VMOVUPS (XMM, M128)

With unroll_count=500 and no inner loop

Code:

   0:	c4 c1 78 10 06       	vmovups xmm0,XMMWORD PTR [r14]

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

Show nanoBench command
Results:
- MPERF: 0.39
- APERF: 0.5
- UOPS: 1.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- 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:	c4 c1 78 10 06       	vmovups xmm0,XMMWORD PTR [r14]

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

Show nanoBench command
Results:
- MPERF: 0.43
- APERF: 0.5
- UOPS: 1.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- 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:	c4 c1 78 10 06       	vmovups xmm0,XMMWORD PTR [r14]

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

Show nanoBench command
Results:
- MPERF: 0.43
- APERF: 0.5
- UOPS: 1.01
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- 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:	c4 c1 78 10 06       	vmovups xmm0,XMMWORD PTR [r14]
   5:	c4 c1 78 10 4e 10    	vmovups xmm1,XMMWORD PTR [r14+0x10]
   b:	c4 c1 78 10 56 20    	vmovups xmm2,XMMWORD PTR [r14+0x20]
  11:	c4 c1 78 10 5e 30    	vmovups xmm3,XMMWORD PTR [r14+0x30]

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

Show nanoBench command
Results:
- MPERF: 1.8
- APERF: 2.0
- UOPS: 4.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- 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:	c4 c1 78 10 06       	vmovups xmm0,XMMWORD PTR [r14]
   5:	c4 c1 78 10 4e 10    	vmovups xmm1,XMMWORD PTR [r14+0x10]
   b:	c4 c1 78 10 56 20    	vmovups xmm2,XMMWORD PTR [r14+0x20]
  11:	c4 c1 78 10 5e 30    	vmovups xmm3,XMMWORD PTR [r14+0x30]

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

Show nanoBench command
Results:
- MPERF: 1.73
- APERF: 2.01
- UOPS: 4.5
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- 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:	c4 c1 78 10 06       	vmovups xmm0,XMMWORD PTR [r14]
   5:	c4 c1 78 10 4e 10    	vmovups xmm1,XMMWORD PTR [r14+0x10]
   b:	c4 c1 78 10 56 20    	vmovups xmm2,XMMWORD PTR [r14+0x20]
  11:	c4 c1 78 10 5e 30    	vmovups xmm3,XMMWORD PTR [r14+0x30]

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

Show nanoBench command
Results:
- MPERF: 1.74
- APERF: 2.01
- UOPS: 4.05
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- 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:	c4 c1 78 10 06       	vmovups xmm0,XMMWORD PTR [r14]
   5:	c4 c1 78 10 4e 10    	vmovups xmm1,XMMWORD PTR [r14+0x10]
   b:	c4 c1 78 10 56 20    	vmovups xmm2,XMMWORD PTR [r14+0x20]
  11:	c4 c1 78 10 5e 30    	vmovups xmm3,XMMWORD PTR [r14+0x30]
  17:	c4 c1 78 10 66 40    	vmovups xmm4,XMMWORD PTR [r14+0x40]
  1d:	c4 c1 78 10 6e 50    	vmovups xmm5,XMMWORD PTR [r14+0x50]
  23:	c4 c1 78 10 76 60    	vmovups xmm6,XMMWORD PTR [r14+0x60]
  29:	c4 c1 78 10 7e 70    	vmovups xmm7,XMMWORD PTR [r14+0x70]

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;
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: 3.53
- APERF: 4.0
- UOPS: 8.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- 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:	c4 c1 78 10 06       	vmovups xmm0,XMMWORD PTR [r14]
   5:	c4 c1 78 10 4e 10    	vmovups xmm1,XMMWORD PTR [r14+0x10]
   b:	c4 c1 78 10 56 20    	vmovups xmm2,XMMWORD PTR [r14+0x20]
  11:	c4 c1 78 10 5e 30    	vmovups xmm3,XMMWORD PTR [r14+0x30]
  17:	c4 c1 78 10 66 40    	vmovups xmm4,XMMWORD PTR [r14+0x40]
  1d:	c4 c1 78 10 6e 50    	vmovups xmm5,XMMWORD PTR [r14+0x50]
  23:	c4 c1 78 10 76 60    	vmovups xmm6,XMMWORD PTR [r14+0x60]
  29:	c4 c1 78 10 7e 70    	vmovups xmm7,XMMWORD PTR [r14+0x70]

