VSHUFPS (YMM, YMM, M256, I8)

With unroll_count=500 and no inner loop

Code:

   0:	c4 c1 74 c6 06 02    	vshufps ymm0,ymm1,YMMWORD PTR [r14],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]

Show nanoBench command
Results:
- MPERF: 0.87
- APERF: 1.0
- UOPS: 2.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 1.0
- FpuPipeAssignment.Total2: 1.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	c4 c1 74 c6 06 02    	vshufps ymm0,ymm1,YMMWORD PTR [r14],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]

Show nanoBench command
Results:
- MPERF: 0.87
- APERF: 1.0
- UOPS: 2.2
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 1.0
- FpuPipeAssignment.Total2: 1.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	c4 c1 74 c6 06 02    	vshufps ymm0,ymm1,YMMWORD PTR [r14],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]

Show nanoBench command
Results:
- MPERF: 0.94
- APERF: 1.08
- UOPS: 2.02
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 1.0
- FpuPipeAssignment.Total2: 1.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

   0:	c4 c1 74 c6 06 02    	vshufps ymm0,ymm1,YMMWORD PTR [r14],0x2
   6:	c4 c1 74 c6 56 20 02 	vshufps ymm2,ymm1,YMMWORD PTR [r14+0x20],0x2
   d:	c4 c1 74 c6 5e 40 02 	vshufps ymm3,ymm1,YMMWORD PTR [r14+0x40],0x2
  14:	c4 c1 74 c6 66 60 02 	vshufps ymm4,ymm1,YMMWORD PTR [r14+0x60],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];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
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

Show nanoBench command
Results:
- MPERF: 3.49
- APERF: 4.0
- UOPS: 8.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=2

Code:

   0:	c4 c1 74 c6 06 02    	vshufps ymm0,ymm1,YMMWORD PTR [r14],0x2
   6:	c4 c1 74 c6 56 20 02 	vshufps ymm2,ymm1,YMMWORD PTR [r14+0x20],0x2
   d:	c4 c1 74 c6 5e 40 02 	vshufps ymm3,ymm1,YMMWORD PTR [r14+0x40],0x2
  14:	c4 c1 74 c6 66 60 02 	vshufps ymm4,ymm1,YMMWORD PTR [r14+0x60],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];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
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

Show nanoBench command
Results:
- MPERF: 3.49
- APERF: 4.0
- UOPS: 9.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=20

Code:

   0:	c4 c1 74 c6 06 02    	vshufps ymm0,ymm1,YMMWORD PTR [r14],0x2
   6:	c4 c1 74 c6 56 20 02 	vshufps ymm2,ymm1,YMMWORD PTR [r14+0x20],0x2
   d:	c4 c1 74 c6 5e 40 02 	vshufps ymm3,ymm1,YMMWORD PTR [r14+0x40],0x2
  14:	c4 c1 74 c6 66 60 02 	vshufps ymm4,ymm1,YMMWORD PTR [r14+0x60],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];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
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

Show nanoBench command
Results:
- MPERF: 3.84
- APERF: 4.4
- UOPS: 8.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 8 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 c1 74 c6 06 02    	vshufps ymm0,ymm1,YMMWORD PTR [r14],0x2
   6:	c4 c1 74 c6 56 20 02 	vshufps ymm2,ymm1,YMMWORD PTR [r14+0x20],0x2
   d:	c4 c1 74 c6 5e 40 02 	vshufps ymm3,ymm1,YMMWORD PTR [r14+0x40],0x2
  14:	c4 c1 74 c6 66 60 02 	vshufps ymm4,ymm1,YMMWORD PTR [r14+0x60],0x2
  1b:	c4 c1 74 c6 ae 80 00 	vshufps ymm5,ymm1,YMMWORD PTR [r14+0x80],0x2
  22:	00 00 02 
  25:	c4 c1 74 c6 b6 a0 00 	vshufps ymm6,ymm1,YMMWORD PTR [r14+0xa0],0x2
  2c:	00 00 02 
  2f:	c4 c1 74 c6 be c0 00 	vshufps ymm7,ymm1,YMMWORD PTR [r14+0xc0],0x2
  36:	00 00 02 
  39:	c4 41 74 c6 86 e0 00 	vshufps ymm8,ymm1,YMMWORD PTR [r14+0xe0],0x2
  40:	00 00 02

