MOVUPS (M128, XMM)

With unroll_count=500 and no inner loop

Code:

   0:	41 0f 11 06          	movups XMMWORD PTR [r14],xmm0

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14]

Show nanoBench command
Results:
- Instructions retired: 1.0
- Core cycles: 4.0
- Reference cycles: 4.0
- RS_UOPS_DISPATCHED: 9.0
- UOPS_PORT_0: 2.0
- UOPS_PORT_1: 0.5
- UOPS_PORT_2: 1.0
- UOPS_PORT_3: 2.0
- UOPS_PORT_4: 2.0
- UOPS_PORT_5: 1.5

With loop_count=1000 and unroll_count=10

Code:

   0:	41 0f 11 06          	movups XMMWORD PTR [r14],xmm0

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14]

Show nanoBench command
Results:
- Instructions retired: 1.2
- Core cycles: 4.1
- Reference cycles: 4.1
- RS_UOPS_DISPATCHED: 9.2
- UOPS_PORT_0: 2.0
- UOPS_PORT_1: 0.6
- UOPS_PORT_2: 1.0
- UOPS_PORT_3: 2.0
- UOPS_PORT_4: 2.0
- UOPS_PORT_5: 1.6

With loop_count=100 and unroll_count=100

Code:

   0:	41 0f 11 06          	movups XMMWORD PTR [r14],xmm0

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14]

Show nanoBench command
Results:
- Instructions retired: 1.02
- Core cycles: 4.01
- Reference cycles: 4.01
- RS_UOPS_DISPATCHED: 9.02
- UOPS_PORT_0: 2.0
- UOPS_PORT_1: 0.51
- UOPS_PORT_2: 1.0
- UOPS_PORT_3: 2.0
- UOPS_PORT_4: 2.0
- UOPS_PORT_5: 1.51

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

   0:	41 0f 11 06          	movups XMMWORD PTR [r14],xmm0
   4:	41 0f 11 46 10       	movups XMMWORD PTR [r14+0x10],xmm0
   9:	41 0f 11 46 20       	movups XMMWORD PTR [r14+0x20],xmm0
   e:	41 0f 11 46 30       	movups XMMWORD PTR [r14+0x30],xmm0

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14]

Show nanoBench command
Results:
- Instructions retired: 4.0
- Core cycles: 16.0
- Reference cycles: 16.0
- RS_UOPS_DISPATCHED: 36.0
- UOPS_PORT_0: 8.0
- UOPS_PORT_1: 2.0
- UOPS_PORT_2: 4.0
- UOPS_PORT_3: 8.0
- UOPS_PORT_4: 8.0
- UOPS_PORT_5: 6.0

With loop_count=1000 and unroll_count=2

Code:

   0:	41 0f 11 06          	movups XMMWORD PTR [r14],xmm0
   4:	41 0f 11 46 10       	movups XMMWORD PTR [r14+0x10],xmm0
   9:	41 0f 11 46 20       	movups XMMWORD PTR [r14+0x20],xmm0
   e:	41 0f 11 46 30       	movups XMMWORD PTR [r14+0x30],xmm0

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14]

Show nanoBench command
Results:
- Instructions retired: 5.0
- Core cycles: 16.51
- Reference cycles: 16.51
- RS_UOPS_DISPATCHED: 37.01
- UOPS_PORT_0: 8.0
- UOPS_PORT_1: 2.5
- UOPS_PORT_2: 4.0
- UOPS_PORT_3: 8.0
- UOPS_PORT_4: 8.0
- UOPS_PORT_5: 6.5

With loop_count=100 and unroll_count=20

Code:

   0:	41 0f 11 06          	movups XMMWORD PTR [r14],xmm0
   4:	41 0f 11 46 10       	movups XMMWORD PTR [r14+0x10],xmm0
   9:	41 0f 11 46 20       	movups XMMWORD PTR [r14+0x20],xmm0
   e:	41 0f 11 46 30       	movups XMMWORD PTR [r14+0x30],xmm0

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14]

