VSHUFPS (YMM, YMM, YMM, I8)

With unroll_count=500 and no inner loop

Code:

   0:	c5 f4 c6 c2 02       	vshufps ymm0,ymm1,ymm2,0x2

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: 0.38
- APERF: 0.5
- UOPS: 1.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.5
- 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:	c5 f4 c6 c2 02       	vshufps ymm0,ymm1,ymm2,0x2

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: 0.41
- APERF: 0.5
- UOPS: 1.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.5
- 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:	c5 f4 c6 c2 02       	vshufps ymm0,ymm1,ymm2,0x2

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: 0.41
- APERF: 0.5
- UOPS: 1.01
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.5
- 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:	c5 f4 c6 c2 02       	vshufps ymm0,ymm1,ymm2,0x2
   5:	c5 f4 c6 da 02       	vshufps ymm3,ymm1,ymm2,0x2
   a:	c5 f4 c6 e2 02       	vshufps ymm4,ymm1,ymm2,0x2
   f:	c5 f4 c6 ea 02       	vshufps ymm5,ymm1,ymm2,0x2

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: 1.57
- APERF: 2.0
- UOPS: 4.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 2.0
- 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:	c5 f4 c6 c2 02       	vshufps ymm0,ymm1,ymm2,0x2
   5:	c5 f4 c6 da 02       	vshufps ymm3,ymm1,ymm2,0x2
   a:	c5 f4 c6 e2 02       	vshufps ymm4,ymm1,ymm2,0x2
   f:	c5 f4 c6 ea 02       	vshufps ymm5,ymm1,ymm2,0x2

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: 1.63
- APERF: 2.0
- UOPS: 4.5
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 2.0
- 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:	c5 f4 c6 c2 02       	vshufps ymm0,ymm1,ymm2,0x2
   5:	c5 f4 c6 da 02       	vshufps ymm3,ymm1,ymm2,0x2
   a:	c5 f4 c6 e2 02       	vshufps ymm4,ymm1,ymm2,0x2
   f:	c5 f4 c6 ea 02       	vshufps ymm5,ymm1,ymm2,0x2

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: 1.65
- APERF: 2.0
- UOPS: 4.05
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 2.0
- 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:	c5 f4 c6 c2 02       	vshufps ymm0,ymm1,ymm2,0x2
   5:	c5 f4 c6 da 02       	vshufps ymm3,ymm1,ymm2,0x2
   a:	c5 f4 c6 e2 02       	vshufps ymm4,ymm1,ymm2,0x2
   f:	c5 f4 c6 ea 02       	vshufps ymm5,ymm1,ymm2,0x2
  14:	c5 f4 c6 f2 02       	vshufps ymm6,ymm1,ymm2,0x2
  19:	c5 f4 c6 fa 02       	vshufps ymm7,ymm1,ymm2,0x2
  1e:	c5 74 c6 c2 02       	vshufps ymm8,ymm1,ymm2,0x2
  23:	c5 74 c6 ca 02       	vshufps ymm9,ymm1,ymm2,0x2

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: 3.33
- APERF: 4.0
- UOPS: 8.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 4.0
- 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:	c5 f4 c6 c2 02       	vshufps ymm0,ymm1,ymm2,0x2
   5:	c5 f4 c6 da 02       	vshufps ymm3,ymm1,ymm2,0x2
   a:	c5 f4 c6 e2 02       	vshufps ymm4,ymm1,ymm2,0x2
   f:	c5 f4 c6 ea 02       	vshufps ymm5,ymm1,ymm2,0x2
  14:	c5 f4 c6 f2 02       	vshufps ymm6,ymm1,ymm2,0x2
  19:	c5 f4 c6 fa 02       	vshufps ymm7,ymm1,ymm2,0x2
  1e:	c5 74 c6 c2 02       	vshufps ymm8,ymm1,ymm2,0x2
  23:	c5 74 c6 ca 02       	vshufps ymm9,ymm1,ymm2,0x2

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: 3.27
- APERF: 4.01
- UOPS: 9.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 4.0
- 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:	c5 f4 c6 c2 02       	vshufps ymm0,ymm1,ymm2,0x2
   5:	c5 f4 c6 da 02       	vshufps ymm3,ymm1,ymm2,0x2
   a:	c5 f4 c6 e2 02       	vshufps ymm4,ymm1,ymm2,0x2
   f:	c5 f4 c6 ea 02       	vshufps ymm5,ymm1,ymm2,0x2
  14:	c5 f4 c6 f2 02       	vshufps ymm6,ymm1,ymm2,0x2
  19:	c5 f4 c6 fa 02       	vshufps ymm7,ymm1,ymm2,0x2
  1e:	c5 74 c6 c2 02       	vshufps ymm8,ymm1,ymm2,0x2
  23:	c5 74 c6 ca 02       	vshufps ymm9,ymm1,ymm2,0x2