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];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
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;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX

Show nanoBench command
Results:
- MPERF: 6.91
- APERF: 8.0
- UOPS: 16.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 8.0
- FpuPipeAssignment.Total2: 8.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c4 c1 74 c6 06 02    	vshufps ymm0,ymm1,YMMWORD PTR [r14],0x2
   6:	c4 c1 74 c6 56 20 02 	vshufps ymm2,ymm1,YMMWORD PTR [r14+0x20],0x2
   d:	c4 c1 74 c6 5e 40 02 	vshufps ymm3,ymm1,YMMWORD PTR [r14+0x40],0x2
  14:	c4 c1 74 c6 66 60 02 	vshufps ymm4,ymm1,YMMWORD PTR [r14+0x60],0x2
  1b:	c4 c1 74 c6 ae 80 00 	vshufps ymm5,ymm1,YMMWORD PTR [r14+0x80],0x2
  22:	00 00 02 
  25:	c4 c1 74 c6 b6 a0 00 	vshufps ymm6,ymm1,YMMWORD PTR [r14+0xa0],0x2
  2c:	00 00 02 
  2f:	c4 c1 74 c6 be c0 00 	vshufps ymm7,ymm1,YMMWORD PTR [r14+0xc0],0x2
  36:	00 00 02 
  39:	c4 41 74 c6 86 e0 00 	vshufps ymm8,ymm1,YMMWORD PTR [r14+0xe0],0x2
  40:	00 00 02

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];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
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;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX

Show nanoBench command
Results:
- MPERF: 6.97
- APERF: 8.01
- UOPS: 18.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 8.01
- FpuPipeAssignment.Total2: 8.01
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c4 c1 74 c6 06 02    	vshufps ymm0,ymm1,YMMWORD PTR [r14],0x2
   6:	c4 c1 74 c6 56 20 02 	vshufps ymm2,ymm1,YMMWORD PTR [r14+0x20],0x2
   d:	c4 c1 74 c6 5e 40 02 	vshufps ymm3,ymm1,YMMWORD PTR [r14+0x40],0x2
  14:	c4 c1 74 c6 66 60 02 	vshufps ymm4,ymm1,YMMWORD PTR [r14+0x60],0x2
  1b:	c4 c1 74 c6 ae 80 00 	vshufps ymm5,ymm1,YMMWORD PTR [r14+0x80],0x2
  22:	00 00 02 
  25:	c4 c1 74 c6 b6 a0 00 	vshufps ymm6,ymm1,YMMWORD PTR [r14+0xa0],0x2
  2c:	00 00 02 
  2f:	c4 c1 74 c6 be c0 00 	vshufps ymm7,ymm1,YMMWORD PTR [r14+0xc0],0x2
  36:	00 00 02 
  39:	c4 41 74 c6 86 e0 00 	vshufps ymm8,ymm1,YMMWORD PTR [r14+0xe0],0x2
  40:	00 00 02

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];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
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;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX

Show nanoBench command
Results:
- MPERF: 7.68
- APERF: 8.81
- UOPS: 16.2
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 8.01
- FpuPipeAssignment.Total2: 8.01
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 12 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 c1 74 c6 06 02    	vshufps ymm0,ymm1,YMMWORD PTR [r14],0x2
   6:	c4 c1 74 c6 56 20 02 	vshufps ymm2,ymm1,YMMWORD PTR [r14+0x20],0x2
   d:	c4 c1 74 c6 5e 40 02 	vshufps ymm3,ymm1,YMMWORD PTR [r14+0x40],0x2
  14:	c4 c1 74 c6 66 60 02 	vshufps ymm4,ymm1,YMMWORD PTR [r14+0x60],0x2
  1b:	c4 c1 74 c6 ae 80 00 	vshufps ymm5,ymm1,YMMWORD PTR [r14+0x80],0x2
  22:	00 00 02 
  25:	c4 c1 74 c6 b6 a0 00 	vshufps ymm6,ymm1,YMMWORD PTR [r14+0xa0],0x2
  2c:	00 00 02 
  2f:	c4 c1 74 c6 be c0 00 	vshufps ymm7,ymm1,YMMWORD PTR [r14+0xc0],0x2
  36:	00 00 02 
  39:	c4 41 74 c6 86 e0 00 	vshufps ymm8,ymm1,YMMWORD PTR [r14+0xe0],0x2
  40:	00 00 02 
  43:	c4 41 74 c6 8e 00 01 	vshufps ymm9,ymm1,YMMWORD PTR [r14+0x100],0x2
  4a:	00 00 02 
  4d:	c4 41 74 c6 96 20 01 	vshufps ymm10,ymm1,YMMWORD PTR [r14+0x120],0x2
  54:	00 00 02 
  57:	c4 41 74 c6 9e 40 01 	vshufps ymm11,ymm1,YMMWORD PTR [r14+0x140],0x2
  5e:	00 00 02 
  61:	c4 41 74 c6 a6 60 01 	vshufps ymm12,ymm1,YMMWORD PTR [r14+0x160],0x2
  68:	00 00 02

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];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
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;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX

Show nanoBench command
Results:
- MPERF: 10.37
- APERF: 12.0
- UOPS: 24.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 12.0
- FpuPipeAssignment.Total2: 12.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c4 c1 74 c6 06 02    	vshufps ymm0,ymm1,YMMWORD PTR [r14],0x2
   6:	c4 c1 74 c6 56 20 02 	vshufps ymm2,ymm1,YMMWORD PTR [r14+0x20],0x2
   d:	c4 c1 74 c6 5e 40 02 	vshufps ymm3,ymm1,YMMWORD PTR [r14+0x40],0x2
  14:	c4 c1 74 c6 66 60 02 	vshufps ymm4,ymm1,YMMWORD PTR [r14+0x60],0x2
  1b:	c4 c1 74 c6 ae 80 00 	vshufps ymm5,ymm1,YMMWORD PTR [r14+0x80],0x2
  22:	00 00 02 
  25:	c4 c1 74 c6 b6 a0 00 	vshufps ymm6,ymm1,YMMWORD PTR [r14+0xa0],0x2
  2c:	00 00 02 
  2f:	c4 c1 74 c6 be c0 00 	vshufps ymm7,ymm1,YMMWORD PTR [r14+0xc0],0x2
  36:	00 00 02 
  39:	c4 41 74 c6 86 e0 00 	vshufps ymm8,ymm1,YMMWORD PTR [r14+0xe0],0x2
  40:	00 00 02 
  43:	c4 41 74 c6 8e 00 01 	vshufps ymm9,ymm1,YMMWORD PTR [r14+0x100],0x2
  4a:	00 00 02 
  4d:	c4 41 74 c6 96 20 01 	vshufps ymm10,ymm1,YMMWORD PTR [r14+0x120],0x2
  54:	00 00 02 
  57:	c4 41 74 c6 9e 40 01 	vshufps ymm11,ymm1,YMMWORD PTR [r14+0x140],0x2
  5e:	00 00 02 
  61:	c4 41 74 c6 a6 60 01 	vshufps ymm12,ymm1,YMMWORD PTR [r14+0x160],0x2
  68:	00 00 02

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];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
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;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX

Show nanoBench command
Results:
- MPERF: 39.2
- APERF: 44.98
- UOPS: 26.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 12.01
- FpuPipeAssignment.Total2: 12.01
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c4 c1 74 c6 06 02    	vshufps ymm0,ymm1,YMMWORD PTR [r14],0x2
   6:	c4 c1 74 c6 56 20 02 	vshufps ymm2,ymm1,YMMWORD PTR [r14+0x20],0x2
   d:	c4 c1 74 c6 5e 40 02 	vshufps ymm3,ymm1,YMMWORD PTR [r14+0x40],0x2
  14:	c4 c1 74 c6 66 60 02 	vshufps ymm4,ymm1,YMMWORD PTR [r14+0x60],0x2
  1b:	c4 c1 74 c6 ae 80 00 	vshufps ymm5,ymm1,YMMWORD PTR [r14+0x80],0x2
  22:	00 00 02 
  25:	c4 c1 74 c6 b6 a0 00 	vshufps ymm6,ymm1,YMMWORD PTR [r14+0xa0],0x2
  2c:	00 00 02 
  2f:	c4 c1 74 c6 be c0 00 	vshufps ymm7,ymm1,YMMWORD PTR [r14+0xc0],0x2
  36:	00 00 02 
  39:	c4 41 74 c6 86 e0 00 	vshufps ymm8,ymm1,YMMWORD PTR [r14+0xe0],0x2
  40:	00 00 02 
  43:	c4 41 74 c6 8e 00 01 	vshufps ymm9,ymm1,YMMWORD PTR [r14+0x100],0x2
  4a:	00 00 02 
  4d:	c4 41 74 c6 96 20 01 	vshufps ymm10,ymm1,YMMWORD PTR [r14+0x120],0x2
  54:	00 00 02 
  57:	c4 41 74 c6 9e 40 01 	vshufps ymm11,ymm1,YMMWORD PTR [r14+0x140],0x2
  5e:	00 00 02 
  61:	c4 41 74 c6 a6 60 01 	vshufps ymm12,ymm1,YMMWORD PTR [r14+0x160],0x2
  68:	00 00 02

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];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
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;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX

Show nanoBench command
Results:
- MPERF: 11.15
- APERF: 12.81
- UOPS: 24.2
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 12.01
- FpuPipeAssignment.Total2: 12.01
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With an indexed addressing mode

With 1 independent instruction

With unroll_count=500 and no inner loop

Code:

   0:	c4 81 74 c6 04 2e 02 	vshufps ymm0,ymm1,YMMWORD PTR [r14+r13*1],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];
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 0.94
- APERF: 1.0
- UOPS: 2.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 1.0
- FpuPipeAssignment.Total2: 1.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	c4 81 74 c6 04 2e 02 	vshufps ymm0,ymm1,YMMWORD PTR [r14+r13*1],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];
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 0.87
- APERF: 1.0
- UOPS: 2.2
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 1.0
- FpuPipeAssignment.Total2: 1.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	c4 81 74 c6 04 2e 02 	vshufps ymm0,ymm1,YMMWORD PTR [r14+r13*1],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];
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 0.87
- APERF: 1.0
- UOPS: 2.02
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 1.0
- FpuPipeAssignment.Total2: 1.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

   0:	c4 81 74 c6 04 2e 02 	vshufps ymm0,ymm1,YMMWORD PTR [r14+r13*1],0x2
   7:	c4 81 74 c6 54 2e 20 	vshufps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20],0x2
   e:	02 
   f:	c4 81 74 c6 5c 2e 40 	vshufps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40],0x2
  16:	02 
  17:	c4 81 74 c6 64 2e 60 	vshufps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60],0x2
  1e:	02

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];
XOR R13, R13;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
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

Show nanoBench command
Results:
- MPERF: 3.51
- APERF: 4.0
- UOPS: 8.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=2

Code:

   0:	c4 81 74 c6 04 2e 02 	vshufps ymm0,ymm1,YMMWORD PTR [r14+r13*1],0x2
   7:	c4 81 74 c6 54 2e 20 	vshufps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20],0x2
   e:	02 
   f:	c4 81 74 c6 5c 2e 40 	vshufps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40],0x2
  16:	02 
  17:	c4 81 74 c6 64 2e 60 	vshufps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60],0x2
  1e:	02