Show nanoBench command
Results:
- Instructions retired: 4.1
- Core cycles: 16.06
- Reference cycles: 16.05
- RS_UOPS_DISPATCHED: 36.11
- UOPS_PORT_0: 8.0
- UOPS_PORT_1: 2.05
- UOPS_PORT_2: 4.0
- UOPS_PORT_3: 8.0
- UOPS_PORT_4: 8.0
- UOPS_PORT_5: 6.05

With 8 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	41 0f 11 06          	movups XMMWORD PTR [r14],xmm0
   4:	41 0f 11 46 10       	movups XMMWORD PTR [r14+0x10],xmm0
   9:	41 0f 11 46 20       	movups XMMWORD PTR [r14+0x20],xmm0
   e:	41 0f 11 46 30       	movups XMMWORD PTR [r14+0x30],xmm0
  13:	41 0f 11 46 40       	movups XMMWORD PTR [r14+0x40],xmm0
  18:	41 0f 11 46 50       	movups XMMWORD PTR [r14+0x50],xmm0
  1d:	41 0f 11 46 60       	movups XMMWORD PTR [r14+0x60],xmm0
  22:	41 0f 11 46 70       	movups XMMWORD PTR [r14+0x70],xmm0

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14]

Show nanoBench command
Results:
- Instructions retired: 8.0
- Core cycles: 32.0
- Reference cycles: 32.0
- RS_UOPS_DISPATCHED: 72.0
- UOPS_PORT_0: 16.0
- UOPS_PORT_1: 4.0
- UOPS_PORT_2: 8.0
- UOPS_PORT_3: 16.0
- UOPS_PORT_4: 16.0
- UOPS_PORT_5: 12.0

With loop_count=1000 and unroll_count=1

Code:

   0:	41 0f 11 06          	movups XMMWORD PTR [r14],xmm0
   4:	41 0f 11 46 10       	movups XMMWORD PTR [r14+0x10],xmm0
   9:	41 0f 11 46 20       	movups XMMWORD PTR [r14+0x20],xmm0
   e:	41 0f 11 46 30       	movups XMMWORD PTR [r14+0x30],xmm0
  13:	41 0f 11 46 40       	movups XMMWORD PTR [r14+0x40],xmm0
  18:	41 0f 11 46 50       	movups XMMWORD PTR [r14+0x50],xmm0
  1d:	41 0f 11 46 60       	movups XMMWORD PTR [r14+0x60],xmm0
  22:	41 0f 11 46 70       	movups XMMWORD PTR [r14+0x70],xmm0

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14]

Show nanoBench command
Results:
- Instructions retired: 10.0
- Core cycles: 33.01
- Reference cycles: 33.01
- RS_UOPS_DISPATCHED: 74.01
- UOPS_PORT_0: 16.01
- UOPS_PORT_1: 5.0
- UOPS_PORT_2: 8.0
- UOPS_PORT_3: 16.0
- UOPS_PORT_4: 16.0
- UOPS_PORT_5: 13.0

With loop_count=100 and unroll_count=10

Code:

   0:	41 0f 11 06          	movups XMMWORD PTR [r14],xmm0
   4:	41 0f 11 46 10       	movups XMMWORD PTR [r14+0x10],xmm0
   9:	41 0f 11 46 20       	movups XMMWORD PTR [r14+0x20],xmm0
   e:	41 0f 11 46 30       	movups XMMWORD PTR [r14+0x30],xmm0
  13:	41 0f 11 46 40       	movups XMMWORD PTR [r14+0x40],xmm0
  18:	41 0f 11 46 50       	movups XMMWORD PTR [r14+0x50],xmm0
  1d:	41 0f 11 46 60       	movups XMMWORD PTR [r14+0x60],xmm0
  22:	41 0f 11 46 70       	movups XMMWORD PTR [r14+0x70],xmm0

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14]

Show nanoBench command
Results:
- Instructions retired: 8.2
- Core cycles: 32.11
- Reference cycles: 32.11
- RS_UOPS_DISPATCHED: 72.21
- UOPS_PORT_0: 16.01
- UOPS_PORT_1: 4.1
- UOPS_PORT_2: 8.0
- UOPS_PORT_3: 16.0
- UOPS_PORT_4: 16.0
- UOPS_PORT_5: 12.1