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;
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: 3.45
- APERF: 4.01
- UOPS: 9.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- 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:	c4 c1 78 10 06       	vmovups xmm0,XMMWORD PTR [r14]
   5:	c4 c1 78 10 4e 10    	vmovups xmm1,XMMWORD PTR [r14+0x10]
   b:	c4 c1 78 10 56 20    	vmovups xmm2,XMMWORD PTR [r14+0x20]
  11:	c4 c1 78 10 5e 30    	vmovups xmm3,XMMWORD PTR [r14+0x30]
  17:	c4 c1 78 10 66 40    	vmovups xmm4,XMMWORD PTR [r14+0x40]
  1d:	c4 c1 78 10 6e 50    	vmovups xmm5,XMMWORD PTR [r14+0x50]
  23:	c4 c1 78 10 76 60    	vmovups xmm6,XMMWORD PTR [r14+0x60]
  29:	c4 c1 78 10 7e 70    	vmovups xmm7,XMMWORD PTR [r14+0x70]

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;
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: 4.04
- APERF: 4.7
- UOPS: 8.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With 13 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 c1 78 10 06       	vmovups xmm0,XMMWORD PTR [r14]
   5:	c4 c1 78 10 4e 10    	vmovups xmm1,XMMWORD PTR [r14+0x10]
   b:	c4 c1 78 10 56 20    	vmovups xmm2,XMMWORD PTR [r14+0x20]
  11:	c4 c1 78 10 5e 30    	vmovups xmm3,XMMWORD PTR [r14+0x30]
  17:	c4 c1 78 10 66 40    	vmovups xmm4,XMMWORD PTR [r14+0x40]
  1d:	c4 c1 78 10 6e 50    	vmovups xmm5,XMMWORD PTR [r14+0x50]
  23:	c4 c1 78 10 76 60    	vmovups xmm6,XMMWORD PTR [r14+0x60]
  29:	c4 c1 78 10 7e 70    	vmovups xmm7,XMMWORD PTR [r14+0x70]
  2f:	c4 41 78 10 86 80 00 	vmovups xmm8,XMMWORD PTR [r14+0x80]
  36:	00 00 
  38:	c4 41 78 10 8e 90 00 	vmovups xmm9,XMMWORD PTR [r14+0x90]
  3f:	00 00 
  41:	c4 41 78 10 96 a0 00 	vmovups xmm10,XMMWORD PTR [r14+0xa0]
  48:	00 00 
  4a:	c4 41 78 10 9e b0 00 	vmovups xmm11,XMMWORD PTR [r14+0xb0]
  51:	00 00 
  53:	c4 41 78 10 a6 c0 00 	vmovups xmm12,XMMWORD PTR [r14+0xc0]
  5a:	00 00

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;
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

Show nanoBench command
Results:
- MPERF: 6.03
- APERF: 6.83
- UOPS: 13.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- 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:	c4 c1 78 10 06       	vmovups xmm0,XMMWORD PTR [r14]
   5:	c4 c1 78 10 4e 10    	vmovups xmm1,XMMWORD PTR [r14+0x10]
   b:	c4 c1 78 10 56 20    	vmovups xmm2,XMMWORD PTR [r14+0x20]
  11:	c4 c1 78 10 5e 30    	vmovups xmm3,XMMWORD PTR [r14+0x30]
  17:	c4 c1 78 10 66 40    	vmovups xmm4,XMMWORD PTR [r14+0x40]
  1d:	c4 c1 78 10 6e 50    	vmovups xmm5,XMMWORD PTR [r14+0x50]
  23:	c4 c1 78 10 76 60    	vmovups xmm6,XMMWORD PTR [r14+0x60]
  29:	c4 c1 78 10 7e 70    	vmovups xmm7,XMMWORD PTR [r14+0x70]
  2f:	c4 41 78 10 86 80 00 	vmovups xmm8,XMMWORD PTR [r14+0x80]
  36:	00 00 
  38:	c4 41 78 10 8e 90 00 	vmovups xmm9,XMMWORD PTR [r14+0x90]
  3f:	00 00 
  41:	c4 41 78 10 96 a0 00 	vmovups xmm10,XMMWORD PTR [r14+0xa0]
  48:	00 00 
  4a:	c4 41 78 10 9e b0 00 	vmovups xmm11,XMMWORD PTR [r14+0xb0]
  51:	00 00 
  53:	c4 41 78 10 a6 c0 00 	vmovups xmm12,XMMWORD PTR [r14+0xc0]
  5a:	00 00

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;
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

