VBLENDVPS (YMM, YMM, YMM, YMM)

With unroll_count=500 and no inner loop

Code:

   0:	c4 e3 75 4a c2 30    	vblendvps ymm0,ymm1,ymm2,ymm3

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];
VXORPS YMM3, YMM3, YMM3

Show nanoBench command
Results:
- MPERF: 0.43
- APERF: 0.5
- UOPS: 1.0
- FpuPipeAssignment.Total0: 0.5
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	c4 e3 75 4a c2 30    	vblendvps ymm0,ymm1,ymm2,ymm3

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];
VXORPS YMM3, YMM3, YMM3

Show nanoBench command
Results:
- MPERF: 0.42
- APERF: 0.5
- UOPS: 1.2
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	c4 e3 75 4a c2 30    	vblendvps ymm0,ymm1,ymm2,ymm3

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];
VXORPS YMM3, YMM3, YMM3

Show nanoBench command
Results:
- MPERF: 0.42
- APERF: 0.5
- UOPS: 1.02
- FpuPipeAssignment.Total0: 0.5
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

   0:	c4 e3 75 4a c2 30    	vblendvps ymm0,ymm1,ymm2,ymm3
   6:	c4 e3 75 4a e2 30    	vblendvps ymm4,ymm1,ymm2,ymm3
   c:	c4 e3 75 4a ea 30    	vblendvps ymm5,ymm1,ymm2,ymm3
  12:	c4 e3 75 4a f2 30    	vblendvps ymm6,ymm1,ymm2,ymm3

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];
VXORPS YMM3, YMM3, YMM3

Show nanoBench command
Results:
- MPERF: 1.77
- APERF: 2.0
- UOPS: 4.0
- FpuPipeAssignment.Total0: 2.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=2

Code:

   0:	c4 e3 75 4a c2 30    	vblendvps ymm0,ymm1,ymm2,ymm3
   6:	c4 e3 75 4a e2 30    	vblendvps ymm4,ymm1,ymm2,ymm3
   c:	c4 e3 75 4a ea 30    	vblendvps ymm5,ymm1,ymm2,ymm3
  12:	c4 e3 75 4a f2 30    	vblendvps ymm6,ymm1,ymm2,ymm3

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];
VXORPS YMM3, YMM3, YMM3

Show nanoBench command
Results:
- MPERF: 1.67
- APERF: 2.0
- UOPS: 5.0
- FpuPipeAssignment.Total0: 0.02
- FpuPipeAssignment.Total1: 0.02
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=20

Code:

   0:	c4 e3 75 4a c2 30    	vblendvps ymm0,ymm1,ymm2,ymm3
   6:	c4 e3 75 4a e2 30    	vblendvps ymm4,ymm1,ymm2,ymm3
   c:	c4 e3 75 4a ea 30    	vblendvps ymm5,ymm1,ymm2,ymm3
  12:	c4 e3 75 4a f2 30    	vblendvps ymm6,ymm1,ymm2,ymm3

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];
VXORPS YMM3, YMM3, YMM3

Show nanoBench command
Results:
- MPERF: 1.69
- APERF: 2.0
- UOPS: 4.1
- FpuPipeAssignment.Total0: 2.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 8 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 e3 75 4a c2 30    	vblendvps ymm0,ymm1,ymm2,ymm3
   6:	c4 e3 75 4a e2 30    	vblendvps ymm4,ymm1,ymm2,ymm3
   c:	c4 e3 75 4a ea 30    	vblendvps ymm5,ymm1,ymm2,ymm3
  12:	c4 e3 75 4a f2 30    	vblendvps ymm6,ymm1,ymm2,ymm3
  18:	c4 e3 75 4a fa 30    	vblendvps ymm7,ymm1,ymm2,ymm3
  1e:	c4 63 75 4a c2 30    	vblendvps ymm8,ymm1,ymm2,ymm3
  24:	c4 63 75 4a ca 30    	vblendvps ymm9,ymm1,ymm2,ymm3
  2a:	c4 63 75 4a d2 30    	vblendvps ymm10,ymm1,ymm2,ymm3