With 16 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	41 0f 11 06          	movups XMMWORD PTR [r14],xmm0
   4:	41 0f 11 46 10       	movups XMMWORD PTR [r14+0x10],xmm0
   9:	41 0f 11 46 20       	movups XMMWORD PTR [r14+0x20],xmm0
   e:	41 0f 11 46 30       	movups XMMWORD PTR [r14+0x30],xmm0
  13:	41 0f 11 46 40       	movups XMMWORD PTR [r14+0x40],xmm0
  18:	41 0f 11 46 50       	movups XMMWORD PTR [r14+0x50],xmm0
  1d:	41 0f 11 46 60       	movups XMMWORD PTR [r14+0x60],xmm0
  22:	41 0f 11 46 70       	movups XMMWORD PTR [r14+0x70],xmm0
  27:	41 0f 11 86 80 00 00 	movups XMMWORD PTR [r14+0x80],xmm0
  2e:	00 
  2f:	41 0f 11 86 90 00 00 	movups XMMWORD PTR [r14+0x90],xmm0
  36:	00 
  37:	41 0f 11 86 a0 00 00 	movups XMMWORD PTR [r14+0xa0],xmm0
  3e:	00 
  3f:	41 0f 11 86 b0 00 00 	movups XMMWORD PTR [r14+0xb0],xmm0
  46:	00 
  47:	41 0f 11 86 c0 00 00 	movups XMMWORD PTR [r14+0xc0],xmm0
  4e:	00 
  4f:	41 0f 11 86 d0 00 00 	movups XMMWORD PTR [r14+0xd0],xmm0
  56:	00 
  57:	41 0f 11 86 e0 00 00 	movups XMMWORD PTR [r14+0xe0],xmm0
  5e:	00 
  5f:	41 0f 11 86 f0 00 00 	movups XMMWORD PTR [r14+0xf0],xmm0
  66:	00

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14]

Show nanoBench command
Results:
- Instructions retired: 16.0
- Core cycles: 64.0
- Reference cycles: 64.0
- RS_UOPS_DISPATCHED: 144.0
- UOPS_PORT_0: 32.0
- UOPS_PORT_1: 8.0
- UOPS_PORT_2: 16.0
- UOPS_PORT_3: 32.0
- UOPS_PORT_4: 32.0
- UOPS_PORT_5: 24.0

With loop_count=1000 and unroll_count=1

Code:

   0:	41 0f 11 06          	movups XMMWORD PTR [r14],xmm0
   4:	41 0f 11 46 10       	movups XMMWORD PTR [r14+0x10],xmm0
   9:	41 0f 11 46 20       	movups XMMWORD PTR [r14+0x20],xmm0
   e:	41 0f 11 46 30       	movups XMMWORD PTR [r14+0x30],xmm0
  13:	41 0f 11 46 40       	movups XMMWORD PTR [r14+0x40],xmm0
  18:	41 0f 11 46 50       	movups XMMWORD PTR [r14+0x50],xmm0
  1d:	41 0f 11 46 60       	movups XMMWORD PTR [r14+0x60],xmm0
  22:	41 0f 11 46 70       	movups XMMWORD PTR [r14+0x70],xmm0
  27:	41 0f 11 86 80 00 00 	movups XMMWORD PTR [r14+0x80],xmm0
  2e:	00 
  2f:	41 0f 11 86 90 00 00 	movups XMMWORD PTR [r14+0x90],xmm0
  36:	00 
  37:	41 0f 11 86 a0 00 00 	movups XMMWORD PTR [r14+0xa0],xmm0
  3e:	00 
  3f:	41 0f 11 86 b0 00 00 	movups XMMWORD PTR [r14+0xb0],xmm0
  46:	00 
  47:	41 0f 11 86 c0 00 00 	movups XMMWORD PTR [r14+0xc0],xmm0
  4e:	00 
  4f:	41 0f 11 86 d0 00 00 	movups XMMWORD PTR [r14+0xd0],xmm0
  56:	00 
  57:	41 0f 11 86 e0 00 00 	movups XMMWORD PTR [r14+0xe0],xmm0
  5e:	00 
  5f:	41 0f 11 86 f0 00 00 	movups XMMWORD PTR [r14+0xf0],xmm0
  66:	00

