DIVSD (XMM, XMM)

With unroll_count=500 and no inner loop

Code:

   0:	66 0f 10 d1          	movupd xmm2,xmm1
   4:	f2 0f 5e d0          	divsd  xmm2,xmm0

Init:

VZEROALL;
MOV RAX, 0x3ff0000000000000;
MOV RBX, 0x3ff0000000000000;
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;
MOVUPD XMM0, [R14];
MOVUPD XMM1, [R14+64];
MOVUPD XMM2, XMM1

Show nanoBench command
Results:
- Instructions retired: 2.0
- Core cycles: 8.0
- Reference cycles: 6.27
- UOPS_RETIRED.ALL: 2.0
- UOPS_MS: 0.0

With unroll_count=500 and no inner loop

Code:

   0:	66 0f 10 d1          	movupd xmm2,xmm1
   4:	f2 0f 5e d0          	divsd  xmm2,xmm0
   8:	0f ae e8             	lfence

Init:

VZEROALL;
MOV RAX, 0x3ff0000000000000;
MOV RBX, 0x3ff0000000000000;
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;
MOVUPD XMM0, [R14];
MOVUPD XMM1, [R14+64];
MOVUPD XMM2, XMM1

Show nanoBench command
Results:
- Instructions retired: 3.0
- Core cycles: 39.25
- Reference cycles: 30.99
- UOPS_RETIRED.ALL: 5.0
- UOPS_MS: 3.0

With loop_count=1000 and unroll_count=10

Code:

   0:	66 0f 10 d1          	movupd xmm2,xmm1
   4:	f2 0f 5e d0          	divsd  xmm2,xmm0

Init:

VZEROALL;
MOV RAX, 0x3ff0000000000000;
MOV RBX, 0x3ff0000000000000;
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;
MOVUPD XMM0, [R14];
MOVUPD XMM1, [R14+64];
MOVUPD XMM2, XMM1

Show nanoBench command
Results:
- Instructions retired: 2.2
- Core cycles: 8.0
- Reference cycles: 6.32
- UOPS_RETIRED.ALL: 2.2
- UOPS_MS: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	66 0f 10 d1          	movupd xmm2,xmm1
   4:	f2 0f 5e d0          	divsd  xmm2,xmm0

Init:

VZEROALL;
MOV RAX, 0x3ff0000000000000;
MOV RBX, 0x3ff0000000000000;
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;
MOVUPD XMM0, [R14];
MOVUPD XMM1, [R14+64];
MOVUPD XMM2, XMM1

Show nanoBench command
Results:
- Instructions retired: 2.02
- Core cycles: 8.0
- Reference cycles: 6.32
- UOPS_RETIRED.ALL: 2.02
- UOPS_MS: 0.0

With unroll_count=500 and no inner loop

Code:

   0:	66 0f 10 d1          	movupd xmm2,xmm1
   4:	f2 0f 5e d0          	divsd  xmm2,xmm0

Init:

VZEROALL;
MOV RAX, 0x429da724b687da66;
MOV RBX, 0x3ff33e97f934078b;
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;
MOVUPD XMM0, [R14];
MOVUPD XMM1, [R14+64];
MOVUPD XMM2, XMM1

Show nanoBench command
Results:
- Instructions retired: 2.0
- Core cycles: 8.0
- Reference cycles: 6.27
- UOPS_RETIRED.ALL: 2.0
- UOPS_MS: 0.0

With unroll_count=500 and no inner loop

Code:

   0:	66 0f 10 d1          	movupd xmm2,xmm1
   4:	f2 0f 5e d0          	divsd  xmm2,xmm0
   8:	0f ae e8             	lfence

Init:

VZEROALL;
MOV RAX, 0x429da724b687da66;
MOV RBX, 0x3ff33e97f934078b;
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;
MOVUPD XMM0, [R14];
MOVUPD XMM1, [R14+64];
MOVUPD XMM2, XMM1

Show nanoBench command
Results:
- Instructions retired: 3.0
- Core cycles: 39.25
- Reference cycles: 30.99
- UOPS_RETIRED.ALL: 5.0
- UOPS_MS: 3.0

With loop_count=1000 and unroll_count=10

Code:

   0:	66 0f 10 d1          	movupd xmm2,xmm1
   4:	f2 0f 5e d0          	divsd  xmm2,xmm0

Init:

VZEROALL;
MOV RAX, 0x429da724b687da66;
MOV RBX, 0x3ff33e97f934078b;
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;
MOVUPD XMM0, [R14];
MOVUPD XMM1, [R14+64];
MOVUPD XMM2, XMM1

Show nanoBench command
Results:
- Instructions retired: 2.2
- Core cycles: 8.0
- Reference cycles: 6.32
- UOPS_RETIRED.ALL: 2.2
- UOPS_MS: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	66 0f 10 d1          	movupd xmm2,xmm1
   4:	f2 0f 5e d0          	divsd  xmm2,xmm0

Init:

VZEROALL;
MOV RAX, 0x429da724b687da66;
MOV RBX, 0x3ff33e97f934078b;
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;
MOVUPD XMM0, [R14];
MOVUPD XMM1, [R14+64];
MOVUPD XMM2, XMM1

Show nanoBench command
Results:
- Instructions retired: 2.02
- Core cycles: 8.0
- Reference cycles: 6.32
- UOPS_RETIRED.ALL: 2.02
- UOPS_MS: 0.0

DIVSD (XMM, XMM) - Throughput and Uops

Fast division

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

Slow division

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