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];
XOR R13, R13;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
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

Show nanoBench command
Results:
- MPERF: 3.49
- APERF: 4.0
- UOPS: 9.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=20

Code:

   0:	c4 81 74 c6 04 2e 02 	vshufps ymm0,ymm1,YMMWORD PTR [r14+r13*1],0x2
   7:	c4 81 74 c6 54 2e 20 	vshufps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20],0x2
   e:	02 
   f:	c4 81 74 c6 5c 2e 40 	vshufps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40],0x2
  16:	02 
  17:	c4 81 74 c6 64 2e 60 	vshufps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60],0x2
  1e:	02

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];
XOR R13, R13;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
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

Show nanoBench command
Results:
- MPERF: 3.84
- APERF: 4.4
- UOPS: 8.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 8 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 81 74 c6 04 2e 02 	vshufps ymm0,ymm1,YMMWORD PTR [r14+r13*1],0x2
   7:	c4 81 74 c6 54 2e 20 	vshufps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20],0x2
   e:	02 
   f:	c4 81 74 c6 5c 2e 40 	vshufps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40],0x2
  16:	02 
  17:	c4 81 74 c6 64 2e 60 	vshufps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60],0x2
  1e:	02 
  1f:	c4 81 74 c6 ac 2e 80 	vshufps ymm5,ymm1,YMMWORD PTR [r14+r13*1+0x80],0x2
  26:	00 00 00 02 
  2a:	c4 81 74 c6 b4 2e a0 	vshufps ymm6,ymm1,YMMWORD PTR [r14+r13*1+0xa0],0x2
  31:	00 00 00 02 
  35:	c4 81 74 c6 bc 2e c0 	vshufps ymm7,ymm1,YMMWORD PTR [r14+r13*1+0xc0],0x2
  3c:	00 00 00 02 
  40:	c4 01 74 c6 84 2e e0 	vshufps ymm8,ymm1,YMMWORD PTR [r14+r13*1+0xe0],0x2
  47:	00 00 00 02

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];
XOR R13, R13;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
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;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX

Show nanoBench command
Results:
- MPERF: 6.91
- APERF: 8.0
- UOPS: 16.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 8.0
- FpuPipeAssignment.Total2: 8.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c4 81 74 c6 04 2e 02 	vshufps ymm0,ymm1,YMMWORD PTR [r14+r13*1],0x2
   7:	c4 81 74 c6 54 2e 20 	vshufps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20],0x2
   e:	02 
   f:	c4 81 74 c6 5c 2e 40 	vshufps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40],0x2
  16:	02 
  17:	c4 81 74 c6 64 2e 60 	vshufps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60],0x2
  1e:	02 
  1f:	c4 81 74 c6 ac 2e 80 	vshufps ymm5,ymm1,YMMWORD PTR [r14+r13*1+0x80],0x2
  26:	00 00 00 02 
  2a:	c4 81 74 c6 b4 2e a0 	vshufps ymm6,ymm1,YMMWORD PTR [r14+r13*1+0xa0],0x2
  31:	00 00 00 02 
  35:	c4 81 74 c6 bc 2e c0 	vshufps ymm7,ymm1,YMMWORD PTR [r14+r13*1+0xc0],0x2
  3c:	00 00 00 02 
  40:	c4 01 74 c6 84 2e e0 	vshufps ymm8,ymm1,YMMWORD PTR [r14+r13*1+0xe0],0x2
  47:	00 00 00 02

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];
XOR R13, R13;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
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;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX