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14]

Show nanoBench command
Results:
- Instructions retired: 18.0
- Core cycles: 65.01
- Reference cycles: 65.01
- RS_UOPS_DISPATCHED: 146.01
- UOPS_PORT_0: 32.01
- UOPS_PORT_1: 9.0
- UOPS_PORT_2: 16.0
- UOPS_PORT_3: 32.0
- UOPS_PORT_4: 32.0
- UOPS_PORT_5: 25.0

With loop_count=100 and unroll_count=10

Code:

   0:	41 0f 11 06          	movups XMMWORD PTR [r14],xmm0
   4:	41 0f 11 46 10       	movups XMMWORD PTR [r14+0x10],xmm0
   9:	41 0f 11 46 20       	movups XMMWORD PTR [r14+0x20],xmm0
   e:	41 0f 11 46 30       	movups XMMWORD PTR [r14+0x30],xmm0
  13:	41 0f 11 46 40       	movups XMMWORD PTR [r14+0x40],xmm0
  18:	41 0f 11 46 50       	movups XMMWORD PTR [r14+0x50],xmm0
  1d:	41 0f 11 46 60       	movups XMMWORD PTR [r14+0x60],xmm0
  22:	41 0f 11 46 70       	movups XMMWORD PTR [r14+0x70],xmm0
  27:	41 0f 11 86 80 00 00 	movups XMMWORD PTR [r14+0x80],xmm0
  2e:	00 
  2f:	41 0f 11 86 90 00 00 	movups XMMWORD PTR [r14+0x90],xmm0
  36:	00 
  37:	41 0f 11 86 a0 00 00 	movups XMMWORD PTR [r14+0xa0],xmm0
  3e:	00 
  3f:	41 0f 11 86 b0 00 00 	movups XMMWORD PTR [r14+0xb0],xmm0
  46:	00 
  47:	41 0f 11 86 c0 00 00 	movups XMMWORD PTR [r14+0xc0],xmm0
  4e:	00 
  4f:	41 0f 11 86 d0 00 00 	movups XMMWORD PTR [r14+0xd0],xmm0
  56:	00 
  57:	41 0f 11 86 e0 00 00 	movups XMMWORD PTR [r14+0xe0],xmm0
  5e:	00 
  5f:	41 0f 11 86 f0 00 00 	movups XMMWORD PTR [r14+0xf0],xmm0
  66:	00

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14]

Show nanoBench command
Results:
- Instructions retired: 16.2
- Core cycles: 64.11
- Reference cycles: 64.11
- RS_UOPS_DISPATCHED: 144.21
- UOPS_PORT_0: 32.01
- UOPS_PORT_1: 8.1
- UOPS_PORT_2: 16.0
- UOPS_PORT_3: 32.0
- UOPS_PORT_4: 32.0
- UOPS_PORT_5: 24.1

With an indexed addressing mode

With 1 independent instruction

With unroll_count=500 and no inner loop

Code:

   0:	43 0f 11 04 2e       	movups XMMWORD PTR [r14+r13*1],xmm0

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14];
XOR R13, R13

Show nanoBench command
Results:
- Instructions retired: 1.0
- Core cycles: 4.0
- Reference cycles: 4.0
- RS_UOPS_DISPATCHED: 9.0
- UOPS_PORT_0: 2.0
- UOPS_PORT_1: 0.5
- UOPS_PORT_2: 1.0
- UOPS_PORT_3: 2.0
- UOPS_PORT_4: 2.0
- UOPS_PORT_5: 1.5

With loop_count=1000 and unroll_count=10

Code:

   0:	43 0f 11 04 2e       	movups XMMWORD PTR [r14+r13*1],xmm0

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14];
XOR R13, R13

Show nanoBench command
Results:
- Instructions retired: 1.2
- Core cycles: 4.1
- Reference cycles: 4.1
- RS_UOPS_DISPATCHED: 9.2
- UOPS_PORT_0: 2.0
- UOPS_PORT_1: 0.6
- UOPS_PORT_2: 1.0
- UOPS_PORT_3: 2.0
- UOPS_PORT_4: 2.0
- UOPS_PORT_5: 1.6