Show nanoBench command
Results:
- MPERF: 5.71
- APERF: 6.62
- UOPS: 14.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- 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:	c4 c1 78 10 06       	vmovups xmm0,XMMWORD PTR [r14]
   5:	c4 c1 78 10 4e 10    	vmovups xmm1,XMMWORD PTR [r14+0x10]
   b:	c4 c1 78 10 56 20    	vmovups xmm2,XMMWORD PTR [r14+0x20]
  11:	c4 c1 78 10 5e 30    	vmovups xmm3,XMMWORD PTR [r14+0x30]
  17:	c4 c1 78 10 66 40    	vmovups xmm4,XMMWORD PTR [r14+0x40]
  1d:	c4 c1 78 10 6e 50    	vmovups xmm5,XMMWORD PTR [r14+0x50]
  23:	c4 c1 78 10 76 60    	vmovups xmm6,XMMWORD PTR [r14+0x60]
  29:	c4 c1 78 10 7e 70    	vmovups xmm7,XMMWORD PTR [r14+0x70]
  2f:	c4 41 78 10 86 80 00 	vmovups xmm8,XMMWORD PTR [r14+0x80]
  36:	00 00 
  38:	c4 41 78 10 8e 90 00 	vmovups xmm9,XMMWORD PTR [r14+0x90]
  3f:	00 00 
  41:	c4 41 78 10 96 a0 00 	vmovups xmm10,XMMWORD PTR [r14+0xa0]
  48:	00 00 
  4a:	c4 41 78 10 9e b0 00 	vmovups xmm11,XMMWORD PTR [r14+0xb0]
  51:	00 00 
  53:	c4 41 78 10 a6 c0 00 	vmovups xmm12,XMMWORD PTR [r14+0xc0]
  5a:	00 00

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;
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

Show nanoBench command
Results:
- MPERF: 5.62
- APERF: 6.51
- UOPS: 13.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 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 78 10 04 2e    	vmovups xmm0,XMMWORD PTR [r14+r13*1]

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;
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 0.42
- APERF: 0.5
- UOPS: 1.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- 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:	c4 81 78 10 04 2e    	vmovups xmm0,XMMWORD PTR [r14+r13*1]

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;
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 0.43
- APERF: 0.5
- UOPS: 1.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- 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:	c4 81 78 10 04 2e    	vmovups xmm0,XMMWORD PTR [r14+r13*1]

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;
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 0.43
- APERF: 0.5
- UOPS: 1.01
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- 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:	c4 81 78 10 04 2e    	vmovups xmm0,XMMWORD PTR [r14+r13*1]
   6:	c4 81 78 10 4c 2e 10 	vmovups xmm1,XMMWORD PTR [r14+r13*1+0x10]
   d:	c4 81 78 10 54 2e 20 	vmovups xmm2,XMMWORD PTR [r14+r13*1+0x20]
  14:	c4 81 78 10 5c 2e 30 	vmovups xmm3,XMMWORD PTR [r14+r13*1+0x30]

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;
XOR R13, R13;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX

Show nanoBench command
Results:
- MPERF: 1.8
- APERF: 2.0
- UOPS: 4.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- 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:	c4 81 78 10 04 2e    	vmovups xmm0,XMMWORD PTR [r14+r13*1]
   6:	c4 81 78 10 4c 2e 10 	vmovups xmm1,XMMWORD PTR [r14+r13*1+0x10]
   d:	c4 81 78 10 54 2e 20 	vmovups xmm2,XMMWORD PTR [r14+r13*1+0x20]
  14:	c4 81 78 10 5c 2e 30 	vmovups xmm3,XMMWORD PTR [r14+r13*1+0x30]

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;
XOR R13, R13;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX

Show nanoBench command
Results:
- MPERF: 1.73
- APERF: 2.01
- UOPS: 4.5
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- 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:	c4 81 78 10 04 2e    	vmovups xmm0,XMMWORD PTR [r14+r13*1]
   6:	c4 81 78 10 4c 2e 10 	vmovups xmm1,XMMWORD PTR [r14+r13*1+0x10]
   d:	c4 81 78 10 54 2e 20 	vmovups xmm2,XMMWORD PTR [r14+r13*1+0x20]
  14:	c4 81 78 10 5c 2e 30 	vmovups xmm3,XMMWORD PTR [r14+r13*1+0x30]

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;
XOR R13, R13;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX