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: 3.26
- APERF: 4.0
- UOPS: 8.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With 11 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c5 f4 c6 c2 02       	vshufps ymm0,ymm1,ymm2,0x2
   5:	c5 f4 c6 da 02       	vshufps ymm3,ymm1,ymm2,0x2
   a:	c5 f4 c6 e2 02       	vshufps ymm4,ymm1,ymm2,0x2
   f:	c5 f4 c6 ea 02       	vshufps ymm5,ymm1,ymm2,0x2
  14:	c5 f4 c6 f2 02       	vshufps ymm6,ymm1,ymm2,0x2
  19:	c5 f4 c6 fa 02       	vshufps ymm7,ymm1,ymm2,0x2
  1e:	c5 74 c6 c2 02       	vshufps ymm8,ymm1,ymm2,0x2
  23:	c5 74 c6 ca 02       	vshufps ymm9,ymm1,ymm2,0x2
  28:	c5 74 c6 d2 02       	vshufps ymm10,ymm1,ymm2,0x2
  2d:	c5 74 c6 da 02       	vshufps ymm11,ymm1,ymm2,0x2
  32:	c5 74 c6 e2 02       	vshufps ymm12,ymm1,ymm2,0x2

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: 4.44
- APERF: 5.5
- UOPS: 11.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 5.5
- FpuPipeAssignment.Total2: 5.5
- 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:	c5 f4 c6 c2 02       	vshufps ymm0,ymm1,ymm2,0x2
   5:	c5 f4 c6 da 02       	vshufps ymm3,ymm1,ymm2,0x2
   a:	c5 f4 c6 e2 02       	vshufps ymm4,ymm1,ymm2,0x2
   f:	c5 f4 c6 ea 02       	vshufps ymm5,ymm1,ymm2,0x2
  14:	c5 f4 c6 f2 02       	vshufps ymm6,ymm1,ymm2,0x2
  19:	c5 f4 c6 fa 02       	vshufps ymm7,ymm1,ymm2,0x2
  1e:	c5 74 c6 c2 02       	vshufps ymm8,ymm1,ymm2,0x2
  23:	c5 74 c6 ca 02       	vshufps ymm9,ymm1,ymm2,0x2
  28:	c5 74 c6 d2 02       	vshufps ymm10,ymm1,ymm2,0x2
  2d:	c5 74 c6 da 02       	vshufps ymm11,ymm1,ymm2,0x2
  32:	c5 74 c6 e2 02       	vshufps ymm12,ymm1,ymm2,0x2

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: 4.5
- APERF: 5.5
- UOPS: 12.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 5.5
- FpuPipeAssignment.Total2: 5.5
- 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:	c5 f4 c6 c2 02       	vshufps ymm0,ymm1,ymm2,0x2
   5:	c5 f4 c6 da 02       	vshufps ymm3,ymm1,ymm2,0x2
   a:	c5 f4 c6 e2 02       	vshufps ymm4,ymm1,ymm2,0x2
   f:	c5 f4 c6 ea 02       	vshufps ymm5,ymm1,ymm2,0x2
  14:	c5 f4 c6 f2 02       	vshufps ymm6,ymm1,ymm2,0x2
  19:	c5 f4 c6 fa 02       	vshufps ymm7,ymm1,ymm2,0x2
  1e:	c5 74 c6 c2 02       	vshufps ymm8,ymm1,ymm2,0x2
  23:	c5 74 c6 ca 02       	vshufps ymm9,ymm1,ymm2,0x2
  28:	c5 74 c6 d2 02       	vshufps ymm10,ymm1,ymm2,0x2
  2d:	c5 74 c6 da 02       	vshufps ymm11,ymm1,ymm2,0x2
  32:	c5 74 c6 e2 02       	vshufps ymm12,ymm1,ymm2,0x2

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: 4.51
- APERF: 5.5
- UOPS: 11.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 5.5
- FpuPipeAssignment.Total2: 5.5
- 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 unroll_count=500 and no inner loop

Code:

   0:	c5 fc c6 c0 02       	vshufps ymm0,ymm0,ymm0,0x2

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: 0.81
- APERF: 1.0
- UOPS: 1.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.5
- 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:	c5 fc c6 c0 02       	vshufps ymm0,ymm0,ymm0,0x2

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: 0.82
- APERF: 1.0
- UOPS: 1.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.5
- 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:	c5 fc c6 c0 02       	vshufps ymm0,ymm0,ymm0,0x2

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: 0.81
- APERF: 1.0
- UOPS: 1.01
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.5
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

VSHUFPS (YMM, YMM, YMM, I8) - 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 unroll_count=500 and no inner loop

With loop_count=1000 and unroll_count=10

With loop_count=100 and unroll_count=100