With loop_count=100 and unroll_count=100

Code:

   0:	43 0f 11 04 2e       	movups XMMWORD PTR [r14+r13*1],xmm0

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14];
XOR R13, R13

Show nanoBench command
Results:
- Instructions retired: 1.02
- Core cycles: 4.01
- Reference cycles: 4.01
- RS_UOPS_DISPATCHED: 9.02
- UOPS_PORT_0: 2.0
- UOPS_PORT_1: 0.51
- UOPS_PORT_2: 1.0
- UOPS_PORT_3: 2.0
- UOPS_PORT_4: 2.0
- UOPS_PORT_5: 1.51

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

   0:	43 0f 11 04 2e       	movups XMMWORD PTR [r14+r13*1],xmm0
   5:	43 0f 11 44 2e 10    	movups XMMWORD PTR [r14+r13*1+0x10],xmm0
   b:	43 0f 11 44 2e 20    	movups XMMWORD PTR [r14+r13*1+0x20],xmm0
  11:	43 0f 11 44 2e 30    	movups XMMWORD PTR [r14+r13*1+0x30],xmm0

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14];
XOR R13, R13

Show nanoBench command
Results:
- Instructions retired: 4.0
- Core cycles: 16.04
- Reference cycles: 16.02
- RS_UOPS_DISPATCHED: 36.0
- UOPS_PORT_0: 8.0
- UOPS_PORT_1: 2.0
- UOPS_PORT_2: 4.0
- UOPS_PORT_3: 8.0
- UOPS_PORT_4: 8.0
- UOPS_PORT_5: 6.0

With loop_count=1000 and unroll_count=2

Code:

   0:	43 0f 11 04 2e       	movups XMMWORD PTR [r14+r13*1],xmm0
   5:	43 0f 11 44 2e 10    	movups XMMWORD PTR [r14+r13*1+0x10],xmm0
   b:	43 0f 11 44 2e 20    	movups XMMWORD PTR [r14+r13*1+0x20],xmm0
  11:	43 0f 11 44 2e 30    	movups XMMWORD PTR [r14+r13*1+0x30],xmm0

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14];
XOR R13, R13

Show nanoBench command
Results:
- Instructions retired: 5.0
- Core cycles: 16.51
- Reference cycles: 16.51
- RS_UOPS_DISPATCHED: 37.01
- UOPS_PORT_0: 8.0
- UOPS_PORT_1: 2.5
- UOPS_PORT_2: 4.0
- UOPS_PORT_3: 8.0
- UOPS_PORT_4: 8.0
- UOPS_PORT_5: 6.5

With loop_count=100 and unroll_count=20

Code:

   0:	43 0f 11 04 2e       	movups XMMWORD PTR [r14+r13*1],xmm0
   5:	43 0f 11 44 2e 10    	movups XMMWORD PTR [r14+r13*1+0x10],xmm0
   b:	43 0f 11 44 2e 20    	movups XMMWORD PTR [r14+r13*1+0x20],xmm0
  11:	43 0f 11 44 2e 30    	movups XMMWORD PTR [r14+r13*1+0x30],xmm0

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14];
XOR R13, R13

Show nanoBench command
Results:
- Instructions retired: 4.1
- Core cycles: 16.06
- Reference cycles: 16.05
- RS_UOPS_DISPATCHED: 36.11
- UOPS_PORT_0: 8.0
- UOPS_PORT_1: 2.05
- UOPS_PORT_2: 4.0
- UOPS_PORT_3: 8.0
- UOPS_PORT_4: 8.0
- UOPS_PORT_5: 6.05