Show nanoBench command
Results:
- MPERF: 1.75
- APERF: 2.01
- UOPS: 4.05
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- 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:	c4 81 78 10 04 2e    	vmovups xmm0,XMMWORD PTR [r14+r13*1]
   6:	c4 81 78 10 4c 2e 10 	vmovups xmm1,XMMWORD PTR [r14+r13*1+0x10]
   d:	c4 81 78 10 54 2e 20 	vmovups xmm2,XMMWORD PTR [r14+r13*1+0x20]
  14:	c4 81 78 10 5c 2e 30 	vmovups xmm3,XMMWORD PTR [r14+r13*1+0x30]
  1b:	c4 81 78 10 64 2e 40 	vmovups xmm4,XMMWORD PTR [r14+r13*1+0x40]
  22:	c4 81 78 10 6c 2e 50 	vmovups xmm5,XMMWORD PTR [r14+r13*1+0x50]
  29:	c4 81 78 10 74 2e 60 	vmovups xmm6,XMMWORD PTR [r14+r13*1+0x60]
  30:	c4 81 78 10 7c 2e 70 	vmovups xmm7,XMMWORD PTR [r14+r13*1+0x70]

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;
XOR R13, R13;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
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: 3.6
- APERF: 4.0
- UOPS: 8.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- 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:	c4 81 78 10 04 2e    	vmovups xmm0,XMMWORD PTR [r14+r13*1]
   6:	c4 81 78 10 4c 2e 10 	vmovups xmm1,XMMWORD PTR [r14+r13*1+0x10]
   d:	c4 81 78 10 54 2e 20 	vmovups xmm2,XMMWORD PTR [r14+r13*1+0x20]
  14:	c4 81 78 10 5c 2e 30 	vmovups xmm3,XMMWORD PTR [r14+r13*1+0x30]
  1b:	c4 81 78 10 64 2e 40 	vmovups xmm4,XMMWORD PTR [r14+r13*1+0x40]
  22:	c4 81 78 10 6c 2e 50 	vmovups xmm5,XMMWORD PTR [r14+r13*1+0x50]
  29:	c4 81 78 10 74 2e 60 	vmovups xmm6,XMMWORD PTR [r14+r13*1+0x60]
  30:	c4 81 78 10 7c 2e 70 	vmovups xmm7,XMMWORD PTR [r14+r13*1+0x70]

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;
XOR R13, R13;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
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: 3.47
- APERF: 4.01
- UOPS: 9.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- 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:	c4 81 78 10 04 2e    	vmovups xmm0,XMMWORD PTR [r14+r13*1]
   6:	c4 81 78 10 4c 2e 10 	vmovups xmm1,XMMWORD PTR [r14+r13*1+0x10]
   d:	c4 81 78 10 54 2e 20 	vmovups xmm2,XMMWORD PTR [r14+r13*1+0x20]
  14:	c4 81 78 10 5c 2e 30 	vmovups xmm3,XMMWORD PTR [r14+r13*1+0x30]
  1b:	c4 81 78 10 64 2e 40 	vmovups xmm4,XMMWORD PTR [r14+r13*1+0x40]
  22:	c4 81 78 10 6c 2e 50 	vmovups xmm5,XMMWORD PTR [r14+r13*1+0x50]
  29:	c4 81 78 10 74 2e 60 	vmovups xmm6,XMMWORD PTR [r14+r13*1+0x60]
  30:	c4 81 78 10 7c 2e 70 	vmovups xmm7,XMMWORD PTR [r14+r13*1+0x70]

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;
XOR R13, R13;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
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: 3.45
- APERF: 4.01
- UOPS: 8.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With 13 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 81 78 10 04 2e    	vmovups xmm0,XMMWORD PTR [r14+r13*1]
   6:	c4 81 78 10 4c 2e 10 	vmovups xmm1,XMMWORD PTR [r14+r13*1+0x10]
   d:	c4 81 78 10 54 2e 20 	vmovups xmm2,XMMWORD PTR [r14+r13*1+0x20]
  14:	c4 81 78 10 5c 2e 30 	vmovups xmm3,XMMWORD PTR [r14+r13*1+0x30]
  1b:	c4 81 78 10 64 2e 40 	vmovups xmm4,XMMWORD PTR [r14+r13*1+0x40]
  22:	c4 81 78 10 6c 2e 50 	vmovups xmm5,XMMWORD PTR [r14+r13*1+0x50]
  29:	c4 81 78 10 74 2e 60 	vmovups xmm6,XMMWORD PTR [r14+r13*1+0x60]
  30:	c4 81 78 10 7c 2e 70 	vmovups xmm7,XMMWORD PTR [r14+r13*1+0x70]
  37:	c4 01 78 10 84 2e 80 	vmovups xmm8,XMMWORD PTR [r14+r13*1+0x80]
  3e:	00 00 00 
  41:	c4 01 78 10 8c 2e 90 	vmovups xmm9,XMMWORD PTR [r14+r13*1+0x90]
  48:	00 00 00 
  4b:	c4 01 78 10 94 2e a0 	vmovups xmm10,XMMWORD PTR [r14+r13*1+0xa0]
  52:	00 00 00 
  55:	c4 01 78 10 9c 2e b0 	vmovups xmm11,XMMWORD PTR [r14+r13*1+0xb0]
  5c:	00 00 00 
  5f:	c4 01 78 10 a4 2e c0 	vmovups xmm12,XMMWORD PTR [r14+r13*1+0xc0]
  66:	00 00 00

