;
MOV [R14+24], RBX;
MOV [R14+32], RBX;
MOV [R14+40], RBX;
MOV [R14+48], RBX;
MOV [R14+56], RBX;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPS ZMM0, [R14+64];
VMOVUPS ZMM1, [R14]

Show nanoBench command
Results:
- MPERF: 5.17
- APERF: 6.0
- 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 f1 7c 48 5e d1    	vdivps zmm2,zmm0,zmm1
   6:	62 f1 7c 48 5e d9    	vdivps zmm3,zmm0,zmm1
   c:	62 f1 7c 48 5e e1    	vdivps zmm4,zmm0,zmm1
  12:	62 f1 7c 48 5e e9    	vdivps zmm5,zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x54ed392654ed3926;
MOV RBX, 0x3f99f4c03f99f4c0;
MOV [R14+0], RBX;
MOV [R14+8], RBX;
MOV [R14+16], RBX;
MOV [R14+24], RBX;
MOV [R14+32], RBX;
MOV [R14+40], RBX;
MOV [R14+48], RBX;
MOV [R14+56], RBX;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPS ZMM0, [R14+64];
VMOVUPS ZMM1, [R14]

Show nanoBench command
Results:
- MPERF: 20.68
- APERF: 24.0
- 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 f1 7c 48 5e d1    	vdivps zmm2,zmm0,zmm1
   6:	62 f1 7c 48 5e d9    	vdivps zmm3,zmm0,zmm1
   c:	62 f1 7c 48 5e e1    	vdivps zmm4,zmm0,zmm1
  12:	62 f1 7c 48 5e e9    	vdivps zmm5,zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x54ed392654ed3926;
MOV RBX, 0x3f99f4c03f99f4c0;
MOV [R14+0], RBX;
MOV [R14+8], RBX;
MOV [R14+16], RBX;
MOV [R14+24], RBX;
MOV [R14+32], RBX;
MOV [R14+40], RBX;
MOV [R14+48], RBX;
MOV [R14+56], RBX;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPS ZMM0, [R14+64];
VMOVUPS ZMM1, [R14]

Show nanoBench command
Results:
- MPERF: 20.7
- APERF: 24.01
- 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 f1 7c 48 5e d1    	vdivps zmm2,zmm0,zmm1
   6:	62 f1 7c 48 5e d9    	vdivps zmm3,zmm0,zmm1
   c:	62 f1 7c 48 5e e1    	vdivps zmm4,zmm0,zmm1
  12:	62 f1 7c 48 5e e9    	vdivps zmm5,zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x54ed392654ed3926;
MOV RBX, 0x3f99f4c03f99f4c0;
MOV [R14+0], RBX;
MOV [R14+8], RBX;
MOV [R14+16], RBX;
MOV [R14+24], RBX;
MOV [R14+32], RBX;
MOV [R14+40], RBX;
MOV [R14+48], RBX;
MOV [R14+56], RBX;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPS ZMM0, [R14+64];
VMOVUPS ZMM1, [R14]

Show nanoBench command
Results:
- MPERF: 20.7
- APERF: 24.01
- 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 f1 7c 48 5e d1    	vdivps zmm2,zmm0,zmm1
   6:	62 f1 7c 48 5e d9    	vdivps zmm3,zmm0,zmm1
   c:	62 f1 7c 48 5e e1    	vdivps zmm4,zmm0,zmm1
  12:	62 f1 7c 48 5e e9    	vdivps zmm5,zmm0,zmm1
  18:	62 f1 7c 48 5e f1    	vdivps zmm6,zmm0,zmm1
  1e:	62 f1 7c 48 5e f9    	vdivps zmm7,zmm0,zmm1
  24:	62 71 7c 48 5e c1    	vdivps zmm8,zmm0,zmm1
  2a:	62 71 7c 48 5e c9    	vdivps zmm9,zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x54ed392654ed3926;
MOV RBX, 0x3f99f4c03f99f4c0;
MOV [R14+0], RBX;
MOV [R14+8], RBX;
MOV [R14+16], RBX;
MOV [R14+24], RBX;
MOV [R14+32], RBX;
MOV [R14+40], RBX;
MOV [R14+48], RBX;
MOV [R14+56], RBX;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPS ZMM0, [R14+64];
VMOVUPS ZMM1, [R14]

Show nanoBench command
Results:
- MPERF: 41.44
- APERF: 48.0
- 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 f1 7c 48 5e d1    	vdivps zmm2,zmm0,zmm1
   6:	62 f1 7c 48 5e d9    	vdivps zmm3,zmm0,zmm1
   c:	62 f1 7c 48 5e e1    	vdivps zmm4,zmm0,zmm1
  12:	62 f1 7c 48 5e e9    	vdivps zmm5,zmm0,zmm1
  18:	62 f1 7c 48 5e f1    	vdivps zmm6,zmm0,zmm1
  1e:	62 f1 7c 48 5e f9    	vdivps zmm7,zmm0,zmm1
  24:	62 71 7c 48 5e c1    	vdivps zmm8,zmm0,zmm1
  2a:	62 71 7c 48 5e c9    	vdivps zmm9,zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x54ed392654ed3926;
MOV RBX, 0x3f99f4c03f99f4c0;
MOV [R14+0], RBX;
MOV [R14+8], RBX;
MOV [R14+16], RBX;
MOV [R14+24], RBX;
MOV [R14+32], RBX;
MOV [R14+40], RBX;
MOV [R14+48], RBX;
MOV [R14+56], RBX;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPS ZMM0, [R14+64];
VMOVUPS ZMM1, [R14]

Show nanoBench command
Results:
- MPERF: 41.41
- APERF: 48.01
- 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 f1 7c 48 5e d1    	vdivps zmm2,zmm0,zmm1
   6:	62 f1 7c 48 5e d9    	vdivps zmm3,zmm0,zmm1
   c:	62 f1 7c 48 5e e1    	vdivps zmm4,zmm0,zmm1
  12:	62 f1 7c 48 5e e9    	vdivps zmm5,zmm0,zmm1
  18:	62 f1 7c 48 5e f1    	vdivps zmm6,zmm0,zmm1
  1e:	62 f1 7c 48 5e f9    	vdivps zmm7,zmm0,zmm1
  24:	62 71 7c 48 5e c1    	vdivps zmm8,zmm0,zmm1
  2a:	62 71 7c 48 5e c9    	vdivps zmm9,zmm0,zmm1

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x54ed392654ed3926;
MOV RBX, 0x3f99f4c03f99f4c0;
MOV [R14+0], RBX;
MOV [R14+8], RBX;
MOV [R14+16], RBX;
MOV [R14+24], RBX;
MOV [R14+32], RBX;
MOV [R14+40], RBX;
MOV [R14+48], RBX;
MOV [R14+56], RBX;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPS ZMM0, [R14+64];
VMOVUPS ZMM1, [R14]

Show nanoBench command
Results:
- MPERF: 41.41
- APERF: 48.01
- 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

VDIVPS (ZMM, ZMM, ZMM) - Throughput and Uops

Fast division

With 1 independent instruction

With unroll_count=500 and no inner loop

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

Slow division

With 1 independent instruction

With unroll_count=500 and no inner loop

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