VMOVMSKPS (R32, XMM)

With unroll_count=500 and no inner loop

Code:

   0:	c5 78 50 c0          	vmovmskps r8d,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:
- Instructions retired: 1.0
- Core cycles: 0.84
- Reference cycles: 0.77
- UOPS_RETIRED.ALL: 1.0
- UOPS_MS: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	c5 78 50 c0          	vmovmskps r8d,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:
- Instructions retired: 1.2
- Core cycles: 0.85
- Reference cycles: 0.72
- UOPS_RETIRED.ALL: 1.2
- UOPS_MS: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	c5 78 50 c0          	vmovmskps r8d,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:
- Instructions retired: 1.02
- Core cycles: 0.84
- Reference cycles: 0.72
- UOPS_RETIRED.ALL: 1.02
- UOPS_MS: 0.0

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

   0:	c5 78 50 c0          	vmovmskps r8d,xmm0
   4:	c5 78 50 c8          	vmovmskps r9d,xmm0
   8:	c5 78 50 d0          	vmovmskps r10d,xmm0
   c:	c5 78 50 d8          	vmovmskps r11d,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:
- Instructions retired: 4.0
- Core cycles: 3.35
- Reference cycles: 2.78
- UOPS_RETIRED.ALL: 4.0
- UOPS_MS: 0.0

With loop_count=1000 and unroll_count=2

Code:

   0:	c5 78 50 c0          	vmovmskps r8d,xmm0
   4:	c5 78 50 c8          	vmovmskps r9d,xmm0
   8:	c5 78 50 d0          	vmovmskps r10d,xmm0
   c:	c5 78 50 d8          	vmovmskps r11d,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:
- Instructions retired: 5.0
- Core cycles: 3.36
- Reference cycles: 2.88
- UOPS_RETIRED.ALL: 5.0
- UOPS_MS: 0.0

With loop_count=100 and unroll_count=20

Code:

   0:	c5 78 50 c0          	vmovmskps r8d,xmm0
   4:	c5 78 50 c8          	vmovmskps r9d,xmm0
   8:	c5 78 50 d0          	vmovmskps r10d,xmm0
   c:	c5 78 50 d8          	vmovmskps r11d,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:
- Instructions retired: 4.1
- Core cycles: 3.37
- Reference cycles: 2.83
- UOPS_RETIRED.ALL: 4.1
- UOPS_MS: 0.0

With 8 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c5 78 50 c0          	vmovmskps r8d,xmm0
   4:	c5 78 50 c8          	vmovmskps r9d,xmm0
   8:	c5 78 50 d0          	vmovmskps r10d,xmm0
   c:	c5 78 50 d8          	vmovmskps r11d,xmm0
  10:	c5 78 50 e0          	vmovmskps r12d,xmm0
  14:	c5 78 50 e8          	vmovmskps r13d,xmm0
  18:	c5 78 50 f0          	vmovmskps r14d,xmm0
  1c:	c5 f8 50 d8          	vmovmskps ebx,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:
- Instructions retired: 8.0
- Core cycles: 6.66
- Reference cycles: 5.89
- UOPS_RETIRED.ALL: 8.0
- UOPS_MS: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c5 78 50 c0          	vmovmskps r8d,xmm0
   4:	c5 78 50 c8          	vmovmskps r9d,xmm0
   8:	c5 78 50 d0          	vmovmskps r10d,xmm0
   c:	c5 78 50 d8          	vmovmskps r11d,xmm0
  10:	c5 78 50 e0          	vmovmskps r12d,xmm0
  14:	c5 78 50 e8          	vmovmskps r13d,xmm0
  18:	c5 78 50 f0          	vmovmskps r14d,xmm0
  1c:	c5 f8 50 d8          	vmovmskps ebx,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:
- Instructions retired: 10.0
- Core cycles: 6.73
- Reference cycles: 5.64
- UOPS_RETIRED.ALL: 10.0
- UOPS_MS: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c5 78 50 c0          	vmovmskps r8d,xmm0
   4:	c5 78 50 c8          	vmovmskps r9d,xmm0
   8:	c5 78 50 d0          	vmovmskps r10d,xmm0
   c:	c5 78 50 d8          	vmovmskps r11d,xmm0
  10:	c5 78 50 e0          	vmovmskps r12d,xmm0
  14:	c5 78 50 e8          	vmovmskps r13d,xmm0
  18:	c5 78 50 f0          	vmovmskps r14d,xmm0
  1c:	c5 f8 50 d8          	vmovmskps ebx,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:
- Instructions retired: 8.2
- Core cycles: 6.69
- Reference cycles: 5.59
- UOPS_RETIRED.ALL: 8.2
- UOPS_MS: 0.0