With 8 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	43 0f 11 04 2e       	movups XMMWORD PTR [r14+r13*1],xmm0
   5:	43 0f 11 44 2e 10    	movups XMMWORD PTR [r14+r13*1+0x10],xmm0
   b:	43 0f 11 44 2e 20    	movups XMMWORD PTR [r14+r13*1+0x20],xmm0
  11:	43 0f 11 44 2e 30    	movups XMMWORD PTR [r14+r13*1+0x30],xmm0
  17:	43 0f 11 44 2e 40    	movups XMMWORD PTR [r14+r13*1+0x40],xmm0
  1d:	43 0f 11 44 2e 50    	movups XMMWORD PTR [r14+r13*1+0x50],xmm0
  23:	43 0f 11 44 2e 60    	movups XMMWORD PTR [r14+r13*1+0x60],xmm0
  29:	43 0f 11 44 2e 70    	movups XMMWORD PTR [r14+r13*1+0x70],xmm0

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14];
XOR R13, R13

Show nanoBench command
Results:
- Instructions retired: 8.0
- Core cycles: 32.07
- Reference cycles: 32.07
- RS_UOPS_DISPATCHED: 72.0
- UOPS_PORT_0: 16.0
- UOPS_PORT_1: 4.0
- UOPS_PORT_2: 8.0
- UOPS_PORT_3: 16.0
- UOPS_PORT_4: 16.0
- UOPS_PORT_5: 12.0

With loop_count=1000 and unroll_count=1

Code:

   0:	43 0f 11 04 2e       	movups XMMWORD PTR [r14+r13*1],xmm0
   5:	43 0f 11 44 2e 10    	movups XMMWORD PTR [r14+r13*1+0x10],xmm0
   b:	43 0f 11 44 2e 20    	movups XMMWORD PTR [r14+r13*1+0x20],xmm0
  11:	43 0f 11 44 2e 30    	movups XMMWORD PTR [r14+r13*1+0x30],xmm0
  17:	43 0f 11 44 2e 40    	movups XMMWORD PTR [r14+r13*1+0x40],xmm0
  1d:	43 0f 11 44 2e 50    	movups XMMWORD PTR [r14+r13*1+0x50],xmm0
  23:	43 0f 11 44 2e 60    	movups XMMWORD PTR [r14+r13*1+0x60],xmm0
  29:	43 0f 11 44 2e 70    	movups XMMWORD PTR [r14+r13*1+0x70],xmm0

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14];
XOR R13, R13

Show nanoBench command
Results:
- Instructions retired: 10.0
- Core cycles: 33.01
- Reference cycles: 33.01
- RS_UOPS_DISPATCHED: 74.01
- UOPS_PORT_0: 16.01
- UOPS_PORT_1: 5.0
- UOPS_PORT_2: 8.0
- UOPS_PORT_3: 16.0
- UOPS_PORT_4: 16.0
- UOPS_PORT_5: 13.0

With loop_count=100 and unroll_count=10

Code:

   0:	43 0f 11 04 2e       	movups XMMWORD PTR [r14+r13*1],xmm0
   5:	43 0f 11 44 2e 10    	movups XMMWORD PTR [r14+r13*1+0x10],xmm0
   b:	43 0f 11 44 2e 20    	movups XMMWORD PTR [r14+r13*1+0x20],xmm0
  11:	43 0f 11 44 2e 30    	movups XMMWORD PTR [r14+r13*1+0x30],xmm0
  17:	43 0f 11 44 2e 40    	movups XMMWORD PTR [r14+r13*1+0x40],xmm0
  1d:	43 0f 11 44 2e 50    	movups XMMWORD PTR [r14+r13*1+0x50],xmm0
  23:	43 0f 11 44 2e 60    	movups XMMWORD PTR [r14+r13*1+0x60],xmm0
  29:	43 0f 11 44 2e 70    	movups XMMWORD PTR [r14+r13*1+0x70],xmm0

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14];
XOR R13, R13

Show nanoBench command
Results:
- Instructions retired: 8.2
- Core cycles: 32.11
- Reference cycles: 32.11
- RS_UOPS_DISPATCHED: 72.21
- UOPS_PORT_0: 16.01
- UOPS_PORT_1: 4.1
- UOPS_PORT_2: 8.0
- UOPS_PORT_3: 16.0
- UOPS_PORT_4: 16.0
- UOPS_PORT_5: 12.1