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;
XOR R13, R13;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
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

Show nanoBench command
Results:
- MPERF: 5.64
- APERF: 6.56
- UOPS: 13.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- 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:	c4 81 78 10 04 2e    	vmovups xmm0,XMMWORD PTR [r14+r13*1]
   6:	c4 81 78 10 4c 2e 10 	vmovups xmm1,XMMWORD PTR [r14+r13*1+0x10]
   d:	c4 81 78 10 54 2e 20 	vmovups xmm2,XMMWORD PTR [r14+r13*1+0x20]
  14:	c4 81 78 10 5c 2e 30 	vmovups xmm3,XMMWORD PTR [r14+r13*1+0x30]
  1b:	c4 81 78 10 64 2e 40 	vmovups xmm4,XMMWORD PTR [r14+r13*1+0x40]
  22:	c4 81 78 10 6c 2e 50 	vmovups xmm5,XMMWORD PTR [r14+r13*1+0x50]
  29:	c4 81 78 10 74 2e 60 	vmovups xmm6,XMMWORD PTR [r14+r13*1+0x60]
  30:	c4 81 78 10 7c 2e 70 	vmovups xmm7,XMMWORD PTR [r14+r13*1+0x70]
  37:	c4 01 78 10 84 2e 80 	vmovups xmm8,XMMWORD PTR [r14+r13*1+0x80]
  3e:	00 00 00 
  41:	c4 01 78 10 8c 2e 90 	vmovups xmm9,XMMWORD PTR [r14+r13*1+0x90]
  48:	00 00 00 
  4b:	c4 01 78 10 94 2e a0 	vmovups xmm10,XMMWORD PTR [r14+r13*1+0xa0]
  52:	00 00 00 
  55:	c4 01 78 10 9c 2e b0 	vmovups xmm11,XMMWORD PTR [r14+r13*1+0xb0]
  5c:	00 00 00 
  5f:	c4 01 78 10 a4 2e c0 	vmovups xmm12,XMMWORD PTR [r14+r13*1+0xc0]
  66:	00 00 00

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;
XOR R13, R13;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
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

Show nanoBench command
Results:
- MPERF: 6.04
- APERF: 7.0
- UOPS: 14.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- 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:	c4 81 78 10 04 2e    	vmovups xmm0,XMMWORD PTR [r14+r13*1]
   6:	c4 81 78 10 4c 2e 10 	vmovups xmm1,XMMWORD PTR [r14+r13*1+0x10]
   d:	c4 81 78 10 54 2e 20 	vmovups xmm2,XMMWORD PTR [r14+r13*1+0x20]
  14:	c4 81 78 10 5c 2e 30 	vmovups xmm3,XMMWORD PTR [r14+r13*1+0x30]
  1b:	c4 81 78 10 64 2e 40 	vmovups xmm4,XMMWORD PTR [r14+r13*1+0x40]
  22:	c4 81 78 10 6c 2e 50 	vmovups xmm5,XMMWORD PTR [r14+r13*1+0x50]
  29:	c4 81 78 10 74 2e 60 	vmovups xmm6,XMMWORD PTR [r14+r13*1+0x60]
  30:	c4 81 78 10 7c 2e 70 	vmovups xmm7,XMMWORD PTR [r14+r13*1+0x70]
  37:	c4 01 78 10 84 2e 80 	vmovups xmm8,XMMWORD PTR [r14+r13*1+0x80]
  3e:	00 00 00 
  41:	c4 01 78 10 8c 2e 90 	vmovups xmm9,XMMWORD PTR [r14+r13*1+0x90]
  48:	00 00 00 
  4b:	c4 01 78 10 94 2e a0 	vmovups xmm10,XMMWORD PTR [r14+r13*1+0xa0]
  52:	00 00 00 
  55:	c4 01 78 10 9c 2e b0 	vmovups xmm11,XMMWORD PTR [r14+r13*1+0xb0]
  5c:	00 00 00 
  5f:	c4 01 78 10 a4 2e c0 	vmovups xmm12,XMMWORD PTR [r14+r13*1+0xc0]
  66:	00 00 00

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;
XOR R13, R13;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
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

Show nanoBench command
Results:
- MPERF: 5.62
- APERF: 6.51
- UOPS: 13.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

VMOVUPS (XMM, M128) - 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 13 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 13 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