With 14 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c5 78 50 c0          	vmovmskps r8d,xmm0
   4:	c5 78 50 c8          	vmovmskps r9d,xmm0
   8:	c5 78 50 d0          	vmovmskps r10d,xmm0
   c:	c5 78 50 d8          	vmovmskps r11d,xmm0
  10:	c5 78 50 e0          	vmovmskps r12d,xmm0
  14:	c5 78 50 e8          	vmovmskps r13d,xmm0
  18:	c5 78 50 f0          	vmovmskps r14d,xmm0
  1c:	c5 f8 50 d8          	vmovmskps ebx,xmm0
  20:	c5 f8 50 c8          	vmovmskps ecx,xmm0
  24:	c5 f8 50 d0          	vmovmskps edx,xmm0
  28:	c5 f8 50 c0          	vmovmskps eax,xmm0
  2c:	c5 f8 50 f8          	vmovmskps edi,xmm0
  30:	c5 f8 50 f0          	vmovmskps esi,xmm0
  34:	c5 f8 50 e8          	vmovmskps ebp,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:
- Instructions retired: 14.0
- Core cycles: 11.64
- Reference cycles: 9.76
- UOPS_RETIRED.ALL: 14.0
- UOPS_MS: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c5 78 50 c0          	vmovmskps r8d,xmm0
   4:	c5 78 50 c8          	vmovmskps r9d,xmm0
   8:	c5 78 50 d0          	vmovmskps r10d,xmm0
   c:	c5 78 50 d8          	vmovmskps r11d,xmm0
  10:	c5 78 50 e0          	vmovmskps r12d,xmm0
  14:	c5 78 50 e8          	vmovmskps r13d,xmm0
  18:	c5 78 50 f0          	vmovmskps r14d,xmm0
  1c:	c5 f8 50 d8          	vmovmskps ebx,xmm0
  20:	c5 f8 50 c8          	vmovmskps ecx,xmm0
  24:	c5 f8 50 d0          	vmovmskps edx,xmm0
  28:	c5 f8 50 c0          	vmovmskps eax,xmm0
  2c:	c5 f8 50 f8          	vmovmskps edi,xmm0
  30:	c5 f8 50 f0          	vmovmskps esi,xmm0
  34:	c5 f8 50 e8          	vmovmskps ebp,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:
- Instructions retired: 16.0
- Core cycles: 11.99
- Reference cycles: 10.1
- UOPS_RETIRED.ALL: 16.0
- UOPS_MS: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c5 78 50 c0          	vmovmskps r8d,xmm0
   4:	c5 78 50 c8          	vmovmskps r9d,xmm0
   8:	c5 78 50 d0          	vmovmskps r10d,xmm0
   c:	c5 78 50 d8          	vmovmskps r11d,xmm0
  10:	c5 78 50 e0          	vmovmskps r12d,xmm0
  14:	c5 78 50 e8          	vmovmskps r13d,xmm0
  18:	c5 78 50 f0          	vmovmskps r14d,xmm0
  1c:	c5 f8 50 d8          	vmovmskps ebx,xmm0
  20:	c5 f8 50 c8          	vmovmskps ecx,xmm0
  24:	c5 f8 50 d0          	vmovmskps edx,xmm0
  28:	c5 f8 50 c0          	vmovmskps eax,xmm0
  2c:	c5 f8 50 f8          	vmovmskps edi,xmm0
  30:	c5 f8 50 f0          	vmovmskps esi,xmm0
  34:	c5 f8 50 e8          	vmovmskps ebp,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:
- Instructions retired: 14.2
- Core cycles: 10.85
- Reference cycles: 9.19
- UOPS_RETIRED.ALL: 14.2
- UOPS_MS: 0.0

VMOVMSKPS (R32, XMM) - Throughput and Uops

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 14 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