With 16 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	43 0f 11 04 2e       	movups XMMWORD PTR [r14+r13*1],xmm0
   5:	43 0f 11 44 2e 10    	movups XMMWORD PTR [r14+r13*1+0x10],xmm0
   b:	43 0f 11 44 2e 20    	movups XMMWORD PTR [r14+r13*1+0x20],xmm0
  11:	43 0f 11 44 2e 30    	movups XMMWORD PTR [r14+r13*1+0x30],xmm0
  17:	43 0f 11 44 2e 40    	movups XMMWORD PTR [r14+r13*1+0x40],xmm0
  1d:	43 0f 11 44 2e 50    	movups XMMWORD PTR [r14+r13*1+0x50],xmm0
  23:	43 0f 11 44 2e 60    	movups XMMWORD PTR [r14+r13*1+0x60],xmm0
  29:	43 0f 11 44 2e 70    	movups XMMWORD PTR [r14+r13*1+0x70],xmm0
  2f:	43 0f 11 84 2e 80 00 	movups XMMWORD PTR [r14+r13*1+0x80],xmm0
  36:	00 00 
  38:	43 0f 11 84 2e 90 00 	movups XMMWORD PTR [r14+r13*1+0x90],xmm0
  3f:	00 00 
  41:	43 0f 11 84 2e a0 00 	movups XMMWORD PTR [r14+r13*1+0xa0],xmm0
  48:	00 00 
  4a:	43 0f 11 84 2e b0 00 	movups XMMWORD PTR [r14+r13*1+0xb0],xmm0
  51:	00 00 
  53:	43 0f 11 84 2e c0 00 	movups XMMWORD PTR [r14+r13*1+0xc0],xmm0
  5a:	00 00 
  5c:	43 0f 11 84 2e d0 00 	movups XMMWORD PTR [r14+r13*1+0xd0],xmm0
  63:	00 00 
  65:	43 0f 11 84 2e e0 00 	movups XMMWORD PTR [r14+r13*1+0xe0],xmm0
  6c:	00 00 
  6e:	43 0f 11 84 2e f0 00 	movups XMMWORD PTR [r14+r13*1+0xf0],xmm0
  75:	00 00

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14];
XOR R13, R13

Show nanoBench command
Results:
- Instructions retired: 16.0
- Core cycles: 64.0
- Reference cycles: 64.04
- RS_UOPS_DISPATCHED: 144.0
- UOPS_PORT_0: 32.0
- UOPS_PORT_1: 8.0
- UOPS_PORT_2: 16.0
- UOPS_PORT_3: 32.0
- UOPS_PORT_4: 32.0
- UOPS_PORT_5: 24.0

With loop_count=1000 and unroll_count=1

Code:

   0:	43 0f 11 04 2e       	movups XMMWORD PTR [r14+r13*1],xmm0
   5:	43 0f 11 44 2e 10    	movups XMMWORD PTR [r14+r13*1+0x10],xmm0
   b:	43 0f 11 44 2e 20    	movups XMMWORD PTR [r14+r13*1+0x20],xmm0
  11:	43 0f 11 44 2e 30    	movups XMMWORD PTR [r14+r13*1+0x30],xmm0
  17:	43 0f 11 44 2e 40    	movups XMMWORD PTR [r14+r13*1+0x40],xmm0
  1d:	43 0f 11 44 2e 50    	movups XMMWORD PTR [r14+r13*1+0x50],xmm0
  23:	43 0f 11 44 2e 60    	movups XMMWORD PTR [r14+r13*1+0x60],xmm0
  29:	43 0f 11 44 2e 70    	movups XMMWORD PTR [r14+r13*1+0x70],xmm0
  2f:	43 0f 11 84 2e 80 00 	movups XMMWORD PTR [r14+r13*1+0x80],xmm0
  36:	00 00 
  38:	43 0f 11 84 2e 90 00 	movups XMMWORD PTR [r14+r13*1+0x90],xmm0
  3f:	00 00 
  41:	43 0f 11 84 2e a0 00 	movups XMMWORD PTR [r14+r13*1+0xa0],xmm0
  48:	00 00 
  4a:	43 0f 11 84 2e b0 00 	movups XMMWORD PTR [r14+r13*1+0xb0],xmm0
  51:	00 00 
  53:	43 0f 11 84 2e c0 00 	movups XMMWORD PTR [r14+r13*1+0xc0],xmm0
  5a:	00 00 
  5c:	43 0f 11 84 2e d0 00 	movups XMMWORD PTR [r14+r13*1+0xd0],xmm0
  63:	00 00 
  65:	43 0f 11 84 2e e0 00 	movups XMMWORD PTR [r14+r13*1+0xe0],xmm0
  6c:	00 00 
  6e:	43 0f 11 84 2e f0 00 	movups XMMWORD PTR [r14+r13*1+0xf0],xmm0
  75:	00 00