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];
VXORPS YMM3, YMM3, YMM3

Show nanoBench command
Results:
- MPERF: 3.36
- APERF: 4.0
- UOPS: 8.0
- FpuPipeAssignment.Total0: 4.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c4 e3 75 4a c2 30    	vblendvps ymm0,ymm1,ymm2,ymm3
   6:	c4 e3 75 4a e2 30    	vblendvps ymm4,ymm1,ymm2,ymm3
   c:	c4 e3 75 4a ea 30    	vblendvps ymm5,ymm1,ymm2,ymm3
  12:	c4 e3 75 4a f2 30    	vblendvps ymm6,ymm1,ymm2,ymm3
  18:	c4 e3 75 4a fa 30    	vblendvps ymm7,ymm1,ymm2,ymm3
  1e:	c4 63 75 4a c2 30    	vblendvps ymm8,ymm1,ymm2,ymm3
  24:	c4 63 75 4a ca 30    	vblendvps ymm9,ymm1,ymm2,ymm3
  2a:	c4 63 75 4a d2 30    	vblendvps ymm10,ymm1,ymm2,ymm3

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];
VXORPS YMM3, YMM3, YMM3

Show nanoBench command
Results:
- MPERF: 3.38
- APERF: 4.01
- UOPS: 10.0
- FpuPipeAssignment.Total0: 0.03
- FpuPipeAssignment.Total1: 0.03
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c4 e3 75 4a c2 30    	vblendvps ymm0,ymm1,ymm2,ymm3
   6:	c4 e3 75 4a e2 30    	vblendvps ymm4,ymm1,ymm2,ymm3
   c:	c4 e3 75 4a ea 30    	vblendvps ymm5,ymm1,ymm2,ymm3
  12:	c4 e3 75 4a f2 30    	vblendvps ymm6,ymm1,ymm2,ymm3
  18:	c4 e3 75 4a fa 30    	vblendvps ymm7,ymm1,ymm2,ymm3
  1e:	c4 63 75 4a c2 30    	vblendvps ymm8,ymm1,ymm2,ymm3
  24:	c4 63 75 4a ca 30    	vblendvps ymm9,ymm1,ymm2,ymm3
  2a:	c4 63 75 4a d2 30    	vblendvps ymm10,ymm1,ymm2,ymm3

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];
VXORPS YMM3, YMM3, YMM3

Show nanoBench command
Results:
- MPERF: 3.38
- APERF: 4.01
- UOPS: 8.2
- FpuPipeAssignment.Total0: 4.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 10 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 e3 75 4a c2 30    	vblendvps ymm0,ymm1,ymm2,ymm3
   6:	c4 e3 75 4a e2 30    	vblendvps ymm4,ymm1,ymm2,ymm3
   c:	c4 e3 75 4a ea 30    	vblendvps ymm5,ymm1,ymm2,ymm3
  12:	c4 e3 75 4a f2 30    	vblendvps ymm6,ymm1,ymm2,ymm3
  18:	c4 e3 75 4a fa 30    	vblendvps ymm7,ymm1,ymm2,ymm3
  1e:	c4 63 75 4a c2 30    	vblendvps ymm8,ymm1,ymm2,ymm3
  24:	c4 63 75 4a ca 30    	vblendvps ymm9,ymm1,ymm2,ymm3
  2a:	c4 63 75 4a d2 30    	vblendvps ymm10,ymm1,ymm2,ymm3
  30:	c4 63 75 4a da 30    	vblendvps ymm11,ymm1,ymm2,ymm3
  36:	c4 63 75 4a e2 30    	vblendvps ymm12,ymm1,ymm2,ymm3