Show nanoBench command
Results:
- MPERF: 6.97
- APERF: 8.01
- UOPS: 18.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 8.01
- FpuPipeAssignment.Total2: 8.01
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c4 81 74 c6 04 2e 02 	vshufps ymm0,ymm1,YMMWORD PTR [r14+r13*1],0x2
   7:	c4 81 74 c6 54 2e 20 	vshufps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20],0x2
   e:	02 
   f:	c4 81 74 c6 5c 2e 40 	vshufps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40],0x2
  16:	02 
  17:	c4 81 74 c6 64 2e 60 	vshufps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60],0x2
  1e:	02 
  1f:	c4 81 74 c6 ac 2e 80 	vshufps ymm5,ymm1,YMMWORD PTR [r14+r13*1+0x80],0x2
  26:	00 00 00 02 
  2a:	c4 81 74 c6 b4 2e a0 	vshufps ymm6,ymm1,YMMWORD PTR [r14+r13*1+0xa0],0x2
  31:	00 00 00 02 
  35:	c4 81 74 c6 bc 2e c0 	vshufps ymm7,ymm1,YMMWORD PTR [r14+r13*1+0xc0],0x2
  3c:	00 00 00 02 
  40:	c4 01 74 c6 84 2e e0 	vshufps ymm8,ymm1,YMMWORD PTR [r14+r13*1+0xe0],0x2
  47:	00 00 00 02

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];
XOR R13, R13;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
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;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX

Show nanoBench command
Results:
- MPERF: 7.68
- APERF: 8.81
- UOPS: 16.2
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 8.01
- FpuPipeAssignment.Total2: 8.01
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 12 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 81 74 c6 04 2e 02 	vshufps ymm0,ymm1,YMMWORD PTR [r14+r13*1],0x2
   7:	c4 81 74 c6 54 2e 20 	vshufps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20],0x2
   e:	02 
   f:	c4 81 74 c6 5c 2e 40 	vshufps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40],0x2
  16:	02 
  17:	c4 81 74 c6 64 2e 60 	vshufps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60],0x2
  1e:	02 
  1f:	c4 81 74 c6 ac 2e 80 	vshufps ymm5,ymm1,YMMWORD PTR [r14+r13*1+0x80],0x2
  26:	00 00 00 02 
  2a:	c4 81 74 c6 b4 2e a0 	vshufps ymm6,ymm1,YMMWORD PTR [r14+r13*1+0xa0],0x2
  31:	00 00 00 02 
  35:	c4 81 74 c6 bc 2e c0 	vshufps ymm7,ymm1,YMMWORD PTR [r14+r13*1+0xc0],0x2
  3c:	00 00 00 02 
  40:	c4 01 74 c6 84 2e e0 	vshufps ymm8,ymm1,YMMWORD PTR [r14+r13*1+0xe0],0x2
  47:	00 00 00 02 
  4b:	c4 01 74 c6 8c 2e 00 	vshufps ymm9,ymm1,YMMWORD PTR [r14+r13*1+0x100],0x2
  52:	01 00 00 02 
  56:	c4 01 74 c6 94 2e 20 	vshufps ymm10,ymm1,YMMWORD PTR [r14+r13*1+0x120],0x2
  5d:	01 00 00 02 
  61:	c4 01 74 c6 9c 2e 40 	vshufps ymm11,ymm1,YMMWORD PTR [r14+r13*1+0x140],0x2
  68:	01 00 00 02 
  6c:	c4 01 74 c6 a4 2e 60 	vshufps ymm12,ymm1,YMMWORD PTR [r14+r13*1+0x160],0x2
  73:	01 00 00 02

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];
XOR R13, R13;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
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;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX

Show nanoBench command
Results:
- MPERF: 10.54
- APERF: 12.08
- UOPS: 24.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 12.0
- FpuPipeAssignment.Total2: 12.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c4 81 74 c6 04 2e 02 	vshufps ymm0,ymm1,YMMWORD PTR [r14+r13*1],0x2
   7:	c4 81 74 c6 54 2e 20 	vshufps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20],0x2
   e:	02 
   f:	c4 81 74 c6 5c 2e 40 	vshufps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40],0x2
  16:	02 
  17:	c4 81 74 c6 64 2e 60 	vshufps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60],0x2
  1e:	02 
  1f:	c4 81 74 c6 ac 2e 80 	vshufps ymm5,ymm1,YMMWORD PTR [r14+r13*1+0x80],0x2
  26:	00 00 00 02 
  2a:	c4 81 74 c6 b4 2e a0 	vshufps ymm6,ymm1,YMMWORD PTR [r14+r13*1+0xa0],0x2
  31:	00 00 00 02 
  35:	c4 81 74 c6 bc 2e c0 	vshufps ymm7,ymm1,YMMWORD PTR [r14+r13*1+0xc0],0x2
  3c:	00 00 00 02 
  40:	c4 01 74 c6 84 2e e0 	vshufps ymm8,ymm1,YMMWORD PTR [r14+r13*1+0xe0],0x2
  47:	00 00 00 02 
  4b:	c4 01 74 c6 8c 2e 00 	vshufps ymm9,ymm1,YMMWORD PTR [r14+r13*1+0x100],0x2
  52:	01 00 00 02 
  56:	c4 01 74 c6 94 2e 20 	vshufps ymm10,ymm1,YMMWORD PTR [r14+r13*1+0x120],0x2
  5d:	01 00 00 02 
  61:	c4 01 74 c6 9c 2e 40 	vshufps ymm11,ymm1,YMMWORD PTR [r14+r13*1+0x140],0x2
  68:	01 00 00 02 
  6c:	c4 01 74 c6 a4 2e 60 	vshufps ymm12,ymm1,YMMWORD PTR [r14+r13*1+0x160],0x2
  73:	01 00 00 02

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];
XOR R13, R13;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
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;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX

Show nanoBench command
Results:
- MPERF: 39.22
- APERF: 44.99
- UOPS: 26.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 12.01
- FpuPipeAssignment.Total2: 12.01
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c4 81 74 c6 04 2e 02 	vshufps ymm0,ymm1,YMMWORD PTR [r14+r13*1],0x2
   7:	c4 81 74 c6 54 2e 20 	vshufps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20],0x2
   e:	02 
   f:	c4 81 74 c6 5c 2e 40 	vshufps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40],0x2
  16:	02 
  17:	c4 81 74 c6 64 2e 60 	vshufps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60],0x2
  1e:	02 
  1f:	c4 81 74 c6 ac 2e 80 	vshufps ymm5,ymm1,YMMWORD PTR [r14+r13*1+0x80],0x2
  26:	00 00 00 02 
  2a:	c4 81 74 c6 b4 2e a0 	vshufps ymm6,ymm1,YMMWORD PTR [r14+r13*1+0xa0],0x2
  31:	00 00 00 02 
  35:	c4 81 74 c6 bc 2e c0 	vshufps ymm7,ymm1,YMMWORD PTR [r14+r13*1+0xc0],0x2
  3c:	00 00 00 02 
  40:	c4 01 74 c6 84 2e e0 	vshufps ymm8,ymm1,YMMWORD PTR [r14+r13*1+0xe0],0x2
  47:	00 00 00 02 
  4b:	c4 01 74 c6 8c 2e 00 	vshufps ymm9,ymm1,YMMWORD PTR [r14+r13*1+0x100],0x2
  52:	01 00 00 02 
  56:	c4 01 74 c6 94 2e 20 	vshufps ymm10,ymm1,YMMWORD PTR [r14+r13*1+0x120],0x2
  5d:	01 00 00 02 
  61:	c4 01 74 c6 9c 2e 40 	vshufps ymm11,ymm1,YMMWORD PTR [r14+r13*1+0x140],0x2
  68:	01 00 00 02 
  6c:	c4 01 74 c6 a4 2e 60 	vshufps ymm12,ymm1,YMMWORD PTR [r14+r13*1+0x160],0x2
  73:	01 00 00 02

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];
XOR R13, R13;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
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;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX

Show nanoBench command
Results:
- MPERF: 11.16
- APERF: 12.81
- UOPS: 24.2
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 12.01
- FpuPipeAssignment.Total2: 12.01
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

VSHUFPS (YMM, YMM, M256, I8) - Throughput and Uops

With a non-indexed addressing mode

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 12 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 an indexed addressing mode

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 12 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