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14];
XOR R13, R13

Show nanoBench command
Results:
- Instructions retired: 18.0
- Core cycles: 65.01
- Reference cycles: 65.01
- RS_UOPS_DISPATCHED: 146.01
- UOPS_PORT_0: 32.01
- UOPS_PORT_1: 9.0
- UOPS_PORT_2: 16.0
- UOPS_PORT_3: 32.0
- UOPS_PORT_4: 32.0
- UOPS_PORT_5: 25.0

With loop_count=100 and unroll_count=10

Code:

   0:	43 0f 11 04 2e       	movups XMMWORD PTR [r14+r13*1],xmm0
   5:	43 0f 11 44 2e 10    	movups XMMWORD PTR [r14+r13*1+0x10],xmm0
   b:	43 0f 11 44 2e 20    	movups XMMWORD PTR [r14+r13*1+0x20],xmm0
  11:	43 0f 11 44 2e 30    	movups XMMWORD PTR [r14+r13*1+0x30],xmm0
  17:	43 0f 11 44 2e 40    	movups XMMWORD PTR [r14+r13*1+0x40],xmm0
  1d:	43 0f 11 44 2e 50    	movups XMMWORD PTR [r14+r13*1+0x50],xmm0
  23:	43 0f 11 44 2e 60    	movups XMMWORD PTR [r14+r13*1+0x60],xmm0
  29:	43 0f 11 44 2e 70    	movups XMMWORD PTR [r14+r13*1+0x70],xmm0
  2f:	43 0f 11 84 2e 80 00 	movups XMMWORD PTR [r14+r13*1+0x80],xmm0
  36:	00 00 
  38:	43 0f 11 84 2e 90 00 	movups XMMWORD PTR [r14+r13*1+0x90],xmm0
  3f:	00 00 
  41:	43 0f 11 84 2e a0 00 	movups XMMWORD PTR [r14+r13*1+0xa0],xmm0
  48:	00 00 
  4a:	43 0f 11 84 2e b0 00 	movups XMMWORD PTR [r14+r13*1+0xb0],xmm0
  51:	00 00 
  53:	43 0f 11 84 2e c0 00 	movups XMMWORD PTR [r14+r13*1+0xc0],xmm0
  5a:	00 00 
  5c:	43 0f 11 84 2e d0 00 	movups XMMWORD PTR [r14+r13*1+0xd0],xmm0
  63:	00 00 
  65:	43 0f 11 84 2e e0 00 	movups XMMWORD PTR [r14+r13*1+0xe0],xmm0
  6c:	00 00 
  6e:	43 0f 11 84 2e f0 00 	movups XMMWORD PTR [r14+r13*1+0xf0],xmm0
  75:	00 00

Init:

MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM0, [R14];
XOR R13, R13

Show nanoBench command
Results:
- Instructions retired: 16.2
- Core cycles: 64.11
- Reference cycles: 64.11
- RS_UOPS_DISPATCHED: 144.21
- UOPS_PORT_0: 32.01
- UOPS_PORT_1: 8.1
- UOPS_PORT_2: 16.0
- UOPS_PORT_3: 32.0
- UOPS_PORT_4: 32.0
- UOPS_PORT_5: 24.1

MOVUPS (M128, XMM) - 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 16 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 16 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