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];
VXORPS YMM3, YMM3, YMM3

Show nanoBench command
Results:
- MPERF: 4.2
- APERF: 5.0
- UOPS: 10.0
- FpuPipeAssignment.Total0: 5.0
- FpuPipeAssignment.Total1: 5.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c4 e3 75 4a c2 30    	vblendvps ymm0,ymm1,ymm2,ymm3
   6:	c4 e3 75 4a e2 30    	vblendvps ymm4,ymm1,ymm2,ymm3
   c:	c4 e3 75 4a ea 30    	vblendvps ymm5,ymm1,ymm2,ymm3
  12:	c4 e3 75 4a f2 30    	vblendvps ymm6,ymm1,ymm2,ymm3
  18:	c4 e3 75 4a fa 30    	vblendvps ymm7,ymm1,ymm2,ymm3
  1e:	c4 63 75 4a c2 30    	vblendvps ymm8,ymm1,ymm2,ymm3
  24:	c4 63 75 4a ca 30    	vblendvps ymm9,ymm1,ymm2,ymm3
  2a:	c4 63 75 4a d2 30    	vblendvps ymm10,ymm1,ymm2,ymm3
  30:	c4 63 75 4a da 30    	vblendvps ymm11,ymm1,ymm2,ymm3
  36:	c4 63 75 4a e2 30    	vblendvps ymm12,ymm1,ymm2,ymm3

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];
VXORPS YMM3, YMM3, YMM3

Show nanoBench command
Results:
- MPERF: 4.21
- APERF: 5.01
- UOPS: 12.0
- FpuPipeAssignment.Total0: 0.03
- FpuPipeAssignment.Total1: 0.03
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c4 e3 75 4a c2 30    	vblendvps ymm0,ymm1,ymm2,ymm3
   6:	c4 e3 75 4a e2 30    	vblendvps ymm4,ymm1,ymm2,ymm3
   c:	c4 e3 75 4a ea 30    	vblendvps ymm5,ymm1,ymm2,ymm3
  12:	c4 e3 75 4a f2 30    	vblendvps ymm6,ymm1,ymm2,ymm3
  18:	c4 e3 75 4a fa 30    	vblendvps ymm7,ymm1,ymm2,ymm3
  1e:	c4 63 75 4a c2 30    	vblendvps ymm8,ymm1,ymm2,ymm3
  24:	c4 63 75 4a ca 30    	vblendvps ymm9,ymm1,ymm2,ymm3
  2a:	c4 63 75 4a d2 30    	vblendvps ymm10,ymm1,ymm2,ymm3
  30:	c4 63 75 4a da 30    	vblendvps ymm11,ymm1,ymm2,ymm3
  36:	c4 63 75 4a e2 30    	vblendvps ymm12,ymm1,ymm2,ymm3

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];
VXORPS YMM3, YMM3, YMM3

Show nanoBench command
Results:
- MPERF: 4.21
- APERF: 5.01
- UOPS: 10.2
- FpuPipeAssignment.Total0: 5.0
- FpuPipeAssignment.Total1: 5.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With the same register for for different operands

With unroll_count=500 and no inner loop

Code:

   0:	c4 e3 7d 4a c0 00    	vblendvps ymm0,ymm0,ymm0,ymm0

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];
VXORPS YMM0, YMM0, YMM0

Show nanoBench command
Results:
- MPERF: 0.83
- APERF: 1.0
- UOPS: 1.0
- FpuPipeAssignment.Total0: 0.5
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	c4 e3 7d 4a c0 00    	vblendvps ymm0,ymm0,ymm0,ymm0

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];
VXORPS YMM0, YMM0, YMM0

Show nanoBench command
Results:
- MPERF: 0.84
- APERF: 1.0
- UOPS: 1.2
- FpuPipeAssignment.Total0: 0.5
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	c4 e3 7d 4a c0 00    	vblendvps ymm0,ymm0,ymm0,ymm0

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];
VXORPS YMM0, YMM0, YMM0

Show nanoBench command
Results:
- MPERF: 0.84
- APERF: 1.0
- UOPS: 1.02
- FpuPipeAssignment.Total0: 0.5
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

VBLENDVPS (YMM, YMM, YMM, YMM) - 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 10 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